Mli_general configuration¶
mli_sample
¶
Sample all explainers. (Boolean)
Default value True
Choose whether to run all explainers on the sampled dataset.
mli_enable_mojo_scorer
¶
Allow use of MOJO scoring pipeline. (Boolean)
Default value True
Use this option to disable MOJO scoring pipeline. Scoring pipeline is chosen automatically (from MOJO and Python pipelines) by default. In case of certain models MOJO vs. Python choice can impact pipeline performance and robustness.
mli_fast_approx
¶
Speed up predictions with a fast approximation. (Boolean)
Default value True
Speed up predictions with a fast approximation (can reduce the number of trees or cross-validation folds).
mli_shapley_sample_size
¶
Sample size for transformed Shapley. (Number)
Default value 100000
When number of rows are above this limit, then sample for MLI transformed Shapley calculation.
mli_custom
¶
Add to config.toml via TOML string. (String)
Default value ''
Add TOML string to Driverless AI server config.toml configuration file.