import numpy as np
from gensim.models.word2vec import Word2Vec
from gensim.corpora.dictionary import Dictionary
from gensim import models
import pandas as pd
import jieba
import logging
import numpy as np
import re
from gensim.models.word2vec import Word2Vec
from gensim.corpora.dictionary import Dictionary
from gensim import models
from sklearn.model_selection import train_test_split
from keras import Sequential
from keras.preprocessing.sequence import pad_sequences
from keras.layers import Bidirectional,LSTM,Dense,Embedding,Dropout,Activation,Softmax
from sklearn.model_selection import train_test_split
from keras.utils import np_utils
def read_data(data_path):
senlist = []
labellist = []
with open(data_path, "r",encoding='utf-8',errors='ignore') as f:
for data in f.readlines():
data = data.strip()
label=data[0]
sen = data[2:]
if sen != "" and (label =="0" or label=="1" ) :
senlist.append(sen)
labellist.append(label)
else:
pass
assert(len(senlist) == len(labellist))
return senlist ,labellist
#训练模型(获得word2vec.model的word2vec训练模型)
def train_word2vec(sentences,save_path):
sentences_seg = []
sen_str = "\n".join(sentences) #以\n为连接符将sentences连接成一个字符串
res = jieba.lcut(sen_str)
seg_str = " ".join(res)
sen_list = seg_str.split("\n")
for i in sen_list:
sentences_seg.append(i.split())
print("开始训练词向量")
# logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s', level=logging.INFO)
model = Word2Vec(sentences_seg,
size=100, # 词向量维度
min_count=5, # 词频阈值 #词的相似度
window=5) # 窗口大小
model.save(save_path)
return model
def generate_id2wec(model):
gensim_dict = Dictionary()
gensim_dict.doc2bow(model.wv.vocab.keys(), allow_update=True)
w2id = {v: k + 1 for k, v in gensim_dict.items()} # 词语的索引，从1开始编号
w2vec = {word: model[word] for word in w2id.keys()} # 词语的词向量
n_vocabs = len(w2id) + 1
embedding_weights = np.zeros((n_vocabs, 100))
for w, index in w2id.items(): # 从索引为1的词语开始，用词向量填充矩阵
embedding_weights[index, :] = w2vec[w]
return w2id,embedding_weights
def text_to_array(w2index, senlist): # 文本转为索引数字模式
sentences_array = []
for sen in senlist:
new_sen = [ w2index.get(word,0) for word in sen] # 单词转索引数字
sentences_array.append(new_sen)
return np.array(sentences_array)
def prepare_data(w2id,sentences,labels,max_len=200):
X_train, X_val, y_train, y_val = train_test_split(sentences,labels, test_size=0.2)
X_train = text_to_array(w2id, X_train)
X_val = text_to_array(w2id, X_val)
X_train = pad_sequences(X_train, maxlen=max_len)
X_val = pad_sequences(X_val, maxlen=max_len)
return np.array(X_train), np_utils.to_categorical(y_train) ,np.array(X_val), np_utils.to_categorical(y_val)
# data = pd.read_csv("weibo.csv") # 读取csv文件
# sentences= data.review.values # 变成list #微博的句
# label = data.label.values# 微博的情感的结果 （用来训练用的）
# sentences=[]
# for text in sents:
# print(text)
# pre = re.compile('@(.*?):')
# s1 = ''.join(pre.findall(text))#以空格的方式连接符合的字符串
# sentences.append(s1)
# print(sentences)
# xxr begin
sentences,labels = read_data("weibo.csv")
# print(sentences)
# print(labels[-100:])
# model = train_word2vec(sentences,'word2vec.model')
# model.save("model")
#xxr end
model = Word2Vec.load("model")
w2id,embedding_weights = generate_id2wec(model)
# #打印结果
# for key in w2id:
# print(str(key)+':'+str(w2id[key]))
# print("-------------------------------------------------------------------")
# print(embedding_weights)
#存储生成的"embedding_weights.npy"np array
# np.save("embedding_weights.npy",embedding_weights)
embedding_weights=np.load("embedding_weights.npy")
# print(embedding_weights)
# # 将获取的字典 存在w2id.txt里面
# f = open("w2id.txt", 'w',encoding='utf-8')
# f.write(str(w2id))
# f.close()
## 读取字典
f = open("w2id.txt", 'r',encoding='utf-8')
