Using the config.toml File

Admins can edit a config.toml file when starting the Driverless AI Docker image. This file is located in a folder on the container, and it includes all possible configuration options that would otherwise be specified in the nvidia-docker run command. You can make updates to environment variables directly in this file. Driverless AI uses the updated config.toml file when starting from native installs. Docker users can specify the updated config.toml file when starting the Driverless AI Docker image.

Note: For information on configuration security, see Configuration Security.

Configuration Override Chain

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

1. h2oai/config/config.toml - This is an internal file that is not visible.

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.

Docker Image Users

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.
nvidia-docker run \
  --pid=host \
  --rm \
  --init \
  -u `id -u`:`id -g` \
  -v `pwd`/config:/config \
  --entrypoint bash \
  h2oai/dai-centos7-x86_64:TAG
  -c "cp /etc/dai/config.toml /config"

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

3. Start Driverless AI with the DRIVERLESS_AI_CONFIG_FILE environment variable. Make sure this points to the location of the edited config.toml file so that the software finds the configuration file.

nvidia-docker run \
  --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-centos7-x86_64:TAG

Native Install Users

Native installs include DEBs, RPMs, and TAR SH installs.

1. Export the Driverless AI config.toml file or add it to ~/.bashrc. For example:

export DRIVERLESS_AI_CONFIG_FILE=“/config/config.toml”

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

3. Start Driverless AI. Note that the command used to start Driverless AI varies depending on your install type.

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

Sample Config.toml File

##############################################################################
#                        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"]
##############################################################################

# Whether to allow user to change non-server toml parameters per experiment in expert page.
#allow_config_overrides_in_expert_page = true

# Every *.toml file is read from this directory and process the same way as main config file.
#user_config_directory = ""

# Keystore file that contains secure config.toml items like passwords, secret keys etc. Ketstore is managed by h2oai.keystore tool.
#keystore_file = ""

# IP address and port of autoviz process.
#vis_server_ip = "127.0.0.1"

# IP and port of autoviz process.
#vis_server_port = 12346

# 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 and port of H2O instance.
#h2o_ip = "127.0.0.1"

# IP address and port of H2O instance for use by MLI.
#h2o_port = 12348

# 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 = 50341

# 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.
#h2o_recipes_nthreads = 4

# 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 = "{}"

# 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"

# 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 = "[]"

# File upload limit (default 100GB)
#max_file_upload_size = 104857600000

# 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

# Redis settings
#redis_ip = "127.0.0.1"

# Redis settings
#redis_port = 6379

# Redis settings
#master_redis_password = ""

# 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 agains 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 = ""

# Data directory. All application data and files related datasets and
# experiments are stored in this directory.
#data_directory = "./tmp"

# 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 = true

# 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

# Whether to run quick startup checks at start of application
#enable_startup_checks = true

# Whether to opt in to usage statistics and bug reporting
#usage_stats_opt_in = false

# 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.
# 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/<authentication_method>' path. Comma separated list. For example: additional_authentication_methods = "['tls_certificate', 'ldap']"
#additional_authentication_methods = "[]"

# default amount of time in hours before we force user to login again (if not provided by authentication_method)
#authentication_default_timeout_hours = 72

# OpenID Connect Settings:
# Refer to 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 (<http://objectpath.org/>) expression is used to
# evaluate the user identity.
# 
#auth_openid_use_objectpath_match = false

# ObjectPath (<http://objectpath.org/>) 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 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 = ""

# 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<username>.*)"

# 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<id>\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<id>\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<token>.*)"

# 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 '<location_to_place_htpasswd_file>' '<username>'
# note: -B forces use of brcypt, a secure encryption method
#local_htpasswd_file = ""

# 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"

# 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

# 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']"

# 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
# list of supported options: csv, tsv, txt, dat, tgz, gz, bz2, zip, xz, xls, xlsx, jay, feather, bin, arff, parquet, pkl, orc
# 
#files_without_extensions_expected_types = "['parquet', 'orc']"

# 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
# 
#enabled_file_systems = "upload, file, hdfs, s3, recipe_file, recipe_url"

#max_files_listed = 100

# do_not_log_list : add configurations that you do not wish to be recorded in logs here
#do_not_log_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', 'master_minio_access_key_id', 'master_minio_secret_access_key', 'master_redis_password', 'minio_access_key_id', 'minio_endpoint_url', 'minio_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']"

# Minio is used for file distribution on multinode architecture.
# These settings are used to specify the local Minio connection to master nodes.
#master_minio_address = "<URL>:<PORT>"

