open resource ：deep learning with python (keras)

open code: https://github.com/fchollet/deep-learning-with-python-notebooks/blob/master/3.6-classifying-newswires.ipynb

# single-label & multi-classifications
from keras.datasets import reuters
from keras import models
from keras import layers

import numpy as np
import matplotlib.pyplot as plt


(train_data, train_labels), (test_data, test_labels) = \
    reuters.load_data(num_words=10000)
    
# translating index-news to synax-news
word_index = reuters.get_word_index()
reverse_word_index = \
    dict([(value,key) for (key, value) in word_index.items()])
decoded_news = \
    ' '.join([reverse_word_index.get(i-3,'?') for i in train_data[0]])

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

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

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

one_hot_train_labels = to_one_hot(train_labels)
one_hot_test_labels  = to_one_hot(test_labels)
"""
the one-hot code is equal to:
    from keras.utils.np_utils import to_categorical
    one_hot_train_labels = to_categorical(train_labels)
    one_hot_test_labels  = to_categorical(test_labels)
"""

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'])

x_val = x_train[:1000]
partial_x_train = x_train[1000:]

y_val = one_hot_train_labels[:1000]
partial_y_train = one_hot_train_labels[1000:]

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

evaluate = model.evaluate(x_test, one_hot_test_labels)
output = model.predict(x_test)

###########################################################

loss = history.history['loss']
val_loss = history.history['val_loss']
epochs = range(1, len(loss)+1)

plt.plot(epochs, loss, 'bo', label = 'Training loss')
plt.plot(epochs, val_loss, 'r', label = 'Validation loss')
plt.title('Training and Validation loss')
plt.xlabel('Epochs')
plt.ylabel('Loss')
plt.legend()
plt.show()

plt.clf()

acc = history.history['acc']
val_acc = history.history['val_acc']

plt.plot(epochs, acc, 'bo', label = 'Training accuracy')
plt.plot(epochs, val_acc, 'r', label = 'Validation accuracy')
plt.title('Training and Validation accuracy')
plt.xlabel('Epochs')
plt.ylabel('Accuracy')
plt.legend()
plt.show()
 

總結：

1. 好奇NLP-新聞內容識別與自主分發的過程，就實現了一下。實際過程中要比這個複雜的多。應該將一個新聞識別出多個標籤，然後根據使用者畫像可以實現新聞的智慧/精準推薦。這也是推薦演算法的核心技術。

2. 這個專案/實驗只是為了熟悉一下keras框架，精度不高，也沒有優化NN結構，所以不用糾結。