jieba库的使用和好玩的词云

Posted 2021-03-02 lsh1628340121

I.三国演义和水浒传的词频统计：

#三国演义的词频统计
import jieba
excludes = {"将军","却说","荆州","二人","不可","不能","如此"}
txt = open("threekingdoms.txt", "r", encoding=‘utf-8‘).read()
words  = jieba.lcut(txt)
counts = {}
for word in words:
    if len(word) == 1:
        continue
    elif word == "诸葛亮" or word == "孔明曰":
        rword = "孔明"
    elif word == "关公" or word == "云长":
        rword = "关羽"
    elif word == "玄德" or word == "玄德曰":
        rword = "刘备"
    elif word == "孟德" or word == "丞相":
        rword = "曹操"
    else:
        rword = word
    counts[rword] = counts.get(rword,0) + 1
for word in excludes:
    del counts[word]
items = list(counts.items())
items.sort(key=lambda x:x[1], reverse=True) 
for i in range(10):
    word, count = items[i]
    print ("{0:<10}{1:>5}".format(word, count))

II.水浒传词频统计：

 

#水浒传词频
import jieba
excludes = {"一个","说道","只见","如何","两个","众人","哥哥","这里","那里","今日","出来","军马","头领","兄弟","梁山泊"}
txt = open("F:水浒传.txt", "r", encoding=‘utf-8‘).read()
words  = jieba.lcut(txt)
counts = {}
for word in words:
    if len(word) == 1:
        continue
    elif word=="宋江道":
        rword="宋江"
    else:
        rword = word
    counts[rword] = counts.get(rword,0) + 1
for word in excludes:
    del counts[word]
items = list(counts.items())
items.sort(key=lambda x:x[1], reverse=True) 
for i in range(10):
    word, count = items[i]
    print ("{0:<10}{1:>5}".format(word, count))

 

 

#水浒传词频
import jieba
txt = open("F:水浒传.txt", "r", encoding=‘utf-8‘).read()
words  = jieba.lcut(txt)
counts = {}
for word in words:
    if len(word) == 1:
        continue
    else:
        counts[word] = counts.get(word,0) + 1
items = list(counts.items())
items.sort(key=lambda x:x[1], reverse=True) 
for i in range(15):
    word, count = items[i]
    print ("{0:<10}{1:>5}".format(word, count))

 

 

 

 

III.好玩的词云图：

 

#三国演义词云
import jieba
import wordcloud
f = open("F:三国演义.txt", "r", encoding="utf-8")
t = f.read()
f.close()
ls = jieba.lcut(t) 
txt = " ".join(ls)
w = wordcloud.WordCloud(     width = 1000, height = 700,    background_color = "white",
    font_path = "msyh.ttc"    
    )
w.generate(txt)
w.to_file("grwordcloud.png")

 

 

#水浒传词云图
import jieba
import wordcloud
f = open("F:水浒传.txt", "r", encoding="utf-8")
t = f.read()
f.close()
ls = jieba.lcut(t)
txt = " ".join(ls)
w = wordcloud.WordCloud(     width = 1000, height = 700,    background_color = "white",
    font_path = "msyh.ttc",max_words=15    
    )
w.generate(txt)
w.to_file("grwordcloud.png")