{"id":3122,"date":"2023-07-19T03:04:16","date_gmt":"2023-07-19T03:04:16","guid":{"rendered":"https:\/\/statorials.org\/cn\/%e7%86%8a%e7%8c%ab%e7%81%ab%e8%bd%a6%e6%b5%8b%e8%af%95\/"},"modified":"2023-07-19T03:04:16","modified_gmt":"2023-07-19T03:04:16","slug":"%e7%86%8a%e7%8c%ab%e7%81%ab%e8%bd%a6%e6%b5%8b%e8%af%95","status":"publish","type":"post","link":"https:\/\/statorials.org\/cn\/%e7%86%8a%e7%8c%ab%e7%81%ab%e8%bd%a6%e6%b5%8b%e8%af%95\/","title":{"rendered":"\u5982\u4f55\u4ece pandas dataframe \u521b\u5efa\u8bad\u7ec3\u96c6\u548c\u6d4b\u8bd5\u96c6"},"content":{"rendered":"

<\/p>\n

\n

\u5f53\u5c06\u673a\u5668\u5b66\u4e60\u6a21\u578b<\/a>\u62df\u5408\u5230\u6570\u636e\u96c6\u65f6\uff0c\u6211\u4eec\u901a\u5e38\u5c06\u6570\u636e\u96c6\u5206\u4e3a\u4e24\u7ec4\uff1a<\/span><\/p>\n

1.\u8bad\u7ec3\u96c6\uff1a<\/strong>\u7528\u4e8e\u8bad\u7ec3\u6a21\u578b\uff08\u539f\u59cb\u6570\u636e\u96c6\u768470-80%\uff09<\/span><\/p>\n

2.\u6d4b\u8bd5\u96c6\uff1a<\/strong>\u7528\u4e8e\u83b7\u5f97\u6a21\u578b\u6027\u80fd\u7684\u65e0\u504f\u4f30\u8ba1\uff08\u539f\u59cb\u6570\u636e\u96c6\u768420-30%\uff09<\/span><\/p>\n

\u5728Python\u4e2d\uff0c\u6709\u4e24\u79cd\u5e38\u89c1\u7684\u65b9\u6cd5\u53ef\u4ee5\u5c06pandas DataFrame\u62c6\u5206\u4e3a\u8bad\u7ec3\u96c6\u548c\u6d4b\u8bd5\u96c6\uff1a<\/span><\/p>\n

\u65b9\u6cd5\u4e00\uff1a\u4f7f\u7528sklearn\u7684train_test_split()<\/strong><\/span><\/p>\n

 from<\/span> sklearn. model_selection<\/span> import<\/span> train_test_split\n\ntrain, test = train_test_split(df, test_size= 0.2<\/span> , random_state= 0<\/span> )<\/strong><\/pre>\n
\u65b9\u6cd52\uff1a\u4f7f\u7528pandas\u4e2d\u7684sample()<\/strong><\/span><\/p>\n
 train = df. sample<\/span> (frac= 0.8<\/span> , random_state= 0<\/span> )\ntest = df. drop<\/span> ( train.index<\/span> )<\/strong><\/pre>\n
\u4ee5\u4e0b\u793a\u4f8b\u5c55\u793a\u4e86\u5982\u4f55\u5c06\u6bcf\u79cd\u65b9\u6cd5\u4e0e\u4ee5\u4e0b pandas DataFrame \u4e00\u8d77\u4f7f\u7528\uff1a<\/span><\/p>\n
 import<\/span> pandas as<\/span> pd\nimport<\/span> numpy as<\/span> np\n\n#make this example reproducible\n<\/span>n.p. random<\/span> . seeds<\/span> (1)\n\n#create DataFrame with 1,000 rows and 3 columns\n<\/span>df = pd. DataFrame<\/span> (<\/span> {' x1<\/span> ': np.random.randint<\/span> (30,size=1000),\n                   ' x2<\/span> ': np. random<\/span> . randint<\/span> (12, size=1000),\n                   ' y<\/span> ': np. random<\/span> . randint<\/span> (2, size=1000)})\n\n#view first few rows of DataFrame<\/span>\ndf. head<\/span> ()\n\n        x1 x2 y\n0 5 1 1\n1 11 8 0\n2 12 4 1\n3 8 7 0\n4 9 0 0\n<\/strong><\/pre>\n
\u793a\u4f8b 1\uff1a\u4f7f\u7528 sklearn \u4e2d\u7684 train_test_split()<\/strong><\/span><\/h3>\n
\u4ee5\u4e0b\u4ee3\u7801\u5c55\u793a\u4e86\u5982\u4f55\u4f7f\u7528sklearn<\/strong>\u7684train_test_split()<\/strong>\u51fd\u6570\u5c06 pandas DataFrame \u62c6\u5206\u4e3a\u8bad\u7ec3\u96c6\u548c\u6d4b\u8bd5\u96c6\uff1a<\/span><\/span><\/p>\n
 from<\/span> sklearn. model_selection<\/span> import<\/span> train_test_split\n\n#split original DataFrame into training and testing sets\n<\/span>train, test = train_test_split(df, test_size= 0.2<\/span> , random_state= 0<\/span> )\n\n#view first few rows of each set<\/span>\nprint<\/span> ( train.head<\/span> ())\n\n     x1 x2 y\n687 16 2 0\n500 18 2 1\n332 4 10 1\n979 2 8 1\n817 11 1 0\n\nprint<\/span> ( test.head<\/span> ())\n\n     x1 x2 y\n993 22 1 1\n859 27 6 0\n298 27 8 1\n553 20 6 0\n672 9 2 1\n\n#print size of each set<\/span>\nprint<\/span> (train. shape<\/span> , test. shape<\/span> )\n\n(800, 3) (200, 3)\n<\/strong><\/pre>\n
\u4ece\u7ed3\u679c\u4e2d\u6211\u4eec\u53ef\u4ee5\u770b\u5230\u521b\u5efa\u4e86\u4e24\u4e2a\u96c6\u5408\uff1a<\/span><\/p>\n