import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Conv1D, MaxPooling1D, Flatten, Dense, Dropout, BatchNormalization

# -------------------------
# Construction du modèle CNN
# -------------------------
def build_cnn_model(input_shape, num_classes, filter1, filter2, filter3, learning_rate, dropout):
    model = Sequential()

    # 1er bloc convolution
    model.add(Conv1D(filters=filter1, kernel_size=3, activation='relu', padding='same', input_shape=input_shape))
    model.add(BatchNormalization())
    model.add(MaxPooling1D(pool_size=2))

    # 2e bloc
    model.add(Conv1D(filters=filter2, kernel_size=3, activation='relu', padding='same'))
    model.add(BatchNormalization())
    model.add(MaxPooling1D(pool_size=2))

    # 3e bloc
    model.add(Conv1D(filters=filter3, kernel_size=3, activation='relu', padding='same'))
    model.add(BatchNormalization())
    model.add(MaxPooling1D(pool_size=2))

    # Fully connected
    model.add(Flatten())
    model.add(Dense(256, activation='relu'))
    model.add(Dropout(dropout))
    model.add(Dense(num_classes, activation='softmax'))

    model.compile(
        optimizer=tf.keras.optimizers.Adam(learning_rate=learning_rate),
        loss='categorical_crossentropy',
        metrics=['accuracy']
    )

    return model