# Minio is used for file distribution on multinode architecture.
# These settings are used to specify the local Minio connection to master nodes.
#master_minio_access_key_id = ""

# Minio is used for file distribution on multinode architecture.
# These settings are used to specify the local Minio connection to master nodes.
#master_minio_secret_access_key = ""

# 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

# 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

# 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

# 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 (to avoid complexity)
# * 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
# '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
# 
#recipe = "auto"

# 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 = ""

# How much effort to spend on feature engineering (0...10)
# Heuristic combination of various developer-level toml parameters
# 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 = 5

# Whether to enable train/valid and train/test distribution shift detection ('auto'/'on'/'off')
#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

# Whether to check leakage for each feature (True/False).
# If fold column, this checks leakage without fold column used.
#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

# 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"

# 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 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 = 100

# 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 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

# Whether to create the pipeline visualization at the end of each experiment.
#make_pipeline_visualization = "auto"

# Whether to create the experiment Autoreport after end of experiment.
# 
#make_autoreport = true

# Max number of CPU cores to use per experiment. Set to <= 0 to use all 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

# 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)
#max_fit_cores = 10

# Control maximum number of cores to use for a model's predict call (0 = all physical cores >= 1 that count)
#max_predict_cores = 0

# 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 (0 = all physical cores >= 1 that count)
#max_predict_cores_in_dai = 4

# 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

# 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
#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.
# Currently num_gpus_per_model!=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
#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.
# 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.
# If tensorflow_nlp_have_gpus_in_production=true, then that overrides this setting for relevant
# TensorFflow NLP transformers.
# 
#num_gpus_for_prediction = 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).
#max_dt_threads_munging = -1

# Maximum number of threads for datatable during data reading and writing (per process) (0 = all, -1 = auto).
#max_dt_threads_readwrite = -1

# Maximum number of threads for datatable stats and openblas (per process) (0 = all, -1 = auto).
#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

# Delimiter/Separator to use when parsing tabular text files like CSV. Automatic if empty. Must be provided at system start.
#datatable_separator = ""

# Which gpu_id to start with
# 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 = 0

# Maximum number of workers for Driverless AI server pool (only 1 needed currently)
#max_workers = 1

# 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

# Period between checking DAI status.
#ping_sleep_period = 1

# 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

# Precision of how data is stored
# 'float32' best for speed, 'float64' best for accuracy or very large input values
# '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 = 65535

# number of threads limit
# Below should be consistent with start-dai.sh
#limit_nproc = 16384

# 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']"

# 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 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 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 = 10000

# Largest number of rows to use for column stats, otherwise sample randomly
#max_rows_col_stats = 1000000

# Whether to obtain permutation feature importance on original features for reporting in logs and file.
# 
#orig_features_fs_report = false

# Maximum number of rows when doing permutation feature importance, reduced by (stratified) random sampling.
# 
#max_rows_fs = 500000

# 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

# 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 = 10000

# Maximum number of numeric columns selected, above which will do feature selection
# same as above (max_orig_cols_selected) but for numeric columns.
#max_orig_numeric_cols_selected = 10000

# Maximum number of non-numeric columns selected, above which will do feature selection on all features and avoid treating numerical as categorical
# same as above (max_orig_numeric_cols_selected) but for categorical columns.
#max_orig_nonnumeric_cols_selected = 300

# 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 = 500

# 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 = 500

# 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

# 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.
#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

# 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

# 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 = 8

# 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 = 5

# 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 = 200

# 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.
# The number 20 is default, but 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

# 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 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.
# 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 Model With Same Parameters: 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 model with Same Params" 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

# 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, 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

# 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 just after scoring them
# 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
#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

# Whether to limit feature counts by interpretability setting via features_allowed_by_interpretability
#limit_features_by_interpretability = true

# 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

# Whether to use Word-based CNN TensorFlow models for NLP if TensorFlow enabled
#enable_tensorflow_textcnn = "auto"

# Whether to use Word-based Bi-GRU TensorFlow models for NLP if TensorFlow enabled
#enable_tensorflow_textbigru = "auto"

# Whether to use Character-level CNN TensorFlow models for NLP if TensorFlow enabled
#enable_tensorflow_charcnn = "auto"

# Path to pretrained embeddings for TensorFlow NLP models
# 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 = ""

# 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

# Whether Python/MOJO scoring runtime will have GPUs (otherwise BiGRU will fail in production if this is enabled).
# Enabling this can speed up training for BiGRU, but will require GPUs and CuDNN in production.
#tensorflow_nlp_have_gpus_in_production = false

