{"id":1100884,"date":"2025-01-08T15:44:08","date_gmt":"2025-01-08T07:44:08","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1100884.html"},"modified":"2025-01-08T15:44:11","modified_gmt":"2025-01-08T07:44:11","slug":"python%e6%95%b0%e6%8d%ae%e5%bd%92%e4%b8%80%e5%8c%96%e5%90%8e%e5%a6%82%e4%bd%95%e5%af%bc%e5%87%ba-2","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1100884.html","title":{"rendered":"python\u6570\u636e\u5f52\u4e00\u5316\u540e\u5982\u4f55\u5bfc\u51fa"},"content":{"rendered":"

\"python\u6570\u636e\u5f52\u4e00\u5316\u540e\u5982\u4f55\u5bfc\u51fa\"<\/p>\n

Python\u6570\u636e\u5f52\u4e00\u5316\u540e\u53ef\u4ee5\u901a\u8fc7\u591a\u79cd\u65b9\u5f0f\u5bfc\u51fa\u6570\u636e\u6587\u4ef6\uff0c\u5e38\u89c1\u7684\u65b9\u6cd5\u5305\u62ec\u4f7f\u7528pandas\u5e93\u5c06\u6570\u636e\u5bfc\u51fa\u4e3aCSV\u3001Excel\u7b49\u683c\u5f0f\u6587\u4ef6\uff0c\u4f7f\u7528numpy\u5e93\u4fdd\u5b58\u4e3anpy\u6587\u4ef6\uff0c\u4ee5\u53ca\u5229\u7528\u5176\u4ed6\u5e93\u8fdb\u884c\u66f4\u591a\u7c7b\u578b\u7684\u6587\u4ef6\u5bfc\u51fa\u3002<\/strong> \u5728\u8fd9\u7bc7\u6587\u7ae0\u4e2d\uff0c\u6211\u4eec\u5c06\u8be6\u7ec6\u4ecb\u7ecd\u8fd9\u4e9b\u65b9\u6cd5\uff0c\u5e76\u7ed9\u51fa\u5177\u4f53\u7684\u4ee3\u7801\u793a\u4f8b\u3002<\/p>\n<\/p>\n

\u4e00\u3001\u6570\u636e\u5f52\u4e00\u5316\u7684\u6982\u8ff0<\/p>\n<\/p>\n

\u6570\u636e\u5f52\u4e00\u5316\u662f\u6570\u636e\u9884\u5904\u7406\u4e2d\u7684\u4e00\u4e2a\u91cd\u8981\u6b65\u9aa4\uff0c\u76ee\u7684\u662f\u5c06\u4e0d\u540c\u5c3a\u5ea6\u7684\u6570\u636e\u8f6c\u6362\u5230\u540c\u4e00\u5c3a\u5ea6\u4e0a\uff0c\u4f7f\u6570\u636e\u66f4\u5bb9\u6613\u8fdb\u884c\u6bd4\u8f83\u548c\u5206\u6790\u3002\u5e38\u89c1\u7684\u6570\u636e\u5f52\u4e00\u5316\u65b9\u6cd5\u5305\u62ec\u6700\u5c0f-\u6700\u5927\u5f52\u4e00\u5316\uff08Min-Max Scaling\uff09\u3001Z-score\u6807\u51c6\u5316\u7b49\u3002\u4e0b\u9762\u6211\u4eec\u5c06\u4f7f\u7528\u6700\u5c0f-\u6700\u5927\u5f52\u4e00\u5316\u65b9\u6cd5\u5bf9\u6570\u636e\u8fdb\u884c\u5f52\u4e00\u5316\u5904\u7406\uff0c\u5e76\u4ecb\u7ecd\u5982\u4f55\u5bfc\u51fa\u5f52\u4e00\u5316\u540e\u7684\u6570\u636e\u3002<\/p>\n<\/p>\n

\u793a\u4f8b\u4ee3\u7801<\/h3>\n<\/p>\n

import pandas as pd<\/p>\n
import numpy as np<\/p>\n
from sklearn.preprocessing import MinMaxScaler<\/p>\n
\u521b\u5efa\u793a\u4f8b\u6570\u636e<\/strong><\/h2>\n
data = {<\/p>\n
    'A': [1, 2, 3, 4, 5],<\/p>\n
    'B': [10, 20, 30, 40, 50],<\/p>\n
    'C': [100, 200, 300, 400, 500]<\/p>\n
}<\/p>\n
df = pd.DataFrame(data)<\/p>\n
\u521b\u5efaMinMaxScaler\u5bf9\u8c61<\/strong><\/h2>\n
scaler = MinMaxScaler()<\/p>\n
\u5bf9\u6570\u636e\u8fdb\u884c\u5f52\u4e00\u5316\u5904\u7406<\/strong><\/h2>\n
normalized_data = scaler.fit_transform(df)<\/p>\n
\u5c06\u5f52\u4e00\u5316\u540e\u7684\u6570\u636e\u8f6c\u6362\u4e3aDataFrame<\/strong><\/h2>\n
normalized_df = pd.DataFrame(normalized_data, columns=df.columns)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e8c\u3001\u5bfc\u51fa\u4e3aCSV\u6587\u4ef6<\/p>\n<\/p>\n
CSV\uff08Comma-Separated Values\uff09\u6587\u4ef6\u662f\u4e00\u79cd\u5e38\u89c1\u7684\u6587\u672c\u6587\u4ef6\u683c\u5f0f\uff0c\u7528\u4e8e\u5b58\u50a8\u8868\u683c\u6570\u636e\u3002Pandas\u5e93\u63d0\u4f9b\u4e86\u65b9\u4fbf\u7684\u65b9\u6cd5\u5c06DataFrame\u5bfc\u51fa\u4e3aCSV\u6587\u4ef6\u3002<\/p>\n<\/p>\n
# \u5bfc\u51fa\u4e3aCSV\u6587\u4ef6<\/p>\n
normalized_df.to_csv('normalized_data.csv', index=False)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e09\u3001\u5bfc\u51fa\u4e3aExcel\u6587\u4ef6<\/p>\n<\/p>\n
Excel\u6587\u4ef6\u662f\u4e00\u79cd\u5e7f\u6cdb\u4f7f\u7528\u7684\u7535\u5b50\u8868\u683c\u6587\u4ef6\u683c\u5f0f\uff0cPandas\u5e93\u540c\u6837\u63d0\u4f9b\u4e86\u5c06DataFrame\u5bfc\u51fa\u4e3aExcel\u6587\u4ef6\u7684\u65b9\u6cd5\u3002<\/p>\n<\/p>\n
# \u5bfc\u51fa\u4e3aExcel\u6587\u4ef6<\/p>\n
normalized_df.to_excel('normalized_data.xlsx', index=False)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u56db\u3001\u5bfc\u51fa\u4e3aNumpy npy\u6587\u4ef6<\/p>\n<\/p>\n
Numpy\u5e93\u662fPython\u4e2d\u5904\u7406\u6570\u7ec4\u548c\u77e9\u9635\u7684\u57fa\u7840\u5e93\uff0cnpy\u6587\u4ef6\u662fNumpy\u7684\u4e8c\u8fdb\u5236\u6587\u4ef6\u683c\u5f0f\uff0c\u7528\u4e8e\u5b58\u50a8Numpy\u6570\u7ec4\u3002<\/p>\n<\/p>\n
# \u5bfc\u51fa\u4e3aNumpy npy\u6587\u4ef6<\/p>\n
np.save('normalized_data.npy', normalized_data)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e94\u3001\u5bfc\u51fa\u4e3aJSON\u6587\u4ef6<\/p>\n<\/p>\n
JSON\uff08JavaScript Object Notation\uff09\u6587\u4ef6\u662f\u4e00\u79cd\u8f7b\u91cf\u7ea7\u7684\u6570\u636e\u4ea4\u6362\u683c\u5f0f\uff0cPandas\u5e93\u4e5f\u652f\u6301\u5c06DataFrame\u5bfc\u51fa\u4e3aJSON\u6587\u4ef6\u3002<\/p>\n<\/p>\n
# \u5bfc\u51fa\u4e3aJSON\u6587\u4ef6<\/p>\n
normalized_df.to_json('normalized_data.json')<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u516d\u3001\u5bfc\u51fa\u4e3aSQL\u6570\u636e\u5e93<\/p>\n<\/p>\n
SQL\uff08Structured Query Language\uff09\u6570\u636e\u5e93\u662f\u4e00\u79cd\u7528\u4e8e\u7ba1\u7406\u548c\u64cd\u4f5c\u5173\u7cfb\u578b\u6570\u636e\u5e93\u7684\u8bed\u8a00\uff0cPandas\u5e93\u63d0\u4f9b\u4e86\u5c06DataFrame\u5bfc\u51fa\u5230SQL\u6570\u636e\u5e93\u7684\u65b9\u6cd5\u3002\u8fd9\u91cc\u6211\u4eec\u4ee5SQLite\u6570\u636e\u5e93\u4e3a\u4f8b\u3002<\/p>\n<\/p>\n
import sqlite3<\/p>\n
\u521b\u5efaSQLite\u6570\u636e\u5e93\u8fde\u63a5<\/strong><\/h2>\n
conn = sqlite3.connect('normalized_data.db')<\/p>\n
\u5c06DataFrame\u5bfc\u51fa\u5230SQL\u6570\u636e\u5e93<\/strong><\/h2>\n
normalized_df.to_sql('normalized_data', conn, if_exists='replace', index=False)<\/p>\n
\u5173\u95ed\u6570\u636e\u5e93\u8fde\u63a5<\/strong><\/h2>\n
conn.close()<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e03\u3001\u5bfc\u51fa\u4e3aParquet\u6587\u4ef6<\/p>\n<\/p>\n
