# -*- coding:utf-8 -*-'''
word embedding测试
在GTX960上，18s一轮
经过30轮迭代，训练集准确率为98.41%，测试集准确率为89.03%
Dropout不能用太多，否则信息损失太严重
'''import numpy as npimport pandas as pdimport jieba
pos = pd.read_excel('pos.xls', header=None)
pos['label'] = 1neg = pd.read_excel('neg.xls', header=None)
neg['label'] = 0all_ = pos.append(neg, ignore_index=True)
all_['words'] = all_[0].apply(lambda s: list(jieba.cut(s))) #调用结巴分词maxlen = 100 #截断词数min_count = 5 #出现次数少于该值的词扔掉。这是最简单的降维方法content = []for i in all_['words']:
content.extend(i)
abc = pd.Series(content).value_counts()
abc = abc[abc >= min_count]
abc[:] = range(1, len(abc)+1)
abc[''] = 0 #添加空字符串用来补全word_set = set(abc.index)def doc2num(s, maxlen):
s = [i for i in s if i in word_set]
s = s[:maxlen] + ['']*max(0, maxlen-len(s)) return list(abc[s])
all_['doc2num'] = all_['words'].apply(lambda s: doc2num(s, maxlen))#手动打乱数据idx = range(len(all_))
np.random.shuffle(idx)
all_ = all_.loc[idx]#按keras的输入要求来生成数据x = np.array(list(all_['doc2num']))
y = np.array(list(all_['label']))
y = y.reshape((-1,1)) #调整标签形状from keras.models import Sequentialfrom keras.layers import Dense, Activation, Dropout, Embeddingfrom keras.layers import LSTM#建立模型model = Sequential()
model.add(Embedding(len(abc), 256, input_length=maxlen))
model.add(LSTM(128))
model.add(Dropout(0.5))
model.add(Dense(1))
model.add(Activation('sigmoid'))
model.compile(loss='binary_crossentropy',
optimizer='adam',
metrics=['accuracy'])
batch_size = 128train_num = 15000model.fit(x[:train_num], y[:train_num], batch_size = batch_size, nb_epoch=30)
model.evaluate(x[train_num:], y[train_num:], batch_size = batch_size)def predict_one(s): #单个句子的预测函数
s = np.array(doc2num(list(jieba.cut(s)), maxlen))
s = s.reshape((1, s.shape[0])) return model.predict_classes(s, verbose=0)[0][0]
