{"id":2913,"date":"2023-07-20T02:59:24","date_gmt":"2023-07-20T02:59:24","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%b3%e1%84%85%e1%85%ae%e1%86%b8%e1%84%87%e1%85%a1%e1%84%8b%e1%85%b5-%e1%84%86%e1%85%a9%e1%84%83%e1%85%b3\/"},"modified":"2023-07-20T02:59:24","modified_gmt":"2023-07-20T02:59:24","slug":"%e1%84%91%e1%85%a2%e1%86%ab%e1%84%83%e1%85%a5-%e1%84%80%e1%85%b3%e1%84%85%e1%85%ae%e1%86%b8%e1%84%87%e1%85%a1%e1%84%8b%e1%85%b5-%e1%84%86%e1%85%a9%e1%84%83%e1%85%b3","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%b3%e1%84%85%e1%85%ae%e1%86%b8%e1%84%87%e1%85%a1%e1%84%8b%e1%85%b5-%e1%84%86%e1%85%a9%e1%84%83%e1%85%b3\/","title":{"rendered":"Pandas: groupby \uac1c\uccb4\uc758 \ubaa8\ub4dc\ub97c \uacc4\uc0b0\ud558\ub294 \ubc29\ubc95"},"content":{"rendered":"

<\/p>\n

\n

\ub2e4\uc74c \uad6c\ubb38\uc744 \uc0ac\uc6a9\ud558\uc5ec Pandas\uc758 GroupBy \uac1c\uccb4\uc5d0\uc11c \ubaa8\ub4dc\ub97c<\/a> \uacc4\uc0b0\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/span><\/p>\n

 df. groupby<\/span> ([' group_var<\/span> '])[' value_var<\/span> ']. agg<\/span> ( pd.Series.mode<\/span> )<\/span>\n<\/strong><\/pre>\n
 \ub2e4\uc74c \uc608\uc5d0\uc11c\ub294 \uc2e4\uc81c\ub85c \uc774 \uad6c\ubb38\uc744 \uc0ac\uc6a9\ud558\ub294 \ubc29\ubc95\uc744 \ubcf4\uc5ec\uc90d\ub2c8\ub2e4.<\/span><\/p>\n
 \uc608: GroupBy \uac1c\uccb4\uc758 \uacc4\uc0b0 \ubaa8\ub4dc<\/strong><\/span><\/h3>\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\n<\/span>df = pd. DataFrame<\/span> ({' team<\/span> ': ['A', 'A', 'A', 'A', 'B', 'B', 'C', 'C', 'C'],\n                   ' points<\/span> ': [10, 10, 12, 15, 19, 23, 20, 20, 26]})\n\n#view DataFrame\n<\/span>print<\/span> (df)\n\n  team points\n0 to 10\n1 to 10\n2 to 12\n3 to 15\n4 B 19\n5 B 23\n6 C 20\n7 C 20\n8 C 26<\/strong><\/span><\/pre>\n
 \ub2e4\uc74c \uad6c\ubb38\uc744 \uc0ac\uc6a9\ud558\uc5ec \uac01 \ud300\uc758 \ud328\uc158 \ud3ec\uc778\ud2b8 \uac12\uc744 \uacc4\uc0b0\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/span><\/p>\n
 #calculate mode points value for each team\ndf. groupby<\/span> ([' team<\/span> '])[' points<\/span> ']. agg<\/span> ( pd.Series.mode<\/span> )<\/span>\n\nteam\nAt 10\nB [19, 23]\nC 20\nName: points, dtype: object\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