{"id":3563,"date":"2023-07-16T19:43:48","date_gmt":"2023-07-16T19:43:48","guid":{"rendered":"https:\/\/statorials.org\/ko\/%e1%84%91%e1%85%a2%e1%86%ab%e1%84%83%e1%85%a5%e1%84%80%e1%85%a1-%e1%84%83%e1%85%a9%e1%86%af%e1%84%8b%e1%85%a7%e1%86%ab%e1%84%87%e1%85%a7%e1%86%ab%e1%84%8b%e1%85%b5%e1%84%85%e1%85%b3%e1%86%af-%e1%84%8b\/"},"modified":"2023-07-16T19:43:48","modified_gmt":"2023-07-16T19:43:48","slug":"%e1%84%91%e1%85%a2%e1%86%ab%e1%84%83%e1%85%a5%e1%84%80%e1%85%a1-%e1%84%83%e1%85%a9%e1%86%af%e1%84%8b%e1%85%a7%e1%86%ab%e1%84%87%e1%85%a7%e1%86%ab%e1%84%8b%e1%85%b5%e1%84%85%e1%85%b3%e1%86%af-%e1%84%8b","status":"publish","type":"post","link":"https:\/\/statorials.org\/ko\/%e1%84%91%e1%85%a2%e1%86%ab%e1%84%83%e1%85%a5%e1%84%80%e1%85%a1-%e1%84%83%e1%85%a9%e1%86%af%e1%84%8b%e1%85%a7%e1%86%ab%e1%84%87%e1%85%a7%e1%86%ab%e1%84%8b%e1%85%b5%e1%84%85%e1%85%b3%e1%86%af-%e1%84%8b\/","title":{"rendered":"Pandas: r\uc5d0 \ud574\ub2f9\ud558\ub294 mutate() \ud568\uc218\ub97c \uc0ac\uc6a9\ud558\ub294 \ubc29\ubc95"},"content":{"rendered":"

<\/p>\n

\n

R \ud504\ub85c\uadf8\ub798\ubc0d \uc5b8\uc5b4\uc5d0\uc11c\ub294 dplyr<\/strong> \ud328\ud0a4\uc9c0\uc758 mutate()<\/strong> \ud568\uc218\ub97c \uc0ac\uc6a9\ud558\uc5ec \uae30\uc874 \uc5f4\uc5d0\uc11c \uacc4\uc0b0\ub41c \ub370\uc774\ud130 \ud504\ub808\uc784\uc5d0 \uc0c8 \uc5f4\uc744 \ube60\ub974\uac8c \ucd94\uac00\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/span><\/span><\/p>\n

\uc608\ub97c \ub4e4\uc5b4 \ub2e4\uc74c \ucf54\ub4dc\ub294 R\uc5d0\uc11c \ud2b9\uc815 \uc5f4\uc758 \ud3c9\uade0 \uac12\uc744 \uacc4\uc0b0\ud558\uace0 \ud574\ub2f9 \uac12\uc744 \ub370\uc774\ud130 \ud504\ub808\uc784\uc758 \uc0c8 \uc5f4\ub85c \ucd94\uac00\ud558\ub294 \ubc29\ubc95\uc744 \ubcf4\uc5ec\uc90d\ub2c8\ub2e4.<\/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\uc758 mutate()<\/strong> \ud568\uc218\uc5d0 \ud574\ub2f9\ud558\ub294 \uac83\uc740 \ubcc0\ud658()<\/strong> \ud568\uc218\uc785\ub2c8\ub2e4.<\/span><\/p>\n
 \ub2e4\uc74c \uc608\uc5d0\uc11c\ub294 \uc774 \uae30\ub2a5\uc744 \uc2e4\uc81c\ub85c \uc0ac\uc6a9\ud558\ub294 \ubc29\ubc95\uc744 \ubcf4\uc5ec\uc90d\ub2c8\ub2e4.<\/span><\/p>\n
 \uc608: \ud32c\ub354\uc5d0\uc11c \ubcc0\ud615()\uc744 \uc0ac\uc6a9\ud558\uc5ec R\uc5d0\uc11c mutate()\ub97c \ubcf5\uc81c\ud569\ub2c8\ub2e4.<\/strong><\/span><\/h2>\n
 \uc11c\ub85c \ub2e4\ub978 \ud300\uc758 \ub18d\uad6c \uc120\uc218\ub4e4\uc774 \ub4dd\uc810\ud55c \uc810\uc218\ub97c \ubcf4\uc5ec\uc8fc\ub294 \ub2e4\uc74c\uacfc \uac19\uc740 \ud32c\ub354 DataFrame\uc774 \uc788\ub2e4\uace0 \uac00\uc815\ud569\ub2c8\ub2e4.<\/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
 \ubcc0\ud658()<\/strong> \ud568\uc218\ub97c \uc0ac\uc6a9\ud558\uc5ec \uac01 \ud300\uc774 \ud68d\ub4dd\ud55c \ud3c9\uade0 \uc810\uc218\ub97c \ud45c\uc2dc\ud558\ub294 Mean_points<\/strong> \ub77c\ub294 \uc0c8 \uc5f4\uc744 \ucd94\uac00\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/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\ud300 \uc120\uc218\uc758 \ud3c9\uade0 \uc810\uc218\ub294 21.25<\/strong> , B\ud300 \uc120\uc218\uc758 \ud3c9\uade0 \uc810\uc218\ub294 18.25<\/strong> \uc774\ubbc0\ub85c \uc774 \uac12\uc740 \uc0c8 \uc5f4\uc758 \uac01 \uc120\uc218\uc5d0\uac8c \uc801\uc808\ud558\uac8c \ud560\ub2f9\ub418\uc5c8\uc2b5\ub2c8\ub2e4.<\/span><\/p>\n
 \uc774\ub294 \uc18c\uac1c \uc608\uc81c\uc5d0\uc11c mutate()<\/strong> \ud568\uc218\ub97c \uc0ac\uc6a9\ud558\uc5ec \uc5bb\uc740 \uacb0\uacfc\uc640 \uc77c\uce58\ud569\ub2c8\ub2e4.<\/span><\/p>\n
 \ub78c\ub2e4\ub97c<\/strong> \uc0ac\uc6a9\ud558\uc5ec \ubcc0\ud658()<\/strong> \ud568\uc218\uc5d0\uc11c \uc0ac\uc6a9\uc790 \uc815\uc758 \uacc4\uc0b0\uc744 \uc218\ud589\ud560 \uc218\ub3c4 \uc788\ub2e4\ub294 \uc810\uc740 \uc8fc\ubaa9\ud560 \uac00\uce58\uac00 \uc788\uc2b5\ub2c8\ub2e4.<\/span><\/p>\n
 \uc608\ub97c \ub4e4\uc5b4 \ub2e4\uc74c \ucf54\ub4dc\ub294 \ub78c\ub2e4\ub97c<\/strong> \uc0ac\uc6a9\ud558\uc5ec<\/span> \ud574\ub2f9 \ud300\uc758 \uac01 \ud50c\ub808\uc774\uc5b4\uac00 \ub4dd\uc810\ud55c \ucd1d\uc810\uc758 \ubc31\ubd84\uc728\uc744 \uacc4\uc0b0\ud558\ub294 \ubc29\ubc95\uc744 \ubcf4\uc5ec\uc90d\ub2c8\ub2e4.<\/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
 \uacb0\uacfc\ub97c \ud574\uc11d\ud558\ub294 \ubc29\ubc95\uc740 \ub2e4\uc74c\uacfc \uac19\uc2b5\ub2c8\ub2e4.<\/span><\/p>\n