Scikeras Tutorial -1

Pre-existing wrappers.py

import numpy as np
from sklearn.datasets import make_classification
from tensorflow import keras
from tensorflow.keras.wrappers.scikit_learn import KerasClassifier

# Make a dummy dataset
X, y = make_classification(1000, 20, n_informative=10, random_state=0)
X = X.astype(np.float32)
y = y.astype(np.int64)

print("Features Shape: ",X.shape)
print("Targets Shape: ",y.shape)

# get_model returns a compiled model
def get_model(n_features_in_, X_shape, n_classes_, hidden_layer_dim=100):
    # Define a sequential model
    model = keras.models.Sequential()
    model.add(keras.layers.Dense(n_features_in_, input_shape=X_shape[1:]))
    model.add(keras.layers.Activation("relu"))
    model.add(keras.layers.Dense(hidden_layer_dim))
    model.add(keras.layers.Activation("relu"))
    model.add(keras.layers.Dense(n_classes_))
    model.add(keras.layers.Activation("softmax"))
    # Compile the model
    model.compile(loss='sparse_categorical_crossentropy', optimizer='adam', metrics=["accuracy"])
    
    return model

clf = KerasClassifier(
    build_fn=get_model,
    n_features_in_=1000, 
    X_shape=X.shape, 
    n_classes_=2,
    hidden_layer_dim=100,
)

clf.fit(X, y)
print(clf.score(X[-100:,:],y[-100:]))