from keras.datasets import reuters
(train_data, train_labels), (test_data, test_labels) = reuters.load_data(num_words = 100000)
print(train_data.shape)
print(train_labels.shape)
print(test_data.shape)
print(test_labels.shape)
word_to_index = reuters.get_word_index()
print(len(word_to_index))
index_to_word = dict([(value, key) for (key, value) in word_to_index.items()])
encoded_article = train_data[0]
decoded_article = ' '.join([index_to_word.get(i - 3, '?') for i in encoded_article])
print(encoded_article)
print(decoded_article)
# 0: padding
# 1: start of sequence
# 2: unknown
'''Trains and evaluate a simple MLP
on the Reuters newswire topic classification task.
'''
from __future__ import print_function
import numpy as np
import keras
from keras.datasets import reuters
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation
from keras.preprocessing.text import Tokenizer
max_words = 1000
batch_size = 32
epochs = 5
print('Loading data...')
(x_train, y_train), (x_test, y_test) = reuters.load_data(num_words=max_words,
test_split=0.2)
print(len(x_train), 'train sequences')
print(len(x_test), 'test sequences')
num_classes = np.max(y_train) + 1
print(num_classes, 'classes')
print('Vectorizing sequence data...')
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')
print('x_train shape:', x_train.shape)
print('x_test shape:', x_test.shape)
print('Convert class vector to binary class matrix '
'(for use with categorical_crossentropy)')
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)
print('y_train shape:', y_train.shape)
print('y_test shape:', y_test.shape)
print(x_train[0])
print('Building model...')
model = Sequential()
model.add(Dense(512, input_shape=(max_words,)))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes))
model.add(Activation('softmax'))
model.summary()
model.compile(loss='categorical_crossentropy',
optimizer='adam',
metrics=['accuracy'])
history = model.fit(x_train, y_train,
batch_size=batch_size,
epochs=epochs,
verbose=1,
validation_split=0.1)
score = model.evaluate(x_test, y_test,
batch_size=batch_size, verbose=1)
print('Test score:', score[0])
print('Test accuracy:', score[1])