# Using the config.toml File¶

The config.toml file is a configuration file that uses the TOML v0.5.0 file format. Administrators can customize various aspects of a Driverless AI (DAI) environment by editing the config.toml file before starting DAI.

Note

For information on configuration security, see Configuration Security.

## Configuration Override Chain¶

The configuration engine reads and overrides variables in the following order:

1. Driverless AI defaults: These are stored in a Python config module.

2. config.toml - Place this file in a folder or mount it in a Docker container and specify the path in the “DRIVERLESS_AI_CONFIG_FILE” environment variable.

3. Keystore file - Set the keystore_file parameter in the config.toml file or the environment variable “DRIVERLESS_AI_KEYSTORE_FILE” to point to a valid DAI keystore file generated using the h2oai.keystore tool. If an environment variable is set, the value in the config.toml for keystore_file is overridden.

4. Environment variable - Configuration variables can also be provided as environment variables. They must have the prefix DRIVERLESS_AI_ followed by the variable name in all caps. For example, “authentication_method” can be provided as “DRIVERLESS_AI_AUTHENTICATION_METHOD”. Setting environment variables overrides values from the keystore file.

1. Copy the config.toml file from inside the Docker image to your local filesystem.

                # Make a config directory
mkdir config

# Copy the config.toml file to the new config directory.
docker run --runtime=nvidia \
--pid=host \
--rm \
--init \
-u id -u:id -g \
-v pwd/config:/config \
--entrypoint bash \
h2oai/dai-ubi8-x86_64:1.10.4.3-cuda11.2.2.xx
-c "cp /etc/dai/config.toml /config"

1. Edit the desired variables in the config.toml file. Save your changes when you are done.

2. Start DAI with the DRIVERLESS_AI_CONFIG_FILE environment variable. Ensure that this environment variable points to the location of the edited config.toml file so that the software can locate the configuration file.

                docker run --runtime=nvidia \
--pid=host \
--init \
--rm \
--shm-size=256m \
-u id -u:id -g \
-p 12345:12345 \
-e DRIVERLESS_AI_CONFIG_FILE="/config/config.toml" \
-v pwd/config:/config \
-v pwd/data:/data \
-v pwd/log:/log \
-v pwd/license:/license \
-v pwd/tmp:/tmp \
h2oai/dai-ubi8-x86_64:1.10.4.3-cuda11.2.2.xx


## Sample config.toml File¶

The following is a copy of the standard config.toml file included with this version of DAI. The sections that follow describe some examples showing how to set different environment variables, data connectors, authentication methods, and notifications.

  1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270  ############################################################################## # DRIVERLESS AI CONFIGURATION FILE # # Comments: # This file is authored in TOML (see https://github.com/toml-lang/toml) # # Config Override Chain # Configuration variables for Driverless AI can be provided in several ways, # the config engine reads and overrides variables in the following order # # 1. h2oai/config/config.toml # [internal not visible to users] # # 2. config.toml # [place file in a folder/mount file in docker container and provide path # in "DRIVERLESS_AI_CONFIG_FILE" environment variable] # # 3. Keystore file # [set keystore_file parameter in config.toml, or environment variable # "DRIVERLESS_AI_KEYSTORE_FILE" to point to a valid DAI keystore file # generated using h2oai.keystore tool # # 4. Environment variable # [configuration variables can also be provided as environment variables # they must have the prefix "DRIVERLESS_AI_" followed by # variable name in caps e.g "authentication_method" can be provided as # "DRIVERLESS_AI_AUTHENTICATION_METHOD"] ############################################################################## # If the experiment is not done after this many minutes, stop feature engineering and model tuning as soon as possible and proceed with building the final modeling pipeline and deployment artifacts, independent of model score convergence or pre-determined number of iterations. Only active is not in reproducible mode. Depending on the data and experiment settings, overall experiment runtime can differ significantly from this setting. #max_runtime_minutes = 1440 # Whether to tune max_runtime_minutes based upon final number of base models,so try to trigger start of final model in order to better ensure stop entire experiment before max_runtime_minutes.Note: If the time given is short enough that tuning models are reduced belowfinal model expectations, the final model may be shorter than expected leadingto an overall shorter experiment time. #max_runtime_minutes_smart = true # If the experiment is not done after this many minutes, push the abort button. Preserves experiment artifacts made so far for summary and log zip files, but further artifacts are made. #max_runtime_minutes_until_abort = 10080 # If the experiment is not done by this time, push the abort button. Accepts time in format given by time_abort_format (defaults to %Y-%m-%d %H:%M:%S)assuming a time zone set by time_abort_timezone (defaults to UTC). One can also give integer seconds since 1970-01-01 00:00:00 UTC. Applies to time on a DAI worker that runs experiments. Preserves experiment artifacts made so far for summary and log zip files, but further artifacts are made.NOTE: If start new experiment with same parameters, restart, or refit, thisabsolute time will apply to such experiments or set of leaderboard experiments. #time_abort = "" # Any format is allowed as accepted by datetime.strptime. #time_abort_format = "%Y-%m-%d %H:%M:%S" # Any time zone in format accepted by datetime.strptime. #time_abort_timezone = "UTC" # Whether to delete all directories and files matching experiment pattern when call do_delete_model (True), # or whether to just delete directories (False). False can be used to preserve experiment logs that do # not take up much space. # #delete_model_dirs_and_files = true # Whether to delete all directories and files matching dataset pattern when call do_delete_dataset (True), # or whether to just delete directories (False). False can be used to preserve dataset logs that do # not take up much space. # #delete_data_dirs_and_files = true # # Recipe type # ## Recipes override any GUI settings # - **'auto'**: all models and features automatically determined by experiment settings, toml settings, and feature_engineering_effort # - **'compliant'** : like 'auto' except: # - *interpretability=10* (to avoid complexity, overrides GUI or python client chose for interpretability) # - *enable_glm='on'* (rest 'off', to avoid complexity and be compatible with algorithms supported by MLI) # - *fixed_ensemble_level=0*: Don't use any ensemble # - *feature_brain_level=0*(: No feature brain used (to ensure every restart is identical) # - *max_feature_interaction_depth=1*: interaction depth is set to 1 (no multi-feature interactions to avoid complexity) # - *target_transformer='identity'*: for regression (to avoid complexity) # - *check_distribution_shift_drop='off'*: Don't use distribution shift between train, valid, and test to drop features (bit risky without fine-tuning) # - **'monotonic_gbm'** : like 'auto' except: # - *monotonicity_constraints_interpretability_switch=1*: enable monotonicity constraints # - *self.config.monotonicity_constraints_correlation_threshold = 0.01*: see below # - *monotonicity_constraints_drop_low_correlation_features=true*: drop features that aren't correlated with target by at least 0.01 (specified by parameter above) # - *fixed_ensemble_level=0*: Don't use any ensemble (to avoid complexity) # - *included_models=['LightGBMModel']* # - *included_transformers=['OriginalTransformer']*: only original (numeric) features will be used # - *feature_brain_level=0*: No feature brain used (to ensure every restart is identical) # - *monotonicity_constraints_log_level='high'* # - *autodoc_pd_max_runtime=-1*: no timeout for PDP creation in AutoDoc # - **'kaggle'** : like 'auto' except: # - external validation set is concatenated with train set, with target marked as missing # - test set is concatenated with train set, with target marked as missing # - transformers that do not use the target are allowed to fit_transform across entire train + validation + test # - several config toml expert options open-up limits (e.g. more numerics are treated as categoricals) # - Note: If plentiful memory, can: # - choose kaggle mode and then change fixed_feature_interaction_depth to large negative number, # otherwise default number of features given to transformer is limited to 50 by default # - choose mutation_mode = "full", so even more types are transformations are done at once per transformer # - **'nlp_model'**: Only enables NLP models that process pure text # - **'nlp_transformer'**: Only enables NLP transformers that process pure text, while any model type is allowed # - **'image_model'**: Only enables Image models that process pure images # - **'image_transformer'**: Only enables Image transformers that process pure images, while any model type is allowed # - **'unsupervised'**: Only enables unsupervised transformers, models and scorers # - **'gpus_max'**: Maximize use of GPUs (e.g. use XGBoost, rapids, Optuna hyperparameter search, etc.) # - **'more_overfit_protection'**: Potentially improve overfit, esp. for small data, by disabling target encoding and making GA behave like final model for tree counts and learning rate # - **'feature_store_mojo'**: Creates a MOJO to be used as transformer in the H2O Feature Store, to augment data on a row-by-row level based on Driverless AI's feature engineering. Only includes transformers that don't depend on the target, since features like target encoding need to be created at model fitting time to avoid data leakage. And features like lags need to be created from the raw data, they can't be computed with a row-by-row MOJO transformer. # Each pipeline building recipe mode can be chosen, and then fine-tuned using each expert settings. Changing the # pipeline building recipe will reset all pipeline building recipe options back to default and then re-apply the # specific rules for the new mode, which will undo any fine-tuning of expert options that are part of pipeline building # recipe rules. # If choose to do new/continued/refitted/retrained experiment from parent experiment, the recipe rules are not re-applied # and any fine-tuning is preserved. To reset recipe behavior, one can switch between 'auto' and the desired mode. This # way the new child experiment will use the default settings for the chosen recipe. #recipe = "auto" # Whether to treat model like UnsupervisedModel, so that one specifies each scorer, pretransformer, and transformer in expert panel like one would do for supervised experiments. # Otherwise (False), custom unsupervised models will assume the moddel itself specified these. # If the unsupervised model chosen has _included_transformers, _included_pretransformers, and _included_scorers selected, this should be set to False (default) else should be set to True. # Then if one wants the unsupervised model to only produce 1 gene-transformer, then the custom unsupervised model can have: # _ngenes_max = 1 # _ngenes_max_by_layer = [1000, 1] # The 1000 for the pretransformer layer just means that layer can have any number of genes. Choose 1 if you expect single instance of the pretransformer to be all one needs, e.g. consumes input features fully and produces complete useful output features. # #custom_unsupervised_expert_mode = false # Whether to enable genetic algorithm for selection and hyper-parameter tuning of features and models. # - If disabled ('off'), will go directly to final pipeline training (using default feature engineering and feature selection). # - 'auto' is same as 'on' unless pure NLP or Image experiment. # - "Optuna": Uses DAI genetic algorithm for feature engineering, but model hyperparameters are tuned with Optuna. # - In the Optuna case, the scores shown in the iteration panel are the best score and trial scores. # - Optuna mode currently only uses Optuna for XGBoost, LightGBM, and CatBoost (custom recipe). # - If Pruner is enabled, as is default, Optuna mode disables mutations of eval_metric so pruning uses same metric across trials to compare properly. # Currently does not supported when pre_transformers or multi-layer pipeline used, which must go through at least one round of tuning or evolution. # #enable_genetic_algorithm = "auto" # How much effort to spend on feature engineering (-1...10) # Heuristic combination of various developer-level toml parameters # -1 : auto (5, except 1 for wide data in order to limit engineering) # 0 : keep only numeric features, only model tuning during evolution # 1 : keep only numeric features and frequency-encoded categoricals, only model tuning during evolution # 2 : Like #1 but instead just no Text features. Some feature tuning before evolution. # 3 : Like #5 but only tuning during evolution. Mixed tuning of features and model parameters. # 4 : Like #5, but slightly more focused on model tuning # 5 : Default. Balanced feature-model tuning # 6-7 : Like #5, but slightly more focused on feature engineering # 8 : Like #6-7, but even more focused on feature engineering with high feature generation rate, no feature dropping even if high interpretability # 9-10: Like #8, but no model tuning during feature evolution # #feature_engineering_effort = -1 # Whether to enable train/valid and train/test distribution shift detection ('auto'/'on'/'off'). # By default, LightGBMModel is used for shift detection if possible, unless it is turned off in model # expert panel, and then only the models selected in recipe list will be used. # #check_distribution_shift = "auto" # Whether to drop high-shift features ('auto'/'on'/'off'). Auto disables for time series. #check_distribution_shift_drop = "auto" # If distribution shift detection is enabled, drop features (except ID, text, date/datetime, time, weight) for # which shift AUC, GINI, or Spearman correlation is above this value # (e.g. AUC of a binary classifier that predicts whether given feature value # belongs to train or test data) # #drop_features_distribution_shift_threshold_auc = 0.999 # Specify whether to check leakage for each feature (on or off). # If a fold column is used, this option checks leakage without using the fold column. # By default, LightGBM Model is used for leakage detection when possible, unless it is # turned off in the Model Expert Settings tab, in which case only the models selected with # the included_models option are used. Note that this option is always disabled for time # series experiments. # #check_leakage = "auto" # If leakage detection is enabled, # drop features for which AUC (R2 for regression), GINI, # or Spearman correlation is above this value. # If fold column present, features are not dropped, # because leakage test applies without fold column used. # #drop_features_leakage_threshold_auc = 0.999 # Max number of rows x number of columns to trigger (stratified) sampling for leakage checks # #leakage_max_data_size = 10000000 # Specify the maximum number of features to use and show in importance tables. # When Interpretability is set higher than 1, # transformed or original features with lower importance than the top max_features_importance features are always removed. # Feature importances of transformed or original features correspondingly will be pruned. # Higher values can lead to lower performance and larger disk space used for datasets with more than 100k columns. # #max_features_importance = 100000 # Whether to create the Python scoring pipeline at the end of each experiment. #make_python_scoring_pipeline = "auto" # Whether to create the MOJO scoring pipeline at the end of each experiment. If set to "auto", will attempt to # create it if possible (without dropping capabilities). If set to "on", might need to drop some models, # transformers or custom recipes. # #make_mojo_scoring_pipeline = "auto" # Perform timing and accuracy benchmarks for Injected MOJO scoring vs Python scoring. This is for full scoring data, and can be slow. This also requires hard asserts. Doesn't force MOJO scoring by itself, so depends on mojo_for_predictions='on' if want full coverage. #mojo_for_predictions_benchmark = true # Fail hard if MOJO scoring is this many times slower than Python scoring. #mojo_for_predictions_benchmark_slower_than_python_threshold = 10 # Fail hard if MOJO scoring is slower than Python scoring by a factor specified by mojo_for_predictions_benchmark_slower_than_python_threshold, but only if have at least this many rows. To reduce false positives. #mojo_for_predictions_benchmark_slower_than_python_min_rows = 100 # Fail hard if MOJO scoring is slower than Python scoring by a factor specified by mojo_for_predictions_benchmark_slower_than_python_threshold, but only if takes at least this many seconds. To reduce false positives. #mojo_for_predictions_benchmark_slower_than_python_min_seconds = 2.0 # Inject MOJO into fitted Python state if mini acceptance test passes, so can use C++ MOJO runtime when calling predict(enable_mojo=True, IS_SCORER=True, ...). Prerequisite for mojo_for_predictions='on' or 'auto'. #inject_mojo_for_predictions = true # Use MOJO for making fast low-latency predictions after experiment has finished (when applicable, for AutoDoc/Diagnostics/Predictions/MLI and standalone Python scoring via scorer.zip). For 'auto', only use MOJO if number of rows is equal or below mojo_for_predictions_max_rows. For larger frames, it can be faster to use the Python backend since used libraries are more likely already vectorized. #mojo_for_predictions = "auto" # For smaller datasets, the single-threaded but low latency C++ MOJO runtime can lead to significantly faster scoring times than the regular in-Driverless AI Python scoring environment. If enable_mojo=True is passed to the predict API, and the MOJO exists and is applicable, then use the MOJO runtime for datasets that have fewer or equal number of rows than this threshold. MLI/AutoDoc set enable_mojo=True by default, so this setting applies. This setting is only used if mojo_for_predictions is 'auto'. #mojo_for_predictions_max_rows = 10000 # Batch size (in rows) for C++ MOJO predictions. Only when enable_mojo=True is passed to the predict API, and when the MOJO is applicable (e.g., fewer rows than mojo_for_predictions_max_rows). Larger values can lead to faster scoring, but use more memory. #mojo_for_predictions_batch_size = 100 # Relative tolerance for mini MOJO acceptance test. If Python/C++ MOJO differs more than this from Python, won't use MOJO inside Python for later scoring. Only applicable if mojo_for_predictions=True. Disabled if <= 0. #mojo_acceptance_test_rtol = 0.0 # Absolute tolerance for mini MOJO acceptance test (for regression/Shapley, will be scaled by max(abs(preds)). If Python/C++ MOJO differs more than this from Python, won't use MOJO inside Python for later scoring. Only applicable if mojo_for_predictions=True. Disabled if <= 0. #mojo_acceptance_test_atol = 0.0 # Whether to attempt to reduce the size of the MOJO scoring pipeline. A smaller MOJO will also lead to # less memory footprint during scoring. It is achieved by reducing some other settings like interaction depth, and # hence can affect the predictive accuracy of the model. # #reduce_mojo_size = false # Whether to create the pipeline visualization at the end of each experiment. # Uses MOJO to show pipeline, input features, transformers, model, and outputs of model. MOJO-capable tree models show first tree. #make_pipeline_visualization = "auto" # Whether to create the python pipeline visualization at the end of each experiment. # Each feature and transformer includes a variable importance at end in brackets. # Only done when forced on, and artifacts as png files will appear in summary zip. # Each experiment has files per individual in final population: # 1) preprune_False_0.0 : Before final pruning, without any additional variable importance threshold pruning # 2) preprune_True_0.0 : Before final pruning, with additional variable importance <=0.0 pruning # 3) postprune_False_0.0 : After final pruning, without any additional variable importance threshold pruning # 4) postprune_True_0.0 : After final pruning, with additional variable importance <=0.0 pruning # 5) posttournament_False_0.0 : After final pruning and tournament, without any additional variable importance threshold pruning # 6) posttournament_True_0.0 : After final pruning and tournament, with additional variable importance <=0.0 pruning # 1-5 are done with 'on' while 'auto' only does 6 corresponding to the final post-pruned individuals. # Even post pruning, some features have zero importance, because only those genes that have value+variance in # variable importance of value=0.0 get pruned. GA can have many folds with positive variance # for a gene, and those are not removed in case they are useful features for final model. # If small mojo option is chosen (reduce_mojo_size True), then the variance of feature gain is ignored # for which genes and features are pruned as well as for what appears in the graph. # #make_python_pipeline_visualization = "auto" # Whether to create the experiment AutoDoc after end of experiment. # #make_autoreport = true #max_cols_make_autoreport_automatically = 1000 #max_cols_make_pipeline_visualization_automatically = 5000 # Pass environment variables from running Driverless AI instance to Python scoring pipeline for # deprecated models, when they are used to make predictions. Use with caution. # If config.toml overrides are set by env vars, and they differ from what the experiment's env # looked like when it was trained, then unexpected consequences can occur. Enable this only to " # override certain well-controlled settings like the port for H2O-3 custom recipe server. # #pass_env_to_deprecated_python_scoring = false #transformer_description_line_length = -1 # Whether to measure the MOJO scoring latency at the time of MOJO creation. #benchmark_mojo_latency = "auto" # Max size of pipeline.mojo file (in MB) for automatic mode of MOJO scoring latency measurement #benchmark_mojo_latency_auto_size_limit = 500 # If MOJO creation times out at end of experiment, can still make MOJO from the GUI or from the R/Py clients (timeout doesn't apply there). #mojo_building_timeout = 1800.0 # If MOJO visualization creation times out at end of experiment, MOJO is still created if possible within the time limit specified by mojo_building_timeout. #mojo_vis_building_timeout = 600.0 # If MOJO creation is too slow, increase this value. Higher values can finish faster, but use more memory. # If MOJO creation fails due to an out-of-memory error, reduce this value to 1. # Set to -1 for all physical cores. # #mojo_building_parallelism = -1 # Size in bytes that all pickled and compressed base models have to satisfy to use parallel MOJO building. # For large base models, parallel MOJO building can use too much memory. # Only used if final_fitted_model_per_model_fold_files is true. # #mojo_building_parallelism_base_model_size_limit = 100000000 # Whether to show model and pipeline sizes in logs. # If 'auto', then not done if more than 10 base models+folds, because expect not concerned with size. #show_pipeline_sizes = "auto" # safe: assume might be running another experiment on same node # moderate: assume not running any other experiments or tasks on same node, but still only use physical core count # max: assume not running anything else on node at all except the experiment # If multinode is enabled, this option has no effect, unless worker_remote_processors=1 when it will still be applied. # Each exclusive mode can be chosen, and then fine-tuned using each expert settings. Changing the # exclusive mode will reset all exclusive mode related options back to default and then re-apply the # specific rules for the new mode, which will undo any fine-tuning of expert options that are part of exclusive mode rules. # If choose to do new/continued/refitted/retrained experiment from parent experiment, all the mode rules are not re-applied # and any fine-tuning is preserved. To reset mode behavior, one can switch between 'safe' and the desired mode. This # way the new child experiment will use the default system resources for the chosen mode. # #exclusive_mode = "safe" # Maximum number of workers for Driverless AI server pool (only 1 needed currently) #max_workers = 1 # Max number of CPU cores to use per experiment. Set to <= 0 to use all (physical) cores. # One can also set environment variable 'OMP_NUM_THREADS' to number of cores to use for OpenMP # (e.g., in bash: 'export OMP_NUM_THREADS=32' and 'export OPENBLAS_NUM_THREADS=32'). # #max_cores = 0 # Max number of CPU cores to use across all of DAI experiments and tasks. # -1 is all available, with stall_subprocess_submission_dai_fork_threshold_count=0 means restricted to core count. # #max_cores_dai = -1 # Number of virtual cores per physical core (0: auto mode, >=1 use that integer value). If >=1, the reported physical cores in logs will match the virtual cores divided by this value. #virtual_cores_per_physical_core = 0 # Number of physical cores to assume are present (0: auto, >=1 use that integer value). # If for some reason DAI does not automatically figure out physical cores correctly, # one can override with this value. Some systems, especially virtualized, do not always provide # correct information about the virtual cores, physical cores, sockets, etc. #override_physical_cores = 0 # Number of virtual cores to assume are present (0: auto, >=1 use that integer value). # If for some reason DAI does not automatically figure out virtual cores correctly, # or only a portion of the system is to be used, one can override with this value. # Some systems, especially virtualized, do not always provide # correct information about the virtual cores, physical cores, sockets, etc. #override_virtual_cores = 0 # Whether to treat data as small recipe in terms of work, by spreading many small tasks across many cores instead of forcing GPUs, for models that support it via static var _use_single_core_if_many. 'auto' looks at _use_single_core_if_many for models and data size, 'on' forces, 'off' disables. #small_data_recipe_work = "auto" # Stall submission of tasks if total DAI fork count exceeds count (-1 to disable, 0 for automatic of max_cores_dai) #stall_subprocess_submission_dai_fork_threshold_count = 0 # Stall submission of tasks if system memory available is less than this threshold in percent (set to 0 to disable). # Above this threshold, the number of workers in any pool of workers is linearly reduced down to 1 once hitting this threshold. # #stall_subprocess_submission_mem_threshold_pct = 2 # Whether to set automatic number of cores by physical (True) or logical (False) count. # Using all logical cores can lead to poor performance due to cache thrashing. # #max_cores_by_physical = true # Absolute limit to core count #max_cores_limit = 100 # Control maximum number of cores to use for a model's fit call (0 = all physical cores >= 1 that count). See also tensorflow_model_max_cores to further limit TensorFlow main models. #max_fit_cores = 10 # Control maximum number of cores to use for a scoring across all chosen scorers (0 = auto) #parallel_score_max_workers = 0 # Whether to use full multinode distributed cluster (True) or single-node dask (False). # In some cases, using entire cluster can be inefficient. E.g. several DGX nodes can be more efficient # if used one DGX at a time for medium-sized data. # #use_dask_cluster = true # Control maximum number of cores to use for a model's predict call (0 = all physical cores >= 1 that count) #max_predict_cores = 0 # Factor by which to reduce physical cores, to use for post-model experiment tasks like autoreport, MLI, etc. #max_predict_cores_in_dai_reduce_factor = 4 # Maximum number of cores to use for post-model experiment tasks like autoreport, MLI, etc. #max_max_predict_cores_in_dai = 10 # Control maximum number of cores to use for a model's transform and predict call when doing operations inside DAI-MLI GUI and R/Py client. # The main experiment and other tasks like MLI and autoreport have separate queues. The main experiments have run at most worker_remote_processors tasks (limited by cores if auto mode), # while other tasks run at most worker_local_processors (limited by cores if auto mode) tasks at the same time, # so many small tasks can add up. To prevent overloading the system, the defaults are conservative. However, if most of the activity involves autoreport or MLI, and no model experiments # are running, it may be safe to increase this value to something larger than 4. # -1 : Auto mode. Up to physical cores divided by 4, up to maximum of 10. # 0 : all physical cores # >= 1: that count). # #max_predict_cores_in_dai = -1 # Control number of workers used in CPU mode for tuning (0 = socket count -1 = all physical cores >= 1 that count). More workers will be more parallel but models learn less from each other. #batch_cpu_tuning_max_workers = 0 # Control number of workers used in CPU mode for training (0 = socket count -1 = all physical cores >= 1 that count) #cpu_max_workers = 0 # Expected maximum number of forks, used to ensure datatable doesn't overload system. For actual use beyond this value, system will start to have slow-down issues #assumed_simultaneous_dt_forks_munging = 3 # Expected maximum number of forks by computing statistics during ingestion, used to ensure datatable doesn't overload system #assumed_simultaneous_dt_forks_stats_openblas = 1 # Maximum of threads for datatable for munging #max_max_dt_threads_munging = 4 # Expected maximum of threads for datatable no matter if many more cores #max_max_dt_threads_stats_openblas = 8 # Maximum of threads for datatable for reading/writing files #max_max_dt_threads_readwrite = 4 # Maximum parallel workers for final model building. # 0 means automatic, >=1 means limit to no more than that number of parallel jobs. # Can be required if some transformer or model uses more than the expected amount of memory. # Ways to reduce final model building memory usage, e.g. set one or more of these and retrain final model: # 1) Increase munging_memory_overhead_factor to 10 # 2) Increase final_munging_memory_reduction_factor to 10 # 3) Lower max_workers_final_munging to 1 # 4) Lower max_workers_final_base_models to 1 # 5) Lower max_cores to, e.g., 1/2 or 1/4 of physical cores. #max_workers_final_base_models = 0 # Maximum parallel workers for final per-model munging. # 0 means automatic, >=1 means limit to no more than that number of parallel jobs. # Can be required if some transformer uses more than the expected amount of memory. #max_workers_final_munging = 0 # Minimum number of threads for datatable (and OpenMP) during data munging (per process). # datatable is the main data munging tool used within Driverless ai (source : # https://github.com/h2oai/datatable) # #min_dt_threads_munging = 1 # Like min_datatable (and OpenMP)_threads_munging but for final pipeline munging #min_dt_threads_final_munging = 1 # Maximum number of threads for datatable during data munging (per process) (0 = all, -1 = auto). # If multiple forks, threads are distributed across forks. #max_dt_threads_munging = -1 # Maximum number of threads for datatable during data reading and writing (per process) (0 = all, -1 = auto). # If multiple forks, threads are distributed across forks. #max_dt_threads_readwrite = -1 # Maximum number of threads for datatable stats and openblas (per process) (0 = all, -1 = auto). # If multiple forks, threads are distributed across forks. #max_dt_threads_stats_openblas = -1 # Maximum number of threads for datatable during TS properties preview panel computations). #max_dt_threads_do_timeseries_split_suggestion = 1 # Number of GPUs to use per experiment for training task. Set to -1 for all GPUs. # An experiment will generate many different models. # Currently num_gpus_per_experiment!=-1 disables GPU locking, so is only recommended for # single experiments and single users. # Ignored if GPUs disabled or no GPUs on system. # More info at: https://github.com/NVIDIA/nvidia-docker/wiki/nvidia-docker#gpu-isolation # In multinode context when using dask, this refers to the per-node value. # For ImageAutoModel, this refers to the total number of GPUs used for that entire model type, # since there is only one model type for the entire experiment. # E.g. if have 4 GPUs and want 2 ImageAuto experiments to run on 2 GPUs each, can set # num_gpus_per_experiment to 2 for each experiment, and each of the 4 GPUs will be used one at a time # by the 2 experiments each using 2 GPUs only. # #num_gpus_per_experiment = -1 # Number of CPU cores per GPU. Limits number of GPUs in order to have sufficient cores per GPU. # Set to -1 to disable. #min_num_cores_per_gpu = 2 # Number of GPUs to use per model training task. Set to -1 for all GPUs. # For example, when this is set to -1 and there are 4 GPUs available, all of them can be used for the training of a single model. # Only applicable currently to image auto pipeline building recipe or Dask models with more than one GPU or more than one node. # Ignored if GPUs disabled or no GPUs on system. # For ImageAutoModel, the maximum of num_gpus_per_model and num_gpus_per_experiment (all GPUs if -1) is taken. # More info at: https://github.com/NVIDIA/nvidia-docker/wiki/nvidia-docker#gpu-isolation # In multinode context when using Dask, this refers to the per-node value. # #num_gpus_per_model = 1 # Number of GPUs to use for predict for models and transform for transformers when running outside of fit/fit_transform. # -1 means all, 0 means no GPUs, >1 means that many GPUs up to visible limit. # If predict/transform are called in same process as fit/fit_transform, number of GPUs will match, # while new processes will use this count for number of GPUs for applicable models/transformers. # Exception: TensorFlow, PyTorch models/transformers, and RAPIDS predict on GPU always if GPUs exist. # RAPIDS requires python scoring package be used also on GPUs. # In multinode context when using Dask, this refers to the per-node value. # #num_gpus_for_prediction = 0 # Which gpu_id to start with # -1 : auto-mode. E.g. 2 experiments can each set num_gpus_per_experiment to 2 and use 4 GPUs # If using CUDA_VISIBLE_DEVICES=... to control GPUs (preferred method), gpu_id=0 is the # first in that restricted list of devices. # E.g. if CUDA_VISIBLE_DEVICES='4,5' then gpu_id_start=0 will refer to the # device #4. # E.g. from expert mode, to run 2 experiments, each on a distinct GPU out of 2 GPUs: # Experiment#1: num_gpus_per_model=1, num_gpus_per_experiment=1, gpu_id_start=0 # Experiment#2: num_gpus_per_model=1, num_gpus_per_experiment=1, gpu_id_start=1 # E.g. from expert mode, to run 2 experiments, each on a distinct GPU out of 8 GPUs: # Experiment#1: num_gpus_per_model=1, num_gpus_per_experiment=4, gpu_id_start=0 # Experiment#2: num_gpus_per_model=1, num_gpus_per_experiment=4, gpu_id_start=4 # E.g. Like just above, but now run on all 4 GPUs/model # Experiment#1: num_gpus_per_model=4, num_gpus_per_experiment=4, gpu_id_start=0 # Experiment#2: num_gpus_per_model=4, num_gpus_per_experiment=4, gpu_id_start=4 # If num_gpus_per_model!=1, global GPU locking is disabled # (because underlying algorithms don't support arbitrary gpu ids, only sequential ids), # so must setup above correctly to avoid overlap across all experiments by all users # More info at: https://github.com/NVIDIA/nvidia-docker/wiki/nvidia-docker#gpu-isolation # Note that GPU selection does not wrap, so gpu_id_start + num_gpus_per_model must be less than number of visibile GPUs # #gpu_id_start = -1 # Whether to reduce features until model does not fail. # Currently for non-dask XGBoost models (i.e. GLMModel, XGBoostGBMModel, XGBoostDartModel, XGBoostRFModel), # during normal fit or when using Optuna. # Primarily useful for GPU OOM. # If XGBoost runs out of GPU memory, this is detected, and # (regardless of setting of skip_model_failures), # we perform feature selection using XGBoost on subsets of features. # The dataset is progressively reduced by factor of 2 with more models to cover all features. # This splitting continues until no failure occurs. # Then all sub-models are used to estimate variable importance by absolute information gain, # in order to decide which features to include. # Finally, a single model with the most important features # is built using the feature count that did not lead to OOM. # For 'auto', this option is set to 'off' when reproducible experiment is enabled, # because the condition of running OOM can change for same experiment seed. # Reduction is only done on features and not on rows for the feature selection step. # #allow_reduce_features_when_failure = "auto" # With allow_reduce_features_when_failure, this controls how many repeats of sub-models # used for feature selection. A single repeat only has each sub-model # consider a single sub-set of features, while repeats shuffle which # features are considered allowing more chance to find important interactions. # More repeats can lead to higher accuracy. # The cost of this option is proportional to the repeat count. # #reduce_repeats_when_failure = 1 # With allow_reduce_features_when_failure, this controls the fraction of features # treated as an anchor that are fixed for all sub-models. # Each repeat gets new anchors. # For tuning and evolution, the probability depends # upon any prior importance (if present) from other individuals, # while final model uses uniform probability for anchor features. # #fraction_anchor_reduce_features_when_failure = 0.1 # Error strings from XGBoost that are used to trigger re-fit on reduced sub-models. # See allow_reduce_features_when_failure. # #xgboost_reduce_on_errors_list = "['Memory allocation error on worker', 'out of memory', 'XGBDefaultDeviceAllocatorImpl', 'invalid configuration argument', 'Requested memory']" # Error strings from LightGBM that are used to trigger re-fit on reduced sub-models. # See allow_reduce_features_when_failure. # #lightgbm_reduce_on_errors_list = "['Out of Host Memory']" # Kaggle username for automatic submission and scoring of test set predictions. # See https://github.com/Kaggle/kaggle-api#api-credentials for details on how to obtain Kaggle API credentials", # #kaggle_username = "" # Kaggle key for automatic submission and scoring of test set predictions. # See https://github.com/Kaggle/kaggle-api#api-credentials for details on how to obtain Kaggle API credentials", # #kaggle_key = "" # Max. number of seconds to wait for Kaggle API call to return scores for given predictions #kaggle_timeout = 120 #kaggle_keep_submission = false # If provided, can extend the list to arbitrary and potentially future Kaggle competitions to make # submissions for. Only used if kaggle_key and kaggle_username are provided. # Provide a quoted comma-separated list of tuples (target column name, number of test rows, competition, metric) like this: # kaggle_competitions='("target", 200000, "santander-customer-transaction-prediction", "AUC"), ("TARGET", 75818, "santander-customer-satisfaction", "AUC")' # #kaggle_competitions = "" # Period (in seconds) of ping by Driverless AI server to each experiment # (in order to get logger info like disk space and memory usage). # 0 means don't print anything. #ping_period = 60 # Whether to enable ping of system status during DAI experiments. #ping_autodl = true # Minimum amount of disk space in GB needed to run experiments. # Experiments will fail if this limit is crossed. # This limit exists because Driverless AI needs to generate data for model training # feature engineering, documentation and other such processes. #disk_limit_gb = 5 # Minimum amount of disk space in GB needed to before stall forking of new processes during an experiment. #stall_disk_limit_gb = 1 # Minimum amount of system memory in GB needed to start experiments. # Similarly with disk space, a certain amount of system memory is needed to run some basic # operations. #memory_limit_gb = 5 # Minimum number of rows needed to run experiments (values lower than 100 might not work). # A minimum threshold is set to ensure there is enough data to create a statistically # reliable model and avoid other small-data related failures. # #min_num_rows = 100 # Minimum required number of rows (in the training data) for each class label for classification problems. #min_rows_per_class = 5 # Minimum required number of rows for each split when generating validation samples. #min_rows_per_split = 5 # Level of reproducibility desired (for same data and same inputs). # Only active if 'reproducible' mode is enabled (GUI button enabled or a seed is set from the client API). # Supported levels are: # reproducibility_level = 1 for same experiment results as long as same O/S, same CPU(s) and same GPU(s) # reproducibility_level = 2 for same experiment results as long as same O/S, same CPU architecture and same GPU architecture # reproducibility_level = 3 for same experiment results as long as same O/S, same CPU architecture, not using GPUs # reproducibility_level = 4 for same experiment results as long as same O/S, (best effort) # #reproducibility_level = 1 # Seed for random number generator to make experiments reproducible, to a certain reproducibility level (see above). # Only active if 'reproducible' mode is enabled (GUI button enabled or a seed is set from the client API). # #seed = 1234 # The list of values that should be interpreted as missing values during data import. # This applies to both numeric and string columns. Note that the dataset must be reloaded after applying changes to this config via the expert settings. # Also note that 'nan' is always interpreted as a missing value for numeric columns. #missing_values = "['', '?', 'None', 'nan', 'NA', 'N/A', 'unknown', 'inf', '-inf', '1.7976931348623157e+308', '-1.7976931348623157e+308']" # Whether to impute (to mean) for GLM on training data. #glm_nan_impute_training_data = false # Whether to impute (to mean) for GLM on validation data. #glm_nan_impute_validation_data = false # Whether to impute (to mean) for GLM on prediction data (required for consistency with MOJO). #glm_nan_impute_prediction_data = true # For tensorflow, what numerical value to give to missing values, where numeric values are standardized. # So 0 is center of distribution, and if Normal distribution then +-5 is 5 standard deviations away from the center. # In many cases, an out of bounds value is a good way to represent missings, but in some cases the mean (0) may be better. #tf_nan_impute_value = -5 # Internal threshold for number of rows x number of columns to trigger certain statistical # techniques (small data recipe like including one hot encoding for all model types, and smaller learning rate) # to increase model accuracy #statistical_threshold_data_size_small = 100000 # Internal threshold for number of rows x number of columns to trigger certain statistical # techniques (fewer genes created, removal of high max_depth for tree models, etc.) that can speed up modeling. # Also controls maximum rows used in training final model, # by sampling statistical_threshold_data_size_large / columns number of rows #statistical_threshold_data_size_large = 500000000 # Internal threshold for number of rows x number of columns to trigger sampling for auxiliary data uses, # like imbalanced data set detection and bootstrap scoring sample size and iterations #aux_threshold_data_size_large = 10000000 # Internal threshold for set-based method for sampling without replacement. # Can be 10x faster than np_random_choice internal optimized method, and # up to 30x faster than np.random.choice to sample 250k rows from 1B rows etc. #set_method_sampling_row_limit = 5000000 # Internal threshold for number of rows x number of columns to trigger certain changes in performance # (fewer threads if beyond large value) to help avoid OOM or unnecessary slowdowns # (fewer threads if lower than small value) to avoid excess forking of tasks #performance_threshold_data_size_small = 100000 # Internal threshold for number of rows x number of columns to trigger certain changes in performance # (fewer threads if beyond large value) to help avoid OOM or unnecessary slowdowns # (fewer threads if lower than small value) to avoid excess forking of tasks #performance_threshold_data_size_large = 100000000 # Maximum fraction of mismatched columns to allow between train and either valid or test. Beyond this value the experiment will fail with invalid data error. #max_relative_cols_mismatch_allowed = 0.5 # Enable various rules to handle wide (Num. columns > Num. rows) datasets ('auto'/'on'/'off'). Setting on forces rules to be enabled regardless of columns. #enable_wide_rules = "auto" # If columns > wide_factor * rows, then enable wide rules if auto. For columns > rows, random forest is always enabled. #wide_factor = 5.0 # Maximum number of columns to start an experiment. This threshold exists to constraint the # complexity and the length of the Driverless AI's processes. #max_cols = 10000000 # Largest number of rows to use for column stats, otherwise sample randomly #max_rows_col_stats = 1000000 # Largest number of rows to use for cv in cv for target encoding when doing gini scoring test #max_rows_cv_in_cv_gini = 100000 # Largest number of rows to use for constant model fit, otherwise sample randomly #max_rows_constant_model = 1000000 # Largest number of rows to use for final ensemble base model fold cores, otherwise sample randomly #max_rows_final_ensemble_base_model_fold_scores = 1000000 # Largest number of rows to use for final ensemble blender for regression and binary (scaled down linearly by number of classes for multiclass for >= 10 classes), otherwise sample randomly. #max_rows_final_blender = 1000000 # Smallest number of rows (or number of rows if less than this) to use for final ensemble blender. #min_rows_final_blender = 10000 # Largest number of rows to use for final training score (no holdout), otherwise sample randomly #max_rows_final_train_score = 5000000 # Largest number of rows to use for final ROC, lift-gains, confusion matrix, residual, and actual vs. predicted. Otherwise sample randomly #max_rows_final_roccmconf = 1000000 # Largest number of rows to use for final holdout scores, otherwise sample randomly #max_rows_final_holdout_score = 5000000 # Largest number of rows to use for final holdout bootstrap scores, otherwise sample randomly #max_rows_final_holdout_bootstrap_score = 1000000 # Whether to obtain permutation feature importance on original features for reporting in logs and summary zip file # (as files with pattern fs_*.json or fs_*.tab.txt). # This computes feature importance on a single un-tuned model # (typically LightGBM with pre-defined un-tuned hyperparameters) # and simple set of features (encoding typically is frequency encoding or target encoding). # Features with low importance are automatically dropped if there are many original features, # or a model with feature selection by permutation importance is created if interpretability is high enough in order to see if it gives a better score. # One can manually drop low importance features, but this can be risky as transformers or hyperparameters might recover # their usefulness. # Permutation importance is obtained by: # 1) Transforming categoricals to frequency or target encoding features. # 2) Fitting that model on many folds, different data sizes, and slightly varying hyperparameters. # 3) Predicting on that model for each feature where each feature has its data shuffled. # 4) Computing the score on each shuffled prediction. # 5) Computing the difference between the unshuffled score and the shuffled score to arrive at a delta score # 6) The delta score becomes the variable importance once normalized by the maximum. # Positive delta scores indicate the feature helped the model score, # while negative delta scores indicate the feature hurt the model score. # The normalized scores are stored in the fs_normalized_* files in the summary zip. # The unnormalized scores (actual delta scores) are stored in the fs_unnormalized_* files in the summary zip. # AutoDoc has a similar functionality of providing permutation importance on original features, # where that takes the specific final model of an experiment and runs training data set through permutation importance to get original importance, # so shuffling of original features is performed and the full pipeline is computed in each shuffled set of original features. # #orig_features_fs_report = false # Maximum number of rows when doing permutation feature importance, reduced by (stratified) random sampling. # #max_rows_fs = 500000 #max_rows_leak = 100000 # How many workers to use for feature selection by permutation for predict phase. # (0 = auto, > 0: min of DAI value and this value, < 0: exactly negative of this value) # #max_workers_fs = 0 # How many workers to use for shift and leakage checks if using LightGBM on CPU. # (0 = auto, > 0: min of DAI value and this value, < 0: exactly negative of this value) # #max_workers_shift_leak = 0 # Maximum number of columns selected out of original set of original columns, using feature selection. # The selection is based upon how well target encoding (or frequency encoding if not available) on categoricals and numerics treated as categoricals. # This is useful to reduce the final model complexity. First the best # [max_orig_cols_selected] are found through feature selection methods and then # these features are used in feature evolution (to derive other features) and in modelling. # #max_orig_cols_selected = 10000000 # Maximum number of numeric columns selected, above which will do feature selection # same max_orig_cols_selected but for numeric columns. #max_orig_numeric_cols_selected = 10000000 #max_orig_nonnumeric_cols_selected_default = 300 # Maximum number of non-numeric columns selected, above which will do feature selection on all features. Same as max_orig_numeric_cols_selected but for categorical columns. # If set to -1, then auto mode which uses max_orig_nonnumeric_cols_selected_default, but then for small data can be increased up to 10x larger. # #max_orig_nonnumeric_cols_selected = -1 # The factor times max_orig_cols_selected, by which column selection is based upon no target encoding and no treating numerical as categorical # in order to limit performance cost of feature engineering #max_orig_cols_selected_simple_factor = 2 # Like max_orig_cols_selected, but columns above which add special individual with original columns reduced. # #fs_orig_cols_selected = 10000000 # Like max_orig_numeric_cols_selected, but applicable to special individual with original columns reduced. # A separate individual in the genetic algorithm is created by doing feature selection by permutation importance on original features. # #fs_orig_numeric_cols_selected = 10000000 # Like max_orig_nonnumeric_cols_selected, but applicable to special individual with original columns reduced. # A separate individual in the genetic algorithm is created by doing feature selection by permutation importance on original features. # #fs_orig_nonnumeric_cols_selected = 200 # Like max_orig_cols_selected_simple_factor, but applicable to special individual with original columns reduced. #fs_orig_cols_selected_simple_factor = 2 #predict_shuffle_inside_model = true #use_native_cats_for_lgbm_fs = true #orig_stddev_max_cols = 1000 # Maximum allowed fraction of unique values for integer and categorical columns (otherwise will treat column as ID and drop) #max_relative_cardinality = 0.95 # Maximum allowed number of unique values for integer and categorical columns (otherwise will treat column as ID and drop) #max_absolute_cardinality = 1000000 # Whether to treat some numerical features as categorical. # For instance, sometimes an integer column may not represent a numerical feature but # represent different numerical codes instead. # Very restrictive to disable, since then even columns with few categorical levels that happen to be numerical # in value will not be encoded like a categorical. # #num_as_cat = true # Max number of unique values for integer/real columns to be treated as categoricals (test applies to first statistical_threshold_data_size_small rows only) #max_int_as_cat_uniques = 50 # Max number of unique values for integer/real columns to be treated as categoricals (test applies to first statistical_threshold_data_size_small rows only). Applies to integer or real numerical feature that violates Benford's law, and so is ID-like but not entirely an ID. #max_int_as_cat_uniques_if_not_benford = 10000 # When the fraction of non-numeric (and non-missing) values is less or equal than this value, consider the # column numeric. Can help with minor data quality issues for experimentation, > 0 is not recommended for production, # since type inconsistencies can occur. Note: Replaces non-numeric values with missing values # at start of experiment, so some information is lost, but column is now treated as numeric, which can help. # If < 0, then disabled. # If == 0, then if number of rows <= max_rows_col_stats, then convert any column of strings of numbers to numeric type. # #max_fraction_invalid_numeric = 0.0 # Number of folds for models used during the feature engineering process. # Increasing this will put a lower fraction of data into validation and more into training # (e.g., num_folds=3 means 67%/33% training/validation splits). # Actual value will vary for small or big data cases. # #num_folds = 3 #fold_balancing_repeats_times_rows = 100000000.0 #max_fold_balancing_repeats = 10 #fixed_split_seed = 0 #show_fold_stats = true # For multiclass problems only. Whether to allow different sets of target classes across (cross-)validation # fold splits. Especially important when passing a fold column that isn't balanced w.r.t class distribution. # #allow_different_classes_across_fold_splits = true # Accuracy setting equal and above which enables full cross-validation (multiple folds) during feature evolution # as opposed to only a single holdout split (e.g. 2/3 train and 1/3 validation holdout) # #full_cv_accuracy_switch = 9 # Accuracy setting equal and above which enables stacked ensemble as final model. # Stacking commences at the end of the feature evolution process.. # It quite often leads to better model performance, but it does increase the complexity # and execution time of the final model. # #ensemble_accuracy_switch = 5 # Number of fold splits to use for ensemble_level >= 2. # The ensemble modelling may require predictions to be made on out-of-fold samples # hence the data needs to be split on different folds to generate these predictions. # Less folds (like 2 or 3) normally create more stable models, but may be less accurate # More folds can get to higher accuracy at the expense of more time, but the performance # may be less stable when the training data is not enough (i.e. higher chance of overfitting). # Actual value will vary for small or big data cases. # #num_ensemble_folds = 4 # Includes pickles of (train_idx, valid_idx) tuples (numpy row indices for original training data) # for all internal validation folds in the experiment summary zip. For debugging. # #save_validation_splits = false # Number of repeats for each fold for all validation # (modified slightly for small or big data cases) # #fold_reps = 1 #max_num_classes_hard_limit = 10000 # Maximum number of classes to allow for a classification problem. # High number of classes may make certain processes of Driverless AI time-consuming. # Memory requirements also increase with higher number of classes # #max_num_classes = 1000 # Maximum number of classes to compute ROC and CM for, # beyond which roc_reduce_type choice for reduction is applied. # Too many classes can take much longer than model building time. # #max_num_classes_compute_roc = 200 # Maximum number of classes to show in GUI for confusion matrix, showing first max_num_classes_client_and_gui labels. # Beyond 6 classes the diagnostics launched from GUI are visually truncated. # This will only modify client-GUI launched diagnostics if changed in config.toml and server is restarted, # while this value can be changed in expert settings to control experiment plots. # #max_num_classes_client_and_gui = 10 # If too many classes when computing roc, # reduce by "rows" by randomly sampling rows, # or reduce by truncating classes to no more than max_num_classes_compute_roc. # If have sufficient rows for class count, can reduce by rows. # #roc_reduce_type = "rows" #min_roc_sample_size = 1 # Maximum number of rows to obtain confusion matrix related plots during feature evolution. # Does not limit final model calculation. # #max_rows_cm_ga = 500000 # Number of actuals vs. predicted data points to use in order to generate in the relevant # plot/graph which is shown at the right part of the screen within an experiment. #num_actuals_vs_predicted = 100 # Whether to use feature_brain results even if running new experiments. # Feature brain can be risky with some types of changes to experiment setup. # Even rescoring may be insufficient, so by default this is False. # For example, one experiment may have training=external validation by accident, and get high score, # and while feature_brain_reset_score='on' means we will rescore, it will have already seen # during training the external validation and leak that data as part of what it learned from. # If this is False, feature_brain_level just sets possible models to use and logs/notifies, # but does not use these feature brain cached models. # #use_feature_brain_new_experiments = false # Whether reuse dataset schema, such as data types set in UI for each column, from parent experiment ('on') or to ignore original dataset schema and only use new schema ('off'). # resume_data_schema=True is a basic form of data lineage, but it may not be desirable if data colunn names changed to incompatible data types like int to string. # 'auto': for restart, retrain final pipeline, or refit best models, default is to resume data schema, but new experiments would not by default reuse old schema. # 'on': force reuse of data schema from parent experiment if possible # 'off': don't reuse data schema under any case. # The reuse of the column schema can also be disabled by: # in UI: selecting Parent Experiment as None # in client: setting resume_experiment_id to None #resume_data_schema = "auto" #resume_data_schema_old_logic = false # Whether to show (or use) results from H2O.ai brain: the local caching and smart re-use of prior experiments, # in order to generate more useful features and models for new experiments. # See use_feature_brain_new_experiments for how new experiments by default do not use brain cache. # It can also be used to control checkpointing for experiments that have been paused or interrupted. # DAI will use H2O.ai brain cache if cache file has # a) any matching column names and types for a similar experiment type # b) exactly matches classes # c) exactly matches class labels # d) matches basic time series choices # e) interpretability of cache is equal or lower # f) main model (booster) is allowed by new experiment. # Level of brain to use (for chosen level, where higher levels will also do all lower level operations automatically) # -1 = Don't use any brain cache and don't write any cache # 0 = Don't use any brain cache but still write cache # Use case: Want to save model for later use, but want current model to be built without any brain models # 1 = smart checkpoint from latest best individual model # Use case: Want to use latest matching model, but match can be loose, so needs caution # 2 = smart checkpoint from H2O.ai brain cache of individual best models # Use case: DAI scans through H2O.ai brain cache for best models to restart from # 3 = smart checkpoint like level #1, but for entire population. Tune only if brain population insufficient size # (will re-score entire population in single iteration, so appears to take longer to complete first iteration) # 4 = smart checkpoint like level #2, but for entire population. Tune only if brain population insufficient size # (will re-score entire population in single iteration, so appears to take longer to complete first iteration) # 5 = like #4, but will scan over entire brain cache of populations to get best scored individuals # (can be slower due to brain cache scanning if big cache) # 1000 + feature_brain_level (above positive values) = use resumed_experiment_id and actual feature_brain_level, # to use other specific experiment as base for individuals or population, # instead of sampling from any old experiments # GUI has 3 options and corresponding settings: # 1) New Experiment: Uses feature brain level default of 2 # 2) New Experiment With Same Settings: Re-uses the same feature brain level as parent experiment # 3) Restart From Last Checkpoint: Resets feature brain level to 1003 and sets experiment ID to resume from # (continued genetic algorithm iterations) # 4) Retrain Final Pipeline: Like Restart but also time=0 so skips any tuning and heads straight to final model # (assumes had at least one tuning iteration in parent experiment) # Other use cases: # a) Restart on different data: Use same column names and fewer or more rows (applicable to 1 - 5) # b) Re-fit only final pipeline: Like (a), but choose time=1 and feature_brain_level=3 - 5 # c) Restart with more columns: Add columns, so model builds upon old model built from old column names (1 - 5) # d) Restart with focus on model tuning: Restart, then select feature_engineering_effort = 3 in expert settings # e) can retrain final model but ignore any original features except those in final pipeline (normal retrain but set brain_add_features_for_new_columns=false) # Notes: # 1) In all cases, we first check the resumed experiment id if given, and then the brain cache # 2) For Restart cases, may want to set min_dai_iterations to non-zero to force delayed early stopping, else may not be enough iterations to find better model. # 3) A "New experiment with Same Settings" of a Restart will use feature_brain_level=1003 for default Restart mode (revert to 2, or even 0 if want to start a fresh experiment otherwise) #feature_brain_level = 2 # Whether to smartly keep score to avoid re-munging/re-training/re-scoring steps brain models ('auto'), always # force all steps for all brain imports ('on'), or never rescore ('off'). # 'auto' only re-scores if a difference in current and prior experiment warrants re-scoring, like column changes, metric changes, etc. # 'on' is useful when smart similarity checking is not reliable enough. # 'off' is uesful when know want to keep exact same features and model for final model refit, despite changes in seed or other behaviors # in features that might change the outcome if re-scored before reaching final model. # If set off, then no limits are applied to features during brain ingestion, # while can set brain_add_features_for_new_columns to false if want to ignore any new columns in data. # In addition, any unscored individuals loaded from parent experiment are not rescored when doing refit or retrain. # Can also set refit_same_best_individual True if want exact same best individual (highest scored model+features) to be used # regardless of any scoring changes. # #feature_brain_reset_score = "auto" #enable_strict_confict_key_check_for_brain = true #allow_change_layer_count_brain = false # Relative number of columns that must match between current reference individual and brain individual. # 0.0: perfect match # 1.0: All columns are different, worst match # e.g. 0.1 implies no more than 10% of columns mismatch between reference set of columns and brain individual. # #brain_maximum_diff_score = 0.1 # Maximum number of brain individuals pulled from H2O.ai brain cache for feature_brain_level=1, 2 #max_num_brain_indivs = 3 # Save feature brain iterations every iter_num % feature_brain_iterations_save_every_iteration == 0, to be able to restart/refit with which_iteration_brain >= 0 # 0 means disable # #feature_brain_save_every_iteration = 0 # When doing restart or re-fit type feature_brain_level with resumed_experiment_id, choose which iteration to start from, instead of only last best # -1 means just use last best # Usage: # 1) Run one experiment with feature_brain_iterations_save_every_iteration=1 or some other number # 2) Identify which iteration brain dump one wants to restart/refit from # 3) Restart/Refit from original experiment, setting which_iteration_brain to that number in expert settings # Note: If restart from a tuning iteration, this will pull in entire scored tuning population and use that for feature evolution # #which_iteration_brain = -1 # When doing re-fit from feature brain, if change columns or features, population of individuals used to refit from may change order of which was best, # leading to better result chosen (False case). But sometimes want to see exact same model/features with only one feature added, # and then would need to set this to True case. # E.g. if refit with just 1 extra column and have interpretability=1, then final model will be same features, # with one more engineered feature applied to that new original feature. # #refit_same_best_individual = false # When doing restart or re-fit of experiment from feature brain, # sometimes user might change data significantly and then warrant # redoing reduction of original features by feature selection, shift detection, and leakage detection. # However, in other cases, if data and all options are nearly (or exactly) identical, then these # steps might change the features slightly (e.g. due to random seed if not setting reproducible mode), # leading to changes in features and model that is refitted. By default, restart and refit avoid # these steps assuming data and experiment setup have no changed significantly. # If check_distribution_shift is forced to on (instead of auto), then this option is ignored. # In order to ensure exact same final pipeline is fitted, one should also set: # 1) brain_add_features_for_new_columns false # 2) refit_same_best_individual true # 3) feature_brain_reset_score 'off' # 4) force_model_restart_to_defaults false # The score will still be reset if the experiment metric chosen changes, # but changes to the scored model and features will be more frozen in place. # #restart_refit_redo_origfs_shift_leak = "[]" # Directory, relative to data_directory, to store H2O.ai brain meta model files #brain_rel_dir = "H2O.ai_brain" # Maximum size in bytes the brain will store # We reserve this memory to save data in order to ensure we can retrieve an experiment if # for any reason it gets interrupted. # -1: unlimited # >=0 number of GB to limit brain to #brain_max_size_GB = 20 # Whether to take any new columns and add additional features to pipeline, even if doing retrain final model. # In some cases, one might have a new dataset but only want to keep same pipeline regardless of new columns, # in which case one sets this to False. For example, new data might lead to new dropped features, # due to shift or leak detection. To avoid change of feature set, one can disable all dropping of columns, # but set this to False to avoid adding any columns as new features, # so pipeline is perfectly preserved when changing data. # #brain_add_features_for_new_columns = true # If restart/refit and no longer have the original model class available, be conservative # and go back to defaults for that model class. If False, then try to keep original hyperparameters, # which can fail to work in general. # #force_model_restart_to_defaults = true # Whether to enable early stopping # Early stopping refers to stopping the feature evolution/engineering process # when there is no performance uplift after a certain number of iterations. # After early stopping has been triggered, Driverless AI will initiate the ensemble # process if selected. #early_stopping = true # Whether to enable early stopping per individual # Each individual in the generic algorithm will stop early if no improvement, # and it will no longer be mutated. # Instead, the best individual will be additionally mutated. #early_stopping_per_individual = true # Minimum number of Driverless AI iterations to stop the feature evolution/engineering # process even if score is not improving. Driverless AI needs to run for at least that many # iterations before deciding to stop. It can be seen a safeguard against suboptimal (early) # convergence. # #min_dai_iterations = 0 # Maximum features per model (and each model within the final model if ensemble) kept. # Keeps top variable importance features, prunes rest away, after each scoring. # Final ensemble will exclude any pruned-away features and only train on kept features, # but may contain a few new features due to fitting on different data view (e.g. new clusters) # Final scoring pipeline will exclude any pruned-away features, # but may contain a few new features due to fitting on different data view (e.g. new clusters) # -1 means no restrictions except internally-determined memory and interpretability restrictions. # Notes: # * If interpretability > remove_scored_0gain_genes_in_postprocessing_above_interpretability, then # every GA iteration post-processes features down to this value just after scoring them. Otherwise, # only mutations of scored individuals will be pruned (until the final model where limits are strictly applied). # * If ngenes_max is not also limited, then some individuals will have more genes and features until # pruned by mutation or by preparation for final model. # * E.g. to generally limit every iteration to exactly 1 features, one must set nfeatures_max=ngenes_max=1 # and remove_scored_0gain_genes_in_postprocessing_above_interpretability=0, but the genetic algorithm # will have a harder time finding good features. # #nfeatures_max = -1 # Maximum genes (transformer instances) per model (and each model within the final model if ensemble) kept. # Controls number of genes before features are scored, so just randomly samples genes if pruning occurs. # If restriction occurs after scoring features, then aggregated gene importances are used for pruning genes. # Instances includes all possible transformers, including original transformer for numeric features. # -1 means no restrictions except internally-determined memory and interpretability restrictions # #ngenes_max = -1 # Like ngenes_max but controls minimum number of genes. # Useful when DAI by default is making too few genes but want many more. # This can be useful when one has few input features, so DAI may remain conservative and not make many transformed features. But user knows that some transformed features may be useful. # E.g. only target encoding transformer might have been chosen, and one wants DAI to explore many more possible input features at once. #ngenes_min = -1 # Whether to limit feature counts by interpretability setting via features_allowed_by_interpretability #limit_features_by_interpretability = true # Whether to use out-of-fold predictions of Word-based CNN TensorFlow models as transformers for NLP if TensorFlow enabled #enable_tensorflow_textcnn = "auto" # Whether to use out-of-fold predictions of Word-based Bi-GRU TensorFlow models as transformers for NLP if TensorFlow enabled #enable_tensorflow_textbigru = "auto" # Whether to use out-of-fold predictions of Character-level CNN TensorFlow models as transformers for NLP if TensorFlow enabled #enable_tensorflow_charcnn = "auto" # Whether to use pretrained PyTorch models as transformers for NLP tasks. Fits a linear model on top of pretrained embeddings. Requires internet connection. Default of 'auto' means disabled. To enable, set to 'on'. GPU(s) are highly recommended.Set string_col_as_text_min_relative_cardinality=0.0 to force string column to be treated as text despite low number of uniques. #enable_pytorch_nlp_transformer = "auto" # More rows can slow down the fitting process. Recommended values are less than 100000. #pytorch_nlp_transformer_max_rows_linear_model = 50000 # Whether to use pretrained PyTorch models and fine-tune them for NLP tasks. Requires internet connection. Default of 'auto' means disabled. To enable, set to 'on'. These models are only using the first text column, and can be slow to train. GPU(s) are highly recommended.Set string_col_as_text_min_relative_cardinality=0.0 to force string column to be treated as text despite low number of uniques. #enable_pytorch_nlp_model = "auto" # Select which pretrained PyTorch NLP model(s) to use. Non-default ones might have no MOJO support. Requires internet connection. Only if PyTorch models or transformers for NLP are set to 'on'. #pytorch_nlp_pretrained_models = "['bert-base-uncased', 'distilbert-base-uncased', 'bert-base-multilingual-cased']" # Max. number of epochs for TensorFlow models for making NLP features #tensorflow_max_epochs_nlp = 2 # Accuracy setting equal and above which will add all enabled TensorFlow NLP models below at start of experiment for text dominated problems # when TensorFlow NLP transformers are set to auto. If set to on, this parameter is ignored. # Otherwise, at lower accuracy, TensorFlow NLP transformations will only be created as a mutation. # #enable_tensorflow_nlp_accuracy_switch = 5 # Path to pretrained embeddings for TensorFlow NLP models, can be a path in local file system or an S3 location (s3://). # For example, download and unzip https://nlp.stanford.edu/data/glove.6B.zip # tensorflow_nlp_pretrained_embeddings_file_path = /path/on/server/to/glove.6B.300d.txt # #tensorflow_nlp_pretrained_embeddings_file_path = "" #tensorflow_nlp_pretrained_s3_access_key_id = "" #tensorflow_nlp_pretrained_s3_secret_access_key = "" # Allow training of all weights of the neural network graph, including the pretrained embedding layer weights. If disabled, then the embedding layer is frozen, but all other weights are still fine-tuned. #tensorflow_nlp_pretrained_embeddings_trainable = false #tensorflow_nlp_have_gpus_in_production = false #bert_migration_timeout_secs = 600 #enable_bert_transformer_acceptance_test = false #enable_bert_model_acceptance_test = false # Whether to parallelize tokenization for BERT Models/Transformers. #pytorch_tokenizer_parallel = true # Number of epochs for fine-tuning of PyTorch NLP models. Larger values can increase accuracy but take longer to train. #pytorch_nlp_fine_tuning_num_epochs = -1 # Batch size for PyTorch NLP models. Larger models and larger batch sizes will use more memory. #pytorch_nlp_fine_tuning_batch_size = -1 # Maximum sequence length (padding length) for PyTorch NLP models. Larger models and larger padding lengths will use more memory. #pytorch_nlp_fine_tuning_padding_length = -1 # Path to pretrained PyTorch NLP models. Note that this can be either a path in the local file system # (/path/on/server/to/bert_models_folder), an URL or a S3 location (s3://). # To get all models, download http://s3.amazonaws.com/artifacts.h2o.ai/releases/ai/h2o/pretrained/bert_models.zip # and unzip and store it in a directory on the instance where DAI is installed. # pytorch_nlp_pretrained_models_dir=/path/on/server/to/bert_models_folder # #pytorch_nlp_pretrained_models_dir = "" #pytorch_nlp_pretrained_s3_access_key_id = "" #pytorch_nlp_pretrained_s3_secret_access_key = "" # Fraction of text columns out of all features to be considered a text-dominated problem #text_fraction_for_text_dominated_problem = 0.3 # Fraction of text transformers to all transformers above which to trigger that text dominated problem #text_transformer_fraction_for_text_dominated_problem = 0.3 # Whether to reduce options for text-dominated models to reduce expense, e.g. disable ensemble, disable genetic algorithm, single identity target encoder for classification, etc. #text_dominated_limit_tuning = true # Whether to reduce options for image-dominated models to reduce expense, e.g. disable ensemble, disable genetic algorithm, single identity target encoder for classification, etc. #image_dominated_limit_tuning = true # Threshold for average string-is-text score as determined by internal heuristics # It decides when a string column will be treated as text (for an NLP problem) or just as # a standard categorical variable. # Higher values will favor string columns as categoricals, lower values will favor string columns as text. # Set string_col_as_text_min_relative_cardinality=0.0 to force string column to be treated as text despite low number of uniques. #string_col_as_text_threshold = 0.3 # Threshold for string columns to be treated as text during preview - should be less than string_col_as_text_threshold to allow data with first 20 rows that don't look like text to still work for Text-only transformers (0.0 - text, 1.0 - string) #string_col_as_text_threshold_preview = 0.1 # Mininum fraction of unique values for string columns to be considered as possible text (otherwise categorical) #string_col_as_text_min_relative_cardinality = 0.1 # Mininum number of uniques for string columns to be considered as possible text (if not already) #string_col_as_text_min_absolute_cardinality = 10000 # If disabled, require 2 or more alphanumeric characters for a token in Text (Count and TF/IDF) transformers, otherwise create tokens out of single alphanumeric characters. True means that 'Street 3' is tokenized into 'Street' and '3', while False means that it's tokenized into 'Street'. #tokenize_single_chars = true # Supported image types. URIs with these endings will be considered as image paths (local or remote). #supported_image_types = "['jpg', 'jpeg', 'png', 'bmp', 'ppm', 'tif', 'tiff', 'JPG', 'JPEG', 'PNG', 'BMP', 'PPM', 'TIF', 'TIFF']" # Whether to create absolute paths for images when importing datasets containing images. Can faciliate testing or re-use of frames for scoring. #image_paths_absolute = false # Whether to use pretrained deep learning models for processing of image data as part of the feature engineering pipeline. A column of URIs to images (jpg, png, etc.) will be converted to a numeric representation using ImageNet-pretrained deep learning models. If no GPUs are found, then must be set to 'on' to enable. #enable_tensorflow_image = "auto" 
 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488  # Supported ImageNet pretrained architectures for Image Transformer. Non-default ones will require internet access to download pretrained models from H2O S3 buckets (To get all models, download http://s3.amazonaws.com/artifacts.h2o.ai/releases/ai/h2o/pretrained/dai_image_models_1_10.zip and unzip inside tensorflow_image_pretrained_models_dir). #tensorflow_image_pretrained_models = "['xception']" # Dimensionality of feature (embedding) space created by Image Transformer. If more than one is selected, multiple transformers can be active at the same time. #tensorflow_image_vectorization_output_dimension = "[100]" # Enable fine-tuning of the ImageNet pretrained models used for the Image Transformer. Enabling this will slow down training, but should increase accuracy. #tensorflow_image_fine_tune = false # Number of epochs for fine-tuning of ImageNet pretrained models used for the Image Transformer. #tensorflow_image_fine_tuning_num_epochs = 2 # The list of possible image augmentations to apply while fine-tuning the ImageNet pretrained models used for the Image Transformer. Details about individual augmentations could be found here: https://albumentations.ai/docs/. #tensorflow_image_augmentations = "['HorizontalFlip']" # Batch size for Image Transformer. Larger architectures and larger batch sizes will use more memory. #tensorflow_image_batch_size = -1 # Path to pretrained Image models. # To get all models, download http://s3.amazonaws.com/artifacts.h2o.ai/releases/ai/h2o/pretrained/dai_image_models_1_10.zip, # then extract it in a directory on the instance where Driverless AI is installed. # #tensorflow_image_pretrained_models_dir = "./pretrained/image/" # Max. number of seconds to wait for image download if images are provided by URL #image_download_timeout = 60 # Maximum fraction of missing elements in a string column for it to be considered as possible image paths (URIs) #string_col_as_image_max_missing_fraction = 0.1 # Fraction of (unique) image URIs that need to have valid endings (as defined by string_col_as_image_valid_types) for a string column to be considered as image data #string_col_as_image_min_valid_types_fraction = 0.8 # Whether to use GPU(s), if available, to transform images into embeddings with Image Transformer. Can lead to significant speedups. #tensorflow_image_use_gpu = true # Nominally, the time dial controls the search space, with higher time trying more options, but any keys present in this dictionary will override the automatic choices. # e.g. params_image_auto_search_space="{'augmentation': ['safe'], 'crop_strategy': ['Resize'], 'optimizer': ['AdamW'], 'dropout': [0.1], 'epochs_per_stage': [5], 'warmup_epochs': [0], 'mixup': [0.0], 'cutmix': [0.0], 'global_pool': ['avg'], 'learning_rate': [3e-4]}" # Options, e.g. used for time>=8 # # Overfit Protection Options: # 'augmentation': ["safe", "semi_safe", "hard"] # 'crop_strategy': ["Resize", "RandomResizedCropSoft", "RandomResizedCropHard"] # 'dropout': [0.1, 0.3, 0.5] # # Global Pool Options: # avgmax -- sum of AVG and MAX poolings # catavgmax -- concatenation of AVG and MAX poolings # https://github.com/rwightman/pytorch-image-models/blob/master/timm/models/layers/adaptive_avgmax_pool.py # 'global_pool': ['avg', 'avgmax', 'catavgmax'] # # Regression: No MixUp and CutMix: # 'mixup': [0.0] # 'cutmix': [0.0] # # Classification: Beta distribution coeff to generate weights for MixUp: # 'mixup': [0.0, 0.4, 1.0, 3.0] # 'cutmix': [0.0, 0.4, 1.0, 3.0] # # Optimization Options: # 'epochs_per_stage': [5, 10, 15] # from 40 to 135 epochs # 'warmup_epochs': [0, 0.5, 1] # 'optimizer': ["AdamW", "SGD"] # 'learning_rate': [1e-3, 3e-4, 1e-4] #params_image_auto_search_space = "{}" # Nominally, the accuracy dial controls the architectures considered if this is left empty, # but one can choose specific ones. The options in the list are ordered by complexity. #image_auto_arch = "[]" # Any images smaller are upscaled to the minimum. Default is 64, but can be as small as 32 given the pooling layers used. #image_auto_min_shape = 64 # 0 means automatic based upon time dial of min(1, time//2). #image_auto_num_final_models = 0 # 0 means automatic based upon time dial of max(4 * (time - 1), 2). #image_auto_num_models = 0 # 0 means automatic based upon time dial of time + 1 if time < 6 else time - 1. #image_auto_num_stages = 0 # 0 means automatic based upon time dial or number of models and stages # set by image_auto_num_models and image_auto_num_stages. #image_auto_iterations = 0 # 0.0 means automatic based upon the current stage, where stage 0 uses half, stage 1 uses 3/4, and stage 2 uses full image. # One can pass 1.0 to override and always use full image. 0.5 would mean use half. #image_auto_shape_factor = 0.0 # Control maximum number of cores to use for image auto model parallel data management. 0 will disable mp: https://pytorch-lightning.readthedocs.io/en/latest/guides/speed.html #max_image_auto_ddp_cores = 10 # Percentile value cutoff of input text token lengths for nlp deep learning models #text_dl_token_pad_percentile = 99 # Maximum token length of input text to be used in nlp deep learning models #text_dl_token_pad_max = 512 # Interpretability setting equal and above which will use automatic monotonicity constraints in # XGBoostGBM/LightGBM/DecisionTree models. # #monotonicity_constraints_interpretability_switch = 7 # For models that support monotonicity constraints, and if enabled, show automatically determined monotonicity constraints for each feature going into the model based on its correlation with the target. 'low' shows only monotonicity constraint direction. 'medium' shows correlation of positively and negatively constraint features. 