mljar / mljar-supervised

Python package for AutoML on Tabular Data with Feature Engineering, Hyper-Parameters Tuning, Explanations and Automatic Documentation
https://mljar.com
MIT License
3.05k stars 406 forks source link

Add validation with split #50

Closed pplonski closed 4 years ago

pplonski commented 4 years ago

Add 2 new options for validation.

  1. Validation with a split.
  2. Validation with a separate dataset. (https://github.com/mljar/mljar-supervised/issues/101)
pplonski commented 4 years ago

Stacking models is disabled for split validation. The example use of split validation:

automl = AutoML(
    validation={
        "validation_type": "split",
        "train_ratio": 0.75,
        "stratify": True,
        "shuffle": True
    }
)