tensortrade.pipeline.transformers.mutual_information module

class tensortrade.pipeline.transformers.mutual_information.MutualInformationTransformer(num_features: int = 20, seed: int = 42, *, target_column: str = 'close', target_shift: int = 3, n_jobs: int = -1)[source]

Bases: AbstractTransformer

Transformer for selecting top features based on mutual information with a target variable.

Parameters:

  • num_features (int) – The number of top features to select based on mutual information scores. (Default = 20)

  • seed (int) – The seed used for the mutual information regression. (Default = 42)

  • 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)

  • n_jobs (int) – The number of parallel jobs to run. If -1, all processors are used. (Default = -1)

transform(df: DataFrame) → DataFrame[source]

Transforms the input DataFrame by selecting the top features based on mutual information with the target variable.

Parameters:

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

Returns:

A DataFrame reduced to the top features based on mutual information scores.

Return type:

DataFrame

Raises:

ValueError – If the number of values in the DataFrame is less than 5 after shifting.