def getLabelWeightOutputStr(labelWordWeightList):
'''
'''
resultStr = ''
for item in labelWordWeightList:
resultStr = resultStr + '(' + str(item[0]) + ',' + str(
item[1]) + ')' + ','
return resultStr
if __name__ == '__main__':
analysisPath = inout.getDataAnalysisPath('analysis.txt')
## 加载停用词列表
stopWordPath = inout.getResourcePath('stopWordList.txt')
stopWordList = inout.readListFromTxt(stopWordPath)
# 这地方加入临时逻辑，后面可以进行停用词合并
stopWordList = list(set(stopWordList))
## 加载关系字典
relationDic = persistent_relation_object.getRelationShipDic()
pd.set_option('display.width', 300)
np.set_printoptions(linewidth=300, suppress=True)
# corpusPath = inout.getDataOriginPath('special_corpus_copy.txt')
corpusPath = inout.getDataOriginPath('special_corpus.txt')
articleTime = mildTime
# finally:
# articleTime = mildTime
else:
articleTime = coldTime
weight = (articleTime - basicTime) / (systemTime - basicTime)
return weight
if __name__ == '__main__':
## 加载包含索引信息的句子到内存
# sentenceList,sentenceFeatureList = loadIndexSentenceList()
sentenceFilePath = inout.getDataAnalysisPath('sentenceList.txt')
sentenceList = inout.readListFromTxt(sentenceFilePath)
# for item in sentenceList:
# print item
# exit(0)
inFilePath = inout.getDataAnalysisPath('vote_classify_module_result_fnlp_150w-2100w.txt')
# inFilePath = '/data/wangtd/workspace/re/vote_classify_module_result_fnlp_150w-2100w.txt'
outFilePath = inout.getDataAnalysisPath('vote_relation_weight_result_fnlp_150w-2000w.txt')
# outFilePath = '/data/wangtd/workspace/re/vote_relation_weight_result_fnlp_150w-2000w.txt'
infoList = inout.readListFromTxt(inFilePath)
## 开始处理
if 'time' in lineList[3]:
if len(lineList[3].split('#INNER#')) == 2:
if lineList[3].split('#INNER#')[1] != '':
time = lineList[3].split('#INNER#')[1]
comSentence = time + '#INNER#' + sentenceStr
if nePairList:
sentenceFeatureList.append([nePairList, otherWordList])
sentenceList.append(comSentence)
return sentenceList, sentenceFeatureList
if __name__ == '__main__':
# 输出路径
outputPath = inout.getDataAnalysisPath(
'analysis_vote_sentence_fnlp_150w-2100w.txt')
# outputPath = inout.getDataAnalysisPath('analysis_vote_sentence_0615.txt')
# outputPath = inout.getDataAnalysisPath('analysis_test.txt')
## 配置
pd.set_option('display.width', 300)
np.set_printoptions(linewidth=300, suppress=True)
## 加载停用词列表
stopWordPath = inout.getResourcePath('stopWordList.txt')
stopWordList = inout.readListFromTxt(stopWordPath)
# 这地方加入临时逻辑，后面可以进行停用词合并
stopWordList = list(set(stopWordList))
## 加载关系字典
relationDic = persistent_relation_object.getRelationShipDic()
splitList[3]
# print resultStr
return resultStr
def handleSentenceTwo(sentenceTwo):
print sentenceTwo
sortedRelationList = eval(sentenceTwo)
print type(sortedRelationList)
print sortedRelationList
exit(0)
if __name__ == '__main__':
inFilePath = inout.getDataAnalysisPath(
'vote_relation_ordered_result_fnlp_150w-2000w.txt')
outFilePath = inout.getDataAnalysisPath(
'vote_relation_ordered_result_fnlp_150w-2000w_handled.txt')
infoList = inout.readListFromTxt(inFilePath)
print 'info list len:', len(infoList)
allSentenceList = []
itemSentenceList = []
for item in infoList:
item = item.strip()
if item != '':
# print item
itemSentenceList.append(item)
# -*- coding:utf-8 -*-
import pandas as pd
import numpy as np
from utils import inout
from utils.inout import printEscapeStr
from collections import OrderedDict
import time
import codecs
if __name__ == '__main__':
filePath = inout.getDataAnalysisPath('test.txt')
fr = codecs.open(filePath, 'rb')
while True:
line = fr.readline()
if line:
reTuple = eval(line.split('DIV')[1].split('INNER')[1])
print type(reTuple), reTuple, len(reTuple)
if len(reTuple) == 1:
print reTuple[0]
else:
break
def getSentenceStrList(sentenceIndexList, sentenceList):
'''
'''
outputStr = ''
for index in sentenceIndexList:
outputStr = outputStr + sentenceList[int(index)].strip() + '\n'
return outputStr
if __name__ == '__main__':
# inFilePath = inout.getDataAnalysisPath('vote_relation_weight_result_fnlp_150w-2000w.txt')
inFilePath = inout.getDataAnalysisPath('test.txt')
infoList = inout.readListFromTxt(inFilePath)
print '关系权重列表长度:', len(infoList)
outFilePath = inout.getDataAnalysisPath(
'map_vote_relation_ordered_result_fnlp_150w-2000w.txt')
sentenceFilePath = inout.getDataAnalysisPath('sentenceList.txt')
sentenceList = inout.readListFromTxt(sentenceFilePath)
print '句子列表长度:', len(sentenceList)
# 初始化字典
classifyDic = dict()
print '归类：'
for i in tqdm(range(len(infoList))):
resultStr = ''
for item in labelWordWeightList:
resultStr = resultStr + '(' + str(item[0]) + ',' + str(
item[1]) + ')' + ','
return resultStr
if __name__ == '__main__':
## 输入参数
n_cluster = 300
# n_cluster = 15000
corpusNum = 500
analysisPath = inout.getDataAnalysisPath('analysis_cluster_sentence.txt')
## 配置
pd.set_option('display.width', 300)
np.set_printoptions(linewidth=300, suppress=True)
## 加载停用词列表
stopWordPath = inout.getResourcePath('stopWordList.txt')
stopWordList = inout.readListFromTxt(stopWordPath)
# 这地方加入临时逻辑，后面可以进行停用词合并
stopWordList = list(set(stopWordList))
## 加载关系字典
relationDic = persistent_relation_object.getRelationShipDic()
## 作为模块的入口，加载对象