This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
max_words, batch_size, epochs = 10000, 256, 3 | |
# Generate split training and testing data (80% training, 20% testing) | |
x_train, x_test, y_train, y_test = load_encoded_data(data_split=0.8) | |
# Determine the number of classes (i.e. sentence types) | |
num_classes = np.max(y_train) + 1 | |
# Vectorizing the data into a Keras readable format (sequence matrix) | |
tokenizer = Tokenizer(num_words=max_words) | |
x_train = tokenizer.sequences_to_matrix(x_train, mode='binary') | |
x_test = tokenizer.sequences_to_matrix(x_test, mode='binary') | |
# Set the classifcation to a Keras readable format (categorical) | |
y_train = keras.utils.to_categorical(y_train, num_classes) | |
y_test = keras.utils.to_categorical(y_test, num_classes) | |
# I(max_words) --(W1)--> H(512) | |
model = Sequential() | |
model.add(Dense(512, input_shape=(max_words,))) | |
model.add(Activation('tanh')) | |
# H(512) --(W2)--> O(num_classes) | |
model.add(Dropout(0.5)) | |
model.add(Dense(num_classes)) | |
model.add(Activation('softmax')) | |
# Add Optimization method, loss function, and optimization variable | |
model.compile(loss='categorical_crossentropy', | |
optimizer='adam', metrics=['accuracy']) | |
# "Fit Model" (i.e. train model), using training data (80% of dataset) | |
model.fit(x_train, y_train, batch_size=batch_size, epochs=epochs) | |
# Evaluate the trained model, using the test data (20% of dataset) | |
score = model.evaluate(x_test, y_test,batch_size=batch_size) | |
# Final testing accuracy, using the resevered 20% testing data | |
print('Test accuracy:', score[1]) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment