tensortrade.pipeline.transformers.univariate_feature_selection module

class tensortrade.pipeline.transformers.univariate_feature_selection.UnivariateFeatureSelectionTransformer(num_features: int = 20, *, target_column: str = 'close', target_shift: int = 3, problem_type: str = 'regression')[source]

Bases: AbstractTransformer

Transformer that does univariate feature selection.

It removes the features to num_features either by regression or classification.

Params num_features:

The number of features that should be returned. (Default = 20)

Parameters:

  • target_column (str) – The name of the target column on which the mutual information score should be calculated. (Default = ‘close’)

  • target_shift (int) – The number of periods to shift the target column to create the prediction target. (Default = 3)

  • problem_type (str) – The problem type to solve, either classification or regression. (Default = ‘regression’)

transform(df: DataFrame) → DataFrame[source]

Reduces features by univariate feature selection.

Parameters:

df (DataFrame) – The input DataFrame containing the features and target column.

Returns:

A DataFrame reduced to the top features based on univariate feature selection.

Return type:

DataFrame

Raises:

ValueError – If the problem_type is not ‘regression’ or ‘classification’.