'high' shows all correlation values. #monotonicity_constraints_log_level = "medium" # Threshold, of Pearson product-moment correlation coefficient between numerical or encoded transformed # feature and target, above (below negative for) which will enforce positive (negative) monotonicity # for XGBoostGBM, LightGBM and DecisionTree models. # Enabled when interpretability >= monotonicity_constraints_interpretability_switch config toml value. # Only if monotonicity_constraints_dict is not provided. # #monotonicity_constraints_correlation_threshold = 0.1 # If enabled, only monotonic features with +1/-1 constraints will be passed to the model(s), and features # without monotonicity constraints (0, as set by monotonicity_constraints_dict or determined automatically) # will be dropped. Otherwise all features will be in the model. # Only active when interpretability >= monotonicity_constraints_interpretability_switch or # monotonicity_constraints_dict is provided. # #monotonicity_constraints_drop_low_correlation_features = false # Manual override for monotonicity constraints. Mapping of original numeric features to desired constraint # (1 for pos, -1 for neg, or 0 to disable. True can be set for automatic handling, False is same as 0). # Features that are not listed here will be treated automatically, # and so get no constraint (i.e., 0) if interpretability < monotonicity_constraints_interpretability_switch # and otherwise the constraint is automatically determined from the correlation between each feature and the target. # Example: {'PAY_0': -1, 'PAY_2': -1, 'AGE': -1, 'BILL_AMT1': 1, 'PAY_AMT1': -1} # #monotonicity_constraints_dict = "{}" # Exploring feature interactions can be important in gaining better predictive performance. # The interaction can take multiple forms (i.e. feature1 + feature2 or feature1 * feature2 + ... featureN) # Although certain machine learning algorithms (like tree-based methods) can do well in # capturing these interactions as part of their training process, still generating them may # help them (or other algorithms) yield better performance. # The depth of the interaction level (as in "up to" how many features may be combined at # once to create one single feature) can be specified to control the complexity of the # feature engineering process. For transformers that use both numeric and categorical features, this constrains # the number of each type, not the total number. Higher values might be able to make more predictive models # at the expense of time (-1 means automatic). # #max_feature_interaction_depth = -1 # Instead of sampling from min to max (up to max_feature_interaction_depth unless all specified) # columns allowed for each transformer (0), choose fixed non-zero number of columns to use. # Can make same as number of columns to use all columns for each transformers if allowed by each transformer. # -n can be chosen to do 50/50 sample and fixed of n features. # #fixed_feature_interaction_depth = 0 # Accuracy setting equal and above which enables tuning of model parameters # Only applicable if parameter_tuning_num_models=-1 (auto) #tune_parameters_accuracy_switch = 3 # Accuracy setting equal and above which enables tuning of target transform for regression. # This is useful for time series when instead of predicting the actual target value, it # might be better to predict a transformed target variable like sqrt(target) or log(target) # as a means to control for outliers. #tune_target_transform_accuracy_switch = 5 # Select a target transformation for regression problems. Must be one of: ['auto', # 'identity', 'identity_noclip', 'center', 'standardize', 'unit_box', 'log', 'log_noclip', 'square', # 'sqrt', 'double_sqrt', 'inverse', 'anscombe', 'logit', 'sigmoid']. # If set to 'auto', will automatically pick the best target transformer (if accuracy is set to # tune_target_transform_accuracy_switch or larger, considering interpretability level of each target transformer), # otherwise will fall back to 'identity_noclip' (easiest to interpret, Shapley values are in original space, etc.). # All transformers except for 'center', 'standardize', 'identity_noclip' and 'log_noclip' perform clipping # to constrain the predictions to the domain of the target in the training data. Use 'center', 'standardize', # 'identity_noclip' or 'log_noclip' to disable clipping and to allow predictions outside of the target domain observed in # the training data (for parametric models or custom models that support extrapolation). # #target_transformer = "auto" # Select list of target transformers to use for tuning. Only for target_transformer='auto' and accuracy >= tune_target_transform_accuracy_switch. # #target_transformer_tuning_choices = "['identity', 'identity_noclip', 'center', 'standardize', 'unit_box', 'log', 'square', 'sqrt', 'double_sqrt', 'anscombe', 'logit', 'sigmoid']" # Tournament style (method to decide which models are best at each iteration) # 'auto' : Choose based upon accuracy and interpretability # 'uniform' : all individuals in population compete to win as best (can lead to all, e.g. LightGBM models in final ensemble, which may not improve ensemble performance due to lack of diversity) # 'model' : individuals with same model type compete (good if multiple models do well but some models that do not do as well still contribute to improving ensemble) # 'feature' : individuals with similar feature types compete (good if target encoding, frequency encoding, and other feature sets lead to good results) # 'fullstack' : Choose among optimal model and feature types # 'model' and 'feature' styles preserve at least one winner for each type (and so 2 total indivs of each type after mutation) # For each case, a round robin approach is used to choose best scores among type of models to choose from. # If enable_genetic_algorithm=='Optuna', then every individual is self-mutated without any tournament # during the genetic algorithm. The tournament is only used to prune-down individuals for, e.g., # tuning -> evolution and evolution -> final model. # #tournament_style = "auto" # Interpretability above which will use 'uniform' tournament style #tournament_uniform_style_interpretability_switch = 8 # Accuracy below which will use uniform style if tournament_style = 'auto' (regardless of other accuracy tournament style switch values) #tournament_uniform_style_accuracy_switch = 6 # Accuracy equal and above which uses model style if tournament_style = 'auto' #tournament_model_style_accuracy_switch = 6 # Accuracy equal and above which uses feature style if tournament_style = 'auto' #tournament_feature_style_accuracy_switch = 13 # Accuracy equal and above which uses fullstack style if tournament_style = 'auto' #tournament_fullstack_style_accuracy_switch = 13 # Whether to use penalized score for GA tournament or actual score #tournament_use_feature_penalized_score = true # Whether to keep poor scores for small data (<10k rows) in case exploration will find good model. # sets tournament_remove_poor_scores_before_evolution_model_factor=1.1 # tournament_remove_worse_than_constant_before_evolution=false # tournament_keep_absolute_ok_scores_before_evolution_model_factor=1.1 # tournament_remove_poor_scores_before_final_model_factor=1.1 # tournament_remove_worse_than_constant_before_final_model=true #tournament_keep_poor_scores_for_small_data = true # Factor (compared to best score plus each score) beyond which to drop poorly scoring models before evolution. # This is useful in cases when poorly scoring models take a long time to train. #tournament_remove_poor_scores_before_evolution_model_factor = 0.7 # For before evolution after tuning, whether to remove models that are worse than (optimized to scorer) constant prediction model #tournament_remove_worse_than_constant_before_evolution = true # For before evolution after tuning, where on scale of 0 (perfect) to 1 (constant model) to keep ok scores by absolute value. #tournament_keep_absolute_ok_scores_before_evolution_model_factor = 0.2 # Factor (compared to best score) beyond which to drop poorly scoring models before building final ensemble. This is useful in cases when poorly scoring models take a long time to train. #tournament_remove_poor_scores_before_final_model_factor = 0.3 # For before final model after evolution, whether to remove models that are worse than (optimized to scorer) constant prediction model #tournament_remove_worse_than_constant_before_final_model = true # Driverless AI uses a genetic algorithm (GA) to find the best features, best models and # best hyper parameters for these models. The GA facilitates getting good results while not # requiring torun/try every possible model/feature/parameter. This version of GA has # reinforcement learning elements - it uses a form of exploration-exploitation to reach # optimum solutions. This means it will capitalise on models/features/parameters that seem # to be working well and continue to exploit them even more, while allowing some room for # trying new (and semi-random) models/features/parameters to avoid settling on a local # minimum. # These models/features/parameters tried are what-we-call individuals of a population. More # individuals connote more models/features/parameters to be tried and compete to find the best # ones. #num_individuals = 2 # set fixed number of individuals (if > 0) - useful to compare different hardware configurations. If want 3 individuals in GA race to be preserved, choose 6, since need 1 mutatable loser per surviving individual. #fixed_num_individuals = 0 #max_fold_reps_hard_limit = 20 # number of unique targets or folds counts after which switch to faster/simpler non-natural sorting and print outs #sanitize_natural_sort_limit = 1000 # Whether target encoding (CV target encoding, weight of evidence, etc.) could be enabled # Target encoding refers to several different feature transformations (primarily focused on # categorical data) that aim to represent the feature using information of the actual # target variable. A simple example can be to use the mean of the target to replace each # unique category of a categorical feature. This type of features can be very predictive, # but are prone to overfitting and require more memory as they need to store mappings of # the unique categories and the target values. # #enable_target_encoding = "auto" # For target encoding, whether a model is used to compute Ginis for checking sanity of transformer. Requires cvte_cv_in_cv to be enabled. If enabled, CV-in-CV isn't done in case the check fails. #cvte_cv_in_cv_use_model = false # For target encoding, # whether an outer level of cross-fold validation is performed, # in cases when GINI is detected to flip sign (or have inconsistent sign for weight of evidence) # between fit_transform on training, transform on training, and transform on validation data. # The degree to which GINI is poor is also used to perform fold-averaging of look-up tables instead # of using global look-up tables. # #cvte_cv_in_cv = true # For target encoding, # when an outer level of cross-fold validation is performed, # increase number of outer folds or abort target encoding when GINI between feature and target # are not close between fit_transform on training, transform on training, and transform on validation data. # #cv_in_cv_overconfidence_protection = "auto" #cv_in_cv_overconfidence_protection_factor = 3.0 #enable_lexilabel_encoding = "off" #enable_isolation_forest = "off" # Whether one hot encoding could be enabled. If auto, then only applied for small data and GLM. #enable_one_hot_encoding = "auto" # Limit number of output features (total number of bins) created by all BinnerTransformers based on this # value, scaled by accuracy, interpretability and dataset size. 0 means unlimited. #binner_cardinality_limiter = 50 # Whether simple binning of numeric features should be enabled by default. If auto, then only for # GLM/FTRL/TensorFlow/GrowNet for time-series or for interpretability >= 6. Binning can help linear (or simple) # models by exposing more signal for features that are not linearly correlated with the target. Note that # NumCatTransformer and NumToCatTransformer already do binning, but also perform target encoding, which makes them # less interpretable. The BinnerTransformer is more interpretable, and also works for time series. #enable_binning = "auto" # Tree uses XGBoost to find optimal split points for binning of numeric features. # Quantile use quantile-based binning. Might fall back to quantile-based if too many classes or # not enough unique values. #binner_bin_method = "['tree']" # If enabled, will attempt to reduce the number of bins during binning of numeric features. # Applies to both tree-based and quantile-based bins. #binner_minimize_bins = true # Given a set of bins (cut points along min...max), the encoding scheme converts the original # numeric feature values into the values of the output columns (one column per bin, and one extra bin for # missing values if any). # Piecewise linear is 0 left of the bin, and 1 right of the bin, and grows linearly from 0 to 1 inside the bin. # Binary is 1 inside the bin and 0 outside the bin. Missing value bin encoding is always binary, either 0 or 1. # If no missing values in the data, then there is no missing value bin. # Piecewise linear helps to encode growing values and keeps smooth transitions across the bin # boundaries, while binary is best suited for detecting specific values in the data. # Both are great at providing features to models that otherwise lack non-linear pattern detection. #binner_encoding = "['piecewise_linear', 'binary']" # If enabled (default), include the original feature value as a output feature for the BinnerTransformer. # This ensures that the BinnerTransformer never has less signal than the OriginalTransformer, since they can # be chosen exclusively. # #binner_include_original = true #isolation_forest_nestimators = 200 # Transformer display names to indicate which transformers to use in experiment. # More information for these transformers can be viewed here: # http://docs.h2o.ai/driverless-ai/latest-stable/docs/userguide/transformations.html # This section allows including/excluding these transformations and may be useful when # simpler (more interpretable) models are sought at the expense of accuracy. # the interpretability setting) # for multi-class: '['NumCatTETransformer', 'TextLinModelTransformer', # 'FrequentTransformer', 'CVTargetEncodeTransformer', 'ClusterDistTransformer', # 'WeightOfEvidenceTransformer', 'TruncSVDNumTransformer', 'CVCatNumEncodeTransformer', # 'DatesTransformer', 'TextTransformer', 'OriginalTransformer', # 'NumToCatWoETransformer', 'NumToCatTETransformer', 'ClusterTETransformer', # 'InteractionsTransformer']' # for regression/binary: '['TextTransformer', 'ClusterDistTransformer', # 'OriginalTransformer', 'TextLinModelTransformer', 'NumToCatTETransformer', # 'DatesTransformer', 'WeightOfEvidenceTransformer', 'InteractionsTransformer', # 'FrequentTransformer', 'CVTargetEncodeTransformer', 'NumCatTETransformer', # 'NumToCatWoETransformer', 'TruncSVDNumTransformer', 'ClusterTETransformer', # 'CVCatNumEncodeTransformer']' # This list appears in the experiment logs (search for 'Transformers used') # #included_transformers = "[]" # Auxiliary to included_transformers # e.g. to disable all Target Encoding: excluded_transformers = # '['NumCatTETransformer', 'CVTargetEncodeF', 'NumToCatTETransformer', # 'ClusterTETransformer']'. # Does not affect transformers used for preprocessing with included_pretransformers. # #excluded_transformers = "[]" # Exclude list of genes (i.e. genes (built on top of transformers) to not use, # independent of the interpretability setting) # Some transformers are used by multiple genes, so this allows different control over feature engineering # for multi-class: '['InteractionsGene', 'WeightOfEvidenceGene', # 'NumToCatTargetEncodeSingleGene', 'OriginalGene', 'TextGene', 'FrequentGene', # 'NumToCatWeightOfEvidenceGene', 'NumToCatWeightOfEvidenceMonotonicGene', ' # CvTargetEncodeSingleGene', 'DateGene', 'NumToCatTargetEncodeMultiGene', ' # DateTimeGene', 'TextLinRegressorGene', 'ClusterIDTargetEncodeSingleGene', # 'CvCatNumEncodeGene', 'TruncSvdNumGene', 'ClusterIDTargetEncodeMultiGene', # 'NumCatTargetEncodeMultiGene', 'CvTargetEncodeMultiGene', 'TextLinClassifierGene', # 'NumCatTargetEncodeSingleGene', 'ClusterDistGene']' # for regression/binary: '['CvTargetEncodeSingleGene', 'NumToCatTargetEncodeSingleGene', # 'CvCatNumEncodeGene', 'ClusterIDTargetEncodeSingleGene', 'TextLinRegressorGene', # 'CvTargetEncodeMultiGene', 'ClusterDistGene', 'OriginalGene', 'DateGene', # 'ClusterIDTargetEncodeMultiGene', 'NumToCatTargetEncodeMultiGene', # 'NumCatTargetEncodeMultiGene', 'TextLinClassifierGene', 'WeightOfEvidenceGene', # 'FrequentGene', 'TruncSvdNumGene', 'InteractionsGene', 'TextGene', # 'DateTimeGene', 'NumToCatWeightOfEvidenceGene', # 'NumToCatWeightOfEvidenceMonotonicGene', ''NumCatTargetEncodeSingleGene']' # This list appears in the experiment logs (search for 'Genes used') # e.g. to disable interaction gene, use: excluded_genes = # '['InteractionsGene']'. # Does not affect transformers used for preprocessing with included_pretransformers. # #excluded_genes = "[]" #included_models = "[]" # Auxiliary to included_models #excluded_models = "[]" #included_scorers = "[]" # Select transformers to be used for preprocessing before other transformers operate. # Pre-processing transformers can potentially take any original features and output # arbitrary features, which will then be used by the normal layer of transformers # whose selection is controlled by toml included_transformers or via the GUI # "Include specific transformers". # Notes: # 1) preprocessing transformers (and all other layers of transformers) are part of the python and (if applicable) mojo scoring packages. # 2) any BYOR transformer recipe or native DAI transformer can be used as a preprocessing transformer. # So, e.g., a preprocessing transformer can do interactions, string concatenations, date extractions as a preprocessing step, # and next layer of Date and DateTime transformers will use that as input data. # Caveats: # 1) one cannot currently do a time-series experiment on a time_column that hasn't yet been made (setup of experiment only knows about original data, not transformed) # However, one can use a run-time data recipe to (e.g.) convert a float date-time into string date-time, and this will # be used by DAIs Date and DateTime transformers as well as auto-detection of time series. # 2) in order to do a time series experiment with the GUI/client auto-selecting groups, periods, etc. the dataset # must have time column and groups prepared ahead of experiment by user or via a one-time data recipe. # #included_pretransformers = "[]" # Auxiliary to included_pretransformers #excluded_pretransformers = "[]" #include_all_as_pretransformers_if_none_selected = false #force_include_all_as_pretransformers_if_none_selected = false # Number of full pipeline layers # (not including preprocessing layer when included_pretransformers is not empty). # #num_pipeline_layers = 1 # There are 2 data recipes: # 1) that adds new dataset or modifies dataset outside experiment by file/url (pre-experiment data recipe) # 2) that modifies dataset during experiment and python scoring (run-time data recipe) # This list applies to the 2nd case. One can use the same data recipe code for either case, but note: # A) the 1st case can make any new data, but is not part of scoring package. # B) the 2nd case modifies data during the experiment, so needs some original dataset. # The recipe can still create all new features, as long as it has same *name* for: # target, weight_column, fold_column, time_column, time group columns. # #included_datas = "[]" # Auxiliary to included_datas #excluded_datas = "[]" # Custom individuals to use in experiment. # DAI contains most information about model type, model hyperparameters, data science types for input features, transformers used, and transformer parameters an Individual Recipe (an object that is evolved by mutation within the context of DAI's genetic algorithm). # Every completed experiment auto-generates python code for the experiment that corresponds to the individual(s) used to build the final model. This auto-generated python code can be edited offline and uploaded as a recipe, or it can be edited within the custom recipe management editor and saved. This allowed one a code-first access to a significant portion of DAI's internal transformer and model generation. # Choices are: # * Empty means all individuals are freshly generated and treated by DAI's AutoML as a container of model and transformer choices. # * Recipe display names of custom individuals, usually chosen via the UI. If the number of included custom individuals is less than DAI would need, then the remaining individuals are freshly generated. # The expert experiment-level option fixed_num_individuals can be used to enforce how many individuals to use in evolution stage. # The expert experiment-level option fixed_ensemble_level can be used to enforce how many individuals (each with one base model) will be used in the final model. # These individuals act in similar way as the feature brain acts for restart and retrain/refit, and one can retrain/refit custom individuals (i.e. skip the tuning and evolution stages) to use them in building a final model. # See toml make_python_code for more details. #included_individuals = "[]" # Auxiliary to included_individuals #excluded_individuals = "[]" # Whether to generate python code for the best individuals for the experiment. # This python code contains a CustomIndividual class that is a recipe that can be edited and customized. The CustomIndividual class itself can also be customized for expert use. # By default, 'auto' means on. # At the end of an experiment, the summary zip contains auto-generated python code for the individuals used in the experiment, including the last best population (best_population_indivXX.py where XX iterates the population), last best individual (best_individual.py), final base models (final_indivYY.py where YY iterates the final base models). # The summary zip also contains an example_indiv.py file that generates other transformers that may be useful that did not happen to be used in the experiment. # In addition, the GUI and python client allow one to generate custom individuals from an aborted or finished experiment. # For finished experiments, this will provide a zip file containing the final_indivYY.py files, and for aborted experiments this will contain the best population and best individual files. # See included_individuals for more details. #make_python_code = "auto" # Whether to generate json code for the best individuals for the experiment. # This python code contains the essential attributes from the internal DAI # individual class. Reading the json code as a recipe is not supported. # By default, 'auto' means off. # #make_json_code = "auto" # Maximum number of genes to make for example auto-generated custom individual, # called example_indiv.py in the summary zip file. # #python_code_ngenes_max = 100 # Minimum number of genes to make for example auto-generated custom individual, # called example_indiv.py in the summary zip file. # #python_code_ngenes_min = 100 # Select the scorer to optimize the binary probability threshold that is being used in related Confusion Matrix based scorers that are trivial to optimize otherwise: Precision, Recall, FalsePositiveRate, FalseDiscoveryRate, FalseOmissionRate, TrueNegativeRate, FalseNegativeRate, NegativePredictiveValue. Use F1 if the target class matters more, and MCC if all classes are equally important. AUTO will try to sync the threshold scorer with the scorer used for the experiment, otherwise falls back to F1. The optimized threshold is also used for creating labels in addition to probabilities in MOJO/Python scorers. #threshold_scorer = "AUTO" # Auxiliary to included_scorers #excluded_scorers = "[]" # Whether to enable constant models ('auto'/'on'/'off') #enable_constant_model = "auto" # Whether to enable Decision Tree models ('auto'/'on'/'off'). 'auto' disables decision tree unless only non-constant model chosen. #enable_decision_tree = "auto" # Whether to enable GLM models ('auto'/'on'/'off') #enable_glm = "auto" # Whether to enable RAPIDS extensions to GLM models (not available until fixes are in xgboost 1.3.0) #enable_glm_rapids = false # Whether to enable XGBoost GBM models ('auto'/'on'/'off') #enable_xgboost_gbm = "auto" # Whether to enable LightGBM models ('auto'/'on'/'off') #enable_lightgbm = "auto" # Whether to enable TensorFlow models ('auto'/'on'/'off') #enable_tensorflow = "auto" # Whether to enable PyTorch-based GrowNet models ('auto'/'on'/'off') #enable_grownet = "auto" # Whether to enable FTRL support (follow the regularized leader) model ('auto'/'on'/'off') #enable_ftrl = "auto" # Whether to enable RuleFit support (beta version, no mojo) ('auto'/'on'/'off') #enable_rulefit = "auto" # Whether to enable automatic addition of zero-inflated models for regression problems with zero-inflated target values that meet certain conditions: y >= 0, y.std() > y.mean() #enable_zero_inflated_models = "auto" # Whether to enable RAPIDS extensions to XGBoost GBM/Dart. If selected, python scoring package can only be used on GPU system. #enable_xgboost_rapids = false # Whether to enable GPU-based RAPIDS CUML models. # No mojo support, but python scoring is supported. # In alpha testing status. # #enable_rapids_cuml_models = false # Whether to enable Multi-GPU mode for capable RAPIDS CUML models. # No mojo support, but python scoring is supported. # In alpha testing status. # #enable_rapids_models_dask = false # Whether to use dask_cudf even for 1 GPU. If False, will use plain cudf. #use_dask_for_1_gpu = false # Number of retrials for dask fit to protect against known xgboost issues https://github.com/dmlc/xgboost/issues/6272 https://github.com/dmlc/xgboost/issues/6551 #dask_retrials_allreduce_empty_issue = 5 # Whether to enable XGBoost RF mode without early stopping. # Disabled unless switched on. # #enable_xgboost_rf = "auto" # Whether to enable dask_cudf (multi-GPU) version of XGBoost GBM/RF. # Disabled unless switched on. # Only applicable for single final model without early stopping. No Shapley possible. # #enable_xgboost_gbm_dask = "auto" # Whether to enable multi-node LightGBM. # Disabled unless switched on. # #enable_lightgbm_dask = "auto" # If num_inner_hyperopt_trials_prefinal > 0, # then whether to do hyper parameter tuning during leakage/shift detection. # Might be useful to find non-trivial leakage/shift, but usually not necessary. # #hyperopt_shift_leak = false # If num_inner_hyperopt_trials_prefinal > 0, # then whether to do hyper parameter tuning during leakage/shift detection, # when checking each column. # #hyperopt_shift_leak_per_column = false # Number of trials for Optuna hyperparameter optimization for tuning and evolution models. # 0 means no trials. # For small data, 100 is ok choice, # while for larger data smaller values are reasonable if need results quickly. # If using RAPIDS or DASK, hyperparameter optimization keeps data on GPU entire time. # Currently applies to XGBoost GBM/Dart and LightGBM. # Useful when there is high overhead of DAI outside inner model fit/predict, # so this tunes without that overhead. # However, can overfit on a single fold when doing tuning or evolution, # and if using CV then averaging the fold hyperparameters can lead to unexpected results. # #num_inner_hyperopt_trials_prefinal = 0 # Number of trials for Optuna hyperparameter optimization for final models. # 0 means no trials. # For small data, 100 is ok choice, # while for larger data smaller values are reasonable if need results quickly. # Applies to final model only even if num_inner_hyperopt_trials=0. # If using RAPIDS or DASK, hyperparameter optimization keeps data on GPU entire time. # Currently applies to XGBoost GBM/Dart and LightGBM. # Useful when there is high overhead of DAI outside inner model fit/predict, # so this tunes without that overhead. # However, for final model each fold is independently optimized and can overfit on each fold, # after which predictions are averaged # (so no issue with averaging hyperparameters when doing CV with tuning or evolution). # #num_inner_hyperopt_trials_final = 0 # Number of individuals in final model (all folds/repeats for given base model) to # optimize with Optuna hyperparameter tuning. # -1 means all. # 0 is same as choosing no Optuna trials. # Might be only beneficial to optimize hyperparameters of best individual (i.e. value of 1) in ensemble. # #num_hyperopt_individuals_final = -1 # Optuna Pruner to use (applicable to XGBoost and LightGBM that support Optuna callbacks). To disable choose None. #optuna_pruner = "MedianPruner" # Set Optuna constructor arguments for particular applicable pruners. # https://optuna.readthedocs.io/en/stable/reference/pruners.html # #optuna_pruner_kwargs = "{'n_startup_trials': 5, 'n_warmup_steps': 20, 'interval_steps': 20, 'percentile': 25.0, 'min_resource': 'auto', 'max_resource': 'auto', 'reduction_factor': 4, 'min_early_stopping_rate': 0, 'n_brackets': 4, 'min_early_stopping_rate_low': 0, 'upper': 1.0, 'lower': 0.0}" # Optuna Pruner to use (applicable to XGBoost and LightGBM that support Optuna callbacks). #optuna_sampler = "TPESampler" # Set Optuna constructor arguments for particular applicable samplers. # https://optuna.readthedocs.io/en/stable/reference/samplers.html # #optuna_sampler_kwargs = "{}" # Whether to enable Optuna's XGBoost Pruning callback to abort unpromising runs. Not done if tuning learning rate. #enable_xgboost_hyperopt_callback = true # Whether to enable Optuna's LightGBM Pruning callback to abort unpromising runs. Not done if tuning learning rate. #enable_lightgbm_hyperopt_callback = true # Whether to enable XGBoost Dart models ('auto'/'on'/'off') #enable_xgboost_dart = "auto" # Whether to enable dask_cudf (multi-GPU) version of XGBoost Dart. # Disabled unless switched on. # If have only 1 GPU, then only uses dask_cudf if use_dask_for_1_gpu is True # Only applicable for single final model without early stopping. No Shapley possible. # #enable_xgboost_dart_dask = "auto" # Whether to enable dask_cudf (multi-GPU) version of XGBoost RF. # Disabled unless switched on. # If have only 1 GPU, then only uses dask_cudf if use_dask_for_1_gpu is True # Only applicable for single final model without early stopping. No Shapley possible. # #enable_xgboost_rf_dask = "auto" # Number of GPUs to use per model hyperopt training task. Set to -1 for all GPUs. # For example, when this is set to -1 and there are 4 GPUs available, all of them can be used for the training of a single model across a Dask cluster. # Ignored if GPUs disabled or no GPUs on system. # In multinode context, this refers to the per-node value. # #num_gpus_per_hyperopt_dask = -1 # Whether to use (and expect exists) xgbfi feature interactions for xgboost. #use_xgboost_xgbfi = false # Which boosting types to enable for LightGBM (gbdt = boosted trees, rf_early_stopping = random forest with early stopping rf = random forest (no early stopping), dart = drop-out boosted trees with no early stopping #enable_lightgbm_boosting_types = "['gbdt']" # Whether to enable automatic class weighting for imbalanced multiclass problems. Can make worse probabilities, but improve confusion-matrix based scorers for rare classes without the need to manually calibrate probabilities or fine-tune the label creation process. #enable_lightgbm_multiclass_balancing = "auto" # Whether to enable LightGBM categorical feature support (runs in CPU mode even if GPUs enabled, and no MOJO built) #enable_lightgbm_cat_support = false # Whether to enable LightGBM linear_tree handling # (only CPU mode currently, no L1 regularization -- mae objective, and no MOJO build). # #enable_lightgbm_linear_tree = false # Whether to enable LightGBM extra trees mode to help avoid overfitting #enable_lightgbm_extra_trees = false # basic: as fast as when no constraints applied, but over-constrains the predictions. # intermediate: very slightly slower, but much less constraining while still holding monotonicity and should be more accurate than basic. # advanced: slower, but even more accurate than intermediate. # #lightgbm_monotone_constraints_method = "intermediate" # Forbids any monotone splits on the first x (rounded down) level(s) of the tree. # The penalty applied to monotone splits on a given depth is a continuous, # increasing function the penalization parameter. # https://lightgbm.readthedocs.io/en/latest/Parameters.html#monotone_penalty # #lightgbm_monotone_penalty = 0.0 # Whether to enable LightGBM CUDA implementation instead of OpenCL. # CUDA with LightGBM only supported for Pascal+ (compute capability >=6.0) #enable_lightgbm_cuda_support = false # Whether to show constant models in iteration panel even when not best model. #show_constant_model = false #drop_constant_model_final_ensemble = true #xgboost_rf_exact_threshold_num_rows_x_cols = 10000 # Select objectives allowed for XGBoost. # Added to allowed mutations (the default reg:squarederror is in sample list 3 times) # Note: logistic, tweedie, gamma, poisson are only valid for targets with positive values. # Note: The objective relates to the form of the (regularized) loss function, # used to determine the split with maximum information gain, # while the metric is the non-regularized metric # measured on the validation set (external or internally generated by DAI). # #xgboost_reg_objectives = "['reg:squarederror']" # Select metrics allowed for XGBoost. # Added to allowed mutations (the default rmse and mae are in sample list twice). # Note: tweedie, gamma, poisson are only valid for targets with positive values. # #xgboost_reg_metrics = "['rmse', 'mae']" # Select which objectives allowed for XGBoost. # Added to allowed mutations (all evenly sampled). #xgboost_binary_metrics = "['logloss', 'auc', 'aucpr', 'error']" # Select objectives allowed for LightGBM. # Added to allowed mutations (the default mse is in sample list 2 times if selected). # "binary" refers to logistic regression. # Note: If choose quantile/huber or fair and data is not normalized, # recommendation is to use params_lightgbm to specify reasonable # value of alpha (for quantile or huber) or fairc (for fair) to LightGBM. # Note: mse is same as rmse correponding to L2 loss. mae is L1 loss. # Note: tweedie, gamma, poisson are only valid for targets with positive values. # Note: The objective relates to the form of the (regularized) loss function, # used to determine the split with maximum information gain, # while the metric is the non-regularized metric # measured on the validation set (external or internally generated by DAI). # #lightgbm_reg_objectives = "['mse', 'mae']" # Select metrics allowed for LightGBM. # Added to allowed mutations (the default rmse is in sample list three times if selected). # Note: If choose huber or fair and data is not normalized, # recommendation is to use params_lightgbm to specify reasonable # value of alpha (for huber or quantile) or fairc (for fair) to LightGBM. # Note: tweedie, gamma, poisson are only valid for targets with positive values. # #lightgbm_reg_metrics = "['rmse', 'mse', 'mae']" # Select objectives allowed for LightGBM. # Added to allowed mutations (the default binary is in sample list 2 times if selected) #lightgbm_binary_objectives = "['binary', 'xentropy']" # Select which binary metrics allowed for LightGBM. # Added to allowed mutations (all evenly sampled). #lightgbm_binary_metrics = "['binary', 'binary', 'auc']" # Select which metrics allowed for multiclass LightGBM. # Added to allowed mutations (evenly sampled if selected). #lightgbm_multi_metrics = "['multiclass', 'multi_error']" # tweedie_variance_power parameters to try for XGBoostModel and LightGBMModel if tweedie is used. # First value is default. #tweedie_variance_power_list = "[1.5, 1.2, 1.9]" # huber parameters to try for LightGBMModel if huber is used. # First value is default. #huber_alpha_list = "[0.9, 0.3, 0.5, 0.6, 0.7, 0.8, 0.1, 0.99]" # fair c parameters to try for LightGBMModel if fair is used. # First value is default. #fair_c_list = "[1.0, 0.1, 0.5, 0.9]" # poisson max_delta_step parameters to try for LightGBMModel if poisson is used. # First value is default. #poisson_max_delta_step_list = "[0.7, 0.9, 0.5, 0.2]" # quantile alpha parameters to try for LightGBMModel if quantile is used. # First value is default. #quantile_alpha = "[0.9, 0.95, 0.99, 0.6]" # Default reg_lambda regularization for XGBoost and LightGBM. #reg_lambda_glm_default = 0.0004 #lossguide_drop_factor = 4.0 #lossguide_max_depth_extend_factor = 8.0 # Parameters for LightGBM to override DAI parameters # e.g. 'eval_metric' instead of 'metric' should be used # e.g. params_lightgbm="{'objective': 'binary', 'n_estimators': 100, 'max_leaves': 64, 'random_state': 1234}" # e.g. params_lightgbm="{'n_estimators': 600, 'learning_rate': 0.1, 'reg_alpha': 0.0, 'reg_lambda': 0.5, 'gamma': 0, 'max_depth': 0, 'max_bin': 128, 'max_leaves': 256, 'scale_pos_weight': 1.0, 'max_delta_step': 3.469919910597877, 'min_child_weight': 1, 'subsample': 0.9, 'colsample_bytree': 0.3, 'tree_method': 'gpu_hist', 'grow_policy': 'lossguide', 'min_data_in_bin': 3, 'min_child_samples': 5, 'early_stopping_rounds': 20, 'num_classes': 2, 'objective': 'binary', 'eval_metric': 'binary', 'random_state': 987654, 'early_stopping_threshold': 0.01, 'monotonicity_constraints': False, 'silent': True, 'debug_verbose': 0, 'subsample_freq': 1}" # avoid including "system"-level parameters like 'n_gpus': 1, 'gpu_id': 0, , 'n_jobs': 1, 'booster': 'lightgbm' # also likely should avoid parameters like: 'objective': 'binary', unless one really knows what one is doing (e.g. alternative objectives) # See: https://xgboost.readthedocs.io/en/latest/parameter.html # And see: https://github.com/Microsoft/LightGBM/blob/master/docs/Parameters.rst # Can also pass objective parameters if choose (or in case automatically chosen) certain objectives # https://lightgbm.readthedocs.io/en/latest/Parameters.html#metric-parameters #params_lightgbm = "{}" # Parameters for XGBoost to override DAI parameters # similar parameters as LightGBM since LightGBM parameters are transcribed from XGBoost equivalent versions # e.g. params_xgboost="{'n_estimators': 100, 'max_leaves': 64, 'max_depth': 0, 'random_state': 1234}" # See: https://xgboost.readthedocs.io/en/latest/parameter.html #params_xgboost = "{}" # Like params_xgboost but for XGBoost random forest. #params_xgboost_rf = "{}" # Like params_xgboost but for XGBoost's dart method #params_dart = "{}" # Parameters for TensorFlow to override DAI parameters # e.g. params_tensorflow="{'lr': 0.01, 'add_wide': False, 'add_attention': True, 'epochs': 30, 'layers': (100, 100), 'activation': 'selu', 'batch_size': 64, 'chunk_size': 1000, 'dropout': 0.3, 'strategy': '1cycle', 'l1': 0.0, 'l2': 0.0, 'ort_loss': 0.5, 'ort_loss_tau': 0.01, 'normalize_type': 'streaming'}" # See: https://keras.io/ , e.g. for activations: https://keras.io/activations/ # Example layers: (500, 500, 500), (100, 100, 100), (100, 100), (50, 50) # Strategies: '1cycle' or 'one_shot', See: https://github.com/fastai/fastai # 'one_shot" is not allowed for ensembles. # normalize_type: 'streaming' or 'global' (using sklearn StandardScaler) # #params_tensorflow = "{}" # Parameters for XGBoost's gblinear to override DAI parameters # e.g. params_gblinear="{'n_estimators': 100}" # See: https://xgboost.readthedocs.io/en/latest/parameter.html #params_gblinear = "{}" # Parameters for Decision Tree to override DAI parameters # parameters should be given as XGBoost equivalent unless unique LightGBM parameter # e.g. 