w2id = eval(f.read())
f.close()
# for key in w2id:
# print(str(key)+':'+str(w2id[key]))
x_train,y_trian, x_val , y_val = prepare_data(w2id,sentences,labels,200)
class Sentiment:
def __init__(self,w2id,embedding_weights,Embedding_dim,maxlen,labels_category):
self.Embedding_dim = Embedding_dim
self.embedding_weights = embedding_weights
self.vocab = w2id
self.labels_category = labels_category
self.maxlen = maxlen
self.model = self.build_model()
def build_model(self):
model = Sequential()
#input dim(140,100)
model.add(Embedding(output_dim = self.Embedding_dim,
input_dim=len(self.vocab)+1,
weights=[self.embedding_weights],
input_length=self.maxlen))
model.add(Bidirectional(LSTM(50),merge_mode='concat'))
model.add(Dropout(0.5))
model.add(Dense(self.labels_category))
model.add(Activation('softmax'))
model.compile(loss='categorical_crossentropy',
optimizer='adam',
metrics=['accuracy'])
model.summary()
return model
def train(self,X_train, y_train,X_test, y_test,n_epoch=5 ):
self.model.fit(X_train, y_train, batch_size=32, epochs=n_epoch,
validation_data=(X_test, y_test))
self.model.save('sentiment.h5')
def predict(self,model_path,new_sen):
model = self.model
model.load_weights(model_path)
new_sen_list = jieba.lcut(new_sen)
sen2id =[ self.vocab.get(word,0) for word in new_sen_list]
sen_input = pad_sequences([sen2id], maxlen=self.maxlen)
res = model.predict(sen_input)[0]
return np.argmax(res)
## 训练
senti = Sentiment(w2id,embedding_weights,100,200,2)
# senti.train(x_train,y_trian, x_val ,y_val,1)
#预测
label_dic = {0:"消极的",1:"积极的"}
sen_new = "现如今的公司能够做成这样已经很不错了，微订点单网站的信息更新很及时，内容来源很真实"
pre = senti.predict("./sentiment.h5",sen_new)
print("'{}'的情感是:\n{}".format(sen_new,label_dic.get(pre)))
情感分析
修改：
import numpy as np
from gensim.models.word2vec import Word2Vec
from gensim.corpora.dictionary import Dictionary
from gensim import models
import pandas as pd
import jieba
import logging
import numpy as np
import re
from gensim.models.word2vec import Word2Vec
from gensim.corpora.dictionary import Dictionary
from gensim import models
from sklearn.model_selection import train_test_split
from keras import Sequential
from keras.preprocessing.sequence import pad_sequences
from keras.layers import Bidirectional,LSTM,Dense,Embedding,Dropout,Activation,Softmax
from sklearn.model_selection import train_test_split
from keras.utils import np_utils
def read_data(data_path):
senlist = []
labellist = []
with open(data_path, "r",encoding='utf-8',errors='ignore') as f:
for data in f.readlines():
data = data.strip()
label=data[0]
sen = data[2:]
if sen != "" and (label =="0" or label=="1" ) :
senlist.append(sen)
labellist.append(label)
else:
pass
assert(len(senlist) == len(labellist))
return senlist ,labellist
#训练模型(获得word2vec.model的word2vec训练模型)
def train_word2vec(sentences,save_path):
sentences_seg = []
sen_str = "\n".join(sentences) #以\n为连接符将sentences连接成一个字符串
res = jieba.lcut(sen_str)
seg_str = " ".join(res)
sen_list = seg_str.split("\n")
for i in sen_list:
sentences_seg.append(i.split())
print("开始训练词向量")
# logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s', level=logging.INFO)
model = Word2Vec(sentences_seg,
size=100, # 词向量维度
min_count=5, # 词频阈值 #词的相似度
window=5) # 窗口大小
model.save(save_path)
return model
def generate_id2wec(model):
gensim_dict = Dictionary()
gensim_dict.doc2bow(model.wv.vocab.keys(), allow_update=True)
w2id = {v: k + 1 for k, v in gensim_dict.items()} # 词语的索引，从1开始编号
w2vec = {word: model[word] for word in w2id.keys()} # 词语的词向量
n_vocabs = len(w2id) + 1
embedding_weights = np.zeros((n_vocabs, 100))
