Deep Learning: Keras + IMDB

Classifying movie reviews: a binary classification example

# -*- coding: utf-8 -*-

"""
@Date: 2018/10/5

@Author: dreamhomes

@Summary:
"""
from keras.datasets import imdb
from keras import models
from keras import layers

import numpy as np
import matplotlib.pyplot as plt

# N 25000
(train_data, train_labels), (test_data,
                             test_labels) = imdb.load_data(num_words=10000)
# print(len(train_data))
# print(train_labels)
# print(max([max(sequence) for sequence in train_data]))

word_index = imdb.get_word_index()

reverse_word_index = dict([(value, key)
                           for (key, value) in word_index.items()])

# decoded_review = ' '.join([reverse_word_index.get(i - 3, '?')
#                            for i in train_data[0]])
# print(decoded_review)


def vectorize_sequences(sequences, dimension=10000):
    """
    one hot encoding - Turn lists to vectors/tensors
    :param sequences:
    :param dimension:
    :return:
    """
    results = np.zeros((len(sequences), dimension))
    for i, sequence in enumerate(sequences):
        results[i, sequence] = 1.
    return results


x_train = vectorize_sequences(train_data)
x_test = vectorize_sequences(test_data)

# print(x_train[0])

y_train = np.asarray(train_labels).astype('float32')
# print(y_train)
y_test = np.asarray(test_labels).astype('float32')


model = models.Sequential()
model.add(layers.Dense(16, activation='relu', input_shape=(10000,)))
model.add(layers.Dense(16, activation='relu'))
model.add(layers.Dense(1, activation='sigmoid'))

model.compile(
    optimizer='rmsprop',
    loss='binary_crossentropy',
    metrics=['accuracy'])

x_val = x_train[:10000]
partial_x_train = x_train[10000:]

y_val = y_train[:10000]
partial_y_train = y_train[10000:]

history = model.fit(
    partial_x_train,
    partial_y_train,
    epochs=20,
    batch_size=512,
    validation_data=(
        x_val,
        y_val))


# Plotting the training and validation lose side by side
# history_dict = history.history
# loss_values = history_dict['loss']
# val_loss_values = history_dict['val_loss']
# acc_values = history_dict['acc']
# val_acc_values = history_dict['val_acc']
#
# epochs = range(1, len(history_dict['acc']) + 1)
#
# plt.figure()
# plt.plot(epochs, loss_values, 'bo', label='Training loss')
# plt.plot(epochs, val_loss_values, 'b', label='Validation loss')
# plt.title('Training and validation loss')
# plt.xlabel('Epochs')
# plt.ylabel('Loss')
# plt.legend()
#
# plt.figure()
# plt.plot(epochs, acc_values, 'bo', label='Training acc')
# plt.plot(epochs, val_acc_values, 'b', label='Validation acc')
# plt.title('Training and validation accuracy')
# plt.xlabel('Epochs')
# plt.ylabel('Accuracy')
# plt.legend()
# plt.show()

result = model.evaluate(x_test, y_test)
print(model.metrics_names)
print(result)