def train_model(neg_path, pos_path):
neg_path = os.path.abspath(os.path.join(os.getcwd(), 'neg.txt'))
pos_path = os.path.abspath(os.path.join(os.getcwd(), 'pos.txt'))
mod_path = os.path.abspath(os.path.join(os.getcwd(), 'sentiment.marshal'))
sentiment.train(neg_path, pos_path)
sentiment.save(mod_path)
return mod_path
def post(self, request):
print(request.POST)
cand_id = -1
senti = -1
if 'submit' in request.POST:
for k in request.POST.keys():
if k.startswith("group"):
try:
cand_id = int(k[5:])
senti = int(request.POST.get(k))
except ValueError:
cand_id = -1
senti = -1
if cand_id > 0:
self.cursor.execute(
self.select_candidate_by_id.format(cand_id))
cand_weibo = self.cursor.fetchone()
if cand_weibo and senti >= 0:
weibo_url = cand_weibo[1]
weibo_content = cand_weibo[2]
weibo_wb_from = cand_weibo[3]
weibo_sentiment = senti
self.cursor.execute(
self.insert_into_weibo.format(weibo_url, weibo_content,
weibo_wb_from,
weibo_sentiment))
self.cursor.execute(self.delete_candidate.format(cand_id))
self.db.commit()
return redirect('index')
elif 'refresh' in request.POST:
print('refresh')
with open('neg_updated.txt', 'w', encoding='utf-8') as neg_writer:
with open('neg.txt', 'r', encoding='utf-8') as neg_reader:
while True:
line = neg_reader.readline()
if not line:
break
line = line.strip()
neg_writer.write(line + '\n')
self.cursor.execute(self.select_all_weibos.format(0))
neg_results = self.cursor.fetchall()
for neg_result in neg_results:
neg_writer.write(neg_result[2].strip() + '\n')
with open('pos_updated.txt', 'w', encoding='utf-8') as pos_writer:
with open('pos.txt', 'r', encoding='utf-8') as pos_reader:
while True:
line = pos_reader.readline()
if not line:
break
line = line.strip()
pos_writer.write(line + '\n')
self.cursor.execute(self.select_all_weibos.format(1))
pos_results = self.cursor.fetchall()
for pos_result in pos_results:
pos_writer.write(pos_result[2].strip() + '\n')
print("开始训练新模型...")
sentiment.train('neg_updated.txt', 'pos_updated.txt')
sentiment.save('sentiment.marshal')
print("训练完成！")
return redirect('index')
def train():
current_path = os.path.dirname(__file__)
neg = current_path + '\\snownlp\\sentiment\\neg.txt'
pos = current_path + '\\snownlp\\sentiment\\pos.txt'
parm = current_path + '\\snownlp\\sentiment\\sentiment.marshal'
sentiment.train(neg, pos)
sentiment.save(parm)
def save_train(request):
f = open(
'/Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/snownlp/sentiment/SGMW_pos.txt',
'w')
high_processeds = Comments.objects.filter(arti_score__gt=0.5, is_scored=1)
for i in high_processeds:
high_list = i.content
f.write('\n')
f.write(high_list)
f.close()
f = open(
'/Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/snownlp/sentiment/SGMW_neg.txt',
'w')
low_processeds = Comments.objects.filter(arti_score__lte=0.5, is_scored=1)
for i in low_processeds:
low_list = i.content
f.write('\n')
f.write(low_list)
f.close()
sentiment.train(
'/Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/snownlp/sentiment/SGMW_neg.txt',
'/Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/snownlp/sentiment/SGMW_pos.txt'
)
sentiment.save(
'/Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/snownlp/sentiment/SGMW_sentiment.marshal'
)
return JsonResponse({"msg": "success"})
def train():
time_str = (datetime.datetime.now().strftime('%Y%m%d %H%M%S')) #日期格式化
print("prepare...")
