{"id":3566,"date":"2023-07-16T19:43:48","date_gmt":"2023-07-16T19:43:48","guid":{"rendered":"https:\/\/statorials.org\/cn\/%e7%86%8a%e7%8c%ab%e5%8f%98%e5%bc%82\/"},"modified":"2023-07-16T19:43:48","modified_gmt":"2023-07-16T19:43:48","slug":"%e7%86%8a%e7%8c%ab%e5%8f%98%e5%bc%82","status":"publish","type":"post","link":"https:\/\/statorials.org\/cn\/%e7%86%8a%e7%8c%ab%e5%8f%98%e5%bc%82\/","title":{"rendered":"Pandas\uff1a\u5982\u4f55\u4f7f\u7528\u76f8\u5f53\u4e8e r \u7684 mutate() \u51fd\u6570"},"content":{"rendered":"

<\/p>\n

\n

\u5728 R \u7f16\u7a0b\u8bed\u8a00\u4e2d\uff0c\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528dplyr<\/strong>\u5305\u4e2d\u7684mutate()<\/strong>\u51fd\u6570\u5feb\u901f\u5c06\u65b0\u5217\u6dfb\u52a0\u5230\u6839\u636e\u73b0\u6709\u5217\u8ba1\u7b97\u7684\u6570\u636e\u5e27\u4e2d\u3002<\/span><\/span><\/p>\n

\u4f8b\u5982\uff0c\u4ee5\u4e0b\u4ee3\u7801\u663e\u793a\u5982\u4f55\u8ba1\u7b97 R \u4e2d\u7279\u5b9a\u5217\u7684\u5e73\u5747\u503c\u5e76\u5c06\u8be5\u503c\u6dfb\u52a0\u4e3a\u6570\u636e\u6846\u4e2d\u7684\u65b0\u5217\uff1a<\/span><\/p>\n