# 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

# 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
#string_col_as_text_threshold = 0.3

# 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 (otherwise categorical)
#string_col_as_text_min_absolute_cardinality = 100

# Interpretability setting equal and above which will use automatic monotonicity constraints in
# XGBoostGBM/LightGBM/DecisionTree models.
# 
#monotonicity_constraints_interpretability_switch = 7

# 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

# Manual override for monotonicity constraints. Mapping of original numeric features to desired constraint
# (1 for pos, -1 for neg, or 0 to disable). Features that are not listed here will automatically get no
# constraint (i.e., 0). Example: {'PAY_0': -1, 'PAY_2': -1, 'AGE': -1, 'BILL_AMT1': 1, 'PAY_AMT1': -1}
# If not provided, then the automatic correlation based method will be in effect if monotonicity constraints are
# enabled at high enough interpretability settings.
# 
#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

# Like fixed_feature_interaction_depth but for categoricals if doing numcat (i.e. numeric and categoricals separated)
# transformers.  Only applies if also fixed_feature_interaction_depth > 0, and then will use sampling (0) unless
# override since doesn't make sense to group by all columns usually.
#fixed_feature_interaction_depth_numcat_cat = 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 = 3

# Select a target transformation for regression problems. Must be one of: ['auto',
# 'identity', 'unit_box', 'log', '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).
# 
#target_transformer = "auto"

# Tournament style (method to decide which models are best at each iteration)
# 'auto' : Choose based upon accuracy, etc.
# 'fullstack' : Choose among optimal model and feature types
# 'model' : individuals with same model type compete
# 'feature' : individuals with similar feature types compete
# 'uniform' : all individuals in population compete to win as best
# '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
#tournament_style = "auto"

# Interpretability above which will use 'uniform' tournament style
#tournament_uniform_style_interpretability_switch = 6

# 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 = 7

# Accuracy equal and above which uses fullstack style if tournament_style = 'auto'
#tournament_fullstack_style_accuracy_switch = 8

# Whether to use penalized score for GA tournament or actual score
#tournament_use_feature_penalized_score = 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
#fixed_num_individuals = 0

# set fixed number of fold reps (if > 0) - useful for quick runs regardless of data
#fixed_fold_reps = 0

# 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 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"

#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"

#isolation_forest_nestimators = 200

# Driverless AI categorises all data (feature engineering) transformers
# 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']'
# 
#excluded_transformers = "[]"

# Include list of genes (i.e. genes (built on top of transformers) to 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 only enable interaction gene, use:  included_genes =
# '['InteractionsGene']'
#included_genes = "[]"

# 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']'
#excluded_genes = "[]"

#included_models = "[]"

# Auxiliary to included_models
#excluded_models = "[]"

#included_scorers = "[]"

# Auxiliary to included_scorers
#excluded_scorers = "[]"

# Whether to enable XGBoost GBM models ('auto'/'on'/'off')
#enable_xgboost_gbm = "auto"

# Whether to enable XGBoost Dart models ('auto'/'on'/'off')
#enable_xgboost_dart = "auto"

# Internal threshold for number of rows x number of columns to trigger no xgboost models due to high memory use
# Overridden if enable_xgboost_gbm = "on" or enable_xgboost_dart = "on", in which case always allow each model type to be used
#xgboost_threshold_data_size_large = 100000000

# Internal threshold for number of rows x number of columns to trigger no xgboost models due to limits on GPU memory capability
# Overridden if enable_xgboost_gbm = "on" or enable_xgboost_dart = "on", in which case always allow each model type to be used
#xgboost_gpu_threshold_data_size_large = 30000000

# Whether to enable GLM models ('auto'/'on'/'off')
#enable_glm = "auto"

# Whether to enable Decision Tree models ('auto'/'on'/'off')
#enable_decision_tree = "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 FTRL support (beta version, no mojo) (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"

# 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 LightGBM categorical feature support (only CPU mode currently)
#enable_lightgbm_cat_support = false

# Whether to enable LightGBM CUDA implementation instead of OpenCL (LightGBM with CUDA needs to be installed manually)
#enable_lightgbm_cuda_support = false

# Whether to enable constant models ('auto'/'on'/'off')
#enable_constant_model = "auto"

# Whether to show constant models in iteration panel
#show_constant_model = false

#drop_constant_model_final_ensemble = true

# Parameters for LightGBM 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_lightgbm = "{'objective': 'binary:logistic', '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:logistic', '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_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'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': 'one_shot', '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
# 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:logistic', '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:logistic', '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 = "{}"

