ml_grid.model_classes.AutoKerasClassifierWrapper

AutoKeras Classifier Wrapper.

This module provides a scikit-learn compatible wrapper for AutoKeras StructuredDataClassifier.

Attributes

ak
logger

Classes

AutoKerasClassifierWrapper

A scikit-learn compatible wrapper for AutoKeras StructuredDataClassifier.

Module Contents

ml_grid.model_classes.AutoKerasClassifierWrapper.ak = None

ml_grid.model_classes.AutoKerasClassifierWrapper.logger

class ml_grid.model_classes.AutoKerasClassifierWrapper.AutoKerasClassifierWrapper(max_trials: int = 3, epochs: int = 10, validation_split: float = 0.2, directory: str | None = None, seed: int = 42, verbose: int = 1, overwrite: bool = True)

Bases: sklearn.base.BaseEstimator, sklearn.base.ClassifierMixin

A scikit-learn compatible wrapper for AutoKeras StructuredDataClassifier.

max_trials = 3

epochs = 10

validation_split = 0.2

directory = None

seed = 42

verbose = 1

overwrite = True

model_ = None

fit(X: numpy.ndarray | pandas.DataFrame, y: numpy.ndarray | pandas.Series, **kwargs) → AutoKerasClassifierWrapper

predict(X: numpy.ndarray | pandas.DataFrame) → numpy.ndarray

predict_proba(X: numpy.ndarray | pandas.DataFrame) → numpy.ndarray