手把手教你对抓取的文本进行分词、词频统计、词云可视化和情感分析

# coding: utf-8
import pandas as pd
df = pd.read_csv('./职位描述.csv', encoding='gbk')
# print(df.head())

for text in df['Job_Description']:
    # print(text)
    if text is not None:
        with open('职位表述文本.txt', mode='a', encoding='utf-8') as file:
            file.write(str(text))

print('写入完成')

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
import jieba

# jieba.load_userdict('userdict.txt')
# 创建停用词list
def stopwordslist(filepath):
    stopwords = [line.strip() for line in open(filepath, 'r', encoding='utf-8').readlines()]
    return stopwords

# 对句子进行分词
def seg_sentence(sentence):
    sentence_seged = jieba.cut(sentence.strip())
    stopwords = stopwordslist('stop_word.txt')  # 这里加载停用词的路径
    outstr = ''
    for word in sentence_seged:
        if word not in stopwords:
            if word != '\t':
                outstr += word
                outstr += " "
    return outstr

inputs = open('职位表述文本.txt', 'r', encoding='utf-8')
outputs = open('职位表述文本分词后_outputs.txt', 'w', encoding='utf-8')
for line in inputs:
    line_seg = seg_sentence(line)  # 这里的返回值是字符串
    outputs.write(line_seg + '\n')
outputs.close()
inputs.close()

from wordcloud import WordCloud
import jieba
import numpy
import PIL.Image as Image

def cut(text):
    wordlist_jieba=jieba.cut(text)
    space_wordlist=" ".join(wordlist_jieba)
    return space_wordlist
with open(r"C:\Users\pdcfi\Desktop\xiaoming\职位表述文本.txt" ,encoding="utf-8")as file:
    text=file.read()
    text=cut(text)
    mask_pic=numpy.array(Image.open(r"C:\Users\pdcfi\Desktop\xiaoming\python.png"))
    wordcloud = WordCloud(font_path=r"C:/Windows/Fonts/simfang.ttf",
    collocations=False,
    max_words= 100,
    min_font_size=10, 
    max_font_size=500,
    mask=mask_pic).generate(text)
    image=wordcloud.to_image()
    # image.show()
    wordcloud.to_file('词云图.png')  # 把词云保存下来

#!/usr/bin/env python3
# -*- coding:utf-8 -*-

import sys
import jieba
import jieba.analyse
import xlwt  # 写入Excel表的库

# reload(sys)
# sys.setdefaultencoding('utf-8')

if __name__ == "__main__":

    wbk = xlwt.Workbook(encoding='ascii')
    sheet = wbk.add_sheet("wordCount")  # Excel单元格名字
    word_lst = []
    key_list = []
    for line in open('职位表述文本.txt', encoding='utf-8'):  # 需要分词统计的原始目标文档

        item = line.strip('\n\r').split('\t')  # 制表格切分
        # print item
        tags = jieba.analyse.extract_tags(item[0])  # jieba分词
        for t in tags:
            word_lst.append(t)

    word_dict = {}
    with open("分词结果.txt", 'w') as wf2:  # 指定生成文件的名称

        for item in word_lst:
            if item not in word_dict:  # 统计数量
                word_dict[item] = 1
            else:
                word_dict[item] += 1

        orderList = list(word_dict.values())
        orderList.sort(reverse=True)
        # print orderList
        for i in range(len(orderList)):
            for key in word_dict:
                if word_dict[key] == orderList[i]:
                    wf2.write(key + ' ' + str(word_dict[key]) + '\n')  # 写入txt文档
                    key_list.append(key)
                    word_dict[key] = 0

    for i in range(len(key_list)):
        sheet.write(i, 1, label=orderList[i])
        sheet.write(i, 0, label=key_list[i])
    wbk.save('wordCount_all_lyrics.xls')  # 保存为 wordCount.xls文件

#!/usr/bin/env python3
# -*- coding: utf-8 -*-

from snownlp import SnowNLP

# 积极/消极
# print(s.sentiments)  # 0.9769551298267365  positive的概率


def get_word():
    with open("情感分析用词.txt", encoding='utf-8') as f:
        line = f.readline()
        word_list = []
        while line:
            line = f.readline()
            word_list.append(line.strip('\r\n'))
        f.close()
        return word_list


def get_sentiment(word):
    text = u'{}'.format(word)
    s = SnowNLP(text)
    print(s.sentiments)


if __name__ == '__main__':
    words = get_word()
    for word in words:
        get_sentiment(word)

# text = u'''
# 也许
# '''
# s = SnowNLP(text)
# print(s.sentiments)
#     with open('lyric_sentiments.txt', 'a', encoding='utf-8') as fp:
#         fp.write(str(s.sentiments)+'\n')
# print('happy end')