for w, index in w2id.items(): # 从索引为1的词语开始，用词向量填充矩阵
embedding_weights[index, :] = w2vec[w]
return w2id,embedding_weights
def text_to_array(w2index, senlist): # 文本转为索引数字模式
sentences_array = []
for sen in senlist:
new_sen = [ w2index.get(word,0) for word in sen] # 单词转索引数字
sentences_array.append(new_sen)
return np.array(sentences_array)
def prepare_data(w2id,sentences,labels,max_len=200):
X_train, X_val, y_train, y_val = train_test_split(sentences,labels, test_size=0.2)
X_train = text_to_array(w2id, X_train)
X_val = text_to_array(w2id, X_val)
X_train = pad_sequences(X_train, maxlen=max_len)
X_val = pad_sequences(X_val, maxlen=max_len)
return np.array(X_train), np_utils.to_categorical(y_train) ,np.array(X_val), np_utils.to_categorical(y_val)
# xxr begin
sentences,labels = read_data("weibo.csv")
# print(sentences)
# print(labels[-100:])
# model = train_word2vec(sentences,'word2vec.model')
# model.save("model")
#xxr end
model = Word2Vec.load("model")
w2id,embedding_weights = generate_id2wec(model)
# #打印结果
# for key in w2id:
# print(str(key)+':'+str(w2id[key]))
# print("-------------------------------------------------------------------")
# print(embedding_weights)
#存储生成的"embedding_weights.npy"np array
# np.save("embedding_weights.npy",embedding_weights)
embedding_weights=np.load("embedding_weights.npy")
# print(embedding_weights)
# # 将获取的字典 存在w2id.txt里面
# f = open("w2id.txt", 'w',encoding='utf-8')
# f.write(str(w2id))
# f.close()
## 读取字典
f = open("w2id.txt", 'r',encoding='utf-8')
w2id = eval(f.read())
f.close()
# for key in w2id:
# print(str(key)+':'+str(w2id[key]))
x_train,y_trian, x_val , y_val = prepare_data(w2id,sentences,labels,200)
class Sentiment:
def __init__(self,w2id,embedding_weights,Embedding_dim,maxlen,labels_category):
self.Embedding_dim = Embedding_dim
self.embedding_weights = embedding_weights
self.vocab = w2id
self.labels_category = labels_category
self.maxlen = maxlen
self.model = self.build_model()
def build_model(self):
model = Sequential()
#input dim(140,100)
model.add(Embedding(output_dim = self.Embedding_dim,
input_dim=len(self.vocab)+1,
weights=[self.embedding_weights],
input_length=self.maxlen))
model.add(Bidirectional(LSTM(50),merge_mode='concat'))
model.add(Dropout(0.5))
model.add(Dense(self.labels_category))
model.add(Activation('softmax'))
model.compile(loss='categorical_crossentropy',
optimizer='adam',
metrics=['accuracy'])
model.summary()
return model
def train(self,X_train, y_train,X_test, y_test,n_epoch=5 ):
self.model.fit(X_train, y_train, batch_size=32, epochs=n_epoch,
validation_data=(X_test, y_test))
self.model.save('sentiment.h5')
def predict(self,model_path,new_sen):
model = self.model
model.load_weights(model_path)
new_sen_list = jieba.lcut(new_sen)
sen2id =[ self.vocab.get(word,0) for word in new_sen_list]
sen_input = pad_sequences([sen2id], maxlen=self.maxlen)
res = model.predict(sen_input)[0]
return np.argmax(res)
## 训练
senti = Sentiment(w2id,embedding_weights,100,200,2)
# senti.train(x_train,y_trian, x_val ,y_val,1)
#预测
sumP=0
sumN=0
label_dic = {0:"消极的",1:"积极的"}
with open("source.csv", "r",encoding='utf-8',errors='ignore') as f:
for data in f.readlines():
data = data.strip()
pre = senti.predict("./sentiment.h5",data)
if(pre==0):
sumN+=1
else :
sumP+=1
print("'{}'的情感是:\n{}".format(data,label_dic.get(pre)))
print(str(sumP)+"hhhh"+str(sumN))
# print(data)
# print("----------------------------------------------")
# sen_new = "现如今的公司能够做成这样已经很不错了，微订点单网站的信息更新很及时，内容来源很真实"
# pre = senti.predict("./sentiment.h5",sen_new)
# print("'{}'的情感是:\n{}".format(sen_new,label_dic.get(pre)))
