Python-在线文本情感分析实验

'''
每次处理两百
'''
import jieba  # 分词
import re  # 过滤特殊字符
import numpy as np  # 辅助处理
import pandas as pd  # 处理
import emoji  # 过滤表情
import jieba.analyse  # 分级级别权重
import imageio  # 图片
import jieba.posseg as pseg  # 词性标注
from wordcloud import WordCloud  # 词云
import os
import matplotlib.pyplot as plt  # 画布
import difflib  # 相似度判断
import configparser  # 配置文件导入

# 路径配置导入
def cfg():
    # 生成config对象
    conf = configparser.ConfigParser()
    # 用config对象读取配置文件
    conf.read("config.ini" , encoding='utf-8')
    # 以列表形式返回所有的section
    sections = conf.sections()
    items = conf.items('filePaths')
    items = dict(items)
    return items

# 采用关键词典简化数据
def wts_dict():
    wts_lst = []
    with open(cfg()['wts_dict_path'], encoding='utf-8') as f:
        for line in f:
            line = line.replace("\n", "").replace("\r", "")
            wts_lst.append(line)
    return wts_lst

# 文件加载
def dict_load(path):
    print("文件加载！")
    dt = []
    with open(path, encoding='utf-8-sig') as f:
        for line in f:
            if line.strip() != '':  # 去除空格
                dt.append(line.strip())
    return (dt)

# 情感值计算
def sents(sent, negdict, posdict, nodict):
    pos = 0  # 积极
    neg = 0  # 消极
    for i in range(len(sent)):
        if sent[i] in negdict:
            if i == 1 and sent[i - 1] in nodict:
                pos = pos + 1  # 否定-消极
            elif i == 1 and sent[i - 1] not in nodict:
                neg = neg + 1  # 其他-消极
            elif i > 1 and sent[i - 1] in nodict:
                if sent[i - 2] in nodict:
                    neg = neg + 1  # 否定-否定-消极
                else:
                    pos = pos + 1  # 其他-否定-消极
            elif i > 1 and sent[i - 1] not in nodict:
                if sent[i