{"id":3558,"date":"2023-07-16T20:42:07","date_gmt":"2023-07-16T20:42:07","guid":{"rendered":"https:\/\/statorials.org\/cn\/sklearn%e6%a0%87%e7%ad%be%e7%bc%96%e7%a0%81%e5%a4%9a%e5%88%97\/"},"modified":"2023-07-16T20:42:07","modified_gmt":"2023-07-16T20:42:07","slug":"sklearn%e6%a0%87%e7%ad%be%e7%bc%96%e7%a0%81%e5%a4%9a%e5%88%97","status":"publish","type":"post","link":"https:\/\/statorials.org\/cn\/sklearn%e6%a0%87%e7%ad%be%e7%bc%96%e7%a0%81%e5%a4%9a%e5%88%97\/","title":{"rendered":"Scikit-learn\uff1a\u4f7f\u7528\u591a\u5217\u6807\u7b7e\u7f16\u7801"},"content":{"rendered":"

<\/p>\n

\n

\u5728\u673a\u5668\u5b66\u4e60\u4e2d\uff0c\u6807\u7b7e\u7f16\u7801<\/strong>\u662f\u5c06\u5206\u7c7b\u53d8\u91cf<\/a>\u7684\u503c\u8f6c\u6362\u4e3a\u6574\u6570\u503c\u7684\u8fc7\u7a0b\u3002<\/span><\/p>\n

\u4f8b\u5982\uff0c\u4ee5\u4e0b\u5c4f\u5e55\u622a\u56fe\u663e\u793a\u4e86\u5982\u4f55\u5c06\u540d\u4e3aTeam<\/strong>\u7684\u5206\u7c7b\u53d8\u91cf\u7684\u6bcf\u4e2a\u552f\u4e00\u503c\u8f6c\u6362\u4e3a\u57fa\u4e8e\u5b57\u6bcd\u987a\u5e8f\u7684\u6574\u6570\u503c\uff1a<\/span> <\/p>\n

\"\"<\/p>\n

\u60a8\u53ef\u4ee5\u4f7f\u7528\u4ee5\u4e0b\u8bed\u6cd5\u5728Python\u4e2d\u6267\u884c\u591a\u5217\u6807\u7b7e\u7f16\u7801\uff1a<\/span><\/p>\n

 from<\/span> sklearn. preprocessing<\/span> import<\/span> LabelEncoder\n\n#perform label encoding on col1, col2 columns\n<\/span>df[[' col1<\/span> ', ' col2<\/span> ']] = df[[' col1<\/span> ', ' col2<\/span> ']]. apply<\/span> (LabelEncoder(). fit_transform<\/span> )\n<\/strong><\/pre>\n
\u4ee5\u4e0b\u793a\u4f8b\u5c55\u793a\u4e86\u5982\u4f55\u5728\u5b9e\u8df5\u4e2d\u4f7f\u7528\u6b64\u8bed\u6cd5\u3002<\/span><\/p>\n
\u793a\u4f8b\uff1a\u5728 Python \u4e2d\u7f16\u7801\u6807\u7b7e<\/strong><\/span><\/h2>\n
\u5047\u8bbe\u6211\u4eec\u6709\u4ee5\u4e0b pandas DataFrame\uff0c\u5176\u4e2d\u5305\u542b\u6709\u5173\u5404\u79cd\u7bee\u7403\u8fd0\u52a8\u5458\u7684\u4fe1\u606f\uff1a<\/span><\/p>\n
 import<\/span> pandas as<\/span> pd\n\n#createDataFrame<\/span>\ndf = pd. DataFrame<\/span> ({' team<\/span> ': ['A', 'A', 'B', 'B', 'B', 'C', 'C', 'D'],\n                   ' position<\/span> ': ['G', 'F', 'G', 'F', 'F', 'G', 'G', 'F'],\n                   ' all_star<\/span> ': ['Y', 'N', 'Y', 'Y', 'Y', 'N', 'Y', 'N'],\n                   ' points<\/span> ': [11, 8, 10, 6, 6, 5, 9, 12]})\n\n#view DataFrame\n<\/span>print<\/span> (df)\n\n  team position all_star points\n0 AGY 11\n1 AFN 8\n2 BGY 10\n3 BFY 6\n4 BFY 6\n5 CGN 5\n6 CGY 9\n7 DFN 12\n<\/strong><\/span><\/pre>\n
\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528\u4ee5\u4e0b\u4ee3\u7801\u6267\u884c\u6807\u7b7e\u7f16\u7801\uff0c\u5c06team<\/strong> \u3001 position<\/strong>\u548call_star<\/strong>\u5217\u4e2d\u7684\u6bcf\u4e2a\u5206\u7c7b\u503c\u8f6c\u6362\u4e3a\u6574\u6570\u503c\uff1a<\/span><\/p>\n
 from<\/span> sklearn. preprocessing<\/span> import<\/span> LabelEncoder\n\n#perform label encoding across team, position, and all_star columns\ndf[[' team<\/span> ', ' position<\/span> ', ' all_star<\/span> ']] = df[[' team<\/span> ', ' position<\/span> ', ' all_star<\/span> ']]. apply<\/span> (LabelEncoder(). fit_transform<\/span> )\n<\/span>\n#view udpated DataFrame\nprint<\/span> (df)\n\n   team position all_star points\n0 0 1 1 11\n1 0 0 0 8\n2 1 1 1 10\n3 1 0 1 6\n4 1 0 1 6\n5 2 1 0 5\n6 2 1 1 9\n7 3 0 0 12<\/span><\/span><\/strong><\/pre>\n
\u4ece\u7ed3\u679c\u4e2d\u6211\u4eec\u53ef\u4ee5\u770b\u5230team<\/strong> \u3001 position<\/strong>\u548call_star<\/strong>\u5217\u7684\u6bcf\u4e2a\u503c\u90fd\u5df2\u8f6c\u6362\u4e3a\u6574\u6570\u503c\u3002<\/span><\/p>\n
\u4f8b\u5982\uff0c\u5728\u56e2\u961f<\/strong>\u4e00\u680f\u4e2d\u6211\u4eec\u53ef\u4ee5\u770b\u5230\uff1a<\/span><\/p>\n