Supplemental material for https://austingwalters.com/convolutional-neural-networks-cnn-to-classify-sentences/

cnn_sentence_type_classifcation.py

max_words, batch_size, maxlen, epochs = 10000, 64, 500, 2
embedding_dims, filters, kernel_size, hidden_dims = 50, 250, 5, 150

# Determine the number of categories + default(i.e. sentence types)
num_classes = np.max(y_train) + 1

# Vectorize the output sentence type classifcations to Keras readable format
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)

# Pad the input vectors to ensure a consistent length
x_train = sequence.pad_sequences(x_train, maxlen=maxlen)
x_test = sequence.pad_sequences(x_test, maxlen=maxlen)

model = Sequential()

# Created Embedding (Input) Layer (max_words) --> Convolutional Layer
model.add(Embedding(max_words, embedding_dims, input_length=maxlen))
model.add(Dropout(0.2)) # masks various input values
    
# Create the convolutional layer
model.add(Conv1D(filters, kernel_size,padding='valid', activation='relu', strides=1))

# Create the pooling layer
model.add(GlobalMaxPooling1D())

# Create the fully connected layer
model.add(Dense(hidden_dims))
model.add(Dropout(0.2))
model.add(Activation('relu'))

# Create the output layer (num_classes)
model.add(Dense(num_classes))
model.add(Activation('softmax'))

# Add optimization method, loss function and optimization value
model.compile(loss='categorical_crossentropy',
              optimizer='adam', metrics=['accuracy'])

# "Fit the model" (train model), using training data (80% of datset)
model.fit(x_train, y_train, batch_size=batch_size, 
          epochs=epochs, validation_data=(x_test, y_test))

# Evaluate the trained model, using the test data (20% of the dataset)
score = model.evaluate(x_test, y_test, batch_size=batch_size)