demo49.py

from keras.datasets import reuters
import numpy as np

(train_data, train_labels), (test_data, test_labels) = reuters.load_data(num_words=10000)
print(len(train_data), len(test_data))
word_index = reuters.get_word_index()
reverse_word_index = dict([(v, k) for k, v in word_index.items()])
print(np.unique(train_labels))
print(train_labels[:5])
for k in range(5):
    news = ' '.join([reverse_word_index.get(i - 3, '?') for i in train_data[k]])
    print(news)


def vectorize_sequence(sequences, dimension=10000):
    results = np.zeros((len(sequences), dimension))
    for i, sequence in enumerate(sequences):
        results[i, sequence] = 1.
    return results


x_train = vectorize_sequence(train_data)
x_test = vectorize_sequence(test_data)


def to_one_hot(labels, dimension=46):
    results = np.zeros((len(labels), dimension))
    for i, label in enumerate(labels):
        results[i, label] = 1
    return results


one_hot_train_labels = to_one_hot(train_labels)
one_hot_test_labels = to_one_hot(test_labels)
print(one_hot_train_labels[:5])

from keras import models, layers

model = models.Sequential()
model.add(layers.Dense(64, activation='relu', input_shape=(10000,)))
model.add(layers.Dense(64, activation='relu'))
model.add(layers.Dense(46, activation='softmax'))
model.compile(optimizer='rmsprop', loss='categorical_crossentropy', metrics=['accuracy'])
model.summary()