1.在pycharm中将要查词频的文档放入同一个目录下,hamlet.txt为纯英文文档,threekingdoms.txt为中文文档
2.CalHamletV1.py为纯英文文档词频
CalThreeKingdomsV1 中文初步版词频
CalThreeKingdomsV2 中文升级版词频
3.代码
CalHamletV1.py为纯英文文档词频
#CalHamletV1.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))
SyntaxError: Non-ASCII character '\xe2' in file F:/Python_test/dictionary_test/Cal