'eval_metric' instead of 'metric' should be used # e.g. params_decision_tree="{'objective': 'binary', 'n_estimators': 100, 'max_leaves': 64, 'random_state': 1234}" # e.g. params_decision_tree="{'n_estimators': 1, 'learning_rate': 1, 'reg_alpha': 0.0, 'reg_lambda': 0.5, 'gamma': 0, 'max_depth': 0, 'max_bin': 128, 'max_leaves': 256, 'scale_pos_weight': 1.0, 'max_delta_step': 3.469919910597877, 'min_child_weight': 1, 'subsample': 0.9, 'colsample_bytree': 0.3, 'tree_method': 'gpu_hist', 'grow_policy': 'lossguide', 'min_data_in_bin': 3, 'min_child_samples': 5, 'early_stopping_rounds': 20, 'num_classes': 2, 'objective': 'binary', 'eval_metric': 'logloss', 'random_state': 987654, 'early_stopping_threshold': 0.01, 'monotonicity_constraints': False, 'silent': True, 'debug_verbose': 0, 'subsample_freq': 1}" # avoid including "system"-level parameters like 'n_gpus': 1, 'gpu_id': 0, , 'n_jobs': 1, 'booster': 'lightgbm' # also likely should avoid parameters like: 'objective': 'binary:logistic', unless one really knows what one is doing (e.g. alternative objectives) # See: https://xgboost.readthedocs.io/en/latest/parameter.html # And see: https://github.com/Microsoft/LightGBM/blob/master/docs/Parameters.rst # Can also pass objective parameters if choose (or in case automatically chosen) certain objectives # https://lightgbm.readthedocs.io/en/latest/Parameters.html#metric-parameters #params_decision_tree = "{}" # Parameters for Rulefit to override DAI parameters # e.g. params_rulefit="{'max_leaves': 64}" # See: https://xgboost.readthedocs.io/en/latest/parameter.html #params_rulefit = "{}" # Parameters for FTRL to override DAI parameters #params_ftrl = "{}" # Parameters for GrowNet to override DAI parameters #params_grownet = "{}" # How to handle tomls like params_tune_lightgbm. # override: For any key in the params_tune_ toml dict, use the list of values instead of DAI's list of values. # override_and_first_as_default: like override, but also use first entry in tuple/list (if present) as override as replacement for (e.g.) params_lightgbm when using params_tune_lightgbm. # exclusive: Only tune the keys in the params_tune_ toml dict, unless no keys are present. Otherwise use DAI's default values. # exclusive_and_first_as_default: Like exclusive but same first as default behavior as override_and_first_as_default. # In order to fully control hyperparameter tuning, either one should set "override" mode and include every hyperparameter and at least one value in each list within the dictionary, or choose "exclusive" and then rely upon DAI unchanging default values for any keys not given. # For custom recipes, one can use recipe_dict to pass hyperparameters and if using the "get_one()" function in a custom recipe, and if user_tune passed contains the hyperparameter dictionary equivalent of params_tune_ tomls, then this params_tune_mode will also work for custom recipes. #params_tune_mode = "override_and_first_as_default" # Whether to adjust GBM trees, learning rate, and early_stopping_rounds for GBM models or recipes with _is_gbm=True. # True: auto mode, that changes trees/LR/stopping if tune_learning_rate=false and early stopping is supported by the model and model is GBM or from custom individual with parameter in adjusted_params. # False: disable any adjusting from tuning-evolution into final model. # Setting this to false is required if (e.g.) one changes params_lightgbm or params_tune_lightgbm and wanted to preserve the tuning-evolution values into the final model. # One should also set tune_learning_rate to true to tune the learning_rate, else it will be fixed to some single value. #params_final_auto_adjust = true # Dictionary of key:lists of values to use for LightGBM tuning, overrides DAI's choice per key # e.g. params_tune_lightgbm="{'min_child_samples': [1,2,5,100,1000], 'min_data_in_bin': [1,2,3,10,100,1000]}" #params_tune_lightgbm = "{}" # Like params_tune_lightgbm but for XGBoost # e.g. params_tune_xgboost="{'max_leaves': [8, 16, 32, 64]}" #params_tune_xgboost = "{}" # Like params_tune_lightgbm but for XGBoost random forest # e.g. params_tune_xgboost_rf="{'max_leaves': [8, 16, 32, 64]}" #params_tune_xgboost_rf = "{}" # Dictionary of key:lists of values to use for LightGBM Decision Tree tuning, overrides DAI's choice per key # e.g. params_tune_decision_tree="{'min_child_samples': [1,2,5,100,1000], 'min_data_in_bin': [1,2,3,10,100,1000]}" #params_tune_decision_tree = "{}" # Like params_tune_lightgbm but for XGBoost's Dart # e.g. params_tune_dart="{'max_leaves': [8, 16, 32, 64]}" #params_tune_dart = "{}" # Like params_tune_lightgbm but for TensorFlow # e.g. params_tune_tensorflow="{'layers': [(10,10,10), (10, 10, 10, 10)]}" #params_tune_tensorflow = "{}" # Like params_tune_lightgbm but for gblinear # e.g. params_tune_gblinear="{'reg_lambda': [.01, .001, .0001, .0002]}" #params_tune_gblinear = "{}" # Like params_tune_lightgbm but for rulefit # e.g. params_tune_rulefit="{'max_depth': [4, 5, 6]}" #params_tune_rulefit = "{}" # Like params_tune_lightgbm but for ftrl #params_tune_ftrl = "{}" # Like params_tune_lightgbm but for GrowNet # e.g. params_tune_grownet="{'input_dropout': [0.2, 0.5]}" #params_tune_grownet = "{}" # Whether to force max_leaves and max_depth to be 0 if grow_policy is depthwise and lossguide, respectively. #params_tune_grow_policy_simple_trees = true # Maximum number of GBM trees or GLM iterations. Can be reduced for lower accuracy and/or higher interpretability. # Early-stopping usually chooses less. Ignored if fixed_max_nestimators is > 0. # #max_nestimators = 3000 # Fixed maximum number of GBM trees or GLM iterations. If > 0, ignores max_nestimators and disables automatic reduction # due to lower accuracy or higher interpretability. Early-stopping usually chooses less. # #fixed_max_nestimators = -1 # LightGBM dart mode and normal rf mode do not use early stopping, # and they will sample from these values for n_estimators. # XGBoost Dart mode will also sample from these n_estimators. # Also applies to XGBoost Dask models that do not yet support early stopping or callbacks. # For default parameters it chooses first value in list, while mutations sample from the list. # #n_estimators_list_no_early_stopping = "[50, 100, 150, 200, 250, 300]" # Lower limit on learning rate for final ensemble GBM models. # In some cases, the maximum number of trees/iterations is insufficient for the final learning rate, # which can lead to no early stopping triggered and poor final model performance. # Then, one can try increasing the learning rate by raising this minimum, # or one can try increasing the maximum number of trees/iterations. # #min_learning_rate_final = 0.01 # Upper limit on learning rate for final ensemble GBM models #max_learning_rate_final = 0.05 # factor by which max_nestimators is reduced for tuning and feature evolution #max_nestimators_feature_evolution_factor = 0.2 # Lower limit on learning rate for feature engineering GBM models #min_learning_rate = 0.05 # Upper limit on learning rate for GBM models # If want to override min_learning_rate and min_learning_rate_final, set this to smaller value # #max_learning_rate = 0.5 # Whether to tune learning rate for GBM algorithms (if not doing just single final model). # If tuning with Optuna, might help isolate optimal learning rate. # #tune_learning_rate = false # Max. number of epochs for TensorFlow and FTRL models #max_epochs = 50 # Number of epochs for TensorFlow when larger data size. #max_epochs_tf_big_data = 5 # Maximum tree depth (and corresponding max max_leaves as 2**max_max_depth) #max_max_depth = 12 # Default max_bin for tree methods #default_max_bin = 256 # Default max_bin for LightGBM (64 recommended for GPU LightGBM for speed) #default_lightgbm_max_bin = 249 # Maximum max_bin for tree features #max_max_bin = 256 # Minimum max_bin for any tree #min_max_bin = 32 # Amount of memory which can handle max_bin = 256 can handle 125 columns and max_bin = 32 for 1000 columns # As available memory on system goes higher than this scale, can handle proportionally more columns at higher max_bin # Currently set to 10GB #scale_mem_for_max_bin = 10737418240 # Factor by which rf gets more depth than gbdt #factor_rf = 1.25 # Whether TensorFlow will use all CPU cores, or if it will split among all transformers. Only for transformers, not TensorFlow model. #tensorflow_use_all_cores = true # Whether TensorFlow will use all CPU cores if reproducible is set, or if it will split among all transformers #tensorflow_use_all_cores_even_if_reproducible_true = false # Whether to disable TensorFlow memory optimizations. Can help fix tensorflow.python.framework.errors_impl.AlreadyExistsError #tensorflow_disable_memory_optimization = true # How many cores to use for each TensorFlow model, regardless if GPU or CPU based (0 = auto mode) #tensorflow_cores = 0 # For TensorFlow models, maximum number of cores to use if tensorflow_cores=0 (auto mode), because TensorFlow model is inefficient at using many cores. See also max_fit_cores for all models. #tensorflow_model_max_cores = 4 # Max number of rules to be used for RuleFit models (-1 for all) #rulefit_max_num_rules = -1 # Max tree depth for RuleFit models #rulefit_max_tree_depth = 6 # Max number of trees for RuleFit models #rulefit_max_num_trees = 500 # Enable One-Hot-Encoding (which does binning to limit to number of bins to no more than 100 anyway) for categorical columns with fewer than this many unique values # Set to 0 to disable #one_hot_encoding_cardinality_threshold = 50 # How many levels to choose one-hot by default instead of other encodings, restricted down to 10x less (down to 2 levels) when number of columns able to be used with OHE exceeds 500. Note the total number of bins is reduced if bigger data independently of this. #one_hot_encoding_cardinality_threshold_default_use = 40 # Treat text columns also as categorical columns if the cardinality is <= this value. # Set to 0 to treat text columns only as text. #text_as_categorical_cardinality_threshold = 1000 # If num_as_cat is true, then treat numeric columns also as categorical columns if the cardinality is > this value. # Setting to 0 allows all numeric to be treated as categorical if num_as_cat is True. #numeric_as_categorical_cardinality_threshold = 2 # If num_as_cat is true, then treat numeric columns also as categorical columns to possibly one-hot encode if the cardinality is > this value. # Setting to 0 allows all numeric to be treated as categorical to possibly ohe-hot encode if num_as_cat is True. #numeric_as_ohe_categorical_cardinality_threshold = 2 #one_hot_encoding_show_actual_levels_in_features = false # Fixed ensemble_level # -1 = auto, based upon ensemble_accuracy_switch, accuracy, size of data, etc. # 0 = No ensemble, only final single model on validated iteration/tree count # 1 = 1 model, multiple ensemble folds (cross-validation) # >=2 = >=2 models, multiple ensemble folds (cross-validation) # #fixed_ensemble_level = -1 # If enabled, use cross-validation to determine optimal parameters for single final model, # and to be able to create training holdout predictions. #cross_validate_single_final_model = true # Model to combine base model predictions, for experiments that create a final pipeline # consisting of multiple base models. # blender: Creates a linear blend with non-negative weights that add to 1 (blending) - recommended # extra_trees: Creates a tree model to non-linearly combine the base models (stacking) - experimental, and recommended to also set enable cross_validate_meta_learner. # neural_net: Creates a neural net model to non-linearly combine the base models (stacking) - experimental, and recommended to also set enable cross_validate_meta_learner. # #ensemble_meta_learner = "blender" # If enabled, use cross-validation to create an ensemble for the meta learner itself. Especially recommended for # ensemble_meta_learner='extra_trees', to make unbiased training holdout predictions. # Will disable MOJO if enabled. Not needed for ensemble_meta_learner='blender'." # #cross_validate_meta_learner = false # Number of models to tune during pre-evolution phase # Can make this lower to avoid excessive tuning, or make higher to do enhanced tuning. # -1 : auto # #parameter_tuning_num_models = -1 # Number of models (out of all parameter_tuning_num_models) to have as SEQUENCE instead of random features/parameters. # -1 : auto, use at least one default individual per model class tuned # #parameter_tuning_num_models_sequence = -1 # Dictionary of model class name (keys) and number (values) of instances. #num_tuning_instances = "{}" #validate_meta_learner = true #validate_meta_learner_extra = false # Specify the fixed number of cross-validation folds (if >= 2) for feature evolution. (The actual number of splits allowed can be less and is determined at experiment run-time). #fixed_num_folds_evolution = -1 # Specify the fixed number of cross-validation folds (if >= 2) for the final model. (The actual number of splits allowed can be less and is determined at experiment run-time). #fixed_num_folds = -1 # set "on" to force only first fold for models - useful for quick runs regardless of data #fixed_only_first_fold_model = "auto" # Set the number of repeated cross-validation folds for feature evolution and final models (if > 0), 0 is default. Only for ensembles that do cross-validation (so no external validation and not time-series), not for single final models. #fixed_fold_reps = 0 #num_fold_ids_show = 10 #fold_scores_instability_warning_threshold = 0.25 # Upper limit on the number of rows x number of columns for feature evolution (applies to both training and validation/holdout splits) # feature evolution is the process that determines which features will be derived. # Depending on accuracy settings, a fraction of this value will be used # #feature_evolution_data_size = 300000000 # Upper limit on the number of rows x number of columns for training final pipeline. # #final_pipeline_data_size = 1000000000 # Whether to automatically limit validation data size using feature_evolution_data_size (giving max_rows_feature_evolution shown in logs) for tuning-evolution, and using final_pipeline_data_size, max_validation_to_training_size_ratio_for_final_ensemble for final model. #limit_validation_size = true # Smaller values can speed up final pipeline model training, as validation data is only used for early stopping. # Note that final model predictions and scores will always be provided on the full dataset provided. # #max_validation_to_training_size_ratio_for_final_ensemble = 2.0 # Ratio of minority to majority class of the target column beyond which stratified sampling is done for binary classification. Otherwise perform random sampling. Set to 0 to always do random sampling. Set to 1 to always do stratified sampling. #force_stratified_splits_for_imbalanced_threshold_binary = 0.01 #force_stratified_splits_for_binary_max_rows = 1000000 # Specify whether to do stratified sampling for validation fold creation for iid regression problems. Otherwise perform random sampling. #stratify_for_regression = true # Sampling method for imbalanced binary classification problems. Choices are: # "auto": sample both classes as needed, depending on data # "over_under_sampling": over-sample the minority class and under-sample the majority class, depending on data # "under_sampling": under-sample the majority class to reach class balance # "off": do not perform any sampling # #imbalance_sampling_method = "off" # For smaller data, there's no generally no benefit in using imbalanced sampling methods. #imbalance_sampling_threshold_min_rows_original = 100000 # For imbalanced binary classification: ratio of majority to minority class equal and above which to enable # special imbalanced models with sampling techniques (specified by imbalance_sampling_method) to attempt to improve model performance. # #imbalance_ratio_sampling_threshold = 5 # For heavily imbalanced binary classification: ratio of majority to minority class equal and above which to enable only # special imbalanced models on full original data, without upfront sampling. # #heavy_imbalance_ratio_sampling_threshold = 25 # Special handling can include special models, special scorers, special feature engineering. # #imbalance_ratio_multiclass_threshold = 5 # Special handling can include special models, special scorers, special feature engineering. # #heavy_imbalance_ratio_multiclass_threshold = 25 # -1: automatic #imbalance_sampling_number_of_bags = -1 # -1: automatic #imbalance_sampling_max_number_of_bags = 10 # Only for shift/leakage/tuning/feature evolution models. Not used for final models. Final models can # be limited by imbalance_sampling_max_number_of_bags. #imbalance_sampling_max_number_of_bags_feature_evolution = 3 # Max. size of data sampled during imbalanced sampling (in terms of dataset size), # controls number of bags (approximately). Only for imbalance_sampling_number_of_bags == -1. #imbalance_sampling_max_multiple_data_size = 1.0 # Rank averaging can be helpful when ensembling diverse models when ranking metrics like AUC/Gini # metrics are optimized. No MOJO support yet. #imbalance_sampling_rank_averaging = "auto" # A value of 0.5 means that models/algorithms will be presented a balanced target class distribution # after applying under/over-sampling techniques on the training data. Sometimes it makes sense to # choose a smaller value like 0.1 or 0.01 when starting from an extremely imbalanced original target # distribution. -1.0: automatic #imbalance_sampling_target_minority_fraction = -1.0 # For binary classification: ratio of majority to minority class equal and above which to notify # of imbalance in GUI to say slightly imbalanced. # More than imbalance_ratio_sampling_threshold will say problem is imbalanced. # #imbalance_ratio_notification_threshold = 2.0 # List of possible bins for FTRL (largest is default best value) #nbins_ftrl_list = "[1000000, 10000000, 100000000]" # Samples the number of automatic FTRL interactions terms to no more than this value (for each of 2nd, 3rd, 4th order terms) #ftrl_max_interaction_terms_per_degree = 10000 # List of possible bins for target encoding (first is default value) #te_bin_list = "[25, 10, 100, 250]" # List of possible bins for weight of evidence encoding (first is default value) # If only want one value: woe_bin_list = [2] #woe_bin_list = "[25, 10, 100, 250]" # List of possible bins for ohe hot encoding (first is default value). If left as default, the actual list is changed for given data size and dials. #ohe_bin_list = "[10, 25, 50, 75, 100]" # List of max possible number of bins for numeric binning (first is default value). If left as default, the actual list is changed for given data size and dials. The binner will automatically reduce the number of bins based on predictive power. #binner_bin_list = "[5, 10, 20]" # If dataset has more columns, then will check only first such columns. Set to 0 to disable. #drop_redundant_columns_limit = 1000 # Whether to drop columns with constant values #drop_constant_columns = true # Whether to detect duplicate rows in training, validation and testing datasets. Done after doing type detection and dropping of redundant or missing columns across datasets, just before the experiment starts, still before leakage detection. Any further dropping of columns can change the amount of duplicate rows. Informative only, if want to drop rows in training data, make sure to check the drop_duplicate_rows setting. Uses a sample size, given by detect_duplicate_rows_max_rows_x_cols. #detect_duplicate_rows = true #drop_duplicate_rows_timeout = 60 # Whether to drop duplicate rows in training data. Done at the start of Driverless AI, only considering columns to drop as given by the user, not considering validation or training datasets or leakage or redundant columns. Any further dropping of columns can change the amount of duplicate rows. Time limited by drop_duplicate_rows_timeout seconds. # 'auto': "off"" # 'weight': If duplicates, then convert dropped duplicates into a weight column for training. Useful when duplicates are added to preserve some distribution of instances expected. Only allowed if no weight columnn is present, else duplicates are just dropped. # 'drop': Drop any duplicates, keeping only first instances. # 'off': Do not drop any duplicates. This may lead to over-estimation of accuracy. #drop_duplicate_rows = "auto" # If > 0, then acts as sampling size for informative duplicate row detection. If set to 0, will do checks for all dataset sizes. #detect_duplicate_rows_max_rows_x_cols = 10000000 # Whether to drop columns that appear to be an ID #drop_id_columns = true # Whether to avoid dropping any columns (original or derived) #no_drop_features = false # Direct control over columns to drop in bulk so can copy-paste large lists instead of selecting each one separately in GUI #cols_to_drop = "[]" #cols_to_drop_sanitized = "[]" # Control over columns to group by for CVCatNumEncode Transformer, default is empty list that means DAI automatically searches all columns, # selected randomly or by which have top variable importance. # The CVCatNumEncode Transformer takes a list of categoricals (or these cols_to_group_by) and uses those columns # as new feature to perform aggregations on (agg_funcs_for_group_by). #cols_to_group_by = "[]" #cols_to_group_by_sanitized = "[]" # Whether to sample from given features to group by (True) or to always group by all features (False) when using cols_to_group_by. 
 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 #sample_cols_to_group_by = false # Aggregation functions to use for groupby operations for CVCatNumEncode Transformer, see also cols_to_group_by and sample_cols_to_group_by. #agg_funcs_for_group_by = "['mean', 'sd', 'min', 'max', 'count']" # Out of fold aggregations ensure less overfitting, but see less data in each fold. For controlling how many folds used by CVCatNumEncode Transformer. #folds_for_group_by = 5 # Control over columns to force-in. Forced-in features are are handled by the most interpretable transformer allowed by experiment # options, and they are never removed (although model may assign 0 importance to them still). # Transformers used by default include: # OriginalTransformer for numeric, # CatOriginalTransformer or FrequencyTransformer for categorical, # TextOriginalTransformer for text, # DateTimeOriginalTransformer for date-times, # DateOriginalTransformer for dates, # ImageOriginalTransformer or ImageVectorizerTransformer for images, # etc. #cols_to_force_in = "[]" #cols_to_force_in_sanitized = "[]" # Strategy to apply when doing mutations on transformers. # Sample mode is default, with tendency to sample transformer parameters. # Batched mode tends to do multiple types of the same transformation together. # Full mode does even more types of the same transformation together. # #mutation_mode = "sample" # 'baseline': Explore explemplar set of models with baselines as reference. # 'random': Explore 10 random seeds for same setup. Useful since nature of genetic algorithm is noisy and repeats might get better results, or one can ensemble the custom individuals from such repeats. # 'line': Explore good model with all features and original features with all models. Useful as first exploration. # 'line_all': Like 'line', but enable all models and transformers possible instead of only what base experiment setup would have inferred. # 'product': Explore one-by-one Cartesian product of each model and transformer. Useful for exhaustive exploration. #leaderboard_mode = "baseline" # Allows control over default accuracy knob setting. # If default models are too complex, set to -1 or -2, etc. # If default models are not accurate enough, set to 1 or 2, etc. # #default_knob_offset_accuracy = 0 # Allows control over default time knob setting. # If default experiments are too slow, set to -1 or -2, etc. # If default experiments finish too fast, set to 1 or 2, etc. # #default_knob_offset_time = 0 # Allows control over default interpretability knob setting. # If default models are too simple, set to -1 or -2, etc. # If default models are too complex, set to 1 or 2, etc. # #default_knob_offset_interpretability = 0 # Whether to enable checking text for shift, currently only via label encoding. #shift_check_text = false # Whether to use LightGBM random forest mode without early stopping for shift detection. #use_rf_for_shift_if_have_lgbm = true # Normalized training variable importance above which to check the feature for shift # Useful to avoid checking likely unimportant features #shift_key_features_varimp = 0.01 # Whether to only check certain features based upon the value of shift_key_features_varimp #shift_check_reduced_features = true # Number of trees to use to train model to check shift in distribution # No larger than max_nestimators #shift_trees = 100 # The value of max_bin to use for trees to use to train model to check shift in distribution #shift_max_bin = 256 # The min. value of max_depth to use for trees to use to train model to check shift in distribution #shift_min_max_depth = 4 # The max. value of max_depth to use for trees to use to train model to check shift in distribution #shift_max_max_depth = 8 # If distribution shift detection is enabled, show features for which shift AUC is above this value # (AUC of a binary classifier that predicts whether given feature value belongs to train or test data) #detect_features_distribution_shift_threshold_auc = 0.55 # Minimum number of features to keep, keeping least shifted feature at least if 1 #drop_features_distribution_shift_min_features = 1 # Shift beyond which shows HIGH notification, else MEDIUM #shift_high_notification_level = 0.8 # Whether to enable checking text for leakage, currently only via label encoding. #leakage_check_text = true # Normalized training variable importance (per 1 minus AUC/R2 to control for leaky varimp dominance) above which to check the feature for leakage # Useful to avoid checking likely unimportant features #leakage_key_features_varimp = 0.001 # Like leakage_key_features_varimp, but applies if early stopping disabled when can trust multiple leaks to get uniform varimp. #leakage_key_features_varimp_if_no_early_stopping = 0.05 # Whether to only check certain features based upon the value of leakage_key_features_varimp. If any feature has AUC near 1, will consume all variable importance, even if another feature is also leaky. So False is safest option, but True generally good if many columns. #leakage_check_reduced_features = true # Whether to use LightGBM random forest mode without early stopping for leakage detection. #use_rf_for_leakage_if_have_lgbm = true # Number of trees to use to train model to check for leakage # No larger than max_nestimators #leakage_trees = 100 # The value of max_bin to use for trees to use to train model to check for leakage #leakage_max_bin = 256 # The value of max_depth to use for trees to use to train model to check for leakage #leakage_min_max_depth = 6 # The value of max_depth to use for trees to use to train model to check for leakage #leakage_max_max_depth = 8 # When leakage detection is enabled, if AUC (R2 for regression) on original data (label-encoded) # is above or equal to this value, then trigger per-feature leakage detection # #detect_features_leakage_threshold_auc = 0.95 # When leakage detection is enabled, show features for which AUC (R2 for regression, # for whether that predictor/feature alone predicts the target) is above or equal to this value. # Feature is dropped if AUC/R2 is above or equal to drop_features_leakage_threshold_auc # #detect_features_per_feature_leakage_threshold_auc = 0.8 # Minimum number of features to keep, keeping least leakage feature at least if 1 #drop_features_leakage_min_features = 1 # Ratio of train to validation holdout when testing for leakage #leakage_train_test_split = 0.25 # Whether to enable detailed traces (in GUI Trace) #detailed_traces = false # Whether to enable debug log level (in log files) #debug_log = false 
 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 # Whether to add logging of system information such as CPU, GPU, disk space at the start of each experiment log. Same information is already logged in system logs. #log_system_info_per_experiment = true #check_system = true #check_system_basic = true # How close to the optimal value (usually 1 or 0) does the validation score need to be to be considered perfect (to stop the experiment)? #abs_tol_for_perfect_score = 0.0001 # Timeout in seconds to wait for data ingestion. #data_ingest_timeout = 86400.0 # How many seconds to allow mutate to take, nominally only takes few seconds at most. But on busy system doing many individuals, might take longer. Optuna sometimes live lock hangs in scipy random distribution maker. #mutate_timeout = 600 # Whether to trust GPU locking for submission of GPU jobs to limit memory usage. # If False, then wait for as GPU submissions to be less than number of GPUs, # even if later jobs could be purely CPU jobs that did not need to wait. # Only applicable if not restricting number of GPUs via num_gpus_per_experiment, # else have to use resources instead of relying upon locking. # #gpu_locking_trust_pool_submission = true # Whether to steal GPU locks when process is neither on GPU PID list nor using CPU resources at all (e.g. sleeping). Only steal from multi-GPU locks that are incomplete. Prevents deadlocks in case multi-GPU model hangs. #gpu_locking_free_dead = true #tensorflow_allow_cpu_only = false #check_pred_contribs_sum = false #debug_daimodel_level = 0 #debug_debug_xgboost_splits = false #log_predict_info = true #log_fit_info = true # Amount of time to stall (in seconds) before killing the job (assumes it hung). Reference time is scaled by train data shape of rows * cols to get used stalled_time_kill #stalled_time_kill_ref = 440.0 # Amount of time between checks for some process taking long time, every cycle full process list will be dumped to console or experiment logs if possible. #long_time_psdump = 1800 # Whether to dump ps every long_time_psdump #do_psdump = false # Whether to check every long_time_psdump seconds and SIGUSR1 to all children to see where maybe stuck or taking long time. #livelock_signal = false # Value to override number of sockets, in case DAIs determination is wrong, for non-trivial systems. 0 means auto. #num_cpu_sockets_override = 0 # Value to override number of GPUs, in case DAIs determination is wrong, for non-trivial systems. -1 means auto.Can also set min_num_cores_per_gpu=-1 to allowany number of GPUs for each experiment regardlessof number of cores. #num_gpus_override = -1 # Whether to show GPU usage only when locking. 'auto' means 'on' if num_gpus_override is different than actual total visible GPUs, else it means 'off' #show_gpu_usage_only_if_locked = "auto" # Show inapplicable models in preview, to be sure not missing models one could have used #show_inapplicable_models_preview = false # Show inapplicable transformers in preview, to be sure not missing transformers one could have used #show_inapplicable_transformers_preview = false # Show warnings for models (image auto, Dask multinode/multi-GPU) if conditions are met to use but not chosen to avoid missing models that could benefit accuracy/performance #show_warnings_preview = false # Show warnings for models that have no transformers for certain features. #show_warnings_preview_unused_map_features = true # Up to how many input features to determine, during GUI/client preview, unused features. Too many slows preview down. #max_cols_show_unused_features = 1000 # Up to how many input features to show transformers used for each input feature. #max_cols_show_feature_transformer_mapping = 1000 # Up to how many input features to show, in preview, that are unused features. #warning_unused_feature_show_max = 3 #interaction_finder_max_rows_x_cols = 200000.0 #interaction_finder_corr_threshold = 0.95 # Required GINI relative improvement for InteractionTransformer. # If GINI is not better than this relative improvement compared to original features considered # in the interaction, then the interaction is not returned. If noisy data, and no clear signal # in interactions but still want interactions, then can decrease this number. #interaction_finder_gini_rel_improvement_threshold = 0.5 # Number of transformed Interactions to make as best out of many generated trial interactions. #interaction_finder_return_limit = 5 # Whether to enable bootstrap sampling. Provides error bars to validation and test scores based on the standard error of the bootstrap mean. #enable_bootstrap = true # Minimum number of bootstrap samples to use for estimating score and its standard deviation # Actual number of bootstrap samples will vary between the min and max, # depending upon row count (more rows, fewer samples) and accuracy settings (higher accuracy, more samples) # #min_bootstrap_samples = 1 # Maximum number of bootstrap samples to use for estimating score and its standard deviation # Actual number of bootstrap samples will vary between the min and max, # depending upon row count (more rows, fewer samples) and accuracy settings (higher accuracy, more samples) # #max_bootstrap_samples = 100 # Minimum fraction of row size to take as sample size for bootstrap estimator # Actual sample size used for bootstrap estimate will vary between the min and max, # depending upon row count (more rows, smaller sample size) and accuracy settings (higher accuracy, larger sample size) # #min_bootstrap_sample_size_factor = 1.0 # Maximum fraction of row size to take as sample size for bootstrap estimator # Actual sample size used for bootstrap estimate will vary between the min and max, # depending upon row count (more rows, smaller sample size) and accuracy settings (higher accuracy, larger sample size) # #max_bootstrap_sample_size_factor = 10.0 # Seed to use for final model bootstrap sampling, -1 means use experiment-derived seed. # E.g. one can retrain final model with different seed to get different final model error bars for scores. # #bootstrap_final_seed = -1 # Benford's law: mean absolute deviance threshold equal and above which integer valued columns are treated as categoricals too #benford_mad_threshold_int = 0.03 # Benford's law: mean absolute deviance threshold equal and above which real valued columns are treated as categoricals too #benford_mad_threshold_real = 0.1 # Variable importance below which feature is dropped (with possible replacement found that is better) # This also sets overall scale for lower interpretability settings. # Set to lower value if ok with many weak features despite choosing high interpretability, # or if see drop in performance due to the need for weak features. # #varimp_threshold_at_interpretability_10 = 0.001 # Whether to avoid setting stabilize_varimp=false and stabilize_fs=false for time series experiments. #allow_stabilize_varimp_for_ts = false # Variable importance is used by genetic algorithm to decide which features are useful, # so this can stabilize the feature selection by the genetic algorithm. # This is by default disabled for time series experiments, which can have real diverse behavior in each split. # But in some cases feature selection is improved in presence of highly shifted variables that are not handled # by lag transformers and one can set allow_stabilize_varimp_for_ts=true. # #stabilize_varimp = true # Whether to take minimum (True) or mean (False) of delta improvement in score when aggregating feature selection scores across multiple folds/depths. # Delta improvement of score corresponds to original metric minus metric of shuffled feature frame if maximizing metric, # and corresponds to negative of such a score difference if minimizing. # Feature selection by permutation importance considers the change in score after shuffling a feature, and using minimum operation # ignores optimistic scores in favor of pessimistic scores when aggregating over folds. # Note, if using tree methods, multiple depths may be fitted, in which case regardless of this toml setting, # only features that are kept for all depths are kept by feature selection. # If interpretability >= config toml value of fs_data_vary_for_interpretability, then half data (or setting of fs_data_frac) # is used as another fit, in which case regardless of this toml setting, # only features that are kept for all data sizes are kept by feature selection. # Note: This is disabled for small data since arbitrary slices of small data can lead to disjoint features being important and only aggregated average behavior has signal. # #stabilize_fs = true # Whether final pipeline uses fixed features for some transformers that would normally # perform search, such as InteractionsTransformer. # Use what learned from tuning and evolution (True) or to freshly search for new features (False). # This can give a more stable pipeline, especially for small data or when using interaction transformer # as pretransformer in multi-layer pipeline. # #stabilize_features = true # Whether to enable GPU-based RAPIDS cuML transformers. # If want to support Dask RAPIDS transformers, you must set enable_rapids_transformers_dask=true. 
 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 # No mojo support, but Python scoring is supported. # In alpha testing status. # #enable_rapids_transformers = false # Whether to enable Multi-GPU mode for capable RAPIDS cuML transformers. # Must also set enable_rapids_transformers=true. # No mojo support, but python scoring is supported. # In alpha testing status. # #enable_rapids_transformers_dask = false #fraction_std_bootstrap_ladder_factor = 0.01 #bootstrap_ladder_samples_limit = 10 #features_allowed_by_interpretability = "{1: 10000000, 2: 10000, 3: 1000, 4: 500, 5: 300, 6: 200, 7: 150, 8: 100, 9: 80, 10: 50, 11: 50, 12: 50, 13: 50}" #nfeatures_max_threshold = 200 #rdelta_percent_score_penalty_per_feature_by_interpretability = "{1: 0.0, 2: 0.1, 3: 1.0, 4: 2.0, 5: 5.0, 6: 10.0, 7: 20.0, 8: 30.0, 9: 50.0, 10: 100.0, 11: 100.0, 12: 100.0, 13: 100.0}" #drop_low_meta_weights = true #meta_weight_allowed_by_interpretability = "{1: 1E-7, 2: 1E-5, 3: 1E-4, 4: 1E-3, 5: 1E-2, 6: 0.03, 7: 0.05, 8: 0.08, 9: 0.10, 10: 0.15, 11: 0.15, 12: 0.15, 13: 0.15}" #meta_weight_allowed_for_reference = 1.0 #feature_cost_mean_interp_for_penalty = 5 #features_cost_per_interp = 0.25 #varimp_threshold_shift_report = 0.3 #apply_featuregene_limits_after_tuning = true #remove_scored_0gain_genes_in_postprocessing_above_interpretability = 13 #remove_scored_0gain_genes_in_postprocessing_above_interpretability_final_population = 2 #remove_scored_by_threshold_genes_in_postprocessing_above_interpretability_final_population = 7 #show_full_pipeline_details = false #num_transformed_features_per_pipeline_show = 10 #fs_data_vary_for_interpretability = 7 #fs_data_frac = 0.5 #many_columns_count = 400 #columns_count_interpretable = 200 #round_up_indivs_for_busy_gpus = true #tuning_share_varimp = "best" # Graphviz is an optional requirement for native installations (RPM/DEP/Tar-SH, outside of Docker)to convert .dot files into .png files for pipeline visualizations as part of experiment artifacts #require_graphviz = true # Unnormalized probability to add genes or instances of transformers with specific attributes. # If no genes can be added, other mutations # (mutating models hyper parmaters, pruning genes, pruning features, etc.) are attempted. # #prob_add_genes = 0.5 # Unnormalized probability, conditioned on prob_add_genes, # to add genes or instances of transformers with specific attributes # that have shown to be beneficial to other individuals within the population. # #prob_addbest_genes = 0.5 # Unnormalized probability to prune genes or instances of transformers with specific attributes. # If a variety of transformers with many attributes exists, default value is reasonable. # However, if one has fixed set of transformers that should not change or no new transformer attributes # can be added, then setting this to 0.0 is reasonable to avoid undesired loss of transformations. # #prob_prune_genes = 0.5 # Unnormalized probability change model hyper parameters. # #prob_perturb_xgb = 0.25 # Unnormalized probability to prune features that have low variable importance, as opposed to pruning entire instances of genes/transformers when prob_prune_genes used. # If prob_prune_genes=0.0 and prob_prune_by_features==0.0, then genes/transformers and transformed features are only pruned if they are: # 1) inconsistent with the genome # 2) inconsistent with the column data types # 3) had no signal (for interactions and cv_in_cv for target encoding) # 4) transformation failed # E.g. these are toml settings are then ignored: # 1) ngenes_max # 2) limit_features_by_interpretability # 3) varimp_threshold_at_interpretability_10 # 4) features_allowed_by_interpretability # 5) remove_scored_0gain_genes_in_postprocessing_above_interpretability # 6) nfeatures_max_threshold # 7) features_cost_per_interp # So this acts similar to no_drop_features, except no_drop_features also applies to shift and leak detection, constant columns are not dropped, ID columns are not dropped. #prob_prune_by_features = 0.25 # Like prob_prune_genes but only for pretransformers, i.e. those transformers in layers except last layer that connects to model. #prob_prune_pretransformer_genes = 0.5 # Like prob_prune_by_features but only for pretransformers, i.e. those transformers in layers except last layer that connects to model. #prob_prune_pretransformer_by_features = 0.25 # Max. number of trees to use for all tree model predictions. For testing, when predictions don't matter. -1 means disabled. #fast_approx_max_num_trees_ever = -1 # Max. number of trees to use for fast_approx=True (e.g., for AutoDoc/MLI). #fast_approx_num_trees = 250 # Whether to speed up fast_approx=True further, by using only one fold out of all cross-validation folds (e.g., for AutoDoc/MLI). #fast_approx_do_one_fold = true # Whether to speed up fast_approx=True further, by using only one model out of all ensemble models (e.g., for AutoDoc/MLI). #fast_approx_do_one_model = false # Max. number of trees to use for fast_approx_contribs=True (e.g., for 'Fast Approximation' in GUI when making Shapley predictions, and for AutoDoc/MLI). #fast_approx_contribs_num_trees = 50 # Whether to speed up fast_approx_contribs=True further, by using only one fold out of all cross-validation folds (e.g., for 'Fast Approximation' in GUI when making Shapley predictions, and for AutoDoc/MLI). #fast_approx_contribs_do_one_fold = true # Whether to speed up fast_approx_contribs=True further, by using only one model out of all ensemble models (e.g., for 'Fast Approximation' in GUI when making Shapley predictions, and for AutoDoc/MLI). #fast_approx_contribs_do_one_model = true # Whether to use exploit-explore logic like DAI 1.8.x. False will explore more. #use_187_prob_logic = true # Whether to enable cross-validated OneHotEncoding+LinearModel transformer #enable_ohe_linear = false #max_absolute_feature_expansion = 1000 #booster_for_fs_permute = "auto" #model_class_name_for_fs_permute = "auto" #switch_from_tree_to_lgbm_if_can = true #default_model_class_name = "LightGBMModel" #num_as_cat_false_if_ohe = true #no_ohe_try = true # Number of classes above which to only use TensorFlow (if TensorFlow is enabled), # instead of others models set on 'auto' (models set to 'on' are still used). # For small data this is decreased by tensorflow_num_classes_small_data_factor, # and for bigger data, this is increased by tensorflow_num_classes_big_data_reduction_factor. #tensorflow_added_num_classes_switch = 5 # Number of classes above which to only use TensorFlow (if TensorFlow is enabled), # instead of others models set on 'auto' (models set to 'on' are still used). # Up to tensorflow_num_classes_switch_but_keep_lightgbm, keep LightGBM. # If small data, this is increased by tensorflow_num_classes_small_data_factor. #tensorflow_num_classes_switch = 10 #tensorflow_num_classes_switch_but_keep_lightgbm = 15 #tensorflow_num_classes_small_data_factor = 3 #tensorflow_num_classes_big_data_reduction_factor = 6 # Compute empirical prediction intervals (based on holdout predictions). #prediction_intervals = true # Confidence level for prediction intervals. #prediction_intervals_alpha = 0.9 # Appends one extra output column with predicted target class (after the per-class probabilities). # Uses argmax for multiclass, and the threshold defined by the optimal scorer controlled by the # 'threshold_scorer' expert setting for binary problems. This setting controls the training, validation and test # set predictions (if applicable) that are created by the experiment. MOJO, scoring pipeline and client APIs # control this behavior via their own version of this parameter. #pred_labels = true # Class count above which do not use TextLin Transformer. #textlin_num_classes_switch = 5 #text_gene_dim_reduction_choices = "[50]" #text_gene_max_ngram = "[1, 2, 3]" # Max size (in tokens) of the vocabulary created during fitting of Tfidf/Count based text # transformers (not CNN/BERT). If multiple values are provided, will use the first one for initial models, and use remaining # values during parameter tuning and feature evolution. Values smaller than 10000 are recommended for speed. #text_transformers_max_vocabulary_size = "[1000, 5000]" # Enables caching of BERT embeddings by temporally saving the embedding vectors to the experiment directory. Set to -1 to cache all text, set to 0 to disable caching. #number_of_texts_to_cache_in_bert_transformer = -1 # Modify early stopping behavior for tree-based models (LightGBM, XGBoostGBM, CatBoost) such # that training score (on training data, not holdout) and validation score differ no more than this absolute value # (i.e., stop adding trees once abs(train_score - valid_score) > max_abs_score_delta_train_valid). # Keep in mind that the meaning of this value depends on the chosen scorer and the dataset (i.e., 0.01 for # LogLoss is different than 0.01 for MSE). Experimental option, only for expert use to keep model complexity low. # To disable, set to 0.0 #max_abs_score_delta_train_valid = 0.0 # Modify early stopping behavior for tree-based models (LightGBM, XGBoostGBM, CatBoost) such # that training score (on training data, not holdout) and validation score differ no more than this relative value # (i.e., stop adding trees once abs(train_score - valid_score) > max_rel_score_delta_train_valid * abs(train_score)). # Keep in mind that the meaning of this value depends on the chosen scorer and the dataset (i.e., 0.01 for # LogLoss is different than 0.01 for MSE). Experimental option, only for expert use to keep model complexity low. # To disable, set to 0.0 #max_rel_score_delta_train_valid = 0.0 # Whether to search for optimal lambda for given alpha for XGBoost GLM. # If 'auto', disabled if training data has more rows * cols than final_pipeline_data_size or for multiclass experiments. # Disabled always for ensemble_level = 0. # Not always a good approach, can be slow for little payoff compared to grid search. # #glm_lambda_search = "auto" # If XGBoost GLM lambda search is enabled, whether to do search by the eval metric (True) # or using the actual DAI scorer (False). #glm_lambda_search_by_eval_metric = false #gbm_early_stopping_rounds_min = 1 #gbm_early_stopping_rounds_max = 10000000000 # Whether to enable early stopping threshold for LightGBM, varying by accuracy. # Stops training once validation score changes by less than the threshold. # This leads to fewer trees, usually avoiding wasteful trees, but may lower accuracy. # 'off' leads to value of 0 used. # 'on' leads to higher values for lower accuracy dial. # 'auto' leads to 'off', unless reduce_mojo_size is true. # #enable_early_stopping_threshold = "auto" #glm_optimal_refit = true # Max. number of top variable importances to save per iteration (GUI can only display a max. of 14) #max_varimp_to_save = 100 # Max. number of top variable importances to show in logs during feature evolution #max_num_varimp_to_log = 10 # Max. number of top variable importance shifts to show in logs and GUI after final model built #max_num_varimp_shift_to_log = 10 # Skipping just avoids the failed transformer. # Sometimes python multiprocessing swallows exceptions, # so skipping and logging exceptions is also more reliable way to handle them. # Recipe can raise h2oaicore.systemutils.IgnoreError to ignore error and avoid logging error. # Features that fail are pruned from the individual. # If that leaves no features in the individual, then backend tuning, feature/model tuning, final model building, etc. # will still fail since DAI should not continue if all features are from a failed state. # #skip_transformer_failures = true # Skipping just avoids the failed model. Failures are logged depending upon detailed_skip_failure_messages_level." # Recipe can raise h2oaicore.systemutils.IgnoreError to ignore error and avoid logging error. # #skip_model_failures = true # Skipping just avoids the failed scorer if among many scorers. Failures are logged depending upon detailed_skip_failure_messages_level." # Recipe can raise h2oaicore.systemutils.IgnoreError to ignore error and avoid logging error. # Default is True to avoid failing in, e.g., final model building due to a single scorer. # #skip_scorer_failures = true # Skipping avoids the failed recipe. Failures are logged depending upon detailed_skip_failure_messages_level." # Default is False because runtime data recipes are one-time at start of experiment and expected to work by default. # #skip_data_recipe_failures = false # Whether can skip final model transformer failures for layer > first layer for multi-layer pipeline. #can_skip_final_upper_layer_failures = true # How much verbosity to log failure messages for failed and then skipped transformers or models. # Full failures always go to disk as *.stack files, # which upon completion of experiment goes into details folder within experiment log zip file. # #detailed_skip_failure_messages_level = 1 # Whether to not just log errors of recipes (models and transformers) but also show high-level notification in GUI. # #notify_failures = true # Instructions for 'Add to config.toml via toml string' in GUI expert page # Self-referential toml parameter, for setting any other toml parameters as string of tomls separated by # (spaces around # are ok). # Useful when toml parameter is not in expert mode but want per-experiment control. # Setting this will override all other choices. # In expert page, each time expert options saved, the new state is set without memory of any prior settings. # The entered item is a fully compliant toml string that would be processed directly by toml.load(). # One should include 2 double quotes around the entire setting, or double quotes need to be escaped. # One enters into the expert page text as follows: # e.g. enable_glm="off" # enable_xgboost_gbm="off" # enable_lightgbm="on" # e.g. ""enable_glm="off" # enable_xgboost_gbm="off" # enable_lightgbm="off" # enable_tensorflow="on""" # e.g. fixed_num_individuals=4 # e.g. params_lightgbm="{'objective':'poisson'}" # e.g. ""params_lightgbm="{'objective':'poisson'}""" # e.g. max_cores=10 # data_precision="float32" # max_rows_feature_evolution=50000000000 # ensemble_accuracy_switch=11 # feature_engineering_effort=1 # target_transformer="identity" # tournament_feature_style_accuracy_switch=5 # params_tensorflow="{'layers': (100, 100, 100, 100, 100, 100)}" # e.g. ""max_cores=10 # data_precision="float32" # max_rows_feature_evolution=50000000000 # ensemble_accuracy_switch=11 # feature_engineering_effort=1 # target_transformer="identity" # tournament_feature_style_accuracy_switch=5 # params_tensorflow="{'layers': (100, 100, 100, 100, 100, 100)}""" # If you see: "toml.TomlDecodeError" then ensure toml is set correctly. # When set in the expert page of an experiment, these changes only affect experiments and not the server # Usually should keep this as empty string in this toml file. # #config_overrides = "" # Whether to dump every scored individual's variable importance to csv/tabulated/json file produces files like: # individual_scored_id%d.iter%d..features.txt for transformed features. # individual_scored_id%d.iter%d..features_orig.txt for original features. # individual_scored_id%d.iter%d..coefs.txt for absolute importance of transformed features. # There are txt, tab.txt, and json formats for some files, and "best_" prefix means it is the best individual for that iteration # The hash in the name matches the hash in the files produced by dump_modelparams_every_scored_indiv=true that can be used to track mutation history. #dump_varimp_every_scored_indiv = false # Whether to dump every scored individual's model parameters to csv/tabulated/json file # produces files like: individual_scored.params.[txt, csv, json]. # Each individual has a hash that matches the hash in the filenames produced if dump_varimp_every_scored_indiv=true, # and the "unchanging hash" is the first parent hash (None if that individual is the first parent itself). # These hashes can be used to track the history of the mutations. # #dump_modelparams_every_scored_indiv = true # Number of features to show in model dump every scored individual #dump_modelparams_every_scored_indiv_feature_count = 3 # Number of past mutations to show in model dump every scored individual #dump_modelparams_every_scored_indiv_mutation_count = 3 # Whether to append (false) or have separate files, files like: individual_scored_id%d.iter%d*params*, (true) for modelparams every scored indiv #dump_modelparams_separate_files = false # Whether to dump every scored fold's timing and feature info to a *timings*.txt file # #dump_trans_timings = false # whether to delete preview timings if wrote transformer timings #delete_preview_trans_timings = true # Attempt to create at most this many exemplars (actual rows behaving like cluster centroids) for the Aggregator # algorithm in unsupervised experiment mode. # #unsupervised_aggregator_n_exemplars = 100 # Attempt to create at least this many clusters for clustering algorithm in unsupervised experiment mode. # #unsupervised_clustering_min_clusters = 2 # Attempt to create no more than this many clusters for clustering algorithm in unsupervised experiment mode. # #unsupervised_clustering_max_clusters = 10 #use_random_text_file = false #runtime_estimation_train_frame = "" #enable_bad_scorer = false #debug_col_dict_prefix = "" #return_early_debug_col_dict_prefix = false #return_early_debug_preview = false #wizard_random_attack = false #wizard_enable_back_button = true #wizard_deployment = "" #wizard_repro_level = -1 #wizard_sample_size = 100000 #wizard_model = "rf" # Maximum number of columns to start an experiment. This threshold exists to constraint the # complexity and the length of the Driverless AI's processes. #wizard_max_cols = 100000 # How many seconds to allow preview to take for Wizard. #wizard_timeout_preview = 30 # How many seconds to allow leakage detection to take for Wizard. #wizard_timeout_leakage = 60 # How many seconds to allow duplicate row detection to take for Wizard. #wizard_timeout_dups = 30 # How many seconds to allow variable importance calculation to take for Wizard. #wizard_timeout_varimp = 30 # How many seconds to allow dataframe schema calculation to take for Wizard. #wizard_timeout_schema = 60 # authentication_method # unvalidated : Accepts user id and password. Does not validate password. # none: Does not ask for user id or password. Authenticated as admin. # openid: Users OpenID Connect provider for authentication. See additional OpenID settings below. # oidc: Renewed OpenID Connect authentication using authorization code flow. See additional OpenID settings below. # pam: Accepts user id and password. Validates user with operating system. # ldap: Accepts user id and password. Validates against an ldap server. Look # for additional settings under LDAP settings. # local: Accepts a user id and password. Validated against an htpasswd file provided in local_htpasswd_file. # ibm_spectrum_conductor: Authenticate with IBM conductor auth api. # tls_certificate: Authenticate with Driverless by providing a TLS certificate. # jwt: Authenticate by JWT obtained from the request metadata. # #authentication_method = "unvalidated" # Additional authentication methods that will be enabled for for the clients.Login forms for each method will be available on the/login/ path.Comma separated list. #additional_authentication_methods = "[]" # The default amount of time in hours before a user is signed out and must log in again. This setting is used when a default timeout value is not provided by authentication_method. #authentication_default_timeout_hours = 72.0 # When enabled, the user's session is automatically prolonged, even when they are not interacting directly with the application. #authentication_gui_polling_prolongs_session = false # OpenID Connect Settings: # Refer to the OpenID Connect Basic Client Implementation Guide for details on how OpenID authentication flow works # https://openid.net/specs/openid-connect-basic-1_0.html # base server URI to the OpenID Provider server (ex: https://oidp.ourdomain.com #auth_openid_provider_base_uri = "" # URI to pull OpenID config data from (you can extract most of required OpenID config from this url) # usually located at: /auth/realms/master/.well-known/openid-configuration #auth_openid_configuration_uri = "" # URI to start authentication flow #auth_openid_auth_uri = "" # URI to make request for token after callback from OpenID server was received #auth_openid_token_uri = "" # URI to get user information once access_token has been acquired (ex: list of groups user belongs to will be provided here) #auth_openid_userinfo_uri = "" # URI to logout user #auth_openid_logout_uri = "" # callback URI that OpenID provide will use to send 'authentication_code' # This is OpenID callback endpoint in Driverless AI. Most OpenID providers need this to be HTTPs. # (ex. https://driverless.ourdomin.com/openid/callback) #auth_openid_redirect_uri = "" # OAuth2 grant type (usually authorization_code for OpenID, can be access_token also) #auth_openid_grant_type = "" # OAuth2 response type (usually code) #auth_openid_response_type = "" # Client ID registered with OpenID provider #auth_openid_client_id = "" # Client secret provided by OpenID provider when registering Client ID #auth_openid_client_secret = "" # Scope of info (usually openid). Can be list of more than one, space delimited, possible # values listed at https://openid.net/specs/openid-connect-basic-1_0.html#Scopes #auth_openid_scope = "" # What key in user_info JSON should we check to authorize user #auth_openid_userinfo_auth_key = "" # What value should the key have in user_info JSON in order to authorize user #auth_openid_userinfo_auth_value = "" # Key that specifies username in user_info JSON (we will use the value of this key as username in Driverless AI) #auth_openid_userinfo_username_key = "" # Quote method from urllib.parse used to encode payload dict in Authentication Request #auth_openid_urlencode_quote_via = "quote" # Key in Token Response JSON that holds the value for access token expiry #auth_openid_access_token_expiry_key = "expires_in" # Key in Token Response JSON that holds the value for access token expiry #auth_openid_refresh_token_expiry_key = "refresh_expires_in" # Expiration time in seconds for access token #auth_openid_token_expiration_secs = 3600 # Enables advanced matching for OpenID Connect authentication. # When enabled ObjectPath () expression is used to # evaluate the user identity. # #auth_openid_use_objectpath_match = false # ObjectPath () expression that will be used # to evaluate whether user is allowed to login into Driverless. # Any expression that evaluates to True means user is allowed to log in. # Examples: # Simple claim equality: \$.our_claim is "our_value" # List of claims contains required value: "expected_role" in @.roles # #auth_openid_use_objectpath_expression = "" # Sets token introspection URL for OpenID Connect authentication. (needs to be an absolute URL) Needs to be set when API token introspection is enabled. Is used to get the token TTL when set and IDP does not provide expires_in field in the token endpoint response. #auth_openid_token_introspection_url = "" # Sets an URL where the user is being redirected after being logged out when set. (needs to be an absolute URL) #auth_openid_end_session_endpoint_url = "" # If set, server will use these scopes when it asks for the token on the login. (space separated list) #auth_openid_default_scopes = "" # Specifies the source from which user identity and username is retrieved. # Currently supported sources are: # user_info: Retrieves username from UserInfo endpoint response # id_token: Retrieves username from ID Token using # auth_openid_id_token_username_key claim # #auth_oidc_identity_source = "userinfo" # Claim of preferred username in a message holding the user identity, which will be used as a username in application. The user identity source is specified by auth_oidc_identity_source, and can be e.g. UserInfo endpoint response or ID Token #auth_oidc_username_claim = "" # OpenID-Connect Issuer URL, which is used for automatic provider infodiscovery. E.g. https://login.microsoftonline.com//v2.0 #auth_oidc_issuer_url = "" # OpenID-Connect Token endpoint URL. Setting this is optional and if it's empty, it'll be automatically set by provider info discovery. #auth_oidc_token_endpoint_url = "" # OpenID-Connect Token introspection endpoint URL. Setting this is optional and if it's empty, it'll be automatically set by provider info discovery. #auth_oidc_introspection_endpoint_url = "" # Absolute URL to which user is redirected, after they log out from the application, in case OIDC authentication is used. Usually this is absolute URL of DriverlessAI Login page e.g. https://1.2.3.4:12345/login #auth_oidc_post_logout_url = "" # Key-value mapping of extra HTTP query parameters in an OIDC authorization request. #auth_oidc_authorization_query_params = "{}" # When set to True, will skip cert verification. #auth_oidc_skip_cert_verification = false # When set will use this value as the location for the CA cert, this takes precedence over auth_oidc_skip_cert_verification. #auth_oidc_ca_cert_location = "" # Enables option to use Bearer token for authentication with the RPC endpoint. #api_token_introspection_enabled = false # Sets the method that is used to introspect the bearer token. # OAUTH2_TOKEN_INTROSPECTION: Uses OAuth 2.0 Token Introspection (RPC 7662) # endpoint to introspect the bearer token. # This useful when 'openid' is used as the authentication method. # Uses 'auth_openid_client_id' and 'auth_openid_client_secret' and to # authenticate with the authorization server and # auth_openid_token_introspection_url to perform the introspection. # #api_token_introspection_method = "OAUTH2_TOKEN_INTROSPECTION" # Sets the minimum of the scopes that the access token needs to have # in order to pass the introspection. Space separated./ # This is passed to the introspection endpoint and also verified after response # for the servers that don't enforce scopes. # Keeping this empty turns any the verification off. # #api_token_oauth2_scopes = "" # Which field of the response returned by the token introspection endpoint should be used as a username. #api_token_oauth2_username_field_name = "username" # Enables the option to initiate a PKCE flow from the UI in order to obtaintokens usable with Driverless clients #oauth2_client_tokens_enabled = false # Sets up client id that will be used in the OAuth 2.0 Authorization Code Flow to obtain the tokens. Client needs to be public and be able to use PKCE with S256 code challenge. #oauth2_client_tokens_client_id = "" # Sets up the absolute url to the authorize endpoint. #oauth2_client_tokens_authorize_url = "" # Sets up the absolute url to the token endpoint. #oauth2_client_tokens_token_url = "" # Sets up the absolute url to the token introspection endpoint.It's displayed in the UI so that clients can inspect the token expiration. #oauth2_client_tokens_introspection_url = "" # Sets up the absolute to the redirect url where Driverless handles the redirect part of the Authorization Code Flow. this /oauth2/client_token #oauth2_client_tokens_redirect_url = "" # Sets up the scope for the requested tokens. Space seprated list. #oauth2_client_tokens_scope = "openid profile ai.h2o.storage" # ldap server domain or ip #ldap_server = "" # ldap server port #ldap_port = "" # Complete DN of the LDAP bind user #ldap_bind_dn = "" # Password for the LDAP bind #ldap_bind_password = "" # Provide Cert file location #ldap_tls_file = "" # use true to use ssl or false #ldap_use_ssl = false # the location in the DIT where the search will start #ldap_search_base = "" # A string that describes what you are searching for. You can use Pythonsubstitution to have this constructed dynamically.(only {{DAI_USERNAME}} is supported) #ldap_search_filter = "" # ldap attributes to return from search #ldap_search_attributes = "" # specify key to find user name #ldap_user_name_attribute = "" # When using this recipe, needs to be set to "1" #ldap_recipe = "0" # Deprecated do not use #ldap_user_prefix = "" # Deprecated, Use ldap_bind_dn #ldap_search_user_id = "" # Deprecated, ldap_bind_password #ldap_search_password = "" # Deprecated, use ldap_search_base instead #ldap_ou_dn = "" # Deprecated, use ldap_base_dn #ldap_dc = "" # Deprecated, use ldap_search_base #ldap_base_dn = "" # Deprecated, use ldap_search_filter #ldap_base_filter = "" # Path to the CRL file that will be used to verify client certificate. #auth_tls_crl_file = "" # What field of the subject would used as source for username or other values used for further validation. #auth_tls_subject_field = "CN" # Regular expression that will be used to parse subject field to obtain the username or other values used for further validation. #auth_tls_field_parse_regexp = "(?P.*)" # Sets up the way how user identity would be obtained # REGEXP_ONLY: Will use 'auth_tls_subject_field' and 'auth_tls_field_parse_regexp' # to extract the username from the client certificate. # LDAP_LOOKUP: Will use LDAP server to lookup for the username. # 'auth_tls_ldap_server', 'auth_tls_ldap_port', # 'auth_tls_ldap_use_ssl', 'auth_tls_ldap_tls_file', # 'auth_tls_ldap_bind_dn', 'auth_tls_ldap_bind_password' # options are used to establish the connection with the LDAP server. # 'auth_tls_subject_field' and 'auth_tls_field_parse_regexp' # options are used to parse the certificate. # 'auth_tls_ldap_search_base', 'auth_tls_ldap_search_filter', and # 'auth_tls_ldap_username_attribute' options are used to do the # lookup. # #auth_tls_user_lookup = "REGEXP_ONLY" # Hostname or IP address of the LDAP server used with LDAP_LOOKUP with 'tls_certificate' authentication method. #auth_tls_ldap_server = "" # Port of the LDAP server used with LDAP_LOOKUP with 'tls_certificate' authentication method. #auth_tls_ldap_port = "" # Whether to SSL to when connecting to the LDAP server used with LDAP_LOOKUP with 'tls_certificate' authentication method. #auth_tls_ldap_use_ssl = false # Path to the SSL certificate used with LDAP_LOOKUP with 'tls_certificate' authentication method. #auth_tls_ldap_tls_file = "" # Complete DN of the LDAP bind user used with LDAP_LOOKUP with 'tls_certificate' authentication method. #auth_tls_ldap_bind_dn = "" # Password for the LDAP bind used with LDAP_LOOKUP with 'tls_certificate' authentication method. #auth_tls_ldap_bind_password = "" # Location in the DIT where the search will start used with LDAP_LOOKUP with 'tls_certificate' authentication method. #auth_tls_ldap_search_base = "" # LDAP filter that will be used to lookup for the user # with LDAP_LOOKUP with 'tls_certificate' authentication method. # Can be built dynamically using the named capturing groups from the # 'auth_tls_field_parse_regexp' for substitution. # Example: # auth_tls_field_parse_regexp="\w+ (?P\d+)" # auth_tls_ldap_search_filter="(&(objectClass=person)(id={{id}}))" # #auth_tls_ldap_search_filter = "" # Specified what LDAP record attribute will be used as username with LDAP_LOOKUP with 'tls_certificate' authentication method. #auth_tls_ldap_username_attribute = "" # Sets optional additional lookup filter that is performed after the # user is found. This can be used for example to check whether the is member of # particular group. # Filter can be built dynamically from the attributes returned by the lookup. # Authorization fails when search does not return any entry. If one ore more # entries are returned authorization succeeds. # Example: # auth_tls_field_parse_regexp="\w+ (?P\d+)" # ldap_search_filter="(&(objectClass=person)(id={{id}}))" # auth_tls_ldap_authorization_lookup_filter="(&(objectClass=group)(member=uid={{uid}},dc=example,dc=com))" # If this option is empty no additional lookup is done and just a successful user # lookup is enough to authorize the user. # #auth_tls_ldap_authorization_lookup_filter = "" # Base DN where to start the Authorization lookup. Used when 'auth_tls_ldap_authorization_lookup_filter' is set. #auth_tls_ldap_authorization_search_base = "" # Sets up the way how the token will picked from the request # COOKIE: Will use 'auth_jwt_cookie_name' cookie content parsed with # 'auth_jwt_source_parse_regexp' to obtain the token content. # HEADER: Will use 'auth_jwt_header_name' header value parsed with # 'auth_jwt_source_parse_regexp' to obtain the token content. # #auth_jwt_token_source = "HEADER" # Specifies name of the cookie that will be used to obtain JWT. #auth_jwt_cookie_name = "" # Specifies name http header that will be used to obtain JWT #auth_jwt_header_name = "" # Regular expression that will be used to parse JWT source. Expression is in Python syntax and must contain named group 'token' with capturing the token value. #auth_jwt_source_parse_regexp = "(?P.*)" # Which JWT claim will be used as username for Driverless. #auth_jwt_username_claim_name = "sub" # Whether to verify the signature of the JWT. #auth_jwt_verify = true # Signature algorithm that will be used to verify the signature according to RFC 7518. #auth_jwt_algorithm = "HS256" # Specifies the secret content for HMAC or public key for RSA and DSA signature algorithms. #auth_jwt_secret = "" # Number of seconds after JWT still can be accepted if when already expired #auth_jwt_exp_leeway_seconds = 0 # List of accepted 'aud' claims for the JWTs. When empty, anyaudience is accepted #auth_jwt_required_audience = "[]" # Value of the 'iss' claim that JWTs need to have in order to be accepted. #auth_jwt_required_issuer = "" # Local password file # Generating a htpasswd file: see syntax below # htpasswd -B '' '' # note: -B forces use of brcypt, a secure encryption method #local_htpasswd_file = "" # Specify the name of the report. #autodoc_report_name = "report" # AutoDoc template path. Provide the full path to your custom AutoDoc template or leave as 'default'to generate the standard AutoDoc. #autodoc_template = "" # Location of the additional AutoDoc templates #autodoc_additional_template_folder = "" # Specify the AutoDoc output type. #autodoc_output_type = "docx" # Specify the type of sub-templates to use. # Options are 'auto', 'docx' or 'md'. #autodoc_subtemplate_type = "auto" # Specify the maximum number of classes in the confusion # matrix. #autodoc_max_cm_size = 10 
 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846  # Specify the number of top features to display in # the document. setting to -1 disables this restriction. #autodoc_num_features = 50 # Specify the minimum relative importance in order # for a feature to be displayed. autodoc_min_relative_importance # must be a float >= 0 and <= 1. #autodoc_min_relative_importance = 0.003 # Whether to compute permutation based feature # importance. #autodoc_include_permutation_feature_importance = false # Number of permutations to make per feature when computing # feature importance. #autodoc_feature_importance_num_perm = 1 # Name of the scorer to be used to calculate feature # importance. Leave blank to use experiments default scorer. #autodoc_feature_importance_scorer = "" # The autodoc_pd_max_rows configuration controls the # number of rows shown for the partial dependence plots (PDP) and Shapley # values summary plot in the AutoDoc. Random sampling is used for # datasets with more than the autodoc_pd_max_rows limit. #autodoc_pd_max_rows = 10000 # Maximum number of seconds Partial Dependency computation # can take when generating report. Set to -1 for no time limit. #autodoc_pd_max_runtime = 45 # Whether to enable fast approximation for predictions that are needed for the # generation of partial dependence plots. Can help when want to create many PDP # plots in short time. Amount of approximation is controlled by fast_approx_num_trees, # fast_approx_do_one_fold, fast_approx_do_one_model experiment expert settings. # #autodoc_pd_fast_approx = true # Max number of unique values for integer/real columns to be treated as categoricals (test applies to first statistical_threshold_data_size_small rows only) # Similar to max_int_as_cat_uniques used for experiment, but here used to control PDP making. #autodoc_pd_max_int_as_cat_uniques = 50 # Number of standard deviations outside of the range of # a column to include in partial dependence plots. This shows how the # model will react to data it has not seen before. #autodoc_out_of_range = 3 # Specify the number of rows to include in PDP and ICE plot # if individual rows are not specified. #autodoc_num_rows = 0 # Whether to include population stability index if # experiment is binary classification/regression. #autodoc_population_stability_index = false # Number of quantiles to use for population stability index # . #autodoc_population_stability_index_n_quantiles = 10 # Whether to include prediction statistics information if # experiment is binary classification/regression. #autodoc_prediction_stats = false # Number of quantiles to use for prediction statistics. #autodoc_prediction_stats_n_quantiles = 20 # Whether to include response rates information if # experiment is binary classification. #autodoc_response_rate = false # Number of quantiles to use for response rates information # . #autodoc_response_rate_n_quantiles = 10 # Whether to show the Gini Plot. #autodoc_gini_plot = false # Show Shapley values results in the AutoDoc. #autodoc_enable_shapley_values = true # The number feature in a KLIME global GLM coefficients # table. Must be an integer greater than 0 or -1. To # show all features set to -1. #autodoc_global_klime_num_features = 10 # Set the number of KLIME global GLM coefficients tables. Set # to 1 to show one table with coefficients sorted by absolute # value. Set to 2 to two tables one with the top positive # coefficients and one with the top negative coefficients. #autodoc_global_klime_num_tables = 1 # Number of features to be show in data summary. Value # must be an integer. Values lower than 1, f.e. 0 or -1, indicate that # all columns should be shown. #autodoc_data_summary_col_num = -1 # Whether to show all config settings. If False, only # the changed settings (config overrides) are listed, otherwise all # settings are listed. #autodoc_list_all_config_settings = false # Line length of the keras model architecture summary. Must # be an integer greater than 0 or -1. To use the default line length set # value -1. #autodoc_keras_summary_line_length = -1 # Maximum number of lines shown for advanced transformer # architecture in the Feature section. Note that the full architecture # can be found in the Appendix. #autodoc_transformer_architecture_max_lines = 30 # Show full NLP/Image transformer architecture in # the Appendix. #autodoc_full_architecture_in_appendix = false # Specify whether to show the full glm coefficient # table(s) in the appendix. coef_table_appendix_results_table must be # a boolean: True to show tables in appendix, False to not show them # . #autodoc_coef_table_appendix_results_table = false # Set the number of models for which a glm coefficients # table is shown in the AutoDoc. coef_table_num_models must # be -1 or an integer >= 1 (-1 shows all models). #autodoc_coef_table_num_models = 1 # Set the number of folds per model for which a glm # coefficients table is shown in the AutoDoc. # coef_table_num_folds must be -1 or an integer >= 1 # (-1 shows all folds per model). #autodoc_coef_table_num_folds = -1 # Set the number of coefficients to show within a glm # coefficients table in the AutoDoc. coef_table_num_coef, controls # the number of rows shown in a glm table and must be -1 or # an integer >= 1 (-1 shows all coefficients). #autodoc_coef_table_num_coef = 50 # Set the number of classes to show within a glm # coefficients table in the AutoDoc. coef_table_num_classes controls # the number of class-columns shown in a glm table and must be -1 or # an integer >= 4 (-1 shows all classes). #autodoc_coef_table_num_classes = 9 # When histogram plots are available: The number of # top (default 10) features for which to show histograms. #autodoc_num_histogram_plots = 10 #pdp_max_threads = -1 # If True, will force AutoDoc to run in only the main server, not on remote workers in case of a multi-node setup #autodoc_force_singlenode = false # IP address and port of autoviz process. #vis_server_ip = "127.0.0.1" # IP and port of autoviz process. #vis_server_port = 12346 # Maximum number of columns autoviz will work with. # If dataset has more columns than this number, # autoviz will pick columns randomly, prioritizing numerical columns # #autoviz_max_num_columns = 50 # When enabled, experiment will try to use feature transformations recommended by Autoviz #autoviz_enable_recommendations = true # Key-value pairs of column names, and transformations that Autoviz recommended #autoviz_recommended_transformation = "{}" #autoviz_enable_transformer_acceptance_tests = false # Enable custom recipes. #enable_custom_recipes = true # Enable uploading of custom recipes from local file system. #enable_custom_recipes_upload = true # Enable downloading of custom recipes from external URL. #enable_custom_recipes_from_url = true # Enable upload recipe files to be zip, containing custom recipe(s) in root folder, # while any other code or auxillary files must be in some sub-folder. # #enable_custom_recipes_from_zip = true #must_have_custom_transformers = false #must_have_custom_transformers_2 = false #must_have_custom_transformers_3 = false #must_have_custom_models = false #must_have_custom_scorers = false # When set to true, it enable downloading custom recipes third party packages from the web, otherwise the python environment will be transferred from main worker. #enable_recreate_custom_recipes_env = true #extra_migration_custom_recipes_missing_modules = false # Include custom recipes in default inclusion lists (warning: enables all custom recipes) #include_custom_recipes_by_default = false #force_include_custom_recipes_by_default = false # Enable h2o recipes server. #enable_h2o_recipes = true # URL of H2O instance for use by transformers, models, or scorers. #h2o_recipes_url = "None" # IP of H2O instance for use by transformers, models, or scorers. #h2o_recipes_ip = "None" # Port of H2O instance for use by transformers, models, or scorers. No other instances must be on that port or on next port. #h2o_recipes_port = 50361 # Name of H2O instance for use by transformers, models, or scorers. #h2o_recipes_name = "None" # Number of threads for H2O instance for use by transformers, models, or scorers. -1 for all. #h2o_recipes_nthreads = 8 # Log Level of H2O instance for use by transformers, models, or scorers. #h2o_recipes_log_level = "None" # Maximum memory size of H2O instance for use by transformers, models, or scorers. #h2o_recipes_max_mem_size = "None" # Minimum memory size of H2O instance for use by transformers, models, or scorers. #h2o_recipes_min_mem_size = "None" # General user overrides of kwargs dict to pass to h2o.init() for recipe server. #h2o_recipes_kwargs = "{}" # Number of trials to give h2o-3 recipe server to start. #h2o_recipes_start_trials = 5 # Number of seconds to sleep before starting h2o-3 recipe server. #h2o_recipes_start_sleep0 = 1 # Number of seconds to sleep between trials of starting h2o-3 recipe server. #h2o_recipes_start_sleep = 5 # Lock source for recipes to a specific github repo. # If True then all custom recipes must come from the repo specified in setting: custom_recipes_git_repo #custom_recipes_lock_to_git_repo = false # If custom_recipes_lock_to_git_repo is set to True, only this repo can be used to pull recipes from #custom_recipes_git_repo = "https://github.com/h2oai/driverlessai-recipes" # Branch constraint for recipe source repo. Any branch allowed if unset or None #custom_recipes_git_branch = "None" #custom_recipes_excluded_filenames_from_repo_download = "[]" #allow_old_recipes_use_datadir_as_data_directory = true # Internal helper to allow memory of if changed recipe #last_recipe = "" # Dictionary to control recipes for each experiment and particular custom recipes. # E.g. if inserting into the GUI as any toml string, can use: # ""recipe_dict="{'key1': 2, 'key2': 'value2'}""" # E.g. if putting into config.toml as a dict, can use: # recipe_dict="{'key1': 2, 'key2': 'value2'}" # #recipe_dict = "{}" # Dictionary to control some mutation parameters. # E.g. if inserting into the GUI as any toml string, can use: # ""mutation_dict="{'key1': 2, 'key2': 'value2'}""" # E.g. if putting into config.toml as a dict, can use: # mutation_dict="{'key1': 2, 'key2': 'value2'}" # #mutation_dict = "{}" #enable_custom_transformers = true #enable_custom_pretransformers = true #enable_custom_models = true #enable_custom_scorers = true #enable_custom_datas = true #enable_custom_explainers = true #enable_custom_individuals = true # Whether to validate recipe names provided in included lists, like included_models, # or (if False) whether to just log warning to server logs and ignore any invalid names of recipes. # #raise_on_invalid_included_list = false #contrib_relative_directory = "contrib" # location of custom recipes packages installed (relative to data_directory) # We will try to install packages dynamically, but can also do (before or after server started): # (inside docker running docker instance if running docker, or as user server is running as (e.g. dai user) if deb/tar native installation: # PYTHONPATH=//lib/python3.6/site-packages/ dai-env.sh python -m pip install --prefix=/ --upgrade --upgrade-strategy only-if-needed --log-file pip_log_file.log # where is /opt/h2oai/dai/ for native rpm/deb installation # Note can also install wheel files if is name of wheel file or archive. # #contrib_env_relative_directory = "contrib/env" # List of package versions to ignore. Useful when small version change but likely to function still with old package version. # #ignore_package_version = "[]" # List of package versions to remove if encounter conflict. Useful when want new version of package, and old recipes likely to function still. # #clobber_package_version = "['catboost']" # List of package versions to remove if encounter conflict. # Useful when want new version of package, and old recipes likely to function still. # Also useful when do not need to use old versions of recipes even if they would no longer function. # #swap_package_version = "{'catboost==0.26.1': 'catboost==1.0.5', 'catboost==0.25.1': 'catboost==1.0.5', 'catboost==0.24.1': 'catboost==1.0.5', 'catboost==1.0.4': 'catboost==1.0.5', 'catboost==1.0.6': 'catboost==1.0.5', 'catboost': 'catboost==1.0.5'}" # If user uploads recipe with changes to package versions, # allow upgrade of package versions. # If DAI protected packages are attempted to be changed, can try using pip_install_options toml with ['--no-deps']. # Or to ignore entirely DAI versions of packages, can try using pip_install_options toml with ['--ignore-installed']. # Any other experiments relying on recipes with such packages will be affected, use with caution. #allow_version_change_user_packages = false # pip install retry for call to pip. Sometimes need to try twice #pip_install_overall_retries = 2 # pip install verbosity level (number of -v's given to pip, up to 3 #pip_install_verbosity = 2 # pip install timeout in seconds, Sometimes internet issues would mean want to fail faster #pip_install_timeout = 15 # pip install retry count #pip_install_retries = 5 # Whether to use DAI constraint file to help pip handle versions. pip can make mistakes and try to install updated packages for no reason. #pip_install_use_constraint = true # pip install options: string of list of other options, e.g. ['--proxy', 'http://user:password@proxyserver:port'] #pip_install_options = "[]" # Whether to enable basic acceptance testing. Tests if can pickle the state, etc. #enable_basic_acceptance_tests = true # Whether acceptance tests should run for custom genes / models / scorers / etc. #enable_acceptance_tests = true #acceptance_tests_use_weather_data = false #acceptance_tests_mojo_benchmark = false # Whether to skip disabled recipes (True) or fail and show GUI message (False). #skip_disabled_recipes = false # Minutes to wait until a recipe's acceptance testing is aborted. A recipe is rejected if acceptance # testing is enabled and times out. # One may also set timeout for a specific recipe by setting the class's staticmethod function called # acceptance_test_timeout to return number of minutes to wait until timeout doing acceptance testing. # This timeout does not include the time to install required packages. # #acceptance_test_timeout = 20.0 # Whether to re-check recipes during server startup (if per_user_directories == false) # or during user login (if per_user_directories == true). # If any inconsistency develops, the bad recipe will be removed during re-doing acceptance testing. This process # can make start-up take alot longer for many recipes, but in LTS releases the risk of recipes becoming out of date # is low. If set to false, will disable acceptance re-testing during sever start but note that previews or experiments may fail if those inconsistent recipes are used. # Such inconsistencies can occur when API changes for recipes or more aggressive acceptance tests are performed. # #contrib_reload_and_recheck_server_start = true # Whether to at least install packages required for recipes during server startup (if per_user_directories == false) # or during user login (if per_user_directories == true). # Important to keep True so any later use of recipes (that have global packages installed) will work. # #contrib_install_packages_server_start = true # Whether to re-check recipes after uploaded from main server to worker in multinode. # Expensive for every task that has recipes to do this. #contrib_reload_and_recheck_worker_tasks = false #data_recipe_isolate = true # Space-separated string list of URLs for recipes that are loaded at user login time #server_recipe_url = "" #num_rows_acceptance_test_custom_transformer = 200 #num_rows_acceptance_test_custom_model = 100 # List of recipes (per dict key by type) that are applicable for given experiment. This is especially relevant # for situations such as new experiment with same params where the user should be able to # use the same recipe versions as the parent experiment if he/she wishes to. # #recipe_activation = "{}" # File System Support # upload : standard upload feature # file : local file system/server file system # hdfs : Hadoop file system, remember to configure the HDFS config folder path and keytab below # dtap : Blue Data Tap file system, remember to configure the DTap section below # s3 : Amazon S3, optionally configure secret and access key below # gcs : Google Cloud Storage, remember to configure gcs_path_to_service_account_json below # gbq : Google Big Query, remember to configure gcs_path_to_service_account_json below # minio : Minio Cloud Storage, remember to configure secret and access key below # snow : Snowflake Data Warehouse, remember to configure Snowflake credentials below (account name, username, password) # kdb : KDB+ Time Series Database, remember to configure KDB credentials below (hostname and port, optionally: username, password, classpath, and jvm_args) # azrbs : Azure Blob Storage, remember to configure Azure credentials below (account name, account key) # jdbc: JDBC Connector, remember to configure JDBC below. (jdbc_app_configs) # hive: Hive Connector, remember to configure Hive below. (hive_app_configs) # recipe_file: Custom recipe file upload # recipe_url: Custom recipe upload via url # h2o_drive: H2O Drive, remember to configure h2o_drive_endpoint_url below # feature_store: Feature Store, remember to configure feature_store_endpoint_url below # #enabled_file_systems = "['upload', 'file', 'hdfs', 's3', 'recipe_file', 'recipe_url']" #max_files_listed = 100 # The option disable access to DAI data_directory from file browser #file_hide_data_directory = true # Enable usage of path filters #file_path_filtering_enabled = false # List of absolute path prefixes to restrict access to in file system browser. # First add the following environment variable to your command line to enable this feature: # file_path_filtering_enabled=true # This feature can be used in the following ways (using specific path or using logged user's directory): # file_path_filter_include="['/data/stage']" # file_path_filter_include="['/data/stage','/data/prod']" # file_path_filter_include=/home/{{DAI_USERNAME}}/ # file_path_filter_include="['/home/{{DAI_USERNAME}}/','/data/stage','/data/prod']" # #file_path_filter_include = "[]" # (Required) HDFS connector # Specify HDFS Auth Type, allowed options are: # noauth : (default) No authentication needed # principal : Authenticate with HDFS with a principal user (DEPRECTATED - use keytab auth type) # keytab : Authenticate with a Key tab (recommended). If running # DAI as a service, then the Kerberos keytab needs to # be owned by the DAI user. # keytabimpersonation : Login with impersonation using a keytab #hdfs_auth_type = "noauth" # Kerberos app principal user. Required when hdfs_auth_type='keytab'; recommended otherwise. #hdfs_app_principal_user = "" # Deprecated - Do Not Use, login user is taken from the user name from login #hdfs_app_login_user = "" # JVM args for HDFS distributions, provide args seperate by space # -Djava.security.krb5.conf=/krb5.conf # -Dsun.security.krb5.debug=True # -Dlog4j.configuration=file:///log4j.properties #hdfs_app_jvm_args = "" # hdfs class path #hdfs_app_classpath = "" # List of supported DFS schemas. Ex. "['hdfs://', 'maprfs://', 'swift://']" # Supported schemas list is used as an initial check to ensure valid input to connector # #hdfs_app_supported_schemes = "['hdfs://', 'maprfs://', 'swift://']" # Maximum number of files viewable in connector ui. Set to larger number to view more files #hdfs_max_files_listed = 100 # Starting HDFS path displayed in UI HDFS browser #hdfs_init_path = "hdfs://" # Starting HDFS path for the artifacts upload operations #hdfs_upload_init_path = "hdfs://" # Enables the multi-user mode for MapR integration, which allows to have MapR ticket per user. #enable_mapr_multi_user_mode = false # Blue Data DTap connector settings are similar to HDFS connector settings. # Specify DTap Auth Type, allowed options are: # noauth : No authentication needed # principal : Authenticate with DTab with a principal user # keytab : Authenticate with a Key tab (recommended). If running # DAI as a service, then the Kerberos keytab needs to # be owned by the DAI user. # keytabimpersonation : Login with impersonation using a keytab # NOTE: "hdfs_app_classpath" and "core_site_xml_path" are both required to be set for DTap connector #dtap_auth_type = "noauth" # Dtap (HDFS) config folder path , can contain multiple config files #dtap_config_path = "" # Path of the principal key tab file, dtap_key_tab_path is deprecated. Please use dtap_keytab_path #dtap_key_tab_path = "" # Path of the principal key tab file #dtap_keytab_path = "" # Kerberos app principal user (recommended) #dtap_app_principal_user = "" # Specify the user id of the current user here as user@realm #dtap_app_login_user = "" # JVM args for DTap distributions, provide args seperate by space #dtap_app_jvm_args = "" # DTap (HDFS) class path. NOTE: set 'hdfs_app_classpath' also #dtap_app_classpath = "" # Starting DTAP path displayed in UI DTAP browser #dtap_init_path = "dtap://" # S3 Connector credentials #aws_access_key_id = "" # S3 Connector credentials #aws_secret_access_key = # S3 Connector credentials #aws_role_arn = "" # What region to use when none is specified in the s3 url. # Ignored when aws_s3_endpoint_url is set. # #aws_default_region = "" # Sets endpoint URL that will be used to access S3. #aws_s3_endpoint_url = "" # If set to true S3 Connector will try to to obtain credentials associated with # the role attached to the EC2 instance. #aws_use_ec2_role_credentials = false # Starting S3 path displayed in UI S3 browser #s3_init_path = "s3://" # S3 Connector will skip cert verification if this is set to true, (mostly used for S3-like connectors, e.g. Ceph) #s3_skip_cert_verification = false # path/to/cert/bundle.pem - A filename of the CA cert bundle to use for the S3 connector #s3_connector_cert_location = "" # GCS Connector credentials # example (suggested) -- '/licenses/my_service_account_json.json' #gcs_path_to_service_account_json = "" # Starting GCS path displayed in UI GCS browser #gcs_init_path = "gs://" # Space-seperated list of OAuth2 scopes for the access token used to authenticate in Google Cloud Storage #gcs_access_token_scopes = "" # When google_cloud_use_oauth is enabled, Google Cloud client cannot automatically infer the default project, thus it must be explicitly specified #gcs_default_project_id = "" # Space-seperated list of OAuth2 scopes for the access token used to authenticate in Google BigQuery #gbq_access_token_scopes = "" # By default the DriverlessAI Google Cloud Storage and BigQuery connectors are using service account file to retrieve authentication credentials.When enabled, the Storage and BigQuery connectors will use OAuth2 user access tokens to authenticate in Google Cloud instead. #google_cloud_use_oauth = false # Minio Connector credentials #minio_endpoint_url = "" # Minio Connector credentials #minio_access_key_id = "" # Minio Connector credentials #minio_secret_access_key = # Minio Connector will skip cert verification if this is set to true #minio_skip_cert_verification = false # path/to/cert/bundle.pem - A filename of the CA cert bundle to use for the Minio connector #minio_connector_cert_location = "" # Starting Minio path displayed in UI Minio browser #minio_init_path = "/" # H2O Drive server endpoint URL #h2o_drive_endpoint_url = "" # Space seperated list of OpenID scopes for the access token used by the H2O Drive connector #h2o_drive_access_token_scopes = "" # Maximum duration (in seconds) for a session with the H2O Drive #h2o_drive_session_duration = 10800 # Recommended Provide: url, user, password # Optionally Provide: account, user, password # Example URL: https://..snowflakecomputing.com # Snowflake Connector credentials #snowflake_url = "" # Snowflake Connector credentials #snowflake_user = "" # Snowflake Connector credentials #snowflake_password = "" # Snowflake Connector credentials #snowflake_account = "" # Setting to allow or disallow Snowflake connector from using Snowflake stages during queries. # True - will permit the connector to use stages and generally improves performance. However, # if the Snowflake user does not have permission to create/use stages will end in errors. # False - will prevent the connector from using stages, thus Snowflake users without permission # to create/use stages will have successful queries, however may significantly negatively impact # query performance. # #snowflake_allow_stages = true # Sets the number of rows to be fetched by Snowflake cursor at one time. This is only used if setting # snowflake_allow_stages is set to False, may help with performance depending on the type and size # of data being queried. # #snowflake_batch_size = 10000 # KDB Connector credentials #kdb_user = "" # KDB Connector credentials #kdb_password = "" # KDB Connector credentials #kdb_hostname = "" # KDB Connector credentials #kdb_port = "" # KDB Connector credentials #kdb_app_classpath = "" # KDB Connector credentials #kdb_app_jvm_args = "" # Azure Blob Store Connector credentials #azure_blob_account_name = "" # Azure Blob Store Connector credentials #azure_blob_account_key = # Azure Blob Store Connector credentials #azure_connection_string = "" # Starting Azure blob store path displayed in UI Azure blob store browser #azure_blob_init_path = "https://" # When enabled, Azure Blob Store Connector will use access token derived from the credentials received on login with OpenID Connect. #azure_blob_use_access_token = false # Configures the scopes for the access token used by Azure Blob Store Connector when the azure_blob_use_access_token us enabled. (space separated list) #azure_blob_use_access_token_scopes = "https://storage.azure.com/.default" # Sets the source of the access token for accessing the Azure bob store # KEYCLOAK: Will exchange the session access token for the federated # refresh token with Keycloak and use it to obtain the access token # directly with the Azure AD. # SESSION: Will use the access token derived from the credentials # received on login with OpenID Connect. # #azure_blob_use_access_token_source = "SESSION" # Application (client) ID registered on Azure AD when the KEYCLOAK source is enabled. #azure_blob_keycloak_aad_client_id = "" # Application (client) secret when the KEYCLOAK source is enabled. #azure_blob_keycloak_aad_client_secret = "" # A URL that identifies a token authority. It should be of the format https://login.microsoftonline.com/your_tenant #azure_blob_keycloak_aad_auth_uri = "" # Keycloak Endpoint for Retrieving External IDP Tokens (https://www.keycloak.org/docs/latest/server_admin/#retrieving-external-idp-tokens) #azure_blob_keycloak_broker_token_endpoint = "" # (DEPRECATED, use azure_blob_use_access_token and # azure_blob_use_access_token_source="KEYCLOAK" instead.) # (When enabled only DEPRECATED options azure_ad_client_id, # azure_ad_client_secret, azure_ad_auth_uri and # azure_keycloak_idp_token_endpoint will be effective) # This is equivalent to setting # azure_blob_use_access_token_source = "KEYCLOAK" # and setting azure_blob_keycloak_aad_client_id, # azure_blob_keycloak_aad_client_secret, # azure_blob_keycloak_aad_auth_uri and # azure_blob_keycloak_broker_token_endpoint # options. # ) # If true, enable the Azure Blob Storage Connector to use Azure AD tokens # obtained from the Keycloak for auth. # #azure_enable_token_auth_aad = false # (DEPRECATED, use azure_blob_keycloak_aad_client_id instead.) Application (client) ID registered on Azure AD #azure_ad_client_id = "" # (DEPRECATED, use azure_blob_keycloak_aad_client_secret instead.) Application Client Secret #azure_ad_client_secret = "" # (DEPRECATED, use azure_blob_keycloak_aad_auth_uri instead)A URL that identifies a token authority. It should be of the format https://login.microsoftonline.com/your_tenant #azure_ad_auth_uri = "" # (DEPRECATED, use azure_blob_use_access_token_scopes instead.)Scopes requested to access a protected API (a resource). #azure_ad_scopes = "[]" # (DEPRECATED, use azure_blob_keycloak_broker_token_endpoint instead.)Keycloak Endpoint for Retrieving External IDP Tokens (https://www.keycloak.org/docs/latest/server_admin/#retrieving-external-idp-tokens) #azure_keycloak_idp_token_endpoint = "" # Configuration for JDBC Connector. # JSON/Dictionary String with multiple keys. # Format as a single line without using carriage returns (the following example is formatted for readability). # Use triple quotations to ensure that the text is read as a single string. # Example: # '{ # "postgres": { # "url": "jdbc:postgresql://ip address:port/postgres", # "jarpath": "/path/to/postgres_driver.jar", # "classpath": "org.postgresql.Driver" # }, # "mysql": { # "url":"mysql connection string", # "jarpath": "/path/to/mysql_driver.jar", # "classpath": "my.sql.classpath.Driver" # } # }' # #jdbc_app_configs = "{}" # extra jvm args for jdbc connector #jdbc_app_jvm_args = "-Xmx4g" # alternative classpath for jdbc connector #jdbc_app_classpath = "" # Configuration for Hive Connector. # Note that inputs are similar to configuring HDFS connectivity. # important keys: # * hive_conf_path - path to hive configuration, may have multiple files. typically: hive-site.xml, hdfs-site.xml, etc # * auth_type - one of noauth, keytab, keytabimpersonation for kerberos authentication # * keytab_path - path to the kerberos keytab to use for authentication, can be "" if using noauth auth_type # * principal_user - Kerberos app principal user. Required when using auth_type keytab or keytabimpersonation # JSON/Dictionary String with multiple keys. Example: # '{ # "hive_connection_1": { # "hive_conf_path": "/path/to/hive/conf", # "auth_type": "one of ['noauth', 'keytab', 'keytabimpersonation']", # "keytab_path": "/path/to/.keytab", # "principal_user": "hive/localhost@EXAMPLE.COM", # }, # "hive_connection_2": { # "hive_conf_path": "/path/to/hive/conf_2", # "auth_type": "one of ['noauth', 'keytab', 'keytabimpersonation']", # "keytab_path": "/path/to/.keytab", # "principal_user": "my_user/localhost@EXAMPLE.COM", # } # }' # #hive_app_configs = "{}" # Extra jvm args for hive connector #hive_app_jvm_args = "-Xmx4g" # Alternative classpath for hive connector. Can be used to add additional jar files to classpath. #hive_app_classpath = "" # Replace all the downloads on the experiment page to exports and allow users to push to the artifact store configured with artifacts_store #enable_artifacts_upload = false # Artifacts store. # file_system: stores artifacts on a file system directory denoted by artifacts_file_system_directory. # s3: stores artifacts to S3 bucket. # bitbucket: stores data into Bitbucket repository. # azure: stores data into Azure Blob Store. # hdfs: stores data into a Hadoop distributed file system location. # #artifacts_store = "file_system" # Decide whether to skip cert verification for Bitbucket when using a repo with HTTPS #bitbucket_skip_cert_verification = false # Local temporary directory to clone artifacts to, relative to data_directory #bitbucket_tmp_relative_dir = "local_git_tmp" # File system location where artifacts will be copied in case artifacts_store is set to file_system #artifacts_file_system_directory = "tmp" # AWS S3 bucket used for experiment artifact export. #artifacts_s3_bucket = "" # Azure Blob Store credentials used for experiment artifact export #artifacts_azure_blob_account_name = "" # Azure Blob Store credentials used for experiment artifact export #artifacts_azure_blob_account_key = "" # Azure Blob Store connection string used for experiment artifact export #artifacts_azure_connection_string = "" # Git auth user #artifacts_git_user = "git" # Git auth password #artifacts_git_password = "" # Git repo where artifacts will be pushed upon and upload #artifacts_git_repo = "" # Git branch on the remote repo where artifacts are pushed #artifacts_git_branch = "dev" # File location for the ssh private key used for git authentication #artifacts_git_ssh_private_key_file_location = "" # Feature Store server endpoint URL #feature_store_endpoint_url = "" # Enable TLS communication between DAI and the Feature Store server #feature_store_enable_tls = false # Path to the client certificate to authenticate with the Feature Store server. This is only effective when feature_store_enable_tls=True. #feature_store_tls_cert_path = "" # A list of access token scopes used by the Feature Store connector to authenticate. (Space separate list) #feature_store_access_token_scopes = "" # Default AWS credentials to be used for scorer deployments. #deployment_aws_access_key_id = "" # Default AWS credentials to be used for scorer deployments. #deployment_aws_secret_access_key = "" # AWS S3 bucket to be used for scorer deployments. #deployment_aws_bucket_name = "" # Whether to allow user to change non-server toml parameters per experiment in expert page. #allow_config_overrides_in_expert_page = true # Maximum number of columns in each head and tail to log when ingesting data or running experiment on data. #max_cols_log_headtail = 1000 # Maximum number of columns in each head and tail to show in GUI, # useful when head or tail has all necessary columns, # but too many for UI or web server to handle. # -1 means no limit. # A reasonable value is 500, after which web server or browser can become overloaded and use too much memory. # Some values of column counts in UI may not show up correctly, and some dataset details functions may not work. # To select (from GUI or client) any columns as being # target, weight column, fold column, time column, time column groups, or dropped columns, # the dataset should have those columns within the selected head or tail set of columns. # #max_cols_gui_headtail = 1000 # Supported file formats (file name endings must match for files to show up in file browser) #supported_file_types = "['csv', 'tsv', 'txt', 'dat', 'tgz', 'gz', 'bz2', 'zip', 'xz', 'xls', 'xlsx', 'jay', 'feather', 'bin', 'arff', 'parquet', 'pkl', 'orc', 'avro']" # Supported file formats of data recipe files (file name endings must match for files to show up in file browser) #recipe_supported_file_types = "['py', 'pyc', 'zip']" # By default, only supported file types (based on the file extensions listed above) will be listed for import into DAI # Some data pipelines generate parquet files without any extensions. Enabling the below option will cause files # without an extension to be listed in the file import dialog. # DAI will import files without extensions as parquet files; if cannot be imported, an error is generated # #list_files_without_extensions = false # Allow using browser localstorage, to improve UX. #allow_localstorage = true # Allow original dataset columns to be present in downloaded predictions CSV #allow_orig_cols_in_predictions = true # Allow the browser to store e.g. login credentials in login form (set to false for higher security) #allow_form_autocomplete = true # Enable Projects workspace (alpha version, for evaluation) #enable_projects = true # Default application language - options are 'en', 'ja', 'cn', 'ko' #app_language = "en" # If true, Logout button is not visible in the GUI. #disablelogout = false # Local path to the location of the Driverless AI Python Client. If empty, will download from s3 #python_client_path = "" # If disabled, server won't verify if WHL package specified in python_client_path is valid DAI python client. Default True #python_client_verify_integrity = true # When enabled, new experiment requires to specify expert name #gui_require_experiment_name = false # When disabled, Deploy option will be disabled on finished experiment page #gui_enable_deploy_button = false # Display experiment tour #enable_gui_product_tour = true # Whether user can download dataset as csv file #enable_dataset_downloading = true # If enabled, user can export experiment as a Zip file #enable_experiment_export = true # If enabled, user can import experiments, exported as Zip files from DriverlessAI #enable_experiment_import = true # (EXPERIMENTAL) If enabled, user can launch experiment via new Predict Wizard options, which navigates to the new Nitro wizard. #enable_experiment_wizard = true # (EXPERIMENTAL) If enabled, user can do joins via new Join Wizard options, which navigates to the new Nitro wizard. #enable_join_wizard = true # URL address of the H2O AI link #hac_link_url = "https://www.h2o.ai/freetrial/?utm_source=dai&ref=dai" # If enabled, user can enable GPU toggle in experiment setup, even if no GPUwas detected in the system. This may be useful in multinode environment, where worker nodes are provisioned dynamically #enable_gpu_experiment_without_gpus_detected = false #show_all_filesystems = false # Switches Driverless AI to use H2O.ai License Management Server to manage licenses/permission to use software #enable_license_manager = false # Address at which to communicate with H2O.ai License Management Server. # Requires above value, enable_license_manager set to True. # Format: {http/https}://{ip address}:{port number} # #license_manager_address = "http://127.0.0.1:9999" # Name of license manager project that Driverless AI will attempt to retrieve leases from. # NOTE: requires an active license within the License Manager Server to function properly # #license_manager_project_name = "default" # Number of milliseconds a lease for users will be expected to last, # if using the H2O.ai License Manager server, before the lease REQUIRES renewal. # Default: 3600000 (1 hour) = 1 hour * 60 min / hour * 60 sec / min * 1000 milliseconds / sec # #license_manager_lease_duration = 3600000 # Number of milliseconds a lease for Driverless AI worker nodes will be expected to last, # if using the H2O.ai License Manager server, before the lease REQUIRES renewal. # Default: 21600000 (6 hour) = 6 hour * 60 min / hour * 60 sec / min * 1000 milliseconds / sec # #license_manager_worker_lease_duration = 21600000 # To be used only if License Manager server is started with HTTPS # Accepts a boolean: true/false, or a path to a file/directory. Denotates whether or not to attempt # SSL Certificate verification when making a request to the License Manager server. # True: attempt ssl certificate verification, will fail if certificates are self signed # False: skip ssl certificate verification. # /path/to/cert/directory: load certificates in directory and use those for certificate verification # Behaves in the same manner as python requests package: # https://requests.readthedocs.io/en/latest/user/advanced/#ssl-cert-verification # #license_manager_ssl_certs = "true" # Amount of time that Driverless AI workers will keep retrying to startup and obtain a lease from # the license manager before timing out. Time out will cause worker startup to fail. # #license_manager_worker_startup_timeout = 3600000 # Emergency setting that will allow Driverless AI to run even if there is issues communicating with # or obtaining leases from, the License Manager server. # This is an encoded string that can be obtained from either the license manager ui or the logs of the license # manager server. # #license_manager_dry_run_token = "" # Choose LIME method to be used for creation of surrogate models. #mli_lime_method = "k-LIME" # Choose whether surrogate models should be built for original or transformed features. #mli_use_raw_features = true # Choose whether time series based surrogate models should be built for original features. #mli_ts_use_raw_features = false # Choose whether to run all explainers on the sampled dataset. #mli_sample = true # Set maximum number of features for which to build Surrogate Partial Dependence Plot. Use -1 to calculate Surrogate Partial Dependence Plot for all features. #mli_vars_to_pdp = 10 # Set the number of cross-validation folds for surrogate models. #mli_nfolds = 3 # Set the number of columns to bin in case of quantile binning. #mli_qbin_count = 0 # Number of threads for H2O instance for use by MLI. #h2o_mli_nthreads = 8 # Use this option to disable MOJO scoring pipeline. Scoring pipeline is chosen automatically (from MOJO and Python pipelines) by default. In case of certain models MOJO vs. Python choice can impact pipeline performance and robustness. #mli_enable_mojo_scorer = true # When number of rows are above this limit sample for MLI for scoring UI data. #mli_sample_above_for_scoring = 1000000 # When number of rows are above this limit sample for MLI for training surrogate models. #mli_sample_above_for_training = 100000 # The sample size, number of rows, used for MLI surrogate models. #mli_sample_size = 100000 # Number of bins for quantile binning. #mli_num_quantiles = 10 # Number of trees for Random Forest surrogate model. #mli_drf_num_trees = 100 # Speed up predictions with a fast approximation (can reduce the number of trees or cross-validation folds). #mli_fast_approx = true # Maximum number of interpreters status cache entries. #mli_interpreter_status_cache_size = 1000 # Max depth for Random Forest surrogate model. #mli_drf_max_depth = 20 # not only sample training, but also sample scoring. #mli_sample_training = true # Regularization strength for k-LIME GLM's. #klime_lambda = "[1e-06, 1e-08]" # Regularization distribution between L1 and L2 for k-LIME GLM's. #klime_alpha = 0.0 # Max cardinality for numeric variables in surrogate models to be considered categorical. #mli_max_numeric_enum_cardinality = 25 # Maximum number of features allowed for k-LIME k-means clustering. #mli_max_number_cluster_vars = 6 # Use all columns for k-LIME k-means clustering (this will override mli_max_number_cluster_vars if set to True). #use_all_columns_klime_kmeans = false # Strict version check for MLI #mli_strict_version_check = true # MLI cloud name #mli_cloud_name = "" # Compute original model ICE using per feature's bin predictions (true) or use "one frame" strategy (false). #mli_ice_per_bin_strategy = false # By default DIA will run for categorical columns with cardinality <= mli_dia_default_max_cardinality. #mli_dia_default_max_cardinality = 10 # By default DIA will run for categorical columns with cardinality >= mli_dia_default_min_cardinality. #mli_dia_default_min_cardinality = 2 # When number of rows are above this limit, then sample for MLI transformed Shapley calculation. #mli_shapley_sample_size = 100000 # Enable MLI keeper which ensures efficient use of filesystem/memory/DB by MLI. #enable_mli_keeper = true # Enable MLI Sensitivity Analysis #enable_mli_sa = true # Enable priority queues based explainers execution. Priority queues restrict available system resources and prevent system over-utilization. Interpretation execution time might be (significantly) slower. #enable_mli_priority_queues = true # Explainers are run sequentially by default. This option can be used to run all explainers in parallel which can - depending on hardware strength and the number of explainers - decrease interpretation duration. Consider explainer dependencies, random explainers order and hardware over utilization. #mli_sequential_task_execution = true # When number of rows are above this limit, then sample for Disparate Impact Analysis. #mli_dia_sample_size = 100000 # When number of rows are above this limit, then sample for Partial Dependence Plot. #mli_pd_sample_size = 25000 # Use dynamic switching between Partial Dependence Plot numeric and categorical binning and UI chart selection in case of features which were used both as numeric and categorical by experiment. #mli_pd_numcat_num_chart = true # If 'mli_pd_numcat_num_chart' is enabled, then use numeric binning and chart if feature unique values count is bigger than threshold, else use categorical binning and chart. #mli_pd_numcat_threshold = 11 # In New Interpretation screen show only datasets which can be used to explain a selected model. This can slow down the server significantly. #new_mli_list_only_explainable_datasets = false # Enable async/await-based non-blocking MLI API #enable_mli_async_api = true # Enable main chart aggregator in Sensitivity Analysis #enable_mli_sa_main_chart_aggregator = true # When to sample for Sensitivity Analysis (number of rows after sampling). #mli_sa_sampling_limit = 500000 # Run main chart aggregator in Sensitivity Analysis when the number of dataset instances is bigger than given limit. #mli_sa_main_chart_aggregator_limit = 1000 # Use predict_safe() (true) or predict_base() (false) in MLI (PD, ICE, SA, ...). #mli_predict_safe = false # Number of max retries should the surrogate model fail to build. #mli_max_surrogate_retries = 5 # Allow use of symlinks (instead of file copy) by MLI explainer procedures. #enable_mli_symlinks = true # Fraction of memory to allocate for h2o MLI jar #h2o_mli_fraction_memory = 0.45 # Add TOML string to Driverless AI server config.toml configuration file. #mli_custom = "" # To exclude e.g. Sensitivity Analysis explainer use: excluded_mli_explainers=['h2oaicore.mli.byor.recipes.sa_explainer.SaExplainer']. #excluded_mli_explainers = "[]" # Enable RPC API performance monitor. #enable_ws_perfmon = false # Number of parallel workers when scoring using MOJO in Kernel Explainer. #mli_kernel_explainer_workers = 4 # Use Kernel Explainer to obtain Shapley values for original features. #mli_run_kernel_explainer = false # Sample input dataset for Kernel Explainer. #mli_kernel_explainer_sample = true # Sample size for input dataset passed to Kernel Explainer. #mli_kernel_explainer_sample_size = 1000 # 'auto' or int. Number of times to re-evaluate the model when explaining each prediction. More samples lead to lower variance estimates of the SHAP values. The 'auto' setting uses nsamples = 2 * X.shape[1] + 2048. This setting is disabled by default and DAI determines the right number internally. #mli_kernel_explainer_nsamples = "auto" # 'num_features(int)', 'auto' (default for now, but deprecated), 'aic', 'bic', or float. The l1 regularization to use for feature selection (the estimation procedure is based on a debiased lasso). The 'auto' option currently uses aic when less that 20% of the possible sample space is enumerated, otherwise it uses no regularization. THE BEHAVIOR OF 'auto' WILL CHANGE in a future version to be based on 'num_features' instead of AIC. The aic and bic options use the AIC and BIC rules for regularization. Using 'num_features(int)' selects a fix number of top features. Passing a float directly sets the alpha parameter of the sklearn.linear_model.Lasso model used for feature selection. #mli_kernel_explainer_l1_reg = "aic" # Max runtime for Kernel Explainer in seconds. Default is 900, which equates to 15 minutes. Setting this parameter to -1 means to honor the Kernel Shapley sample size provided regardless of max runtime. #mli_kernel_explainer_max_runtime = 900 # Tokenizer used to extract tokens from text columns for MLI. #mli_nlp_tokenizer = "tfidf" # Number of tokens used for MLI NLP explanations. -1 means all. #mli_nlp_top_n = 20 # Maximum number of records used by MLI NLP explainers #mli_nlp_sample_limit = 10000 # Minimum number of documents in which token has to appear. Integer mean absolute count, float means percentage. #mli_nlp_min_df = 3 # Maximum number of documents in which token has to appear. Integer mean absolute count, float means percentage. #mli_nlp_max_df = 0.9 # The minimum value in the ngram range. The tokenizer will generate all possible tokens in the (mli_nlp_min_ngram, mli_nlp_max_ngram) range. #mli_nlp_min_ngram = 1 # The maximum value in the ngram range. The tokenizer will generate all possible tokens in the (mli_nlp_min_ngram, mli_nlp_max_ngram) range. #mli_nlp_max_ngram = 1 # Mode used to choose N tokens for MLI NLP. # "top" chooses N top tokens. # "bottom" chooses N bottom tokens. # "top-bottom" chooses math.floor(N/2) top and math.ceil(N/2) bottom tokens. # "linspace" chooses N evenly spaced out tokens. #mli_nlp_min_token_mode = "top" # The number of top tokens to be used as features when building token based feature importance. #mli_nlp_tokenizer_max_features = -1 # The number of top tokens to be used as features when computing text LOCO. #mli_nlp_loco_max_features = -1 # The tokenizer method to use when tokenizing a dataset for surrogate models. Can either choose 'TF-IDF' or 'Linear Model + TF-IDF', which first runs TF-IDF to get tokens and then fits a linear model between the tokens and the target to get importances of tokens, which are based on coefficients of the linear model. Default is 'Linear Model + TF-IDF'. Only applies to NLP models. #mli_nlp_surrogate_tokenizer = "Linear Model + TF-IDF" # The number of top tokens to be used as features when building surrogate models. Only applies to NLP models. #mli_nlp_surrogate_tokens = 100 # Use stop words for MLI NLP. #mli_nlp_use_stop_words = true # List of words to filter out before generation of text tokens, which are passed to MLI NLP LOCO and surrogate models (if enabled). Default is 'english'. Pass in custom stop-words as a list, e.g., ['great', 'good']. #mli_nlp_stop_words = "english" # Append passed in list of custom stop words to default 'english' stop words. #mli_nlp_append_to_english_stop_words = false # Enable MLI for image experiments. #mli_image_enable = true # Set dask CUDA/RAPIDS cluster settings for single node workers. # Additional environment variables can be set, see: https://dask-cuda.readthedocs.io/en/latest/ucx.html#dask-scheduler # e.g. for ucx use: {} dict version of: dict(n_workers=None, threads_per_worker=1, processes=True, memory_limit='auto', device_memory_limit=None, CUDA_VISIBLE_DEVICES=None, data=None, local_directory=None, protocol='ucx', enable_tcp_over_ucx=True, enable_infiniband=False, enable_nvlink=False, enable_rdmacm=False, ucx_net_devices='auto', rmm_pool_size='1GB') # WARNING: Do not add arguments like {'n_workers': 1, 'processes': True, 'threads_per_worker': 1} this will lead to hangs, cuda cluster handles this itself. # #dask_cuda_cluster_kwargs = "{'scheduler_port': 0, 'dashboard_address': ':0', 'protocol': 'tcp'}" # Set dask cluster settings for single node workers. # #dask_cluster_kwargs = "{'n_workers': 1, 'processes': True, 'threads_per_worker': 1, 'scheduler_port': 0, 'dashboard_address': ':0', 'protocol': 'tcp'}" # Whether to enable dask scheduler DAI server node and dask workers on DAI worker nodes. # #enable_dask_cluster = true # Whether to start dask workers on this multinode worker. # #start_dask_worker = true # Set dask scheduler env. # See https://docs.dask.org/en/latest/setup/cli.html # #dask_scheduler_env = "{}" # Set dask scheduler env. # See https://docs.dask.org/en/latest/setup/cli.html # #dask_cuda_scheduler_env = "{}" # Set dask scheduler options. # See https://docs.dask.org/en/latest/setup/cli.html # #dask_scheduler_options = "" # Set dask cuda scheduler options. # See https://docs.dask.org/en/latest/setup/cli.html # #dask_cuda_scheduler_options = "" # Set dask worker env. # See https://docs.dask.org/en/latest/setup/cli.html # #dask_worker_env = "{'NCCL_P2P_DISABLE': '1', 'NCCL_DEBUG': 'WARN'}" # Set dask worker options. # See https://docs.dask.org/en/latest/setup/cli.html # #dask_worker_options = "--memory-limit 0.95" # Set dask cuda worker options. # Similar options as dask_cuda_cluster_kwargs. # See https://dask-cuda.readthedocs.io/en/latest/ucx.html#launching-scheduler-workers-and-clients-separately # "--rmm-pool-size 1GB" can be set to give 1GB to RMM for more efficient rapids # #dask_cuda_worker_options = "--memory-limit 0.95" # Set dask cuda worker env. # See: https://dask-cuda.readthedocs.io/en/latest/ucx.html#launching-scheduler-workers-and-clients-separately # https://ucx-py.readthedocs.io/en/latest/dask.html # #dask_cuda_worker_env = "{}" # See https://docs.dask.org/en/latest/setup/cli.html # e.g. ucx is optimal, while tcp is most reliable # #dask_protocol = "tcp" # See https://docs.dask.org/en/latest/setup/cli.html # #dask_server_port = 8786 # See https://docs.dask.org/en/latest/setup/cli.html # #dask_dashboard_port = 8787 # See https://docs.dask.org/en/latest/setup/cli.html # e.g. ucx is optimal, while tcp is most reliable # #dask_cuda_protocol = "tcp" # See https://docs.dask.org/en/latest/setup/cli.html # port + 1 is used for dask dashboard # #dask_cuda_server_port = 8790 # See https://docs.dask.org/en/latest/setup/cli.html # #dask_cuda_dashboard_port = 8791 # If empty string, auto-detect IP capable of reaching network. # Required to be set if using worker_mode=multinode. # #dask_server_ip = "" # Number of processses per dask (not cuda-GPU) worker. # If -1, uses dask default of cpu count + 1 + nprocs. # If -2, uses DAI default of total number of physical cores. Recommended for heavy feature engineering. # If 1, assumes tasks are mostly multi-threaded and can use entire node per task. Recommended for heavy multinode model training. # Only applicable to dask (not dask_cuda) workers # #dask_worker_nprocs = 1 # Number of threads per process for dask workers #dask_worker_nthreads = 1 # Number of threads per process for dask_cuda workers # If -2, uses DAI default of physical cores per GPU, # since must have 1 worker/GPU only. # #dask_cuda_worker_nthreads = -2 # See https://github.com/dask/dask-lightgbm # #lightgbm_listen_port = 12400 # Whether to enable jupyter server #enable_jupyter_server = false # Port for jupyter server #jupyter_server_port = 8889 # Whether to enable jupyter server browser #enable_jupyter_server_browser = false # Whether to root access to jupyter server browser #enable_jupyter_server_browser_root = false # When set to true, CPU executors will strictly run just CPU tasks. #multinode_enable_strict_queue_policy = false # Controls whether CPU tasks can run on GPU machines. #multinode_enable_cpu_tasks_on_gpu_machines = true # Storage medium to be used to exchange data between main server and remote worker nodes. #multinode_storage_medium = "minio" # How the long running tasks are scheduled. # multiprocessing: forks the current process immediately. # singlenode: shares the task through redis and needs a worker running. # multinode: same as singlenode and also shares the data through minio # and allows worker to run on the different machine. # #worker_mode = "singlenode" # Redis settings #redis_ip = "127.0.0.1" # Redis settings #redis_port = 6379 # Redis database. Each DAI instance running on the redis server should have unique integer. #redis_db = 0 # Redis password. Will be randomly generated main server startup, and by default it will show up in config file uncommented.If you are running more than one DriverlessAI instance per system, make sure each and every instance is connected to its own redis queue. #main_server_redis_password = "PlWUjvEJSiWu9j0aopOyL5KwqnrKtyWVoZHunqxr" # If set to true, the config will get encrypted before it gets saved into the Redis database. #redis_encrypt_config = false # The port that Minio will listen on, this only takes effect if the current system is a multinode main server. #local_minio_port = 9001 # Location of main server's minio server. #main_server_minio_address = "127.0.0.1:9001" # Access key of main server's minio server. #main_server_minio_access_key_id = "GMCSE2K2T3RV6YEHJUYW" # Secret access key of main server's minio server. #main_server_minio_secret_access_key = "JFxmXvE/W1AaqwgyPxAUFsJZRnDWUaeQciZJUe9H" # Name of minio bucket used for file synchronization. #main_server_minio_bucket = "h2oai" # S3 global access key. #main_server_s3_access_key_id = "access_key" # S3 global secret access key #main_server_s3_secret_access_key = "secret_access_key" # S3 bucket. #main_server_s3_bucket = "h2oai-multinode-tests" # Maximum number of local tasks processed at once, limited to no more than total number of physical (not virtual) cores divided by two (minimum of 1). #worker_local_processors = 32 # A concurrency limit for the 3 priority queues, only enabled when worker_remote_processors is greater than 0. #worker_priority_queues_processors = 4 # A timeout before which a scheduled task is bumped up in priority #worker_priority_queues_time_check = 30 # Maximum number of remote tasks processed at once, if value is set to -1 the system will automatically pick a reasonable limit depending on the number of available virtual CPU cores. #worker_remote_processors = -1 # If worker_remote_processors >= 3, factor by which each task reduces threads, used by various packages like datatable, lightgbm, xgboost, etc. #worker_remote_processors_max_threads_reduction_factor = 0.7 # Temporary file system location for multinode data transfer. #multinode_tmpfs = "" # How often the server should extract results from redis queue in milliseconds. #redis_result_queue_polling_interval = 100 # Sleep time for worker loop. #worker_sleep = 0.1 # For how many seconds worker should wait for main server minio bucket before it fails #main_server_minio_bucket_ping_timeout = 180 # How long the worker should wait on redis db initialization in seconds. #worker_start_timeout = 30 #worker_no_main_server_wait_time = 1800 #worker_no_main_server_wait_time_with_hard_assert = 30 # For how many seconds the worker shouldn't respond to be marked unhealthy. #worker_healthy_response_period = 300 # Exposes the DriverlessAI base version when enabled. #expose_server_version = true # https settings # You can make a self-signed certificate for testing with the following commands: # sudo openssl req -x509 -newkey rsa:4096 -keyout private_key.pem -out cert.pem -days 3650 -nodes -subj '/O=Driverless AI' # sudo chown dai:dai cert.pem private_key.pem # sudo chmod 600 cert.pem private_key.pem # sudo mv cert.pem private_key.pem /etc/dai #enable_https = false # https settings # You can make a self-signed certificate for testing with the following commands: # sudo openssl req -x509 -newkey rsa:4096 -keyout private_key.pem -out cert.pem -days 3650 -nodes -subj '/O=Driverless AI' # sudo chown dai:dai cert.pem private_key.pem # sudo chmod 600 cert.pem private_key.pem # sudo mv cert.pem private_key.pem /etc/dai #ssl_key_file = "/etc/dai/private_key.pem" # https settings # You can make a self-signed certificate for testing with the following commands: # sudo openssl req -x509 -newkey rsa:4096 -keyout private_key.pem -out cert.pem -days 3650 -nodes -subj '/O=Driverless AI' # sudo chown dai:dai cert.pem private_key.pem # sudo chmod 600 cert.pem private_key.pem # sudo mv cert.pem private_key.pem /etc/dai #ssl_crt_file = "/etc/dai/cert.pem" # SSL TLS #ssl_no_sslv2 = true # SSL TLS #ssl_no_sslv3 = true # SSL TLS #ssl_no_tlsv1 = true # SSL TLS #ssl_no_tlsv1_1 = true # SSL TLS #ssl_no_tlsv1_2 = false # SSL TLS #ssl_no_tlsv1_3 = false # https settings # Sets the client verification mode. # CERT_NONE: Client does not need to provide the certificate and if it does any # verification errors are ignored. # CERT_OPTIONAL: Client does not need to provide the certificate and if it does # certificate is verified against set up CA chains. # CERT_REQUIRED: Client needs to provide a certificate and certificate is # verified. # You'll need to set 'ssl_client_key_file' and 'ssl_client_crt_file' # When this mode is selected for Driverless to be able to verify # it's own callback requests. # #ssl_client_verify_mode = "CERT_NONE" # https settings # Path to the Certification Authority certificate file. This certificate will be # used when to verify client certificate when client authentication is turned on. # If this is not set, clients are verified using default system certificates. # #ssl_ca_file = "" # https settings # path to the private key that Driverless will use to authenticate itself when # CERT_REQUIRED mode is set. # #ssl_client_key_file = "" # https settings # path to the client certificate that Driverless will use to authenticate itself # when CERT_REQUIRED mode is set. # #ssl_client_crt_file = "" # If enabled, webserver will serve xsrf cookies and verify their validity upon every POST request #enable_xsrf_protection = true #enable_secure_cookies = false # When enabled each authenticated access will be verified comparing IP address of initiator of session and current request IP #verify_session_ip = false # Enables automatic detection for forbidden/dangerous constructs in custom recipe #custom_recipe_security_analysis_enabled = false # List of modules that can be imported in custom recipes. Default empty list means all modules are allowed except for banlisted ones #custom_recipe_import_allowlist = "[]" # List of modules that cannot be imported in custom recipes #custom_recipe_import_banlist = "['shlex', 'plumbum', 'pexpect', 'envoy', 'commands', 'fabric', 'subprocess', 'os.system', 'system']" # Regex pattern list of calls which are allowed in custom recipes. # Empty list means everything (except for banlist) is allowed. # E.g. if only os.path.