如何让此代码计算单词而不是字母?

Question

我对python相当陌生，我正在尝试让这段代码打开txt文件并删除文件中的标点符号，阅读这些文件，创建一个单词列表，然后计算每个单词的出现次数。它正在计算字母的出现次数。另外，如何在其他函数中正确调用函数？

import os

# create the dictionary
dictionary = {}
# create dictionary list
dictionarylist = []

def make_a_listh():
path = 'data/training/'
Heal = path + 'Health/'
heal_files = os.listdir(Heal)
# print(heal_files)
punctuations = '''!()-—[]{};:'",<>.|/?@#$%^&*_~'''
no_puncth = ""
line = "--------------------------------------------------- 
--------------------------"
for j in heal_files:
file2 = open(Heal + j, 'r').read()
for char in file2:
if char not in punctuations:
no_puncth = no_puncth + char
print(j + line, "n", no_puncth)

def make_a_listm():
path = 'data/training/'
Minn = path + 'Minnesota/'
minn_files = os.listdir(Minn)
# print the filename and a new line
punctuations = '''!()—-—[]{};:’'",<>.|/?@“#$%^&*_~'''
no_punctm = ""
line = "--------------------------------------------------- 
-------------------------"
for i in minn_files:
file1 = open(Minn + i, 'r')
for char in file1:
if char not in punctuations:
no_punctm = no_punctm + char
# print(i + line, "n", no_punctm.replace('"',''))
return no_punctm

def Freq(file1):
# as long as there is a line in file loop
for line in file1:
# create variable to hold each word from the file
words = line.split()
# as long as there is a word in words loop
for eachword in words:
# if there is an existing word in dictionary 
increase occurrence count
if eachword in dictionary:
dictionary[eachword] = dictionary[eachword] + 1
# if there is a word that is new set count to 1
else:
dictionary[eachword] = 1
# for every item (k and v) in dictionary, loop
for k, v in dictionary.items():
# create temporary place holder for v and k values
temporary = [v, k]
# (add) temporary values to dictionaryList
dictionarylist.append(temporary)
# print out each value from dictionaryList in. 
descending order on new lines
print("n".join(map(str, sorted(dictionarylist, 
reverse=True))))
Freq(file1=make_a_listm())

Answer 1

下面介绍如何使用集合模块中的Counter()方法，以及如何使用re.sub()更有效地处理标点符号：

from glob import glob
import re
from collections import Counter
words = []
for file in glob("C:\Users\User\Desktop\Folder\*.txt"): # For every file in Folder that ends with .txt
with open(file, 'r') as r: # Open the file in read mode
nopunc = re.sub('W', ' ', r.read()) # Use re.sub to replace all punctuations with spaces
words += [w.strip().lower() for w in nopunc.split() if w.strip()] # List all the words in lower case, and add the list to words
print(Counter(words)) # prints out a dictionary with each unique word as the keys, and the frequency of those words as values