ml_grid.model_classes.nni_sklearn_wrapper

Classes

NeuralNetworkClassifier

Initializes the NeuralNetworkClassifier.

Module Contents

class ml_grid.model_classes.nni_sklearn_wrapper.NeuralNetworkClassifier(hidden_units_1: int = 64, hidden_units_2: int = 64, dropout_rate: float = 0.3, learning_rate: float = 0.001, activation_func: str = 'relu', epochs: int = 10, batch_size: int = 32, random_state: int | None = None)[source]

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

Initializes the NeuralNetworkClassifier.

Parameters:

hidden_units_1 (int) – Number of units in the first hidden layer.
hidden_units_2 (int) – Number of units in the second hidden layer.
dropout_rate (float) – Dropout rate for the dropout layers.
learning_rate (float) – Learning rate for the Adam optimizer.
activation_func (str) – Activation function for the hidden layers.
epochs (int) – Number of epochs to train the model.
batch_size (int) – Number of samples per gradient update.
random_state (Optional[int]) – Seed for reproducibility. Defaults to None.

hidden_units_1 = 64[source]

hidden_units_2 = 64[source]

dropout_rate = 0.3[source]

learning_rate = 0.001[source]

activation_func = 'relu'[source]

epochs = 10[source]

batch_size = 32[source]

random_state = None[source]

model: tensorflow.keras.models.Sequential | None = None[source]

classes_: numpy.ndarray | None = None[source]

build_model(input_dim: int) → tensorflow.keras.models.Sequential[source]

Builds and compiles the Keras Sequential model.

Parameters:: input_dim (int) – The number of input features.
Returns:: The compiled Keras model.
Return type:: Sequential

fit(X: numpy.ndarray, y: numpy.ndarray) → NeuralNetworkClassifier[source]

Fits the neural network model to the training data.

Parameters:

X (np.ndarray) – The training input samples.
y (np.ndarray) – The target values.

Returns:

The fitted estimator.

Return type:

NeuralNetworkClassifier

predict(X: numpy.ndarray) → numpy.ndarray[source]

Predicts class labels for samples in X.

Parameters:: X (np.ndarray) – The input samples to predict.
Returns:: The predicted class labels (0 or 1).
Return type:: np.ndarray

predict_proba(X: numpy.ndarray) → numpy.ndarray[source]

Predicts class probabilities for samples in X.

Parameters:: X (np.ndarray) – The input samples.
Returns:: The class probabilities of the input samples.
Return type:: np.ndarray

score(X: numpy.ndarray, y: numpy.ndarray) → float[source]

Returns the mean accuracy on the given test data and labels.

Parameters:

X (np.ndarray) – Test samples.
y (np.ndarray) – True labels for X.

Returns:

Mean accuracy of self.predict(X) wrt. y.

Return type: