{"id":1130960,"date":"2025-01-08T20:44:40","date_gmt":"2025-01-08T12:44:40","guid":{"rendered":""},"modified":"2025-01-08T20:44:42","modified_gmt":"2025-01-08T12:44:42","slug":"python%e5%a6%82%e4%bd%95%e8%be%93%e5%87%ba%e6%96%87%e6%9c%ac%e4%b8%ad%e5%8d%95%e8%af%8d%e5%87%ba%e7%8e%b0%e7%9a%84%e6%ac%a1%e6%95%b0","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1130960.html","title":{"rendered":"python\u5982\u4f55\u8f93\u51fa\u6587\u672c\u4e2d\u5355\u8bcd\u51fa\u73b0\u7684\u6b21\u6570"},"content":{"rendered":"

\"python\u5982\u4f55\u8f93\u51fa\u6587\u672c\u4e2d\u5355\u8bcd\u51fa\u73b0\u7684\u6b21\u6570\"<\/p>\n

Python\u53ef\u4ee5\u901a\u8fc7\u591a\u79cd\u65b9\u5f0f\u6765\u8f93\u51fa\u6587\u672c\u4e2d\u5355\u8bcd\u51fa\u73b0\u7684\u6b21\u6570<\/strong>\uff0c\u4f7f\u7528Counter\u6a21\u5757\u3001\u6b63\u5219\u8868\u8fbe\u5f0f\u3001\u5b57\u5178\u7edf\u8ba1<\/strong>\u7b49\u3002\u4e0b\u9762\u6211\u4eec\u5c06\u6df1\u5165\u8ba8\u8bba\u5176\u4e2d\u7684\u4e00\u4e2a\u65b9\u6cd5\uff0c\u5373\u4f7f\u7528collections.Counter<\/code>\u6a21\u5757\u6765\u7edf\u8ba1\u5355\u8bcd\u51fa\u73b0\u6b21\u6570\u3002<\/p>\n<\/p>\n

Python\u63d0\u4f9b\u4e86\u8bb8\u591a\u5f3a\u5927\u7684\u5e93\u548c\u6a21\u5757\uff0c\u53ef\u4ee5\u5e2e\u52a9\u6211\u4eec\u8f7b\u677e\u5b8c\u6210\u5404\u79cd\u4efb\u52a1\u3002collections.Counter<\/code>\u662f\u4e00\u4e2a\u975e\u5e38\u6709\u7528\u7684\u7c7b\uff0c\u53ef\u4ee5\u7528\u6765\u5bf9\u53ef\u54c8\u5e0c\u5bf9\u8c61\u8fdb\u884c\u8ba1\u6570\u3002\u5b83\u7279\u522b\u9002\u7528\u4e8e\u7edf\u8ba1\u5355\u8bcd\u51fa\u73b0\u7684\u6b21\u6570\u3002<\/p>\n<\/p>\n

\u4e00\u3001\u4f7f\u7528Counter\u6a21\u5757<\/h3>\n<\/p>\n

1. \u5bfc\u5165\u5fc5\u8981\u7684\u5e93<\/h4>\n<\/p>\n

\u9996\u5148\uff0c\u6211\u4eec\u9700\u8981\u5bfc\u5165collections<\/code>\u6a21\u5757\u4e2d\u7684Counter<\/code>\u7c7b\u3002<\/p>\n<\/p>\n

