利用keras進行情感分析（四）

 TextBiRNN

# -*- coding: utf-8 -*-
# @Time    : 2019/7/4 9:39
# @Author  : hejipei
# @File    : keras_sentiment_TextBiRNN.py
""" """
# coding=utf-8

from keras import Input, Model
from keras.layers import Embedding, Dense, Dropout, Bidirectional, CuDNNLSTM


class TextBiRNN(object):
    def __init__(self, maxlen, max_features, embedding_dims,
                 class_num=1,
                 last_activation='sigmoid'):
        self.maxlen = maxlen
        self.max_features = max_features
        self.embedding_dims = embedding_dims
        self.class_num = class_num
        self.last_activation = last_activation

    def get_model(self):
        input = Input((self.maxlen,))

        embedding = Embedding(self.max_features, self.embedding_dims, input_length=self.maxlen)(input)
        x = Bidirectional(CuDNNLSTM(128))(embedding)  # LSTM or GRU

        output = Dense(self.class_num, activation=self.last_activation)(x)
        model = Model(inputs=input, outputs=output)
        return model


from keras.callbacks import EarlyStopping
from keras.datasets import imdb
from keras.preprocessing import sequence

# from text_birnn import TextBiRNN

max_features = 5000
maxlen = 400
batch_size = 32
embedding_dims = 50
epochs = 1

print('Loading data...')
(x_train, y_train), (x_test, y_test) = imdb.load_data(num_words=max_features)
print(len(x_train), 'train sequences')
print(len(x_test), 'test sequences')

print('Pad sequences (samples x time)...')
x_train = sequence.pad_sequences(x_train, maxlen=maxlen)
x_test = sequence.pad_sequences(x_test, maxlen=maxlen)
print('x_train shape:', x_train.shape)
print('x_test shape:', x_test.shape)

print('Build model...')
model = TextBiRNN(maxlen, max_features, embedding_dims).get_model()
model.compile('adam', 'binary_crossentropy', metrics=['accuracy'])

print('Train...')
early_stopping = EarlyStopping(monitor='val_acc', patience=3, mode='max')
model.fit(x_train, y_train,
          batch_size=batch_size,
          epochs=epochs,
          callbacks=[early_stopping],
          validation_data=(x_test, y_test))

print('Test...')
result = model.predict(x_test)

TextCNN

# -*- coding: utf-8 -*-
# @Time    : 2019/7/4 9:41
# @Author  : hejipei
# @File    : keras_sentiment_TextCNN.py
""" """
from keras import Input, Model
from keras.layers import Embedding, Dense, Conv1D, GlobalMaxPooling1D, Concatenate, Dropout


class TextCNN(object):
    def __init__(self, maxlen, max_features, embedding_dims,
                 class_num=1,
                 last_activation='sigmoid'):
        self.maxlen = maxlen
        self.max_features = max_features
        self.embedding_dims = embedding_dims
        self.class_num = class_num
        self.last_activation = last_activation

    def get_model(self):
        input = Input((self.maxlen,))

        # Embedding part can try multichannel as same as origin paper
        embedding = Embedding(self.max_features, self.embedding_dims, input_length=self.maxlen)(input)
        convs = []
        for kernel_size in [3, 4, 5]:
            c = Conv1D(128, kernel_size, activation='relu')(embedding)
            c = GlobalMaxPooling1D()(c)
            convs.append(c)
        x = Concatenate()(convs)

        output = Dense(self.class_num, activation=self.last_activation)(x)
        model = Model(inputs=input, outputs=output)
        return model


from keras.callbacks import EarlyStopping
from keras.datasets import imdb
from keras.preprocessing import sequence

# from text_cnn import TextCNN

max_features = 5000
maxlen = 400
batch_size = 32
embedding_dims = 50
epochs = 1

print('Loading data...')
(x_train, y_train), (x_test, y_test) = imdb.load_data(num_words=max_features)
print(len(x_train), 'train sequences')
print(len(x_test), 'test sequences')

print('Pad sequences (samples x time)...')
x_train = sequence.pad_sequences(x_train, maxlen=maxlen)
x_test = sequence.pad_sequences(x_test, maxlen=maxlen)
print('x_train shape:', x_train.shape)
print('x_test shape:', x_test.shape)

print('Build model...')
model = TextCNN(maxlen, max_features, embedding_dims).get_model()
model.compile('adam', 'binary_crossentropy', metrics=['accuracy'])

print('Train...')
early_stopping = EarlyStopping(monitor='val_acc', patience=3, mode='max')
model.fit4(x_train, y_train,
          batch_size=batch_size,
          epochs=epochs,
          callbacks=[early_stopping],
          validation_data=(x_test, y_test))

print('Test...')
result = model.predict(x_test)