)
jieba.load_userdict(
"E:\postgraduate\\no_space_environment\category\pycharm\pycharm_file_location\\thesis\新闻文本处理\论文词典法CSDN\Sentiment_dict\degree_dict\inverse.txt"
)
jieba.load_userdict(
"E:\postgraduate\\no_space_environment\category\pycharm\pycharm_file_location\\thesis\新闻文本处理\论文词典法CSDN\Sentiment_dict\emotion_dict\\stop_words.txt"
)
jieba.load_userdict(
"E:\postgraduate\\no_space_environment\category\pycharm\pycharm_file_location\\thesis\新闻文本处理\论文词典法CSDN\Sentiment_dict\my_dict\\my_words.txt"
)
# 1.读取情感词典和待处理文件
# 情感词典
stopdict = tp.read_lines(
'E:\postgraduate\\no_space_environment\category\pycharm\pycharm_file_location\\thesis\新闻文本处理\论文词典法CSDN\Sentiment_dict\emotion_dict\stop_words.txt'
)
posdict = tp.read_lines(
"E:\postgraduate\\no_space_environment\category\pycharm\pycharm_file_location\\thesis\新闻文本处理\论文词典法CSDN\Sentiment_dict\emotion_dict\pos_all_dict.txt"
)
negdict = tp.read_lines(
"E:\postgraduate\\no_space_environment\category\pycharm\pycharm_file_location\\thesis\新闻文本处理\论文词典法CSDN\Sentiment_dict\emotion_dict\\neg_all_dict.txt"
)
# 程度副词词典
mostdict = tp.read_lines(
'E:\postgraduate\\no_space_environment\category\pycharm\pycharm_file_location\\thesis\新闻文本处理\论文词典法CSDN\Sentiment_dict\degree_dict\most.txt'
) # 权值为2.5
verydict = tp.read_lines(
'E:\postgraduate\\no_space_environment\category\pycharm\pycharm_file_location\\thesis\新闻文本处理\论文词典法CSDN\Sentiment_dict\degree_dict\\very.txt'
) # 权值为2
moredict = tp.read_lines(
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
import text_process as tp
import numpy as np
import pandas as pd
# 1.读取情感词典和待处理文件
# 情感词典
posdict = tp.read_lines("./emotion_dict/pos_all_dict.txt")
negdict = tp.read_lines("./emotion_dict/neg_all_dict.txt")
# 程度副词词典
mostdict = tp.read_lines('./degree_dict/most.txt') # 权值为2
verydict = tp.read_lines('./degree_dict/very.txt') # 权值为1.5
moredict = tp.read_lines('./degree_dict/more.txt') # 权值为1.25
ishdict = tp.read_lines('./degree_dict/ish.txt') # 权值为0.5
insufficientdict = tp.read_lines('./degree_dict/insufficiently.txt') # 权值为0.25
inversedict = tp.read_lines('./degree_dict/inverse.txt') # 权值为-1
# 情感级别
emotion_level1 = "悲伤。在这个级别的人过的是八辈子都懊丧和消沉的生活。这种生活充满了对过去的懊悔、自责和悲恸。在悲伤中的人，看这个世界都是灰黑色的。"
emotion_level2 = "愤怒。如果有人能跳出冷漠和内疚的怪圈，并摆脱恐惧的控制，他就开始有欲望了，而欲望则带来挫折感，接着引发愤怒。愤怒常常表现为怨恨和复仇心里，它是易变且危险的。愤怒来自未能满足的欲望，来自比之更低的能量级。挫败感来自于放大了欲望的重要性。愤怒很容易就导致憎恨，这会逐渐侵蚀一个人的心灵。"
emotion_level3 = "淡定。到达这个能级的能量都变得很活跃了。淡定的能级则是灵活和无分别性的看待现实中的问题。到来这个能级，意味着对结果的超然，一个人不会再经验挫败和恐惧。这是一个有安全感的能级。到来这个能级的人们，都是很容易与之相处的，而且让人感到温馨可靠,这样的人总是镇定从容。他们不会去强迫别人做什么。"
emotion_level4 = "平和。他感觉到所有的一切都生机勃勃并光芒四射，虽然在其他人眼里这个世界还是老样子，但是在这人眼里世界却是一个。所以头脑保持长久的沉默，不再分析判断。观察者和被观察者成为同一个人，观照者消融在观照中，成为观照本身。"
emotion_level5 = "喜悦。当爱变得越来越无限的时候，它开始发展成为内在的喜悦。这是在每一个当下，从内在而非外在升起的喜悦。这个能级的人的特点是，他们具有巨大的耐性，以及对一再显现的困境具有持久的乐观态度，以及慈悲。同时发生着。在他们开来是稀松平常的作为，却会被平常人当成是奇迹来看待。"
# 情感波动级别
emotion_level6 = "情感波动很小，个人情感是不易改变的、经得起考验的。能够理性的看待周围的人和事。"
emotion_level7 = "情感波动较大，周围的喜悦或者悲伤都能轻易的感染他，他对周围的事物有敏感的认知。"
def match(word, sentiment_value):
# -*- coding: utf-8 -*-
__author__ = 'Bai Chenjia'
import text_process as tp
import numpy as np
# 1.读取情感词典和待处理文件
# 情感词典
print "reading..."