* is in allowlist, custom recipe can only call methods # from os.path module and the built in ones # #custom_recipe_method_call_allowlist = "[]" # Regex pattern list of calls which need to be rejected in custom recipes. # E.g. if os.system in banlist, custom recipe cannot call os.system(). # If socket.* in banlist, recipe cannot call any method of socket module such as # socket.socket() or any socket.a.b.c() # #custom_recipe_method_call_banlist = "['os\\.system', 'socket\\..*', 'subprocess.*', 'os.spawn.*']" # List of regex patterns representing dangerous sequences/constructs # which could be harmful to whole system and should be banned from code # #custom_recipe_dangerous_patterns = "['rm -rf', 'rm -fr']" # If enabled, user can log in from 2 browsers (scripts) at the same time #allow_concurrent_sessions = true # Extra HTTP headers. #extra_http_headers = "{}" # By default DriverlessAI issues cookies with HTTPOnly and Secure attributes (morsels) enabled. In addition to that, SameSite attribute is set to 'Lax', as it's a default in modern browsers. The config overrides the default key/value (morsels). #http_cookie_attributes = "{'samesite': 'Lax'}" # Enable column imputation #enable_imputation = false # Adds advanced settings panel to experiment setup, which allows creating # custom features and more. # #enable_advanced_features_experiment = false # Address of the H2O Storage endpoint. Keep empty to use the local storage only. #h2o_storage_address = "" # Whether to use remote projects stored in H2O Storage instead of local projects. #h2o_storage_projects_enabled = false # Whether the channel to the storage should be encrypted. #h2o_storage_tls_enabled = true # Path to the certification authority certificate that H2O Storage server identity will be checked against. #h2o_storage_tls_ca_path = "" # Path to the client certificate to authenticate with H2O Storage server #h2o_storage_tls_cert_path = "" # Path to the client key to authenticate with H2O Storage server #h2o_storage_tls_key_path = "" # UUID of a Storage project to use instead of the remote HOME folder. #h2o_storage_internal_default_project_id = "" # Deadline for RPC calls with H2O Storage in seconds. Sets maximum number of seconds that Driverless waits for RPC call to complete before it cancels it. #h2o_storage_rpc_deadline_seconds = 60 # Deadline for RPC bytestrteam calls with H2O Storage in seconds. Sets maximum number of seconds that Driverless waits for RPC call to complete before it cancels it. This value is used for uploading and downloading artifacts. #h2o_storage_rpc_bytestream_deadline_seconds = 7200 # Storage client manages it's own access tokens derived from the refresh token received on the user login. When this option is set access token with the scopes defined here is requested. (space separated list) #h2o_storage_oauth2_scopes = "" # Maximum size of message size of RPC request in bytes. Requests larger than this limit will fail. #h2o_storage_message_size_limit = 1048576000 # If the h2o_mlops_ui_url is provided alongside the enable_storage, DAI is able to redirect user to the MLOps app upon clicking the Deploy button. #h2o_mlops_ui_url = "" # Keystore file that contains secure config.toml items like passwords, secret keys etc. Keystore is managed by h2oai.keystore tool. #keystore_file = "" # Verbosity of logging # 0: quiet (CRITICAL, ERROR, WARNING) # 1: default (CRITICAL, ERROR, WARNING, INFO, DATA) # 2: verbose (CRITICAL, ERROR, WARNING, INFO, DATA, DEBUG) # Affects server and all experiments #log_level = 1 # Whether to collect relevant server logs (h2oai_server.log, dai.log from systemctl or docker, and h2o log) # Useful for when sending logs to H2O.ai #collect_server_logs_in_experiment_logs = false # Whether to have all user content isolated into a directory for each user. # If set to False, all users content is common to single directory, # recipes are shared, and brain folder for restart/refit is shared. # If set to True, each user has separate folder for all user tasks, # recipes are isolated to each user, and brain folder for restart/refit is # only for the specific user. # Migration from False to True or back to False is allowed for # all experiment content accessible by GUI or python client, # all recipes, and starting experiment with same settings, restart, or refit. # However, if switch to per-user mode, the common brain folder is no longer used. # #per_user_directories = true # List of file names to ignore during dataset import. Any files with names listed above will be skipped when # DAI creates a dataset. Example, directory contains 3 files: [data_1.csv, data_2.csv, _SUCCESS] # DAI will only attempt to create a dataset using files data_1.csv and data_2.csv, and _SUCCESS file will be ignored. # Default is to ignore _SUCCESS files which are commonly created in exporting data from Hadoop # #data_import_ignore_file_names = "['_SUCCESS']" # For data import from a directory (multiple files), allow column types to differ and perform upcast during import. #data_import_upcast_multi_file = false # If set to true, will explode columns with list data type when importing parquet files. #data_import_explode_list_type_columns_in_parquet = false # List of file types that Driverless AI should attempt to import data as IF no file extension exists in the file name # If no file extension is provided, Driverless AI will attempt to import the data starting with first type # in the defined list. Default ["parquet", "orc"] # Example: 'test.csv' (file extension exists) vs 'test' (file extension DOES NOT exist) # NOTE: see supported_file_types configuration option for more details on supported file types # #files_without_extensions_expected_types = "['parquet', 'orc']" # do_not_log_list : add configurations that you do not wish to be recorded in logs here.They will still be stored in experiment information so child experiments can behave consistently. #do_not_log_list = "['cols_to_drop', 'cols_to_drop_sanitized', 'cols_to_group_by', 'cols_to_group_by_sanitized', 'cols_to_force_in', 'cols_to_force_in_sanitized', 'do_not_log_list', 'do_not_store_list', 'pytorch_nlp_pretrained_s3_access_key_id', 'pytorch_nlp_pretrained_s3_secret_access_key', 'auth_openid_end_session_endpoint_url']" # do_not_store_list : add configurations that you do not wish to be stored at all here.Will not be remembered across experiments, so not applicable to data science related itemsthat could be controlled by a user. These items are automatically not logged. #do_not_store_list = "['artifacts_git_password', 'auth_jwt_secret', 'auth_openid_client_id', 'auth_openid_client_secret', 'auth_openid_userinfo_auth_key', 'auth_openid_userinfo_auth_value', 'auth_openid_userinfo_username_key', 'auth_tls_ldap_bind_password', 'aws_access_key_id', 'aws_secret_access_key', 'azure_blob_account_key', 'azure_blob_account_name', 'azure_connection_string', 'deployment_aws_access_key_id', 'deployment_aws_secret_access_key', 'gcs_path_to_service_account_json', 'kaggle_key', 'kaggle_username', 'kdb_password', 'kdb_user', 'ldap_bind_password', 'ldap_search_password', 'local_htpasswd_file', 'main_server_minio_access_key_id', 'main_server_minio_secret_access_key', 'main_server_redis_password', 'minio_access_key_id', 'minio_endpoint_url', 'minio_secret_access_key', 'main_server_s3_access_key_id', 'main_server_s3_secret_access_key', 'snowflake_account', 'snowflake_password', 'snowflake_url', 'snowflake_user', 'custom_recipe_security_analysis_enabled', 'custom_recipe_import_allowlist', 'custom_recipe_import_banlist', 'custom_recipe_method_call_allowlist', 'custom_recipe_method_call_banlist', 'custom_recipe_dangerous_patterns', 'azure_ad_client_secret', 'azure_blob_keycloak_aad_client_secret', 'artifacts_azure_blob_account_name', 'artifacts_azure_blob_account_key', 'artifacts_azure_connection_string', 'tensorflow_nlp_pretrained_s3_access_key_id', 'tensorflow_nlp_pretrained_s3_secret_access_key']" # Memory limit in bytes for datatable to use during parsing of CSV files. -1 for unlimited. 0 for automatic. >0 for constraint. #datatable_parse_max_memory_bytes = -1 # Delimiter/Separator to use when parsing tabular text files like CSV. Automatic if empty. Must be provided at system start. #datatable_separator = "" # Whether to enable ping of system status during DAI data ingestion. #ping_load_data_file = false # Period between checking DAI status. Should be small enough to avoid slowing parent who stops ping process. #ping_sleep_period = 0.5 # Precision of how data is stored # 'datatable' keeps original datatable storage types (i.e. bool, int, float32, float64) (experimental) # 'float32' best for speed, 'float64' best for accuracy or very large input values, "datatable" best for memory # 'float32' allows numbers up to about +-3E38 with relative error of about 1E-7 # 'float64' allows numbers up to about +-1E308 with relative error of about 1E-16 # Some calculations, like the GLM standardization, can only handle up to sqrt() of these maximums for data values, # So GLM with 32-bit precision can only handle up to about a value of 1E19 before standardization generates inf values. # If you see "Best individual has invalid score" you may require higher precision. #data_precision = "float32" # Precision of most data transformers (same options and notes as data_precision). # Useful for higher precision in transformers with numerous operations that can accumulate error. # Also useful if want faster performance for transformers but otherwise want data stored in high precision. #transformer_precision = "float32" # Whether to change ulimit soft limits up to hard limits (for DAI server app, which is not a generic user app). # Prevents resource limit problems in some cases. # Restricted to no more than limit_nofile and limit_nproc for those resources. #ulimit_up_to_hard_limit = true #disable_core_files = false # number of file limit # Below should be consistent with start-dai.sh #limit_nofile = 131071 # number of threads limit # Below should be consistent with start-dai.sh #limit_nproc = 16384 # ' # Whether to compute training, validation, and test correlation matrix (table and heatmap pdf) and save to disk # alpha: currently single threaded and slow for many columns #compute_correlation = false # Whether to dump to disk a correlation heatmap #produce_correlation_heatmap = false # Value to report high correlation between original features #high_correlation_value_to_report = 0.95 # If True, experiments aborted by server restart will automatically restart and continue upon user login #restart_experiments_after_shutdown = false # Include byte order mark (BOM) when writing CSV files. Required to support UTF-8 encoding in Excel. #datatable_bom_csv = false #return_quickly_autodl_testing = false #return_quickly_autodl_testing2 = false #return_before_final_model = false # Whether to check if config.toml keys are valid and fail if not valid #check_invalid_config_toml_keys = true #predict_safe_trials = 2 #fit_safe_trials = 2 #enable_preview_time_estimate = true #enable_preview_mojo_size_estimate = true #enable_preview_time_estimate_rough = false #allow_no_pid_host = true #main_logger_with_experiment_ids = true # Reduce memory usage during final ensemble feature engineering (1 uses most memory, larger values use less memory) #final_munging_memory_reduction_factor = 2 # How much more memory a typical transformer needs than the input data. # Can be increased if, e.g., final model munging uses too much memory due to parallel operations. #munging_memory_overhead_factor = 5 #per_transformer_segfault_protection_ga = false #per_transformer_segfault_protection_final = false # How often to check resources (disk, memory, cpu) to see if need to stall submission. #submit_resource_wait_period = 10 # Stall submission of subprocesses if system CPU usage is higher than this threshold in percent (set to 100 to disable). A reasonable number is 90.0 if activated #stall_subprocess_submission_cpu_threshold_pct = 100 # Restrict/Stall submission of subprocesses if DAI fork count (across all experiments) per unit ulimit nproc soft limit is higher than this threshold in percent (set to -1 to disable, 0 for minimal forking. A reasonable number is 90.0 if activated #stall_subprocess_submission_dai_fork_threshold_pct = -1.0 # Restrict/Stall submission of subprocesses if experiment fork count (across all experiments) per unit ulimit nproc soft limit is higher than this threshold in percent (set to -1 to disable, 0 for minimal forking). A reasonable number is 90.0 if activated. For small data leads to overhead of about 0.1s per task submitted due to checks, so for scoring can slow things down for tests. #stall_subprocess_submission_experiment_fork_threshold_pct = -1.0 # Whether to restrict pool workers even if not used, by reducing number of pool workers available. Good if really huge number of experiments, but otherwise, best to have all pool workers ready and only stall submission of tasks so can be dynamic to multi-experiment environment #restrict_initpool_by_memory = true # Whether to terminate experiments if the system memory available falls below memory_limit_gb_terminate #terminate_experiment_if_memory_low = false # Memory in GB beyond which will terminate experiment if terminate_experiment_if_memory_low=true. #memory_limit_gb_terminate = 5 # Path to use for scoring directory path relative to run path #scoring_data_directory = "tmp" #num_models_for_resume_graph = 1000 # Internal helper to allow memory of if changed exclusive mode #last_exclusive_mode = "" #mojo_acceptance_test_errors_fatal = true #mojo_acceptance_test_errors_shap_fatal = true #mojo_acceptance_test_orig_shap = true # Which MOJO runtimes should be tested as part of the mini acceptance tests #mojo_acceptance_test_mojo_types = "['C++', 'Java']" # Create MOJO for feature engineering pipeline only (no predictions) #make_mojo_scoring_pipeline_for_features_only = false # Replaces target encoding features by their input columns. Instead of CVTE_Age:Income:Zip, this will create Age:Income:Zip. Only when make_mojo_scoring_pipeline_for_features_only is enabled. #mojo_replace_target_encoding_with_grouped_input_cols = false # If set to true, will make sure only current instance can access its database #enable_single_instance_db_access = true # Deprecated - maps to enable_pytorch_nlp_transformer and enable_pytorch_nlp_model in 1.10.2+ #enable_pytorch_nlp = "auto" # How long to wait per GPU for tensorflow/torch to run during system checks. #check_timeout_per_gpu = 20 # Whether to fail start-up if cannot successfully run GPU checks #gpu_exit_if_fails = true #how_started = "" #wizard_state = "" # Enable time series lag-based recipe with lag transformers. If disabled, the same train-test gap and periods are used, but no lag transformers are enabled. If disabled, the set of feature transformations is quite limited without lag transformers, so consider setting enable_time_unaware_transformers to true in order to treat the problem as more like an IID type problem. #time_series_recipe = true # Whether causal splits are used when time_series_recipe is false orwhether to use same train-gap-test splits when lag transformers are disabled (default behavior).For train-test gap, period, etc. to be used when lag-based recipe is disabled, this must be false. #time_series_causal_split_recipe = false # Whether to use lag transformers when using causal-split for validation # (as occurs when not using time-based lag recipe). # If no time groups columns, lag transformers will still use time-column as sole time group column. # #use_lags_if_causal_recipe = false # 'diverse': explore a diverse set of models built using various expert settings. Note that it's possible to rerun another such diverse leaderboard on top of the best-performing model(s), which will effectively help you compose these expert settings. # 'sliding_window': If the forecast horizon is N periods, create a separate model for each of the (gap, horizon) pairs of (0,n), (n,n), (2*n,n), ..., (2*N-1, n) in units of time periods. # The number of periods to predict per model n is controlled by the expert setting 'time_series_leaderboard_periods_per_model', which defaults to 1. #time_series_leaderboard_mode = "diverse" # Fine-control to limit the number of models built in the 'sliding_window' mode. Larger values lead to fewer models. #time_series_leaderboard_periods_per_model = 1 # Whether to create larger validation splits that are not bound to the length of the forecast horizon. #time_series_merge_splits = true # Maximum ratio of training data samples used for validation across splits when larger validation splits are created. #merge_splits_max_valid_ratio = -1.0 # Whether to keep a fixed-size train timespan across time-based splits. # That leads to roughly the same amount of train samples in every split. # #fixed_size_train_timespan = false # Provide date or datetime timestamps (in same format as the time column) for custom training and validation splits like this: "tr_start1, tr_end1, va_start1, va_end1, ..., tr_startN, tr_endN, va_startN, va_endN" #time_series_validation_fold_split_datetime_boundaries = "" # Set fixed number of time-based splits for internal model validation (actual number of splits allowed can be less and is determined at experiment run-time). #time_series_validation_splits = -1 # Maximum overlap between two time-based splits. Higher values increase the amount of possible splits. #time_series_splits_max_overlap = 0.5 # Earliest allowed datetime (in %Y%m%d format) for which to allow automatic conversion of integers to a time column during parsing. For example, 2010 or 201004 or 20100402 or 201004022312 can be converted to a valid date/datetime, but 1000 or 100004 or 10000402 or 10004022313 can not, and neither can 201000 or 20100500 etc. #min_ymd_timestamp = 19000101 # Latest allowed datetime (in %Y%m%d format) for which to allow automatic conversion of integers to a time column during parsing. For example, 2010 or 201004 or 20100402 can be converted to a valid date/datetime, but 3000 or 300004 or 30000402 or 30004022313 can not, and neither can 201000 or 20100500 etc. #max_ymd_timestamp = 21000101 # maximum number of data samples (randomly selected rows) for date/datetime format detection #max_rows_datetime_format_detection = 100000 # Manually disables certain datetime formats during data ingest and experiments. # For example, ['%y'] will avoid parsing columns that contain '00', '01', '02' string values as a date column. # #disallowed_datetime_formats = "['%y']" # Whether to use datetime cache #use_datetime_cache = true # Minimum amount of rows required to utilize datetime cache #datetime_cache_min_rows = 10000 # Automatically generate is-holiday features from date columns #holiday_features = true #holiday_country = "" # List of countries for which to look up holiday calendar and to generate is-Holiday features for #holiday_countries = "['UnitedStates', 'UnitedKingdom', 'EuropeanCentralBank', 'Germany', 'Mexico', 'Japan']" # Max. sample size for automatic determination of time series train/valid split properties, only if time column is selected #max_time_series_properties_sample_size = 250000 # Maximum number of lag sizes to use for lags-based time-series experiments. are sampled from if sample_lag_sizes==True, else all are taken (-1 == automatic) #max_lag_sizes = 30 # Minimum required autocorrelation threshold for a lag to be considered for feature engineering #min_lag_autocorrelation = 0.1 # How many samples of lag sizes to use for a single time group (single time series signal) #max_signal_lag_sizes = 100 # If enabled, sample from a set of possible lag sizes (e.g., lags=[1, 4, 8]) for each lag-based transformer, to no more than max_sampled_lag_sizes lags. Can help reduce overall model complexity and size. #sample_lag_sizes = false # If sample_lag_sizes is enabled, sample from a set of possible lag sizes (e.g., lags=[1, 4, 8]) for each lag-based transformer, to no more than max_sampled_lag_sizes lags. Can help reduce overall model complexity and size. Defaults to -1 (auto), in which case it's the same as the feature interaction depth controlled by max_feature_interaction_depth. #max_sampled_lag_sizes = -1 # Override lags to be used # e.g. [7, 14, 21] # this exact list # e.g. 21 # produce from 1 to 21 # e.g. 21:3 produce from 1 to 21 in step of 3 # e.g. 5-21 produce from 5 to 21 # e.g. 5-21:3 produce from 5 to 21 in step of 3 # #override_lag_sizes = "[]" # Override lags to be used for features that are not known ahead of time # e.g. [7, 14, 21] # this exact list # e.g. 21 # produce from 1 to 21 # e.g. 21:3 produce from 1 to 21 in step of 3 # e.g. 5-21 produce from 5 to 21 # e.g. 5-21:3 produce from 5 to 21 in step of 3 # #override_ufapt_lag_sizes = "[]" # Override lags to be used for features that are known ahead of time # e.g. [7, 14, 21] # this exact list # e.g. 21 # produce from 1 to 21 # e.g. 21:3 produce from 1 to 21 in step of 3 # e.g. 5-21 produce from 5 to 21 # e.g. 5-21:3 produce from 5 to 21 in step of 3 # #override_non_ufapt_lag_sizes = "[]" # Smallest considered lag size #min_lag_size = -1 # Whether to enable feature engineering based on selected time column, e.g. Date~weekday. #allow_time_column_as_feature = true # Whether to enable integer time column to be used as a numeric feature. # If using time series recipe, using time column (numeric time stamps) as input features can lead to model that # memorizes the actual time stamps instead of features that generalize to the future. # #allow_time_column_as_numeric_feature = false # Allowed date or date-time transformations. # Date transformers include: year, quarter, month, week, weekday, day, dayofyear, num. # Date transformers also include: hour, minute, second. # Features in DAI will show up as get_ + transformation name. # E.g. num is a direct numeric value representing the floating point value of time, # which can lead to over-fitting if used on IID problems. So this is turned off by default. #datetime_funcs = "['year', 'quarter', 'month', 'week', 'weekday', 'day', 'dayofyear', 'hour', 'minute', 'second']" # Whether to filter out date and date-time transformations that lead to unseen values in the future. # #filter_datetime_funcs = true # Whether to consider time groups columns (tgc) as standalone features. # Note that 'time_column' is treated separately via 'Allow to engineer features from time column'. # Use allowed_coltypes_for_tgc_as_features for control per feature type. # #allow_tgc_as_features = false # Which time groups columns (tgc) feature types to consider as standalone features, # if the corresponding flag "Consider time groups columns as standalone features" is set to true. # E.g. all column types would be ["numeric", "categorical", "ohe_categorical", "datetime", "date", "text"] # Note that 'time_column' is treated separately via 'Allow to engineer features from time column'. # Note that if lag-based time series recipe is disabled, then all tgc are allowed features. # #allowed_coltypes_for_tgc_as_features = "['numeric', 'categorical', 'ohe_categorical', 'datetime', 'date', 'text']" # Whether various transformers (clustering, truncated SVD) are enabled, # that otherwise would be disabled for time series due to # potential to overfit by leaking across time within the fit of each fold. # #enable_time_unaware_transformers = "auto" # Whether to group by all time groups columns for creating lag features, instead of sampling from them #tgc_only_use_all_groups = true # Whether to allow target encoding of time groups. This can be useful if there are many groups #tgc_allow_target_encoding = false # Enable creation of holdout predictions on training data # using moving windows (useful for MLI, but can be slow) #time_series_holdout_preds = true # Max number of splits used for creating final time-series model's holdout/backtesting predictions. With the default value '-1' the same amount of splits as during model validation will be used. Use 'time_series_validation_splits' to control amount of time-based splits used for model validation. #time_series_max_holdout_splits = -1 #single_model_vs_cv_score_reldiff = 0.05 #single_model_vs_cv_score_reldiff2 = 0.0 # Whether to blend ensembles in link space, so that can apply inverse link function to get predictions after blending. This allows to get Shapley values to sum up to final predictions, after applying inverse link function: preds = inverse_link( (blend(base learner predictions in link space ))) = inverse_link(sum(blend(base learner shapley values in link space))) = inverse_link(sum( ensemble shapley values in link space ))For binary classification, this is only supported if inverse_link = logistic = 1/(1+exp(-x))For multiclass classification, this is only supported if inverse_link = softmax = exp(x)/sum(exp(x))For regression, this behavior happens naturally if all base learners use the identity link function, otherwise not possible #blend_in_link_space = true # Whether to speed up time-series holdout predictions for back-testing on training data (used for MLI and metrics calculation). Can be slightly less accurate. #mli_ts_fast_approx = false # Whether to speed up Shapley values for time-series holdout predictions for back-testing on training data (used for MLI). Can be slightly less accurate. #mli_ts_fast_approx_contribs = true # Enable creation of Shapley values for holdout predictions on training data # using moving windows (useful for MLI, but can be slow), at the time of the experiment. If disabled, MLI will # generate Shapley values on demand. #mli_ts_holdout_contribs = true # Values of 5 or more can improve generalization by more aggressive dropping of least important features. Set to 1 to disable. #time_series_min_interpretability = 5 # Dropout mode for lag features in order to achieve an equal n.a.-ratio between train and validation/test. The independent mode performs a simple feature-wise dropout, whereas the dependent one takes lag-size dependencies per sample/row into account. #lags_dropout = "dependent" # Normalized probability of choosing to lag non-targets relative to targets (-1.0 = auto) #prob_lag_non_targets = -1.0 # Method to create rolling test set predictions, if the forecast horizon is shorter than the time span of the test set. One can choose between test time augmentation (TTA) and a successive refitting of the final pipeline. #rolling_test_method = "tta" #rolling_test_method_max_splits = 1000 # Apply TTA in one pass instead of using rolling windows for internal validation split predictions. Note: Setting this to 'False' leads to significantly longer runtimes. #fast_tta_internal = true # Apply TTA in one pass instead of using rolling windows for test set predictions. This only applies if the forecast horizon is shorter than the time span of the test set. Note: Setting this to 'False' leads to significantly longer runtimes. #fast_tta_test = true # Probability for new Lags/EWMA gene to use default lags (determined by frequency/gap/horizon, independent of data) (-1.0 = auto) #prob_default_lags = -1.0 # Unnormalized probability of choosing other lag time-series transformers based on interactions (-1.0 = auto) #prob_lagsinteraction = -1.0 # Unnormalized probability of choosing other lag time-series transformers based on aggregations (-1.0 = auto) #prob_lagsaggregates = -1.0 # Time series centering or detrending transformation. The free parameter(s) of the trend model are fitted and the trend is removed from the target signal, and the pipeline is fitted on the residuals. Predictions are made by adding back the trend. Note: Can be cascaded with 'Time series lag-based target transformation', but is mutually exclusive with regular target transformations. The robust centering or linear detrending variants use RANSAC to achieve a higher tolerance w.r.t. outliers. The Epidemic target transformer uses the SEIR model: https://en.wikipedia.org/wiki/Compartmental_models_in_epidemiology#The_SEIR_model #ts_target_trafo = "none" # Dictionary to control Epidemic SEIRD model for de-trending of target per time series group. # Note: The target column must correspond to I(t), the infected cases as a function of time. # For each training split and time series group, the SEIRD model is fitted to the target signal (by optimizing # the free parameters shown below for each time series group). # Then, the SEIRD model's value is subtracted from the training response, and the residuals are passed to # the feature engineering and modeling pipeline. For predictions, the SEIRD model's value is added to the residual # predictions from the pipeline, for each time series group. # Note: Careful selection of the bounds for the free parameters N, beta, gamma, delta, alpha, rho, lockdown, # beta_decay, beta_decay_rate is extremely important for good results. # - S(t) : susceptible/healthy/not immune # - E(t) : exposed/not yet infectious # - I(t) : infectious/active <= target column # - R(t) : recovered/immune # - D(t) : deceased # ### Free parameters: # - N : total population, N=S+E+I+R+D # - beta : rate of exposure (S -> E) # - gamma : rate of recovering (I -> R) # - delta : incubation period # - alpha : fatality rate # - rho : rate at which people die # - lockdown : day of lockdown (-1 => no lockdown) # - beta_decay : beta decay due to lockdown # - beta_decay_rate : speed of beta decay # ### Dynamics: # if lockdown >= 0: # beta_min = beta * (1 - beta_decay) # beta = (beta - beta_min) / (1 + np.exp(-beta_decay_rate * (-t + lockdown))) + beta_min # dSdt = -beta * S * I / N # dEdt = beta * S * I / N - delta * E # dIdt = delta * E - (1 - alpha) * gamma * I - alpha * rho * I # dRdt = (1 - alpha) * gamma * I # dDdt = alpha * rho * I # Provide lower/upper bounds for each parameter you want to control the bounds for. Valid parameters are: # N_min, N_max, beta_min, beta_max, gamma_min, gamma_max, delta_min, delta_max, alpha_min, alpha_max, # rho_min, rho_max, lockdown_min, lockdown_max, beta_decay_min, beta_decay_max, # beta_decay_rate_min, beta_decay_rate_max. You can change any subset of parameters, e.g., # ts_target_trafo_epidemic_params_dict="{'N_min': 1000, 'beta_max': 0.2}" # To get SEIR model (in cases where death rates are very low, can speed up calculations significantly): # set alpha_min=alpha_max=rho_min=rho_max=beta_decay_rate_min=beta_decay_rate_max=0, lockdown_min=lockdown_max=-1. # #ts_target_trafo_epidemic_params_dict = "{}" #ts_target_trafo_epidemic_target = "I" # Time series lag-based target transformation. One can choose between difference and ratio of the current and a lagged target target. The corresponding lag size can be set via 'Target transformation lag size'. Note: Can be cascaded with 'Time series target transformation', but is mutually exclusive with regular target transformations. #ts_lag_target_trafo = "none" # Lag size used for time series target transformation. See setting 'Time series lag-based target transformation'. -1 => smallest valid value = prediction periods + gap (automatically adjusted by DAI if too small). #ts_target_trafo_lag_size = -1 # Maximum amount of columns send from UI to backend in order to auto-detect TGC #tgc_via_ui_max_ncols = 10 # Maximum frequency of duplicated timestamps for TGC detection #tgc_dup_tolerance = 0.01 # Timeout in seconds for time-series properties detection in UI. #timeseries_split_suggestion_timeout = 30.0 # Every *.toml file is read from this directory and process the same way as main config file. #user_config_directory = "" # IP address and port of procsy process. #procsy_ip = "127.0.0.1" # IP address and port of procsy process. #procsy_port = 12347 # IP address for use by MLI. #h2o_ip = "127.0.0.1" # Port of H2O instance for use by MLI. Each H2O node has an internal port (web port+1, so by default port 12349) for internal node-to-node communication #h2o_port = 12348 # IP address and port for Driverless AI HTTP server. #ip = "127.0.0.1" # IP address and port for Driverless AI HTTP server. #port = 12345 # A list of two integers indicating the port range to search over, and dynamically find an open port to bind to (e.g., [11111,20000]). #port_range = "[]" # Strict version check for DAI #strict_version_check = true # File upload limit (default 100GB) #max_file_upload_size = 104857600000 # Data directory. All application data and files related datasets and # experiments are stored in this directory. #data_directory = "./tmp" # Path to the directory where the logs of HDFS, Hive, JDBC, and KDB+ data connectors will be saved. #data_connectors_logs_directory = "./tmp" # Subdirectory within data_directory to store server logs. #server_logs_sub_directory = "server_logs" # Subdirectory within data_directory to store pid files for controlling kill/stop of DAI servers. #pid_sub_directory = "pids" # Path to the directory which will be use to save MapR tickets when MapR multi-user mode is enabled. # This is applicable only when enable_mapr_multi_user_mode is set to true. # #mapr_tickets_directory = "./tmp/mapr-tickets" # MapR tickets duration in minutes, if set to -1, it will use the default value # (not specified in maprlogin command), otherwise will be the specified configuration # value but no less than one day. # #mapr_tickets_duration_minutes = -1 # Whether to run through entire data directory and remove all temporary files. # Can lead to slow start-up time if have large number (much greater than 100) of experiments. # #remove_temp_files_server_start = false # Whether to delete temporary files after experiment is aborted/cancelled. # #remove_temp_files_aborted_experiments = true # Whether to opt in to usage statistics and bug reporting #usage_stats_opt_in = true # Configurations for a HDFS data source # Path of hdfs coresite.xml # core_site_xml_path is deprecated, please use hdfs_config_path #core_site_xml_path = "" # (Required) HDFS config folder path. Can contain multiple config files. #hdfs_config_path = "" # Path of the principal key tab file. Required when hdfs_auth_type='principal'. # key_tab_path is deprecated, please use hdfs_keytab_path # #key_tab_path = "" # Path of the principal key tab file. Required when hdfs_auth_type='principal'. # #hdfs_keytab_path = "" # Whether to delete preview cache on server exit #preview_cache_upon_server_exit = true # When this setting is enabled, any user can see all tasks running in the system, including their owner and an identification key. If this setting is turned off, user can see only their own tasks. #all_tasks_visible_to_users = true # When enabled, server exposes Health API at /apis/health/v1, which provides system overview and utilization statistics #enable_health_api = true #notification_url = "https://s3.amazonaws.com/ai.h2o.notifications/dai_notifications_prod.json" # When enabled, the notification scripts will inherit # the parent's process (DriverlessAI) environment variables. # #listeners_inherit_env_variables = false # Notification scripts # - the variable points to a location of script which is executed at given event in experiment lifecycle # - the script should have executable flag enabled # - use of absolute path is suggested # The on experiment start notification script location #listeners_experiment_start = "" # The on experiment finished notification script location #listeners_experiment_done = "" # Notification script triggered when building of MOJO pipeline for experiment is # finished. The value should be an absolute path to executable script. # #listeners_mojo_done = "" # Notification script triggered when rendering of AutoDoc for experiment is # finished. The value should be an absolute path to executable script. # #listeners_autodoc_done = "" # Notification script triggered when building of python scoring pipeline # for experiment is finished. # The value should be an absolute path to executable script. # #listeners_scoring_pipeline_done = "" # Notification script triggered when experiment and all its artifacts selected # at the beginning of experiment are finished building. # The value should be an absolute path to executable script. # #listeners_experiment_artifacts_done = "" # Whether to run quick performance benchmark at start of application #enable_quick_benchmark = true # Whether to run extended performance benchmark at start of application #enable_extended_benchmark = false # Scaling factor for number of rows for extended performance benchmark. For rigorous performance benchmarking, # values of 1 or larger are recommended. #extended_benchmark_scale_num_rows = 0.1 # Number of columns for extended performance benchmark. #extended_benchmark_num_cols = 20 # Seconds to allow for testing memory bandwidth by generating numpy frames #benchmark_memory_timeout = 2 # Maximum portion of vm total to use for numpy memory benchmark #benchmark_memory_vm_fraction = 0.25 # Maximum number of columns to use for numpy memory benchmark #benchmark_memory_max_cols = 1500 # Whether to run quick startup checks at start of application #enable_startup_checks = true # Application ID override, which should uniquely identify the instance #application_id = "" # Specifies the DB backend which application uses. Possible options are: - *legacy* - Uses legacy SQLite with entity JSON blobs - *sqlite* - Uses relational SQLite separate entity tables #db_backend = "legacy" # After how many seconds to abort MLI recipe execution plan or recipe compatibility checks. # Blocks main server from all activities, so long timeout is not desired, esp. in case of hanging processes, # while a short timeout can too often lead to abortions on busy system. # #main_server_fork_timeout = 10.0 # After how many days the audit log records are removed. # Set equal to 0 to disable removal of old records. # #audit_log_retention_period = 5