 library<\/span> (dplyr)\n\n#create data frame\n<\/span>df <- data. frame<\/span> (team=c('A', 'A', 'A', 'A', 'B', 'B', 'B', 'B'),\n                 points=c(30, 22, 19, 14, 14, 11, 20, 28))\n\n#add new column that shows mean points by team\n<\/span>df <- df %>%\n      group_by(team) %>%\n      mutate(mean_points = mean(points))\n\n#view updated data frame\n<\/span>df\n\n  team points mean_points           \n1 to 30 21.2\n2 A 22 21.2\n3 A 19 21.2\n4 A 14 21.2\n5 B 14 18.2\n6 B 11 18.2\n7 B 20 18.2\n8 B 28 18.2\n<\/strong><\/pre>\n
 pandas \u4e2dmutate()<\/strong>\u51fd\u6570\u7684\u7b49\u6548\u9879\u662ftransform()<\/strong>\u51fd\u6570\u3002<\/span><\/p>\n
\u4e0b\u9762\u7684\u4f8b\u5b50\u5c55\u793a\u4e86\u5982\u4f55\u5728\u5b9e\u9645\u4e2d\u4f7f\u7528\u8fd9\u4e2a\u529f\u80fd\u3002<\/span><\/p>\n
\u793a\u4f8b\uff1a\u4f7f\u7528pandas \u4e2d\u7684transform() \u6765\u590d\u5236R \u4e2d\u7684mutate()<\/strong><\/span><\/h2>\n
\u5047\u8bbe\u6211\u4eec\u6709\u4ee5\u4e0b pandas DataFrame\uff0c\u663e\u793a\u6765\u81ea\u4e0d\u540c\u7403\u961f\u7684\u7bee\u7403\u8fd0\u52a8\u5458\u7684\u5f97\u5206\uff1a<\/span><\/p>\n
 import<\/span> pandas as<\/span> pd\n\n#createDataFrame\ndf = pd. DataFrame<\/span> ({' team<\/span> ': ['A', 'A', 'A', 'A', 'B', 'B', 'B', 'B'],\n                   ' points<\/span> ': [30, 22, 19, 14, 14, 11, 20, 28]})<\/span>\n\n#view DataFrame\nprint<\/span> (df)\n\n  team points\n0 to 30\n1 to 22\n2 to 19\n3 to 14\n4 B 14\n5 B 11\n6 B 20\n7 B 28\n<\/span><\/span><\/strong><\/pre>\n
\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528transform()<\/strong>\u51fd\u6570\u6dfb\u52a0\u4e00\u4e2a\u540d\u4e3aMean_points<\/strong>\u7684\u65b0\u5217\uff0c\u8be5\u5217\u663e\u793a\u6bcf\u4e2a\u56e2\u961f\u7684\u5e73\u5747\u5f97\u5206\uff1a<\/span><\/p>\n
 #add new column to DataFrame that shows mean points by team\n<\/span>df[' mean_points<\/span> '] = df. groupby<\/span> (' team<\/span> ')[' points<\/span> ']. transform<\/span> (' mean<\/span> ')\n\n#view updated DataFrame\n<\/span>print<\/span> (df)\n\n  team points mean_points\n0 to 30 21.25\n1 to 22 21.25\n2 A 19 21.25\n3 to 14 21.25\n4 B 14 18.25\n5 B 11 18.25\n6 B 20 18.25\n7 B 28 18.25\n<\/strong><\/pre>\n
 A \u961f\u7403\u5458\u7684\u5e73\u5747\u5f97\u5206\u4e3a21.25<\/strong> \uff0cB \u961f\u7403\u5458\u7684\u5e73\u5747\u5f97\u5206\u4e3a18.25<\/strong> \uff0c\u56e0\u6b64\u8fd9\u4e9b\u503c\u88ab\u76f8\u5e94\u5730\u5206\u914d\u7ed9\u65b0\u5217\u4e2d\u7684\u6bcf\u4e2a\u7403\u5458\u3002<\/span><\/p>\n
\u8bf7\u6ce8\u610f\uff0c\u8fd9\u4e0e\u4ecb\u7ecd\u6027\u793a\u4f8b\u4e2d\u4f7f\u7528mutate()<\/strong>\u51fd\u6570\u83b7\u5f97\u7684\u7ed3\u679c\u76f8\u5339\u914d\u3002<\/span><\/p>\n
\u503c\u5f97\u6ce8\u610f\u7684\u662f\uff0c\u60a8\u8fd8\u53ef\u4ee5\u5728transform()<\/strong>\u51fd\u6570\u4e2d\u4f7f\u7528lambda<\/strong>\u6765\u6267\u884c\u81ea\u5b9a\u4e49\u8ba1\u7b97\u3002<\/span><\/p>\n
\u4f8b\u5982\uff0c\u4ee5\u4e0b\u4ee3\u7801\u5c55\u793a\u4e86\u5982\u4f55\u4f7f\u7528lambda<\/strong>\u8ba1\u7b97<\/span>\u5404\u81ea\u7403\u961f\u4e2d\u6bcf\u4e2a\u7403\u5458\u7684\u603b\u5f97\u5206\u767e\u5206\u6bd4\uff1a<\/span><\/p>\n
 #create new column called percent_of_points\ndf[' percent_of_points<\/span> '] = df. groupby<\/span> (' team<\/span> ')[' points<\/span> ']. transform<\/span> ( lambda<\/span> x:x\/ x.sum<\/span> ())\n<\/span>\n#view updated DataFrame\nprint<\/span> (df)\n\n  team points percent_of_points\n0 A 30 0.352941\n1 A 22 0.258824\n2 A 19 0.223529\n3 A 14 0.164706\n4 B 14 0.191781\n5 B 11 0.150685\n6 B 20 0.273973\n7 B 28 0.383562\n<\/span><\/span><\/strong><\/pre>\n
\u4ee5\u4e0b\u662f\u5982\u4f55\u89e3\u91ca\u7ed3\u679c\uff1a<\/span><\/p>\n