모든 영어의 순수한 텍스트 파일, 그 중의 단어 출현 개수 통계

path = 'test.txt'
with open(path,encoding='utf-8',newline='') as f:
    word = []
    words_dict= {}
    for letter in f.read():
        if letter.isalnum():
            word.append(letter)
        elif letter.isspace(): #    \t 

            if word:
                word = ''.join(word).lower() # 
                if word not in words_dict:
                    words_dict[word] = 1
                else:
                    words_dict[word] += 1
                word = []

# 
if word:
    word = ''.join(word).lower()  #  
    if word not in words_dict:
        words_dict[word] = 1
    else:
        words_dict[word] += 1
    word = []

for k,v in words_dict.items():
    print(k,v)

path = 'test.txt'
with open(path,'r',encoding='utf-8') as f:
    data = f.read()
    word_reg = re.compile(r'\w+')
    #word_reg = re.compile(r'\w+\b')
    word_list = word_reg.findall(data)
    word_list = [word.lower() for word in word_list] # 
    word_set = set(word_list)  # 
    # words_dict = {}
    # for word in word_set:
    #     words_dict[word] = word_list.count(word)

    #  
    words_dict = {word: word_list.count(word) for word in word_set}
    for k,v in words_dict.items():
        print(k,v)

path = 'test.txt'
with open(path, 'r', encoding='utf-8') as f:
    word_list = []
    word_reg = re.compile(r'\w+')
    for line in f:
        #line_words = word_reg.findall(line)
        # 
        line_words = line.split()
        word_list.extend(line_words)
    word_set = set(word_list)  #  
    words_dict = {word: word_list.count(word) for word in word_set}
    for k, v in words_dict.items():
        print(k, v)

import collections  
path = 'test.txt'
with open(path, 'r', encoding='utf-8') as f:
    word_list = []
    word_reg = re.compile(r'\w+')
    for line in f:
        line_words = line.split()
        word_list.extend(line_words)
   
    words_dict = dict(Counter(word_list)) # Counter 
    for k, v in words_dict.items():
        print(k, v)