{"id":3197,"date":"2023-07-18T17:44:30","date_gmt":"2023-07-18T17:44:30","guid":{"rendered":"https:\/\/statorials.org\/ko\/pandas-groupby-%e1%84%87%e1%85%a7%e1%86%ab%e1%84%92%e1%85%aa%e1%86%ab\/"},"modified":"2023-07-18T17:44:30","modified_gmt":"2023-07-18T17:44:30","slug":"pandas-groupby-%e1%84%87%e1%85%a7%e1%86%ab%e1%84%92%e1%85%aa%e1%86%ab","status":"publish","type":"post","link":"https:\/\/statorials.org\/ko\/pandas-groupby-%e1%84%87%e1%85%a7%e1%86%ab%e1%84%92%e1%85%aa%e1%86%ab\/","title":{"rendered":"Pandas\uc5d0\uc11c groupby() \ubc0f \ubcc0\ud658() \ud568\uc218\ub97c \uc0ac\uc6a9\ud558\ub294 \ubc29\ubc95"},"content":{"rendered":"

<\/p>\n

\n

\ub2e4\uc74c \uba54\uc11c\ub4dc\ub97c \uc0ac\uc6a9\ud558\uc5ec pandas DataFrame\uc5d0\uc11c groupby()<\/strong> \ubc0f \ubcc0\ud658()<\/strong> \ud568\uc218\ub97c \ud568\uaed8 \uc0ac\uc6a9\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/span><\/p>\n

\ubc29\ubc95 1: \ub0b4\uc7a5 \ud568\uc218\uc640 \ud568\uaed8 groupby() \ubc0f \ubcc0\ud658() \uc0ac\uc6a9<\/strong><\/span><\/p>\n

 df[' new<\/span> '] = df. groupby<\/span> (' group_var<\/span> ')[' value_var<\/span> ']. transform<\/span> (' mean<\/span> ')\n<\/strong><\/pre>\n
 \ubc29\ubc95 2: \uc0ac\uc6a9\uc790 \uc815\uc758 \ud568\uc218\uc640 \ud568\uaed8 groupby() \ubc0f \ubcc0\ud658() \uc0ac\uc6a9<\/strong><\/span><\/p>\n
 df[' new<\/span> '] = df. groupby<\/span> (' group_var<\/span> ')[' value_var<\/span> ']. transform<\/span> ( lambda<\/span> x: some function)<\/strong><\/pre>\n
 \ub2e4\uc74c \uc608\uc5d0\uc11c\ub294 \ub2e4\uc74c pandas DataFrame\uc5d0\uc11c \uc2e4\uc81c\ub85c \uac01 \uba54\uc11c\ub4dc\ub97c \uc0ac\uc6a9\ud558\ub294 \ubc29\ubc95\uc744 \ubcf4\uc5ec\uc90d\ub2c8\ub2e4.<\/span><\/p>\n
 import<\/span> pandas as<\/span> pd\n\n#createDataFrame<\/span>\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]})\n\n#view DataFrame\nprint<\/span><\/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<\/b><\/pre>\n
 \uc608 1: \ub0b4\uc7a5 \ud568\uc218\uc640 \ud568\uaed8 groupby() \ubc0f \ubcc0\ud658() \uc0ac\uc6a9<\/strong><\/span><\/h3>\n
 \ub2e4\uc74c \ucf54\ub4dc\ub294 groupby(<\/strong> ) \ubc0f \ubcc0\ud658()<\/strong> \ud568\uc218\ub97c \uc0ac\uc6a9\ud558\uc5ec Mean_points\ub77c\ub294 DataFrame\uc5d0 \uc0c8 \uc5f4\uc744 \ucd94\uac00\ud558\ub294 \ubc29\ubc95\uc744 \ubcf4\uc5ec\uc90d\ub2c8\ub2e4.<\/span><\/p>\n
 #create new column called mean_points\ndf[' mean_points<\/span> '] = df. groupby<\/span> (' team<\/span> ')[' points<\/span> ']. transform<\/span> (' mean<\/span> ')\n<\/span>\n#view updated DataFrame\nprint<\/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<\/span><\/span><\/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
 sum()<\/strong> \uacfc \uac19\uc740 \ub2e4\ub978 \ub0b4\uc7a5 \ud568\uc218\ub97c \uc0ac\uc6a9\ud558\uc5ec \uac01 \ud300\uc774 \ud68d\ub4dd\ud55c \uc810\uc218\uc758 \ud569\uacc4\ub97c \ud45c\uc2dc\ud558\ub294 \uc0c8 \uc5f4\uc744 \uc0dd\uc131\ud560 \uc218\ub3c4 \uc788\uc2b5\ub2c8\ub2e4.<\/span><\/p>\n
 #create new column called sum_points\ndf[' sum_points<\/span> '] = df. groupby<\/span> (' team<\/span> ')[' points<\/span> ']. transform<\/span> (' sum<\/span> ')\n<\/span>\n#view updated DataFrame\nprint<\/span> (df)\n\n  team points sum_points\n0 to 30 85\n1 to 22 85\n2 A 19 85\n3 to 14 85\n4 B 14 73\n5 B 11 73\n6 B 20 73\n7 B 28 73<\/span><\/span><\/strong><\/pre>\n
 A\ud300 \uc120\uc218\ub4e4\uc758 \uc810\uc218 \ud569\uacc4\ub294 85<\/b> \uc810, B\ud300 \uc120\uc218\ub4e4\uc758 \uc810\uc218 \ud569\uacc4\ub294 73\uc810<\/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
 \uc608\uc81c 2: \uc0ac\uc6a9\uc790 \uc815\uc758 \ud568\uc218\uc640 \ud568\uaed8 groupby() \ubc0f \ubcc0\ud658() \uc0ac\uc6a9<\/strong><\/span><\/h3>\n
 \ub2e4\uc74c \ucf54\ub4dc\ub294 groupby(<\/strong> ) \ubc0f \ubcc0\ud658()<\/strong> \ud568\uc218\ub97c \uc0ac\uc6a9\ud558\uc5ec \uac01 \ud300\uc758 \uac01 \ud50c\ub808\uc774\uc5b4\uac00 \ub4dd\uc810\ud55c \ucd1d\uc810\uc758 \ubc31\ubd84\uc728\uc744 \uacc4\uc0b0\ud558\ub294 \uc0ac\uc6a9\uc790 \uc815\uc758 \ud568\uc218\ub97c \ub9cc\ub4dc\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><\/span><\/p>\n