版权声明:本文为博主原创文章,未经博主允许不得转载。 https://blog.csdn.net/shenziheng1/article/details/84108617
open resource :deep learning with python (keras)
# 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()
总结:
1. 好奇NLP-新闻内容识别与自主分发的过程,就实现了一下。实际过程中要比这个复杂的多。应该将一个新闻识别出多个标签,然后根据用户画像可以实现新闻的智能/精准推荐。这也是推荐算法的核心技术。
2. 这个项目/实验只是为了熟悉一下keras框架,精度不高,也没有优化NN结构,所以不用纠结。