global start
start = time.time()
sentiment.train('target/neg.txt', 'target/pos.txt', printPer)
sentiment.save('target/sen %s.marshal' % time_str)
def train_and_test():
from snownlp import sentiment
print("start")
sentiment.train('eastmoney_neg.txt', 'eastmoney_pos.txt')
print("finish")
sentiment.save('sentiment.marshal')
sentiment_rating = SnowNLP("明天涨停").sentiments
print(sentiment_rating)
def selfTrainSentiment(infile):
sentiment.train("pos", "neg")
sentiment.save('sentfwhyj.marshal')
sentiments_list = sentiment_analysis(infile)
x = range(len(sentiments_list))
pl.plot(x, sentiments_list, 'b.')
pl.xlabel('sample')
pl.ylabel('score')
pl.show()
def trainSentimentCorpus(self, negPath, posPath, target_encoding):
"""训练Sentiment语料库"""
self.convertEncoding(negPath, target_encoding)
self.convertEncoding(posPath, target_encoding)
# pos_docs = codecs.open(posPath, 'r', 'utf-8').readlines()
sentiment.train(neg_file=negPath, pos_file=posPath)
path_name = 'sentiment_Jxl_line'
print u'数据训练完毕，即将保存{}.marshal文件'.format(path_name)
sentiment.save('{}.marshal'.format(path_name))
print u'保存完毕!'
def train_snowNLP(table):
filter_comment.filter_opppsive_comments(table)
neg_file = FILE_PATH + 'train_files/' + table + '_neg.txt'
pos_file = FILE_PATH + 'train_files/' + table + '_pos.txt'
get_sentiment_file(DATA_PATH + table + '/big_files/' + 'positive.txt',
pos_file)
get_sentiment_file(DATA_PATH + table + '/big_files/' + 'negative.txt',
neg_file)
file_path = 'F:/computer_science/python3/lib/site-packages/snownlp/sentiment/'
sentiment.train(neg_file, pos_file)
sentiment.save(file_path + table + '.marshal')
def train():
if 'raw_data.csv' in dirlist:
df = pd.read_csv('raw_data.csv')
else:
raise Exception('请先创建raw_data.csv文件')
df.fillna('nan')
commands = df.评论内容.dropna().tolist()
models(commands)
sentiment.train('neg.txt', 'pos.txt')
sentiment.save('mysentiment.marshal')
print('得到模型后需拷贝到snownlp的sentiment文件夹下\
并修改__init.py__的路径来加载新权重')
def train_model():
data= pd.read_csv(r"./Train/weibo_senti_100k/weibo_senti_100k.csv",header=0)
data = data.sample(frac = 1)
train = data.iloc[:110000,[0,1]]
test = data.iloc[110000:,[0,1]]
train_neg = train.iloc[:, 1][train.label == 0]
train_pos = train.iloc[:, 1][train.label == 1]
train_neg.to_csv(r"./Train/weibo_senti_100k/neg.csv", index=0, header=0)
train_pos.to_csv(r"./Train/weibo_senti_100k/pos.csv", index=0, header=0)
test.to_csv(r"./Train/weibo_senti_100k/test.csv",index=0,columns=['label','review'])
sentiment.train(r'./Train/weibo_senti_100k/neg.csv',r'./Train/weibo_senti_100k/pos.csv')
sentiment.save(r'C:/Users/RA1LGUN/Anaconda3/Lib/site-packages/snownlp/sentiment/newsentiment.marshal')
def train_model():
data = pd.read_csv(r"./DataSet.csv", header=0)
train = data.iloc[:40000, [1, 2]]
test = data.iloc[40000:, [1, 2]]
train_neg = train.iloc[:, 1][train.label == 0]
train_pos = train.iloc[:, 1][train.label == 1]
train_neg.to_csv(r"./neg.csv", index=0, header=0)
