利用python实现对中英文文本的词频统计
英文文本《Hamlet》
code1：
#CalHamlet.py
def getText():
txt = open("hamlet.txt", "r").read()
txt = txt.lower()
for ch in '!"#$%&()*+,-./:;<=>?@[\\]^_‘{|}~':
txt = txt.replace(ch, " ") #将文本中特殊字符替换为空格
return txt
hamletTxt = getText()
words = hamletTxt.split()
counts = {}
for word in words:
counts[word] = counts.get(word,0) + 1
items = list(counts.items())
items.sort(key=lambda x:x[1], reverse=True)
for i in range(10):
word, count = items[i]
print ("{0:<10}{1:>5}".format(word, count))
code2：（带排除个别词汇效果）
excludes = {"the","and","of","you","a","i","my","in"} #要排除的词
def getText():
txt = open("hamlet.txt", "r").read()
txt = txt.lower()
for ch in '!"#$%&()*+,-./:;<=>?@[\\]^_‘{|}~':
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
for word in excludes:
del(counts[word]) #删除排除词汇
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))
运行结果1：
运行结果2：
中文文本《三国演义》人名统计：
code：
import jieba
excludes = {"将军","却说","荆州","二人","不可","不能","如此","商议","如何","主公"
,"军士","左右","军马","引兵","次日","大喜","天下","东吴","于是","今日",
"不敢","魏兵","陛下","一人","都督","人马","不知"}
txt = open("三国演义.txt", "r", encoding='utf-8').read()
words = jieba.lcut(txt)
counts = {}
for word in words:
if len(word) == 1:
continue
elif word == "孔明" or word == "孔明曰":
rword = "诸葛亮"
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(40):
word, count = items[i]
if count < 215 :
break
print ("{0:<10}{1:>5}".format(word, count))
运行结果：