jieba库概述
jieba库的安装
如果无法安装,请看Pyinstaller库的安装与使用方法里面有详细的安装教程
jieba分词的原理
jieba分词的三种形式
jieba库常用函数
实例1:Hamlet词频统计
code
def getText():
txt = open("hamlet.txt", "r").read()
txt = txt.lower()
for ch in '!"#$%&()*+,-./:;<=>?@[\\]^_‘{|}~':
txt = txt.replace(ch, " ") # 将文本中特殊字符替换为空格
return txt
hamletTxt = getText()
words = hamletTxt.split()
counts = {}
for word in words:
counts[word] = counts.get(word, 0) + 1
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))
实例2:《三国演义》人物出场统计
code
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))