train_pos.to_csv(r"./pos.csv", index=0, header=0)
test.to_csv(r"./TestModel.csv", index=0, columns=['label', 'review'])
sentiment.train(r'./neg.csv', r'./pos.csv')
sentiment.save(
r'C:/ProgramData/Miniconda3/Lib/site-packages/snownlp/sentiment/sentiment.marshal'
)
def train():
pos = get_pos_reviews()
neg = get_neg_reviews()
pos_train, pos_test = split(pos)
write(pos_train, "./train/pos_train")
write(pos_test, "./train/pos_test")
neg_train, neg_test = split(neg)
write(neg_train, "./train/neg_train")
write(neg_test, "./train/neg_test")
sentiment.train("./train/neg_train", "./train/pos_train")
sentiment.save('./train/sentiment.marshal')
def train_sentiment(use_all_data=True):
"""
读取negative和positive来训练模型
use_all_data选择使用所有数据还是仅仅是训练集
:return:
"""
print 'train model'
if not use_all_data:
sentiment.train('../data/train_negative.txt', '../data/train_positive.txt')
sentiment.save('../data/train_impurity_classifier')
else:
sentiment.train('../data/clean_negative.txt', '../data/clean_positive.txt')
sentiment.save('../data/impurity_classifier')
def nlp(filepath, neg, pos):
text = pd.read_excel(filepath)
contents = text.iloc[:, 0]
contents_t = contents.values.tolist()
sentiment.train(neg, pos)
sent = [SnowNLP(i).sentiments for i in contents_t]
predict = []
# 大于0.5则输出1，小于0.5则输出-1
for i in sent:
if (i >= 0.5):
predict.append(1)
else:
predict.append(-1)
text['predict'] = predict
text.to_excel('G:\\content_data.xlsx')
return text
def trainEmotion():
fn = open('thuhole_ana/analysisExisted/neg.', 'a+', encoding='utf-8')
fp = open('thuhole_ana/analysisExisted/pos.', 'a+', encoding='utf-8')
f = csv.reader(
open('thuhole_ana/analysisExisted/备份.csv', 'r', encoding='utf-8'))
for i in f:
if i[1] == ' 0' or i[1] == ' -1':
fn.write(i[0].replace('\n', '') + '\n')
if i[1] == ' 1':
fp.write(i[0].replace('\n', '') + '\n')
fn.close()
fp.close()
sentiment.train('venv/Lib/site-packages/snownlp/sentiment/neg.txt',
'venv/Lib/site-packages/snownlp/sentiment/pos.txt')
sentiment.save(
'venv/Lib/site-packages/snownlp/sentiment/sentiment.marshal2')
def f():
# 目标模型路径
import os
data_path = os.path.join(os.path.dirname(os.path.abspath(__file__)),
'seg.marshal')
print("data_path:" + data_path)
# 训练
from snownlp import sentiment #加载情感分析模块
from datetime import datetime
startTime = datetime.now()
print(datetime.now().strftime("%X") + " 开始训练")
sentiment.train('neg.txt', 'pos.txt') #对语料库进行训练 可进一步构建语料库
sentiment.save(
data_path
) #这一步是对上一步的训练结果进行保存，如果以后语料库没有改变，下次不用再进行训练，直接使用就可以了，所以一定要保存，保存位置可以自己决定，但是要把`snownlp/seg/__init__.py`里的`data_path`也改成你保存的位置，不然下次使用还是默认的。
endTime = datetime.now()
runTime = endTime - startTime
print(datetime.now().strftime("%X") + " 训练完毕,耗时：" + str(runTime.seconds) +
"秒")
def SnowNLP_TRAIN(TrainPath):
# 0.指定训练模型的保持路径
pospath = "D:\\Users\\Musk18\\Desktop\\数据挖掘课设\\pos.txt"
negpath = "D:\\Users\\Musk18\\Desktop\\数据挖掘课设\\neg.txt"
sentimentpath = "F:/ProgramData/Anaconda3/envs/untitled2/Lib/site-packages/snownlp/sentiment/sentiment.marshal"
