书生大模型实战营学习[2]Python task

news2024/9/20 4:07:36

学习目标：Python学习

Python实现wordcount
Vscode连接InternStudio debug笔记

学习内容：

任务1：请实现一个wordcount函数，统计英文字符串中每个单词出现的次数。返回一个字典，key为单词，value为对应单词出现的次数。

input:

"""Hello world!  
This is an example.  
Word count is fun.  
Is it fun to count words?  
Yes, it is fun!"""

output:

{'hello': 1, 'world': 1, 'this': 1, 'is': 4, 'an': 1, 'example': 1, 'word': 1, 'count': 2,
'fun': 3, 'it': 2, 'to': 1, 'words': 1, 'yes': 1}

第一种是使用正则：

import re
from collections import Counter

def wordcount(text):
    # 使用正则表达式将文本中的单词分割开来，同时转换为小写
    words = re.findall(r'\b\w+\b', text.lower())
    # 使用 Counter 来计算每个单词出现的次数
    word_counts = Counter(words)
    return dict(word_counts)

# 输入文本
text = """Hello world!  
This is an example.  
Word count is fun.  
Is it fun to count words?  
Yes, it is fun!"""

# 调用函数并打印结果
print(wordcount(text))

第二种是使用hash

def word_count(text):
    # 创建一个字典来存储单词计数
    hash = {}
    
    # 遍历字符串中的每个字符
    i = 0
    while i < len(text):
        # 检查当前字符是否是字母
        if text[i].isalpha():
            j = i
            word = ''
            # 继续向后查找，直到遇到非字母字符
            while j < len(text) and text[j].isalpha():
                word += text[j].lower()
                j += 1
            # 更新字典中的单词计数
            hash[word] = hash.get(word, 0) + 1
            # 移动索引到单词的末尾
            i = j
        else:
            i += 1
    
    # 返回包含单词计数的字典
    return hash

def main():
    text = """Hello world!  
This is an example.  
Word count is fun.  
Is it fun to count words?  
Yes, it is fun!"""
    word_counts = word_count(text)

    for word, count in word_counts.items():
        print(f"{word}: {count}")

if __name__ == "__main__":
    main()