keras探索：nlp-电影评论分类

open resource ：deep learning with python (keras)

opencode ：https://github.com/fchollet/deep-learning-with-python-notebooks/blob/master/3.5-classifying-movie-reviews.ipynb

from keras.datasets import imdb
import matplotlib.pyplot as plt
import numpy as np

from keras import models
from keras import layers
from keras import optimizers


def vectorize_sequences(sequences, dimension=4000):
    # Create an all-zero matrix of shape (len(sequences), dimension)
    results = np.zeros((len(sequences), dimension), dtype = int)
    for i, sequence in enumerate(sequences):
        results[i, sequence] = 1  # set specific indices of results[i] to 1s
    return results
    
    
# saving the most common 10000 words
(train_data, train_labels),(test_data, test_labels) \
    = imdb.load_data(num_words =4000)

# word_index is a dictionary mapping words to an integer index
word_index = imdb.get_word_index()
# We reverse it, mapping integer indices to words
reverse_word_index = dict([(value, key) for (key, value) in word_index.items()])
# We decode the review; note that our indices were offset by 3
# because 0, 1 and 2 are reserved indices for "padding", "start of sequence", and "unknown".
# this is just an example about review-1
decoded_review = ' '.join([reverse_word_index.get(i-3, '?') for i in train_data[0]])


# Our vectorized training data : 25000
x_train = vectorize_sequences(train_data)
# Our vectorized test data : 25000
x_test = vectorize_sequences(test_data)


# Our vectorized labels
y_train = np.asarray(train_labels).astype('float32')
y_test = np.asarray(test_labels).astype('float32')


model = models.Sequential()
model.add(layers.Dense(64, activation='relu', input_shape=(4000,)))
model.add(layers.Dense(32, activation='relu'))
model.add(layers.Dense(1, activation='sigmoid'))


model.compile(optimizer=optimizers.RMSprop(lr=0.001),
              loss='binary_crossentropy',
              metrics=['acc'])

#v validation & training data
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))


##########################################################
acc = history.history['acc']
val_acc = history.history['val_acc']
loss = history.history['loss']
val_loss = history.history['val_loss']

epochs = range(1, len(acc) + 1)

# "bo" is for "blue dot"
plt.plot(epochs, loss, 'bo', label='Training loss')
# b is for "solid blue line"
plt.plot(epochs, val_loss, 'b', label='Validation loss')
plt.title('Training and validation loss')
plt.xlabel('Epochs')
plt.ylabel('Loss')
plt.legend()

plt.show()


plt.clf()   # clear figure
acc_values = history.history['acc']
val_acc_values = history.history['val_acc']

plt.plot(epochs, acc, 'bo', label='Training acc')
plt.plot(epochs, val_acc, 'b', label='Validation acc')
plt.title('Training and validation accuracy')
plt.xlabel('Epochs')
plt.ylabel('Loss')
plt.legend()

plt.show()

predit = model.predict(x_test)
output = model.evaluate(x_test, y_test)

总结：

1. 神经网络在进行自然语言的张量处理过程中，需要首先讲自然语言符号变成向量，然后构造神经网络模型即可。

2. NLP-Vectors一般需要采用‘字典（通过统计词的频率）’进行数值化。这里涉及到了编码问题。如果采用one-hot编码，即使采用最常出现的前10000个单词也需要非常大的内存消耗。所以如果出现‘Memory Error’不用担心，降低num_words就好了。当然精度也会下降。

3. 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。

keras探索：nlp-电影评论分类

猜你喜欢