posdict = tp.read_lines("f://emotion/mysite/Sentiment_dict/emotion_dict/pos_all_dict.txt")
negdict = tp.read_lines("f://emotion/mysite/Sentiment_dict/emotion_dict/neg_all_dict.txt")
# 程度副词词典
mostdict = tp.read_lines('f://emotion/mysite/Sentiment_dict/degree_dict/most.txt') # 权值为2
verydict = tp.read_lines('f://emotion/mysite/Sentiment_dict/degree_dict/very.txt') # 权值为1.5
moredict = tp.read_lines('f://emotion/mysite/Sentiment_dict/degree_dict/more.txt') # 权值为1.25
ishdict = tp.read_lines('f://emotion/mysite/Sentiment_dict/degree_dict/ish.txt') # 权值为0.5
insufficientdict = tp.read_lines('f://emotion/mysite/Sentiment_dict/degree_dict/insufficiently.txt') # 权值为0.25
inversedict = tp.read_lines('f://emotion/mysite/Sentiment_dict/degree_dict/inverse.txt') # 权值为-1
# 情感级别
emotion_level1 = "悲伤。在这个级别的人过的是八辈子都懊丧和消沉的生活。这种生活充满了对过去的懊悔、自责和悲恸。在悲伤中的人，看这个世界都是灰黑色的。"
emotion_level2 = "愤怒。如果有人能跳出冷漠和内疚的怪圈，并摆脱恐惧的控制，他就开始有欲望了，而欲望则带来挫折感，接着引发愤怒。愤怒常常表现为怨恨和复仇心里，它是易变且危险的。愤怒来自未能满足的欲望，来自比之更低的能量级。挫败感来自于放大了欲望的重要性。愤怒很容易就导致憎恨，这会逐渐侵蚀一个人的心灵。"
emotion_level3 = "淡定。到达这个能级的能量都变得很活跃了。淡定的能级则是灵活和无分别性的看待现实中的问题。到来这个能级，意味着对结果的超然，一个人不会再经验挫败和恐惧。这是一个有安全感的能级。到来这个能级的人们，都是很容易与之相处的，而且让人感到温馨可靠,这样的人总是镇定从容。他们不会去强迫别人做什么。"
emotion_level4 = "平和。他感觉到所有的一切都生机勃勃并光芒四射，虽然在其他人眼里这个世界还是老样子，但是在这人眼里世界却是一个。所以头脑保持长久的沉默，不再分析判断。观察者和被观察者成为同一个人，观照者消融在观照中，成为观照本身。"
emotion_level5 = "喜悦。当爱变得越来越无限的时候，它开始发展成为内在的喜悦。这是在每一个当下，从内在而非外在升起的喜悦。这个能级的人的特点是，他们具有巨大的耐性，以及对一再显现的困境具有持久的乐观态度，以及慈悲。同时发生着。在他们开来是稀松平常的作为，却会被平常人当成是奇迹来看待。"
# 情感波动级别
emotion_level6 = "情感波动很小，个人情感是不易改变的、经得起考验的。能够理性的看待周围的人和事。"
emotion_level7 = "情感波动较大，周围的喜悦或者悲伤都能轻易的感染他，他对周围的事物有敏感的认知。"
# 2.程度副词处理，根据程度副词的种类不同乘以不同的权值
# -*- coding: utf-8 -*-
import text_process as tp
import codecs
#1 read sentimental dict and adverb dict
# sentimental dict
posdict = tp.read_lines("D://PythonProject/Sentiment_dict/emotion_dict/pos_all_dict.txt")
negdict = tp.read_lines("D://PythonProject/Sentiment_dict/emotion_dict/neg_all_dict.txt")
# adverb of dict
mostdict = tp.read_lines('D://PythonProject/Sentiment_dict/degree_dict/most.txt') # weight is 2
verydict = tp.read_lines('D://PythonProject/Sentiment_dict/degree_dict/very.txt') # weight is 1.75
moredict = tp.read_lines('D://PythonProject/Sentiment_dict/degree_dict/more.txt') # weight is 1.5
ishdict = tp.read_lines('D://PythonProject/Sentiment_dict/degree_dict/ish.txt') # weight is 1.2
insufficientdict = tp.read_lines('D://PythonProject/Sentiment_dict/degree_dict/insufficiently.txt') # weight is 0.5
inversedict = tp.read_lines('D://PythonProject/Sentiment_dict/degree_dict/inverse.txt') # weight is -1
# 2 handle adverb and multiply word according to different weight
def match(word, sentiment_value):