# 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'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 = "{}"

# 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
# Early-stopping usually chooses less
#max_nestimators = 3000

# LightGBM dart mode and normal rf mode do not use early stopping and will sample from these values for n_estimators.
#n_estimators_list_no_early_stopping = [50, 100, 200, 300]

# Lower limit on learning rate for final ensemble GBM models.
# In some cases, the maximum number of treess/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

# Max. number of epochs for TensorFlow and FTRL models
#max_epochs = 10

# 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 (recommended for GPU lightgbm)
#default_lightgbm_max_bin = 64

# 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
#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

# How many cores to use for each TensorFlow model, regardless if GPU or CPU based (0 = auto mode)
#tensorflow_cores = 0

# 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 = 100

# Internal threshold for number of rows x number of columns to trigger no rulefit models due to being too slow currently
#rulefit_threshold_data_size_large = 100000000

# 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

# 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)
# 3 = 3 models, multiple ensemble folds (cross-validation)
# 4 = 4 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

# 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

#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"

#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 = 100000000

# Upper limit on the number of rows x number of columns for training final pipeline.
# 
#final_pipeline_data_size = 500000000

# 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

# 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 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

# -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)
#ohe_bin_list = "[10, 25, 50, 75, 100]"

# Whether to drop columns with constant values
#drop_constant_columns = true

# 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 = ""

# Control over columns to group by, default is empty list that means DAI automatically searches all columns,
# selected randomly or by which have top variable importance.
#cols_to_group_by = ""

# Whether to sample from given features to group by (True) or to always group by all features (False).
#sample_cols_to_group_by = false

# Aggregation functions to use for groupby operations.
#agg_funcs_for_group_by = "['mean', 'sd', 'min', 'max', 'count']"

# Out of fold aggregations ensure less overfitting, but see less data in each fold.
#folds_for_group_by = 5

# 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"

# 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

# 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 = 4

# 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

# 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

# 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

# Enable time series recipe
#time_series_recipe = true

# 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 = ""

# Timeout in seconds for time-series properties detection in UI.
#timeseries_split_suggestion_timeout = 30.0

# 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_not_time_series_recipe = false

# earliest datetime for automatic conversion of integers in %Y%m%d format to a time column during parsing
#min_ymd_timestamp = 19000101

# lastet datetime for automatic conversion of integers in %Y%m%d format to a time column during parsing
#max_ymd_timestamp = 21000101

# maximum number of data samples (randomly selected rows) for date/datetime format detection
#max_rows_datetime_format_detection = 100000

# Automatically generate is-holiday features from date columns
#holiday_features = true

#holiday_country = ""

# Country code(s) to use to look up holiday calendar (Python package 'holidays')
#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

# Whether to sample lag sizes
#sample_lag_sizes = false

# How many samples of lag sizes to use, chosen randomly out of original set of lag sizes
#max_sampled_lag_sizes = 10

# 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 = []

# 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 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

# Enable creation of holdout predictions on training data
# using moving windows (useful for MLI, but can be slow)
#time_series_holdout_preds = true

# 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

# 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 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"

# 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

# 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

# Build (if missing but available) the MOJO pipeline to be used for predictions in MLI. For certain models this can improve performance.
#mli_use_mojo_pipeline = false

# 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

# When sample for MLI how many rows to sample
#mli_sample_size = 100000

# how many bins to do quantile binning
#mli_num_quantiles = 10

# mli random forest number of trees
#mli_drf_num_trees = 100

# Whether to speed up predictions used inside MLI with a fast approximation
#mli_fast_approx = true

# mli number of trees for fast_approx during predict for Shapley
#fast_approx_num_trees = 50

# whether to do only 1 fold and 1 model of all folds and models if ensemble
#fast_approx_do_one_fold_one_model = true

# mli random forest max depth
#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 strength for k-LIME GLM's
#klime_alpha = 0.0

# mli converts numeric columns to enum when cardinality is <= this value
#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

# Enable MLI Sensitivity Analysis
#enable_mli_sa = true

# When number of rows are above this limit, then sample for DIA
#mli_dia_sample_size = 100000

# Whether to speed up predictions used inside DIA with a fast approximation
#mli_dia_fast_approx = false

# When number of rows are above this limit, then sample for DAI PD/ICE
#mli_pd_sample_size = 100000

# Use dynamic switching between PD numeric and categorical binning and UI chart selection in case of features which were used both as numeric and categorical by auto ML
#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 = 10