Parquet\u6587\u4ef6\u662f\u4e00\u79cd\u5217\u5f0f\u5b58\u50a8\u6587\u4ef6\u683c\u5f0f\uff0c\u9002\u7528\u4e8e\u5927\u6570\u636e\u5904\u7406\uff0cPandas\u5e93\u652f\u6301\u5c06DataFrame\u5bfc\u51fa\u4e3aParquet\u6587\u4ef6\u3002<\/p>\n<\/p>\n
# \u5bfc\u51fa\u4e3aParquet\u6587\u4ef6<\/p>\n
normalized_df.to_parquet('normalized_data.parquet')<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u516b\u3001\u5bfc\u51fa\u4e3aHDF5\u6587\u4ef6<\/p>\n<\/p>\n
HDF5\uff08Hierarchical Data Format version 5\uff09\u6587\u4ef6\u662f\u4e00\u79cd\u7528\u4e8e\u5b58\u50a8\u548c\u7ec4\u7ec7\u5927\u89c4\u6a21\u6570\u636e\u7684\u6587\u4ef6\u683c\u5f0f\uff0cPandas\u5e93\u652f\u6301\u5c06DataFrame\u5bfc\u51fa\u4e3aHDF5\u6587\u4ef6\u3002<\/p>\n<\/p>\n
# \u5bfc\u51fa\u4e3aHDF5\u6587\u4ef6<\/p>\n
normalized_df.to_hdf('normalized_data.h5', key='df', mode='w')<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e5d\u3001\u5bfc\u51fa\u4e3aFeather\u6587\u4ef6<\/p>\n<\/p>\n
Feather\u6587\u4ef6\u662f\u4e00\u79cd\u5feb\u901f\u3001\u8f7b\u91cf\u7ea7\u7684\u5217\u5f0f\u5b58\u50a8\u6587\u4ef6\u683c\u5f0f\uff0cPandas\u5e93\u652f\u6301\u5c06DataFrame\u5bfc\u51fa\u4e3aFeather\u6587\u4ef6\u3002<\/p>\n<\/p>\n
# \u5bfc\u51fa\u4e3aFeather\u6587\u4ef6<\/p>\n
normalized_df.to_feather('normalized_data.feather')<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u5341\u3001\u5bfc\u51fa\u4e3aPickle\u6587\u4ef6<\/p>\n<\/p>\n
Pickle\u6587\u4ef6\u662fPython\u7684\u5bf9\u8c61\u5e8f\u5217\u5316\u6587\u4ef6\u683c\u5f0f\uff0cPandas\u5e93\u652f\u6301\u5c06DataFrame\u5bfc\u51fa\u4e3aPickle\u6587\u4ef6\u3002<\/p>\n<\/p>\n
# \u5bfc\u51fa\u4e3aPickle\u6587\u4ef6<\/p>\n
normalized_df.to_pickle('normalized_data.pkl')<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u603b\u7ed3<\/p>\n<\/p>\n
\u901a\u8fc7\u4e0a\u8ff0\u65b9\u6cd5\uff0c\u6211\u4eec\u53ef\u4ee5\u5c06\u5f52\u4e00\u5316\u540e\u7684\u6570\u636e\u5bfc\u51fa\u4e3a\u591a\u79cd\u6587\u4ef6\u683c\u5f0f\uff0c\u5305\u62ecCSV\u3001Excel\u3001Numpy npy\u3001JSON\u3001SQL\u6570\u636e\u5e93\u3001Parquet\u3001HDF5\u3001Feather\u548cPickle\u6587\u4ef6\u3002\u6839\u636e\u5177\u4f53\u7684\u5e94\u7528\u573a\u666f\u548c\u9700\u6c42\uff0c\u9009\u62e9\u5408\u9002\u7684\u5bfc\u51fa\u65b9\u6cd5\uff0c\u53ef\u4ee5\u65b9\u4fbf\u5730\u4fdd\u5b58\u548c\u5171\u4eab\u5f52\u4e00\u5316\u540e\u7684\u6570\u636e\u3002\u5e0c\u671b\u8fd9\u7bc7\u6587\u7ae0\u5bf9\u4f60\u4e86\u89e3\u548c\u638c\u63e1Python\u6570\u636e\u5f52\u4e00\u5316\u540e\u7684\u5bfc\u51fa\u65b9\u6cd5\u6709\u6240\u5e2e\u52a9\u3002<\/p>\n<\/p>\n
\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n
 \u5728Python\u4e2d\u5982\u4f55\u8fdb\u884c\u6570\u636e\u5f52\u4e00\u5316\uff1f<\/strong>
