ml_grid.model_classes.keras_classifier_class

Classes

kerasClassifier_class

Initializes the kerasClassifier_class.

Module Contents

class ml_grid.model_classes.keras_classifier_class.kerasClassifier_class(X: pandas.DataFrame, y: pandas.Series, parameter_space_size: str | None = None)

Initializes the kerasClassifier_class.

This configures a Keras Sequential model for binary classification, wrapped in a KerasClassifier to be compatible with scikit-learn’s hyperparameter tuning utilities.

Parameters:

• X (pd.DataFrame) – Feature matrix for training.

• y (pd.Series) – Target vector for training.

• parameter_space_size (Optional[str]) – Size of the parameter space for optimization. Defaults to None.

X

y

x_train_col_val

algorithm_implementation

method_name = 'kerasClassifier_class'

parameter_space

create_model(kernel_reg: tensorflow.keras.regularizers.Regularizer = tf.keras.regularizers.l1_l2(l1=0, l2=0), width: int = 15, learning_rate: float = 0.01, dropout_val: float = 0.2, input_dim_val: int = 0) → keras.models.Sequential

Builds and compiles a Keras Sequential model.

Note: This method appears to be a duplicate of the nested create_model function inside __init__.

Parameters:

• layers (int) – The number of dense layers in the model.

• kernel_reg (tf.keras.regularizers.Regularizer) – Kernel regularizer.

• width (int) – The number of units in each dense layer.

• learning_rate (float) – The learning rate for the Adam optimizer.

• dropout_val (float) – The dropout rate.

• input_dim_val (int) – The input dimension for the first layer.

Returns:

The compiled Keras model.

Return type:

Sequential