from collections import Counter<\/p>\n
<\/code><\/pre>\n<\/p>\n
2. \u8bfb\u53d6\u6587\u672c<\/h4>\n<\/p>\n
\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u9700\u8981\u8bfb\u53d6\u6587\u672c\u3002\u6211\u4eec\u53ef\u4ee5\u4ece\u6587\u4ef6\u4e2d\u8bfb\u53d6\u6587\u672c\uff0c\u4e5f\u53ef\u4ee5\u76f4\u63a5\u5728\u4ee3\u7801\u4e2d\u5b9a\u4e49\u6587\u672c\u5b57\u7b26\u4e32\u3002<\/p>\n<\/p>\n
text = """Python is an interpreted, high-level and general-purpose programming language. Python's design philosophy emphasizes code readability with its notable use of significant whitespace."""<\/p>\n
<\/code><\/pre>\n<\/p>\n
3. \u9884\u5904\u7406\u6587\u672c<\/h4>\n<\/p>\n
\u5728\u7edf\u8ba1\u5355\u8bcd\u51fa\u73b0\u6b21\u6570\u4e4b\u524d\uff0c\u6700\u597d\u5bf9\u6587\u672c\u8fdb\u884c\u4e00\u4e9b\u9884\u5904\u7406\u3002\u6bd4\u5982\uff0c\u5c06\u6240\u6709\u5b57\u7b26\u8f6c\u6362\u4e3a\u5c0f\u5199\uff0c\u53bb\u6389\u6807\u70b9\u7b26\u53f7\u7b49\u3002<\/p>\n<\/p>\n
import re<\/p>\n
\u5c06\u6587\u672c\u8f6c\u6362\u4e3a\u5c0f\u5199<\/strong><\/h2>\n
text = text.lower()<\/p>\n
\u53bb\u6389\u6807\u70b9\u7b26\u53f7<\/strong><\/h2>\n
text = re.sub(r'[^\\w\\s]', '', text)<\/p>\n
<\/code><\/pre>\n<\/p>\n
4. \u5206\u8bcd<\/h4>\n<\/p>\n
\u5c06\u9884\u5904\u7406\u540e\u7684\u6587\u672c\u6309\u7a7a\u683c\u5206\u5272\u6210\u5355\u8bcd\u5217\u8868\u3002<\/p>\n<\/p>\n
words = text.split()<\/p>\n
<\/code><\/pre>\n<\/p>\n
5. \u4f7f\u7528Counter\u7edf\u8ba1\u5355\u8bcd\u51fa\u73b0\u6b21\u6570<\/h4>\n<\/p>\n
\u73b0\u5728\uff0c\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528Counter<\/code>\u6765\u7edf\u8ba1\u5355\u8bcd\u51fa\u73b0\u7684\u6b21\u6570\u3002<\/p>\n<\/p>\n
word_counts = Counter(words)<\/p>\n
<\/code><\/pre>\n<\/p>\n
6. \u8f93\u51fa\u7ed3\u679c<\/h4>\n<\/p>\n
\u6700\u540e\uff0c\u6211\u4eec\u53ef\u4ee5\u5c06\u7ed3\u679c\u8f93\u51fa\u3002<\/p>\n<\/p>\n
for word, count in word_counts.items():<\/p>\n
    print(f'{word}: {count}')<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u901a\u8fc7\u4e0a\u8ff0\u6b65\u9aa4\uff0c\u6211\u4eec\u53ef\u4ee5\u8f7b\u677e\u7edf\u8ba1\u6587\u672c\u4e2d\u6bcf\u4e2a\u5355\u8bcd\u51fa\u73b0\u7684\u6b21\u6570\u3002\u8fd9\u4e2a\u65b9\u6cd5\u7b80\u6d01\u9ad8\u6548\uff0c\u9002\u7528\u4e8e\u5404\u79cd\u6587\u672c\u5904\u7406\u4efb\u52a1\u3002<\/p>\n<\/p>\n
\u4e8c\u3001\u6b63\u5219\u8868\u8fbe\u5f0f\u548c\u5b57\u5178\u7edf\u8ba1<\/h3>\n<\/p>\n
\u9664\u4e86\u4f7f\u7528Counter<\/code>\uff0c\u6211\u4eec\u8fd8\u53ef\u4ee5\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u548c\u5b57\u5178\u6765\u7edf\u8ba1\u5355\u8bcd\u51fa\u73b0\u7684\u6b21\u6570\u3002\u8fd9\u79cd\u65b9\u6cd5\u867d\u7136\u7565\u663e\u590d\u6742\uff0c\u4f46\u540c\u6837\u975e\u5e38\u6709\u6548\u3002<\/p>\n<\/p>\n
1. \u5bfc\u5165\u5fc5\u8981\u7684\u5e93<\/h4>\n<\/p>\n
import re<\/p>\n
<\/code><\/pre>\n<\/p>\n
2. \u8bfb\u53d6\u6587\u672c<\/h4>\n<\/p>\n
\u540c\u6837\uff0c\u6211\u4eec\u9700\u8981\u8bfb\u53d6\u6587\u672c\u3002<\/p>\n<\/p>\n
text = """Python is an interpreted, high-level and general-purpose programming language. Python's design philosophy emphasizes code readability with its notable use of significant whitespace."""<\/p>\n
<\/code><\/pre>\n<\/p>\n
3. \u9884\u5904\u7406\u6587\u672c<\/h4>\n<\/p>\n
\u4f7f\u7528\u6b63\u5219\u8868\u8fbe\u5f0f\u53bb\u6389\u6807\u70b9\u7b26\u53f7\uff0c\u5e76\u5c06\u6587\u672c\u8f6c\u6362\u4e3a\u5c0f\u5199\u3002<\/p>\n<\/p>\n
text = text.lower()<\/p>\n
text = re.sub(r'[^\\w\\s]', '', text)<\/p>\n
<\/code><\/pre>\n<\/p>\n
4. \u5206\u8bcd<\/h4>\n<\/p>\n
\u5c06\u6587\u672c\u6309\u7a7a\u683c\u5206\u5272\u6210\u5355\u8bcd\u5217\u8868\u3002<\/p>\n<\/p>\n
words = text.split()<\/p>\n
<\/code><\/pre>\n<\/p>\n
5. \u4f7f\u7528\u5b57\u5178\u7edf\u8ba1\u5355\u8bcd\u51fa\u73b0\u6b21\u6570<\/h4>\n<\/p>\n
\u521d\u59cb\u5316\u4e00\u4e2a\u7a7a\u5b57\u5178\uff0c\u7136\u540e\u904d\u5386\u5355\u8bcd\u5217\u8868\uff0c\u7edf\u8ba1\u6bcf\u4e2a\u5355\u8bcd\u51fa\u73b0\u7684\u6b21\u6570\u3002<\/p>\n<\/p>\n
word_counts = {}<\/p>\n
for word in words:<\/p>\n
    if word in word_counts:<\/p>\n
        word_counts[word] += 1<\/p>\n
    else:<\/p>\n
        word_counts[word] = 1<\/p>\n
<\/code><\/pre>\n<\/p>\n
6. \u8f93\u51fa\u7ed3\u679c<\/h4>\n<\/p>\n
\u6700\u540e\uff0c\u8f93\u51fa\u7edf\u8ba1\u7ed3\u679c\u3002<\/p>\n<\/p>\n
for word, count in word_counts.items():<\/p>\n
    print(f'{word}: {count}')<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e09\u3001\u5e94\u7528\u573a\u666f\u548c\u4f18\u5316<\/h3>\n<\/p>\n
1. \u5e94\u7528\u573a\u666f<\/h4>\n<\/p>\n
\u7edf\u8ba1\u5355\u8bcd\u51fa\u73b0\u6b21\u6570\u5728\u5f88\u591a\u5b9e\u9645\u5e94\u7528\u4e2d\u975e\u5e38\u6709\u7528\u3002\u4f8b\u5982\uff1a<\/p>\n<\/p>\n