用python分别实现计算给定文本文件中英语字母、英语单词、汉字、汉语词的熵

英语字母熵的实现：

import math

def english_letter_entropy(file_path):
    # 统计英文字母出现次数
    letter_counts = {}
    with open(file_path, 'r') as f:
        for line in f:
            for letter in line:
                if letter.isalpha() and letter.isascii():
                    letter = letter.lower()
                    if letter in letter_counts:
                        letter_counts[letter] += 1
                    else:
                        letter_counts[letter] = 1
    
    # 计算熵值
    total_count = sum(letter_counts.values())
    entropy = 0
    for count in letter_counts.values():
        p = count / total_count
        entropy -= p * math.log2(p)
    
    return entropy

英语单词熵的实现：

import math
import re

def english_word_entropy(file_path):
    # 统计单词出现次数
    word_counts = {}
    with open(file_path, 'r') as f:
        for line in f:
            words = re.findall('[a-zA-Z]+', line)
            for word in words:
                word = word.lower()
                if word in word_counts:
                    word_counts[word] += 1
                else:
                    word_counts[word] = 1
    
    # 计算熵值
    total_count = sum(word_counts.values())
    entropy = 0
    for count in word_counts.values():
        p = count / total_count
        entropy -= p * math.log2(p)
    
    return entropy

汉字熵的实现：

import math

def chinese_character_entropy(file_path):
    # 统计汉字出现次数
    character_counts = {}
    with open(file_path, 'r', encoding='utf-8') as f:
        for line in f:
            for character in line:
                if '\u4e00' <= character <= '\u9fff':
                    if character in character_counts:
                        character_counts[character] += 1
                    else:
                        character_counts[character] = 1
    
    # 计算熵值
    total_count = sum(character_counts.values())
    entropy = 0
    for count in character_counts.values():
        p = count / total_count
        entropy -= p * math.log2(p)
    
    return entropy

汉语词熵的实现：

import math
import jieba

def chinese_word_entropy(file_path):
    # 统计汉语词出现次数
    word_counts = {}
    with open(file_path, 'r', encoding='utf-8') as f:
        for line in f:
            words = jieba.cut(line)
            for word in words:
                if len(word) > 1:
                    if word in word_counts:
                        word_counts[word] += 1
                    else:
                        word_counts[word] = 1
    
    # 计算熵值
    total_count = sum(word_counts.values())
    entropy = 0
    for count in word_counts.values():
        p = count / total_count
        entropy -= p * math.log2(p)
    
    return entropy