jieba库分词

# 如果您需要使用此代码，os.chdir路经需要指定到txt文本所在路径
# 使用Zipin函数，需要txt有read()函数可以打开的正确的编码格式
# 使用Cipin函数需要安装jieba库
# 使用word cloud函数需要安装wordcloud与matplotlib库
import os
import codecs
import jieba
import pandas as pd
from wordcloud import WordCloud
from scipy.misc import imread
import matplotlib.pyplot as plt
os.chdir("/Users/Zhaohaibo/Desktop")

class Hlm(object):

    # —————————————————————
    # Zipin(self, readdoc, writedoc)
    # readdoc: 要读取的文件名
    # writedoc:要写入的文件名

    # output
    # 字频前100，并写入writedoc
    # —————————————————————
    def Zipin(self, readdoc, writedoc):
        word_lst = []
        word_dict = {}
        exclude_str = "，。！？、（）【】<>《》=：+-*—“”…"
        with open(readdoc,"r") as fileIn ,open(writedoc,‘w‘) as fileOut:

            # 添加每一个字到列表中
            for line in fileIn:
                for char in line:
                    word_lst.append(char)

            # 用字典统计每个字出现的个数
            for char in word_lst:
                if char not in exclude_str:
                    if char.strip() not in word_dict: # strip去除各种空白
                        word_dict[char] = 1
                    else :
                        word_dict[char] += 1

            # 排序x[1]是按字频排序，x[0]则是按字排序
            lstWords = sorted(word_dict.items(), key=lambda x:x[1],  reverse=True)

            # 输出结果 (前100)
            print (‘字符\t字频‘)
            print (‘=============‘)
            for e in lstWords[:100]:
                print (‘%s\t%d‘ % e)
                fileOut.write(‘%s, %d\n‘ % e)


    # —————————————————————
    # Cipin(self, doc)
    # doc: 要读取的文件名

    # return:
    # 词频表（DataFrame格式）
    # —————————————————————
    def Cipin(self, doc):
        wdict = {}
        f = open(doc,"r")
        for line in f.readlines():
            words = jieba.cut(line)
            for w in words:
                if(w not in wdict):
                    wdict[w] = 1
                else:
                    wdict[w] += 1
        # 导入停用词表
        stop = pd.read_csv(‘stoplist.txt‘, encoding = ‘utf-8‘, sep = ‘zhao‘, header = None,engine = ‘python‘) #sep:分割符号（需要用一个确定不会出现在停用词表中的单词）
        stop.columns = [‘word‘]
        stop = [‘ ‘] + list(stop.word) #python读取时不会读取到空格。但空格依旧需要去除。所以加上空格； 读取后的stop是series的结构，需要转成列表
        for i in range(len(stop)):
            if(stop[i] in wdict):
                wdict.pop(stop[i])

        ind = list(wdict.keys())
        val = list(wdict.values())
        ind = pd.Series(ind)
        val = pd.Series(val)
        data =  pd.DataFrame()
        data[‘词‘] = ind
        data[‘词频‘] = val
        return data

    # —————————————————————
    # Ciyun(self, doc)
    # doc: 要读取的文件名

    # output:
    # 词云图
    # —————————————————————
    def Ciyun(self,doc):
        g = open(doc,"r").read()
        back_pic = imread("aixin.jpg")  # 设置背景图片
        wc = WordCloud( font_path=‘/System/Library/Fonts/STHeiti Medium.ttc‘,#设置字体
                          background_color="white", #背景颜色
                          max_words=2000,# 词云显示的最大词数
                          mask=back_pic,#设置背景图片
                          max_font_size=200, #字体最大值
                          random_state=42,
                         ).generate(g)
        plt.figure(figsize=(64,32))
        plt.imshow(wc)
        plt.axis(‘off‘)
        plt.savefig("ciyun.jpg")
        plt.show()


    def main(self,readdoc):
        # self.Zipin(readdoc,writedoc)
        df = self.Cipin(readdoc)
        #self.Ciyun(readdoc)
        return df


if __name__ == ‘__main__‘:
    hlm = Hlm()
    hlm.Zipin("红楼梦.txt","红楼梦字频.txt")
    df_hlm1 = hlm.main("红楼梦.txt")
---------------------
作者：Iovebecky
来源：CSDN
原文：https://blog.csdn.net/zhaohaibo_/article/details/81902456
版权声明：本文为博主原创文章，转载请附上博文链接！