# 1.将爬取的影评按照打分，分为正负样本，并分别保存，正样本保存到pos.txt，负样本保存到neg.txt
posfile = open(pospath, 'w', encoding='utf-8')
negfile = open(negpath, 'w', encoding='utf-8')
df = pd.read_excel(TrainPath + '评分和影评.xls')
i = 0
for data in df['评分']:
if data >= 4:
posfile.write(str(df['评论'][i]) + '\n')
elif data <= 2:
negfile.write(str(df['评论'][i]) + '\n')
i = i + 1
# 2.利用snownlp训练新的模型
sentiment.train(negpath, pospath)
# 3.保存好新训练的模型
sentiment.save(sentimentpath)
print('训练完毕！模型已替换！')
def train_model(text_set,train_frequency):
'''
:param text_set: 文本集合
:param train_frequency: 训练次数
:return:
'''
# 情感模型训练，分值大于0.8判断为积极，分值小于0.3判断为消极
for i in range(1,train_frequency + 1):
print('开始第{}次训练'.format(i))
for text in text_set:
sub_text = ','.join(re.findall("([\u4E00-\u9FA5]+)", text))
socre = SnowNLP(sub_text)
if socre.sentiments > 0.8:
with open('pos.txt', mode='a', encoding='utf-8') as g:
g.writelines(sub_text + "\n")
elif socre.sentiments < 0.3:
with open('neg.txt', mode='a', encoding='utf-8') as f:
f.writelines(sub_text + "\n")
else:
pass
sentiment.train('neg.txt', 'pos.txt')
sentiment.save('sentiment.marshal')
def train_model():
#自行百度如何训练snownlp模型，实验室的同学请自己在实验室电脑里拿数据，github上没有
from snownlp import sentiment
sentiment.train('/home/hadoopnew/neg.txt', '/home/hadoopnew/pos.txt')
sentiment.save('sentiment.marshal_knee')
def train(path):
"""训练正向和负向情感数据集，并保存训练模型"""
sentiment.train(f'{path}/差评.csv', f'{path}/好评.csv')
sentiment.save('./sentiment.marshal')
def train_material():
sentiment.train('neg.txt', 'pos.txt')
sentiment.save('sentiment.marshal')
# coding: utf-8 from snownlp import SnowNLP,sentiment import os.path base = os.path.dirname(__file__) pos = os.path.join(base,'model/sentiment/pos.txt') neg = os.path.join(base,'model/sentiment/neg.txt') tagdest = os.path.join(base,'model/sentiment/sentiment.marshal') sentiment.train(neg,pos) sentiment.save(tagdest)
#-*-coding:utf-8-*-
from snownlp import sentiment
sentiment.train(
'neg.txt', 'pos.txt') #消极文本，积极文本 txt格式按行存储 记得修改txt编码为utf8，另存为时有选项
sentiment.save('my_sentiment.marshal') #生成训练文件
#训练好后把生成的文件放到下面文件夹里
#D:\Python2.7\Lib\site-packages\snownlp\sentiment
#然后修改D:\Python2.7\Lib\site-packages\snownlp\sentiment\__init__.py里的data_path
#mac里：
#/Library/Python/2.7/site-packages/snownlp/sentiment
from snownlp import SnowNLP
from snownlp import sentiment
import csv
f1 = open('./pos.txt', 'a+', encoding='utf-8') # 存放正面 名字也可自定义哦
f2 = open('./neg.txt', 'a+', encoding='utf-8') # 存放负面
with open('微博信息20191208-20200122.csv', 'r', encoding='utf-8') as f:
reader = csv.DictReader(f)
for i in reader:
mytxt = open('commentqinggan.txt', mode='a', encoding='utf-8')
s = SnowNLP(dict(i)['正文'])
if s.sentiments < 0.25:
f2.write(dict(i)['正文'])
f2.write('\n')
if s.sentiments > 0.8:
f1.write(dict(i)['正文'])
f1.write('\n')
print(dict(i)['正文'], s.sentiments, file=mytxt)
# 保存此次的训练模型
sentiment.train('neg.txt', 'pos.txt')
# 生成新的训练模型
sentiment.save('sentiment.marshal')
def train_my_data():