# When number of rows are above this limit, then sample for MLI Shapley calculation
#mli_shapley_sample_size = 100000

# 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

# Allow predict method with fast approximation in MLI (PD, ICE, SA, ...
#enable_mli_predict_fast_approx = false

# Number of max retries should the surrogate model fail to build.
#mli_max_surrogate_retries = 5

# Number of rows per batch when scoring using MOJO.
#mli_mojo_batch_size = 50

# 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 on which we'll perform MLI NLP
#mli_nlp_sample_limit = 10000

# Number of parallel workers when scoring using MOJO in MLI NLP.
#mli_nlp_workers = 4

# 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 number of top tokens to be used as features when building surrogate models.
#mli_nlp_surrogate_tokens = 100

# Whether to dump every scored individual's variable importance (both derived and original) to csv/tabulated/json file
# produces files like: individual_scored_id%d.iter%d*features*
#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]
#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

# 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

# Location of the AutoReport template or templates. This configuration allows you to generate a single AutoDoc or a zip of multiple AutoDocs from different templates, for each experiment. A list with a single string path will generate one AutoReport; a list with multiple string paths will generate multiple a zip of multiple AutoReports. Defaults to a single AutoReport using the Standard AutoReport template.
#autodoc_template = []

# Specify the output of the report.
# Options are docx or md.
#autodoc_output_type = "docx"

# Specify the name of the report.
#autodoc_report_name = "report"

# Specify the maximum number of classes in the confusion
# matrix.
#autodoc_max_cm_size = 10

# Set the number of models for which a glm coefficients
# table is shown in the Autoreport. 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 Autoreport. 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 Autoreport. 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 Autoreport. 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

# 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

# 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

# Specify the number of top features to display in
# the document. setting to -1 disables this restriction
#autodoc_num_features = 50

# Specify the number of rows to include in PDP and ICE plot
# if individual rows are not specified.
#autodoc_num_rows = 0

# Maximum number of seconds Partial Dependency computation
# can take when generating report. Set to -1 for no time limit.
#autodoc_pd_max_runtime = 20

# 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

# Number of columns 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 include prediction statistics information if
# experiment is binary classification/regression.
#autodoc_prediction_stats = false

# Number of quantiles to use for prediction statistics
# computation.
#autodoc_prediction_stats_n_quantiles = 20

# 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
# computation.
#autodoc_population_stability_index_n_quantiles = 10

# Whether to compute permutation based feature importance.
#autodoc_include_permutation_feature_importance = false

# Name of the scorer to be used to calculate feature
# importance. Leave blank to use experiments default scorer
#autodoc_feature_importance_scorer = ""

# Number of permutations to make per feature when computing
# feature importance.
#autodoc_feature_importance_num_perm = 1

# Whether to include response rates information if
# experiment is binary classification.
#autodoc_response_rate = false

# Number of quantiles to use for response rates information
# computation.
#autodoc_response_rate_n_quantiles = 10

# 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. Must
# be set to the integer 1 or 2.
#autodoc_global_klime_num_tables = 1

# Whether to show the Gini Plot.
#autodoc_gini_plot = false

# 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

# When histogram plots are available: The number of
# top (default 10) features for which to show histograms.
#autodoc_num_histogram_plots = 10

# 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

# '
# 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

# Whether to delete preview cache on server exit
#preview_cache_upon_server_exit = 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 = ""

# 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 browser.
# For example:
# file_path_filter_include = "['/data','/home/michal/']"
#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=<path>/krb5.conf
# -Dsun.security.krb5.debug=True
# -Dlog4j.configuration=file:///<path>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://"

# 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 enpoint URL that will be used to access S3.
#aws_s3_endpoint_url = ""

# If set to true S3 Connector will try to to obtain credentials assiciated 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://"

# 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://"

# 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

# Recommended Provide: url, user, password
# Optionally Provide: account, user, password
# Example URL: https://<snowflake_account>.<region>.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://"

# 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/<filename>.keytab",
# "principal_user": "hive/LOCALHOST@H2O.AI",
# },
# "hive_connection_2": {
# "hive_conf_path": "/path/to/hive/conf_2",
# "auth_type": "one of ['noauth', 'keytab', 'keytabimpersonation']",
# "keytab_path": "/path/to/<filename_2>.keytab",
# "principal_user": "my_user/LOCALHOST@H2O.AI",
# }
# }'
# 
#hive_app_configs = "{}"

