{"id":3198,"date":"2023-07-18T17:44:30","date_gmt":"2023-07-18T17:44:30","guid":{"rendered":"https:\/\/statorials.org\/ar\/%d8%a7%d9%84%d8%a8%d8%a7%d9%86%d8%af%d8%a7-groupby-%d8%aa%d8%ad%d9%88%d9%8a%d9%84\/"},"modified":"2023-07-18T17:44:30","modified_gmt":"2023-07-18T17:44:30","slug":"%d8%a7%d9%84%d8%a8%d8%a7%d9%86%d8%af%d8%a7-groupby-%d8%aa%d8%ad%d9%88%d9%8a%d9%84","status":"publish","type":"post","link":"https:\/\/statorials.org\/ar\/%d8%a7%d9%84%d8%a8%d8%a7%d9%86%d8%af%d8%a7-groupby-%d8%aa%d8%ad%d9%88%d9%8a%d9%84\/","title":{"rendered":"\u0643\u064a\u0641\u064a\u0629 \u0627\u0633\u062a\u062e\u062f\u0627\u0645 \u0648\u0638\u0627\u0626\u0641 groupby() \u0648transform() \u0641\u064a pandas"},"content":{"rendered":"

<\/p>\n

\n

\u064a\u0645\u0643\u0646\u0643 \u0627\u0633\u062a\u062e\u062f\u0627\u0645 \u0627\u0644\u0637\u0631\u0642 \u0627\u0644\u062a\u0627\u0644\u064a\u0629 \u0644\u0627\u0633\u062a\u062e\u062f\u0627\u0645 \u0627\u0644\u062f\u0627\u0644\u062a\u064a\u0646 groupby()<\/strong> \u0648 transform()<\/strong> \u0645\u0639\u064b\u0627 \u0641\u064a pandas DataFrame:<\/span><\/p>\n

\u0627\u0644\u0637\u0631\u064a\u0642\u0629 \u0627\u0644\u0623\u0648\u0644\u0649: \u0627\u0633\u062a\u062e\u062f\u0645 groupby() \u0648transform() \u0645\u0639 \u0627\u0644\u0648\u0638\u064a\u0641\u0629 \u0627\u0644\u0645\u0636\u0645\u0646\u0629<\/strong><\/span><\/p>\n