if word in mostdict:
sentiment_value *= 2.0
elif word in verydict:
sentiment_value *= 1.75
elif word in moredict:
sentiment_value *= 1.5
elif word in ishdict:
sentiment_value *= 1.2
elif word in insufficientdict:
import jieba.analyse
import jieba.posseg as pseg
from model import Dict
import text_process as tp
# 程度副词词典
mostdict = tp.read_lines('degree_dict/most.txt') # 权值为2
verydict = tp.read_lines('degree_dict/very.txt') # 权值为1.5
moredict = tp.read_lines('degree_dict/more.txt') # 权值为1.25
ishdict = tp.read_lines('degree_dict/ish.txt') # 权值为0.5
insufficientdict = tp.read_lines('degree_dict/insufficiently.txt') # 权值为0.25
inversedict = tp.read_lines('degree_dict/inverse.txt') # 权值为-1
# 2.程度副词处理，根据程度副词的种类不同乘以不同的权值
def match(word, sentiment_value):
if word in mostdict:
sentiment_value *= 2.0
elif word in verydict:
sentiment_value *= 1.75
elif word in moredict:
sentiment_value *= 1.5
elif word in ishdict:
sentiment_value *= 1.2
elif word in insufficientdict:
sentiment_value *= 0.5
elif word in inversedict:
#print "inversedict", word
sentiment_value *= -1
return sentiment_value
jieba.load_userdict(
'E:\postgraduate\\no_space_environment\category\pycharm\pycharm_file_location\\thesis\新闻文本处理\论文词典法CSDN\Sentiment_dict\emotion_dict\pos_all_dict.txt'
)
jieba.load_userdict(
'E:\postgraduate\\no_space_environment\category\pycharm\pycharm_file_location\\thesis\新闻文本处理\论文词典法CSDN\Sentiment_dict\emotion_dict\\neg_all_dict.txt'
)
jieba.load_userdict(
"E:\postgraduate\\no_space_environment\category\pycharm\pycharm_file_location\\thesis\新闻文本处理\论文词典法CSDN\Sentiment_dict\degree_dict\insufficiently_inverse.txt"
)
# 1.读取情感词典和待处理文件
# 情感词典
print("reading...")
posdict = tp.read_lines(
"E:\postgraduate\\no_space_environment\category\pycharm\pycharm_file_location\\thesis\新闻文本处理\论文词典法CSDN\Sentiment_dict\emotion_dict\pos_all_dict.txt"
)
negdict = tp.read_lines(
"E:\postgraduate\\no_space_environment\category\pycharm\pycharm_file_location\\thesis\新闻文本处理\论文词典法CSDN\Sentiment_dict\emotion_dict\\neg_all_dict.txt"
)
# 程度副词词典
mostdict = tp.read_lines(
'E:\postgraduate\\no_space_environment\category\pycharm\pycharm_file_location\\thesis\新闻文本处理\论文词典法CSDN\Sentiment_dict\degree_dict\most.txt'
) # 权值为2
verydict = tp.read_lines(
'E:\postgraduate\\no_space_environment\category\pycharm\pycharm_file_location\\thesis\新闻文本处理\论文词典法CSDN\Sentiment_dict\degree_dict\\very.txt'
) # 权值为1.5
moredict = tp.read_lines(
'E:\postgraduate\\no_space_environment\category\pycharm\pycharm_file_location\\thesis\新闻文本处理\论文词典法CSDN\Sentiment_dict\degree_dict\more.txt'
) # 权值为1.25
ishdict = tp.read_lines(