# Extra jvm args for hive connector. Provide args separated by a space.
# Notes regarding default jvm args:
# * -Djavax.security.auth.useSubjectCredsOnly=false -- setting required for kerberos authentication + impersonation
# * -Djava.security.auth.login.config=/etc/dai/jaas.conf -- setting required to allow underlying connector process
# to adopt kerberos login properties as defined in the file /etc/dai/jaas.conf
# -- Note: user must create the `jaas.conf` and place it in the specified directory
# * Example /etc/dai/jaas.conf (result of `cat /etc/dai/jaas.conf`) --
# com.sun.security.jgss.initiate {
# com.sun.security.auth.module.Krb5LoginModule required
# useKeyTab=true
# useTicketCache=false
# principal="hive/LOCALHOST@H2O.AI"
# doNotPrompt=true
# keyTab="/path/to/<filename>.keytab"
# debug=true;
# };
# -- Note: principal and keytab settings should be the same as configurations above for hive_app_configs.
# and are the ONLY settings that need to be changed for DAI Hive connector to function.
# 
#hive_app_jvm_args = "-Xmx4g -Djavax.security.auth.useSubjectCredsOnly=false -Djava.security.auth.login.config=/etc/dai/jaas.conf"

# Alternative classpath for hive connector. Can be used to add additional jar files to classpath.
#hive_app_classpath = ""

# 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 = ""

# Address of the H2O Storage endpoint. Keep empty to use the local storage only.
#h2o_storage_address = ""

# 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 = ""

# 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 = ""

# 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

# Enable custom recipes.
#enable_custom_recipes = true

# Enable uploading of custom recipes.
#enable_custom_recipes_upload = true

# Enable downloading of custom recipes from external URL.
#enable_custom_recipes_from_url = true

# Include custom recipes in default inclusion lists (warning: enables all custom recipes)
#include_custom_recipes_by_default = false

# Default application language - options are 'en', 'ja', 'cn', 'ko'
#app_language = "en"

# If true, Logout button is not visible in the GUI.
#disablelogout = false

# When enabled each authenticated access will be verified
# comparing IP address of initiator of session and current request IP
# 
#verify_session_ip = false

# If enabled, user can log in from 2 browsers (scripts) at the same time
#allow_concurrent_sessions = true

# 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

# If enabled, webserver will serve xsrf cookies and verify their validity upon every POST request
#enable_xsrf_protection = true

#enable_secure_cookies = 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']

# Whether to check if config.toml keys are valid and fail if not valid
#check_invalid_config_toml_keys = true

#enable_funnel = true

#clean_funnel = true

#quiet_funnel = false

#debug_daimodel_level = 0

# Value to override number of sockets, in case DAIs determination is wrong, for non-trivial systems.  0 means auto.
#num_cpu_sockets_override = 0

#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

#varimp_threshold_at_interpretability_10 = 0.05

#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}"

#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

# 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.
# 
#prob_prune_by_features = 0.25

#max_absolute_feature_expansion = 1000

#booster_for_fs_permute = "auto"

#model_class_name_for_fs_permute = "auto"

# Number of classes above which to always use TensorFlow (if TensorFlow is enabled),
# instead of others models set on 'auto' (models set to 'on' are still used).
#tensorflow_num_classes_switch = 10

# 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]"

#gbm_early_stopping_rounds_min = 1

#gbm_early_stopping_rounds_max = 10000000000

# 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

# 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 = "{}"

# 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=<full tmp dir>/<contrib_env_relative_directory>/lib/python3.6/site-packages/ <path to dai>dai-env.sh python -m pip install --prefix=<full tmp dir>/<contrib_env_relative_directory> <packagename> --upgrade --upgrade-strategy only-if-needed --log-file pip_log_file.log
# where <path to dai> is /opt/h2oai/dai/ for native rpm/deb installation
# Note can also install wheel files if <packagename> is name of wheel file or archive.
# 
#contrib_env_relative_directory = "contrib/env"

# 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

# 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

# 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 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, 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

# 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.
# 
#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

# 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

# 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 user can download dataset as csv file
#enable_dataset_downloading = true

# Extra HTTP headers.
#extra_http_headers = "{}"

# 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

# 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
# 
#artifacts_store = "file_system"

# 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 to be used for storing artifacts.
#artifacts_s3_bucket = ""

# 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"

# 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 = ""

#num_models_for_resume_graph = 1000