{"id":3222,"date":"2023-07-18T14:35:49","date_gmt":"2023-07-18T14:35:49","guid":{"rendered":"https:\/\/statorials.org\/ko\/%e1%84%8c%e1%85%a9%e1%84%80%e1%85%a5%e1%86%ab%e1%84%8b%e1%85%b5-%e1%84%91%e1%85%a9%e1%84%92%e1%85%a1%e1%86%b7%e1%84%83%e1%85%ac%e1%86%ab-pandas-groupby-%e1%84%80%e1%85%a2%e1%84%89%e1%85%ae\/"},"modified":"2023-07-18T14:35:49","modified_gmt":"2023-07-18T14:35:49","slug":"%e1%84%8c%e1%85%a9%e1%84%80%e1%85%a5%e1%86%ab%e1%84%8b%e1%85%b5-%e1%84%91%e1%85%a9%e1%84%92%e1%85%a1%e1%86%b7%e1%84%83%e1%85%ac%e1%86%ab-pandas-groupby-%e1%84%80%e1%85%a2%e1%84%89%e1%85%ae","status":"publish","type":"post","link":"https:\/\/statorials.org\/ko\/%e1%84%8c%e1%85%a9%e1%84%80%e1%85%a5%e1%86%ab%e1%84%8b%e1%85%b5-%e1%84%91%e1%85%a9%e1%84%92%e1%85%a1%e1%86%b7%e1%84%83%e1%85%ac%e1%86%ab-pandas-groupby-%e1%84%80%e1%85%a2%e1%84%89%e1%85%ae\/","title":{"rendered":"Pandas: groupby\ub97c \uc0ac\uc6a9\ud558\uace0 \uc870\uac74\ubd80\ub85c \uacc4\uc0b0\ud558\ub294 \ubc29\ubc95"},"content":{"rendered":"

<\/p>\n

\n

\ub2e4\uc74c \uae30\ubcf8 \uad6c\ubb38\uc744 \uc0ac\uc6a9\ud558\uc5ec Pandas DataFrame\uc5d0\uc11c \uc870\uac74\uc744 \uc0ac\uc6a9\ud558\uc5ec \uadf8\ub8f9\ud654 \ubc0f \uac1c\uc218 \uacc4\uc0b0\uc744 \uc218\ud589\ud560 \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/span><\/p>\n

 df. groupby<\/span> (' var1<\/span> ')[' var2<\/span> ']. apply<\/span> ( lambda<\/span> x:(x==' val<\/span> '). sum<\/span> ()). reset_index<\/span> (name=' count<\/span> ')\n<\/strong><\/pre>\n
 \uc774 \ud2b9\uc815 \uad6c\ubb38\uc740 var1\uc744<\/strong> \uae30\uc900\uc73c\ub85c DataFrame\uc758 \ud589\uc744 \uadf8\ub8f9\ud654\ud55c \ub2e4\uc74c var2\uac00<\/strong> “val”\uacfc \ub3d9\uc77c\ud55c \ud589 \uc218\ub97c \uacc4\uc0b0\ud569\ub2c8\ub2e4.<\/span><\/p>\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: Pandas\uc758 \uc870\uac74\uc774 \uc788\ub294 Groupby \ubc0f Count<\/strong><\/span><\/h3>\n
 \ub2e4\uc591\ud55c \ub18d\uad6c \uc120\uc218\uc5d0 \ub300\ud55c \uc815\ubcf4\uac00 \ud3ec\ud568\ub41c \ub2e4\uc74c\uacfc \uac19\uc740 pandas 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', 'B', 'B'],\n                   ' pos<\/span> ': ['Gu', 'Fo', 'Fo', 'Fo', 'Gu', 'Gu', 'Fo', 'Fo'],\n                   ' points<\/span> ': [18, 22, 19, 14, 14, 11, 20, 28]})\n\n#view DataFrame\n<\/span>print<\/span> (df)\n\n  team pos points\n0 A Gu 18\n1 A Fo 22\n2 A Fo 19\n3 A Fo 14\n4 B Gu 14\n5 B Gu 11\n6 B Fo 20\n7 B Fo 28<\/strong><\/pre>\n
 \ub2e4\uc74c \ucf54\ub4dc\ub294 DataFrame\uc744 \ud300<\/strong> \ubcc0\uc218\ub85c \uadf8\ub8f9\ud654\ud558\uace0 pos<\/strong> \ubcc0\uc218\uac00 “Gu”\uc778 \ud589 \uc218\ub97c \uacc4\uc0b0\ud558\ub294 \ubc29\ubc95\uc744 \ubcf4\uc5ec\uc90d\ub2c8\ub2e4.<\/span><\/p>\n
 #groupby team and count number of 'pos' equal to 'Gu'\n<\/span>df_count = df. groupby<\/span> (' team<\/span> ')[' pos<\/span> ']. apply<\/span> ( lambda<\/span> x: (x==' Gu<\/span> '). sum<\/span> ()). reset_index<\/span> (name=' count<\/span> ')\n\n#view results\n<\/span>print<\/span> (df_count)\n\n  team count\n0 to 1\n1 B 2\n<\/strong><\/pre>\n
 \uacb0\uacfc\uc5d0\uc11c \uc6b0\ub9ac\ub294 \ub2e4\uc74c\uc744 \ubcfc \uc218 \uc788\uc2b5\ub2c8\ub2e4:<\/span><\/p>\n