\u6570\u636e\u5f52\u4e00\u5316\u901a\u5e38\u662f\u901a\u8fc7\u5c06\u6570\u636e\u8f6c\u6362\u5230\u4e00\u4e2a\u7279\u5b9a\u8303\u56f4\uff08\u4f8b\u59820\u52301\uff09\u6765\u5b8c\u6210\u7684\u3002\u5e38\u7528\u7684\u65b9\u6cd5\u5305\u62ecMin-Max\u7f29\u653e\u548cZ-score\u6807\u51c6\u5316\u3002\u5728Python\u4e2d\uff0c\u53ef\u4ee5\u4f7f\u7528\u5e93\u5982scikit-learn<\/code>\u4e2d\u7684MinMaxScaler<\/code>\u6216StandardScaler<\/code>\u6765\u5b9e\u73b0\u5f52\u4e00\u5316\u3002\u5177\u4f53\u6b65\u9aa4\u5305\u62ec\u5bfc\u5165\u5e93\u3001\u521b\u5efa\u5f52\u4e00\u5316\u5bf9\u8c61\u3001\u62df\u5408\u6570\u636e\u5e76\u8f6c\u6362\u3002<\/p>\n
\u5f52\u4e00\u5316\u540e\u7684\u6570\u636e\u53ef\u4ee5\u4fdd\u5b58\u4e3a\u54ea\u4e9b\u683c\u5f0f\uff1f<\/strong>
\u5f52\u4e00\u5316\u540e\u7684\u6570\u636e\u53ef\u4ee5\u4fdd\u5b58\u4e3a\u591a\u79cd\u683c\u5f0f\uff0c\u5e38\u89c1\u7684\u6709CSV\u3001Excel\u3001JSON\u7b49\u3002\u4f7f\u7528Pandas\u5e93\u53ef\u4ee5\u8f7b\u677e\u5b9e\u73b0\u6570\u636e\u7684\u5bfc\u51fa\u3002\u4f8b\u5982\uff0c\u4f7f\u7528DataFrame.to_csv()<\/code>\u65b9\u6cd5\u53ef\u4ee5\u5c06\u6570\u636e\u4fdd\u5b58\u4e3aCSV\u6587\u4ef6\uff0c\u4f7f\u7528DataFrame.to_excel()<\/code>\u53ef\u4ee5\u4fdd\u5b58\u4e3aExcel\u683c\u5f0f\u3002<\/p>\n
\u5982\u4f55\u786e\u4fdd\u5bfc\u51fa\u7684\u5f52\u4e00\u5316\u6570\u636e\u51c6\u786e\u65e0\u8bef\uff1f<\/strong>
\u4e3a\u4e86\u786e\u4fdd\u5bfc\u51fa\u7684\u5f52\u4e00\u5316\u6570\u636e\u51c6\u786e\uff0c\u53ef\u4ee5\u5728\u5bfc\u51fa\u524d\u6253\u5370\u6216\u67e5\u770b\u6570\u636e\u7684\u524d\u51e0\u884c\uff0c\u786e\u8ba4\u5f52\u4e00\u5316\u7684\u7ed3\u679c\u7b26\u5408\u9884\u671f\u3002\u6b64\u5916\uff0c\u68c0\u67e5\u6570\u636e\u7c7b\u578b\u548c\u7f3a\u5931\u503c\u4e5f\u662f\u5fc5\u8981\u7684\u6b65\u9aa4\u3002\u5728\u4fdd\u5b58\u6570\u636e\u65f6\uff0c\u53ef\u4ee5\u8bbe\u7f6e\u53c2\u6570\u6765\u63a7\u5236\u5bfc\u51fa\u7684\u683c\u5f0f\u548c\u5185\u5bb9\uff0c\u4ee5\u786e\u4fdd\u6570\u636e\u7684\u5b8c\u6574\u6027\u548c\u53ef\u9760\u6027\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"Python\u6570\u636e\u5f52\u4e00\u5316\u540e\u53ef\u4ee5\u901a\u8fc7\u591a\u79cd\u65b9\u5f0f\u5bfc\u51fa\u6570\u636e\u6587\u4ef6\uff0c\u5e38\u89c1\u7684\u65b9\u6cd5\u5305\u62ec\u4f7f\u7528pandas\u5e93\u5c06\u6570\u636e\u5bfc\u51fa\u4e3aCSV\u3001Ex […]","protected":false},"author":3,"featured_media":1100897,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[37],"tags":[],"acf":[],"_links":{"self":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1100884"}],"collection":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/comments?post=1100884"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1100884\/revisions"}],"predecessor-version":[{"id":1100902,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1100884\/revisions\/1100902"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1100897"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1100884"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1100884"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1100884"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}