python词频统计txt

在Python中，我们可以使用内置的`collections`模块或者第三方库如`nltk`（Natural Language Toolkit）来进行文本文件（如.txt格式）的词频统计。以下是使用这两个方法的基本步骤：

**使用collections模块**:

from collections import Counter
import re

def word_frequency(file_path):
    with open(file_path, 'r', encoding='utf-8') as file:
        text = file.read()
        
    # 使用正则表达式去除标点符号和换行符，并转换为小写
    words = re.findall(r'\b\w+\b', text.lower())
    
    # 使用Counter计算词频
    word_counts = Counter(words)
    
    return word_counts

# 示例
word_counts = word_frequency('your_text_file.txt')

**使用nltk库**:

import nltk
from nltk.corpus import stopwords
from nltk.tokenize import word_tokenize

def word_freq_from_nltk(file_path):
    nltk.download('punkt')  # 如果第一次使用，需要下载punkt数据集
    nltk.download('stopwords')  # 下载停用词列表
    
    with open(file_path, 'r', encoding='utf-8') as file:
        text = file.read()
        
    stop_words = set(stopwords.words('chinese'))  # 或者英文，看你的文本内容
    words = [word for word in word_tokenize(text) if word.isalnum() and not word in stop_words]
    
    freq_dist = nltk.FreqDist(words)
    
    return freq_dist

# 示例
freq_distribution = word_freq_from_nltk('your_text_file.txt')