机器学习实践四：文本词频分析

import jieba # jieba中文分词库

with open('test.txt', 'r', encoding='UTF-8') as novelFile:
    novel = novelFile.read()
# print(novel)
stopwords = [line.strip() for line in open('stop.txt', 'r', encoding='UTF-8').readlines()]
#line.strip()用空格划分，删除所有的空格
novelList = list(jieba.lcut(novel))#把文本精确的划分开，不存在冗余单词
novelDict = {}

# 统计出词频字典
for word in novelList:
    if word not in stopwords:
            # 不统计字数为一的词
            if len(word) == 1:
                continue
            else:
                novelDict[word] = novelDict.get(word, 0) + 1

# 对词频进行排序
novelListSorted = list(novelDict.items())
novelListSorted.sort(key=lambda e: e[1], reverse=True)sort排序，根据元组第二个元素排序

# 打印前10词频
topWordNum = 0
for topWordTup in novelListSorted[:10]:
    print(topWordTup)

from matplotlib import pyplot as plt
x = [c for c,v in novelListSorted]
y = [v for c,v in novelListSorted]
plt.plot(x[:10],y[:10],color='r')
plt.show()

import jieba # jieba中文分词库

with open('data/data131368/test.txt', 'r', encoding='UTF-8') as novelFile:
    novel = novelFile.read()
# print(novel)
stopwords = [line.strip() for line in open('/home/aistudio/data/data131368/stop.txt', 'r', encoding='UTF-8').readlines()]
novelList = list(jieba.lcut(novel))
novelDict = {}

# 统计出词频字典
for word in novelList:
    if word not in stopwords:
            # 不统计字数为一的词
            if len(word) == 1:
                continue
            else:
                novelDict[word] = novelDict.get(word, 0) + 1
from wordcloud import WordCloud,ImageColorGenerator
import jieba
import matplotlib.pyplot as plt 
from imageio import imread


#读入背景图片

#生成词云图片
wordcloud = WordCloud(background_color='white',
    scale=1.5,font_path='data/data131368/msyh.ttc').generate(' '.join(novelDict.keys()))
plt.imshow(wordcloud) 
plt.axis('off') 
plt.show()
#保存图片
wordcloud.to_file('父亲1.jpg')
#https://www.bbsmax.com/A/8Bz89m4LJx/

wordcloud用法