統計哈姆雷特文本中高頻詞的個數

三國演義人物出場統計

開源代碼
講解視頻

kou@ubuntu:~/python$ cat ClaHamlet.py 
#!/usr/bin/env python
# coding=utf-8#e10.1CalHamlet.py
def getText():txt = open("hamlet.txt", "r").read()txt = txt.lower()for ch in '!"#$%&()*+,-./:;<=>?@[\\]^_‘{|}~':txt = txt.replace(ch, " ")   #將文本中特殊字符替換為空格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))