# 重新训练模型
sentiment.train(r'Data/Output/neg.txt', r'Data/Output/pos.txt')
# 保存好新训练的模型
sentiment.save(r'Data/Output/sentiment.marshal')
import pandas as pd
from snownlp import SnowNLP, sentiment
sentiment.train('E:\\data\\low.txt','E:\\data\\high.txt')
mix=pd.read_csv('E:\\data\\mix.csv',encoding='gbk')
mix=mix.dropna()
right=0
wrong=0
for i in mix.index:
txt=mix.loc[i,'txt']
fen=mix.loc[i,'fen']
s = SnowNLP(txt)
f=s.sentiments
print((f,fen))
if f>0.5 and fen>2.5 or f<0.5 and fen<2.5:
right += 1
else:
wrong += 1
print(right/(right+wrong))
def TrainAndSave(negfile, posfile):
sentiment.train(negfile, posfile)
sentiment.save('sentiment.marshal')
def train():
sentiment.train('F:/Anaconda/Lib/site-packages/snownlp/sentiment/neg.txt','F:/Anaconda/Lib/site-packages/snownlp/sentiment/pos.txt')
sentiment.save('F:/Anaconda/Lib/site-packages/snownlp/sentiment/sentiment2.marshal')
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Thu Jan 4 09:59:46 2018
@author: Ming JIN
"""
from snownlp import sentiment
sentiment.train('negative_dict.txt', 'positive_dict.txt')
sentiment.save('sentiment.marshal')
# 去除英文字符和数字
clean_txt=re.sub(r'[A-Za-z\d]*','',clean_txt)
# 对文本进行分词
clean_list=clean_txt.split('\n')
return clean_list
if __name__ == '__main__':
#####################################################################
print("正在加载训练集...")
# 必须传入positive.txt和negative.txt
sentiment.train('./../../Resources/sentiment_folders/hotel/positive.txt', './../../Resources/sentiment_folders/hotel/neg.txt') # 修改
sentiment.save('sentiment.marshal')
#############################################
# # 测试的json文件
# filename='./../../Resources/jsonfiles/ChnSentiCorp.json' # 修改
# type_list,content_list=file_op.readfile(filename)
###############################################
# 知乎的评论内容作为测试集
comment_file='./../../Resources/CutWordPath/sentiment_comment.txt'
content_list=Read_comment_file(comment_file)
###################################################
# 进行snownlp情感分析
sentences,sentences_score=sentiment_snownlp(content_list)
import sys
import pandas as pd #加载pandas
from snownlp import sentiment #加载情感分析模块
from snownlp import SnowNLP
text = pd.read_excel(u'D:/自然语言处理/川大相关微博内容.xlsx', header=0) # 读取文本数据
text0 = text.iloc[:, 0] # 提取所有数据
text1 = [i.decode('utf-8') for i in text0] # 上一步提取数据不是字符而是object，所以在这一步进行转码为字符
#对语料库进行训练，把路径改成相应的位置
sentiment.train('D:/Anaconda3/Lib/site-packages/snownlp/sentiment/neg.txt',
'D:/Anaconda3/Lib/site-packages/snownlp/sentiment/pos.txt')
#这一步是对上一步的训练结果进行保存，如果以后语料库没有改变，下次不用再进行训练
sentiment.save('D:/pyscript/sentiment.marshal')
senti = [SnowNLP(i).sentiments for i in text1] #遍历每条评论进行预测
newsenti = []
for i in senti:
if (i >= 0.6):
newsenti.append(1)
else:
newsenti.append(-1)
text[
'predict'] = newsenti #将新的预测标签增加为text的某一列，所以现在text的第0列为评论文本，第1列为实际标签，第2列为预测标签
counts = 0
for j in range(len(text.iloc[:, 0])): #遍历所有标签，将预测标签和实际标签进行比较，相同则判断正确。
if text.iloc[j, 2] == text.iloc[j, 1]:
counts += 1
print("准确率为:%f", (float(counts) / float(len(text)))) #输出本次预测的准确率