 df[' new<\/span> '] = df. groupby<\/span> (' group_var<\/span> ')[' value_var<\/span> ']. transform<\/span> (' mean<\/span> ')\n<\/strong><\/pre>\n
 \u0627\u0644\u0637\u0631\u064a\u0642\u0629 \u0627\u0644\u062b\u0627\u0646\u064a\u0629: \u0627\u0633\u062a\u062e\u062f\u0627\u0645 groupby() \u0648transform() \u0645\u0639 \u0648\u0638\u064a\u0641\u0629 \u0645\u062e\u0635\u0635\u0629<\/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
 \u062a\u0648\u0636\u062d \u0627\u0644\u0623\u0645\u062b\u0644\u0629 \u0627\u0644\u062a\u0627\u0644\u064a\u0629 \u0643\u064a\u0641\u064a\u0629 \u0627\u0633\u062a\u062e\u062f\u0627\u0645 \u0643\u0644 \u0637\u0631\u064a\u0642\u0629 \u0639\u0645\u0644\u064a\u064b\u0627 \u0645\u0639 \u0627\u0644\u0628\u0627\u0646\u062f\u0627 DataFrame \u0627\u0644\u062a\u0627\u0644\u064a\u0629:<\/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
 \u0645\u062b\u0627\u0644 1: \u0627\u0633\u062a\u062e\u062f\u0645 groupby() \u0648transform() \u0645\u0639 \u0648\u0638\u064a\u0641\u0629 \u0645\u062f\u0645\u062c\u0629<\/strong><\/span><\/h3>\n
 \u064a\u0648\u0636\u062d \u0627\u0644\u062a\u0639\u0644\u064a\u0645\u0629 \u0627\u0644\u0628\u0631\u0645\u062c\u064a\u0629 \u0627\u0644\u062a\u0627\u0644\u064a\u0629 \u0643\u064a\u0641\u064a\u0629 \u0627\u0633\u062a\u062e\u062f\u0627\u0645 \u0627\u0644\u062f\u0627\u0644\u062a\u064a\u0646 groupby(<\/strong> ) \u0648 transform()<\/strong> \u0644\u0625\u0636\u0627\u0641\u0629 \u0639\u0645\u0648\u062f \u062c\u062f\u064a\u062f \u0625\u0644\u0649 DataFrame \u064a\u0633\u0645\u0649 mean_points:<\/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
 \u0643\u0627\u0646 \u0645\u062a\u0648\u0633\u0637 \u0642\u064a\u0645\u0629 \u0627\u0644\u0646\u0642\u0627\u0637 \u0644\u0644\u0627\u0639\u0628\u064a\u0646 \u0641\u064a \u0627\u0644\u0641\u0631\u064a\u0642 \u0623 21.25<\/strong> \u0648\u0643\u0627\u0646 \u0645\u062a\u0648\u0633\u0637 \u0642\u064a\u0645\u0629 \u0627\u0644\u0646\u0642\u0627\u0637 \u0644\u0644\u0627\u0639\u0628\u064a\u0646 \u0641\u064a \u0627\u0644\u0641\u0631\u064a\u0642 \u0628 18.25<\/strong> \u060c \u0644\u0630\u0644\u0643 \u062a\u0645 \u062a\u062e\u0635\u064a\u0635 \u0647\u0630\u0647 \u0627\u0644\u0642\u064a\u0645 \u0648\u0641\u0642\u064b\u0627 \u0644\u0630\u0644\u0643 \u0644\u0643\u0644 \u0644\u0627\u0639\u0628 \u0641\u064a \u0639\u0645\u0648\u062f \u062c\u062f\u064a\u062f.<\/span><\/p>\n
 \u0644\u0627\u062d\u0638 \u0623\u0646\u0647 \u064a\u0645\u0643\u0646\u0646\u0627 \u0623\u064a\u0636\u064b\u0627 \u0627\u0633\u062a\u062e\u062f\u0627\u0645 \u062f\u0627\u0644\u0629 \u0645\u062f\u0645\u062c\u0629 \u0623\u062e\u0631\u0649 \u0645\u062b\u0644 sum()<\/strong> \u0644\u0625\u0646\u0634\u0627\u0621 \u0639\u0645\u0648\u062f \u062c\u062f\u064a\u062f \u064a\u0639\u0631\u0636 \u0645\u062c\u0645\u0648\u0639 \u0627\u0644\u0646\u0642\u0627\u0637 \u0627\u0644\u0645\u0633\u062c\u0644\u0629 \u0644\u0643\u0644 \u0641\u0631\u064a\u0642:<\/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
 \u0645\u062c\u0645\u0648\u0639 \u0646\u0642\u0627\u0637 \u0644\u0627\u0639\u0628\u064a \u0627\u0644\u0641\u0631\u064a\u0642 \u0623 \u0643\u0627\u0646 85<\/b> \u0648\u0645\u062c\u0645\u0648\u0639 \u0646\u0642\u0627\u0637 \u0644\u0627\u0639\u0628\u064a \u0627\u0644\u0641\u0631\u064a\u0642 \u0628 73<\/strong> \u060c \u0644\u0630\u0644\u0643 \u062a\u0645 \u062a\u062e\u0635\u064a\u0635 \u0647\u0630\u0647 \u0627\u0644\u0642\u064a\u0645 \u0648\u0641\u0642\u064b\u0627 \u0644\u0630\u0644\u0643 \u0644\u0643\u0644 \u0644\u0627\u0639\u0628 \u0641\u064a \u0639\u0645\u0648\u062f \u062c\u062f\u064a\u062f.<\/span><\/p>\n
 \u0627\u0644\u0645\u062b\u0627\u0644 2: \u0627\u0633\u062a\u062e\u062f\u0645 groupby() \u0648transform() \u0645\u0639 \u0648\u0638\u064a\u0641\u0629 \u0645\u062e\u0635\u0635\u0629<\/strong><\/span><\/h3>\n
 \u064a\u0648\u0636\u062d \u0627\u0644\u062a\u0639\u0644\u064a\u0645\u0629 \u0627\u0644\u0628\u0631\u0645\u062c\u064a\u0629 \u0627\u0644\u062a\u0627\u0644\u064a\u0629 \u0643\u064a\u0641\u064a\u0629 \u0627\u0633\u062a\u062e\u062f\u0627\u0645 \u0627\u0644\u062f\u0627\u0644\u062a\u064a\u0646 groupby(<\/strong> ) \u0648 transform()<\/strong> \u0644\u0625\u0646\u0634\u0627\u0621 \u0648\u0638\u064a\u0641\u0629 \u0645\u062e\u0635\u0635\u0629 \u062a\u062d\u0633\u0628 \u0627\u0644\u0646\u0633\u0628\u0629 \u0627\u0644\u0645\u0626\u0648\u064a\u0629 \u0644\u0625\u062c\u0645\u0627\u0644\u064a \u0627\u0644\u0646\u0642\u0627\u0637 \u0627\u0644\u062a\u064a \u0633\u062c\u0644\u0647\u0627 \u0643\u0644 \u0644\u0627\u0639\u0628 \u0641\u064a \u0641\u0631\u0642\u0647 \u0627\u0644\u062e\u0627\u0635\u0629:<\/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
 \u0648\u0625\u0644\u064a\u0643 \u0643\u064a\u0641\u064a\u0629 \u062a\u0641\u0633\u064a\u0631 \u0627\u0644\u0646\u062a\u064a\u062c\u0629:<\/span><\/span><\/p>\n