<\/p>\n
Ara\u015ft\u0131rmac\u0131lar genellikle bir pop\u00fclasyondan\u00f6rnekler<\/a> al\u0131r ve bu \u00f6rnekteki verileri, bir b\u00fct\u00fcn olarak pop\u00fclasyon hakk\u0131nda sonu\u00e7lar \u00e7\u0131karmak i\u00e7in kullan\u0131r.<\/span><\/p>\n Yayg\u0131n olarak kullan\u0131lan bir \u00f6rnekleme y\u00f6ntemi, bir pop\u00fclasyonun gruplara ayr\u0131ld\u0131\u011f\u0131 ve her gruptan belirli say\u0131da \u00fcyenin \u00f6rne\u011fe dahil edilmek \u00fczere rastgele se\u00e7ildi\u011fi tabakal\u0131 rastgele \u00f6rneklemedir<\/strong> .<\/span><\/p>\n Bu e\u011fitimde Python’da katmanl\u0131 rastgele \u00f6rnekleme ger\u00e7ekle\u015ftirmek i\u00e7in iki y\u00f6ntem a\u00e7\u0131klanmaktad\u0131r.<\/span><\/p>\n 2 farkl\u0131 tak\u0131mdan 8 basketbol oyuncusunun verilerini i\u00e7eren a\u015fa\u011f\u0131daki panda DataFrame’e sahip oldu\u011fumuzu varsayal\u0131m:<\/span><\/p>\n A\u015fa\u011f\u0131daki kod, her tak\u0131mdan \u00f6rne\u011fe dahil edilecek 2 oyuncuyu rastgele se\u00e7erek katmanl\u0131 rastgele \u00f6rneklemenin nas\u0131l ger\u00e7ekle\u015ftirilece\u011fini g\u00f6sterir:<\/span><\/p>\n Tabakal\u0131 \u00f6rne\u011fe her tak\u0131mdan iki oyuncunun dahil edildi\u011fini unutmay\u0131n.<\/span><\/p>\n Yine 2 farkl\u0131 tak\u0131mdan 8 basketbolcunun verilerini i\u00e7eren a\u015fa\u011f\u0131daki panda DataFrame’e sahip oldu\u011fumuzu varsayal\u0131m:<\/span><\/p>\n DataFrame’deki 8 oyuncudan 6’s\u0131n\u0131n (%75) A Tak\u0131m\u0131nda ve 8 oyuncudan 2’sinin (%25) B Tak\u0131m\u0131nda oldu\u011funu unutmay\u0131n.<\/span><\/p>\n A\u015fa\u011f\u0131daki kod, her tak\u0131mdan \u00f6rnekteki oyuncular\u0131n oran\u0131n\u0131n daha b\u00fcy\u00fck DataFrame’deki her tak\u0131mdan oyuncular\u0131n oran\u0131yla e\u015fle\u015fece\u011fi \u015fekilde katmanl\u0131 rastgele \u00f6rneklemenin nas\u0131l ger\u00e7ekle\u015ftirilece\u011fini g\u00f6sterir:<\/span><\/p>\n Katmanl\u0131 \u00f6rnekteki A Tak\u0131m\u0131 oyuncular\u0131n\u0131n oran\u0131n\u0131n (%25) daha b\u00fcy\u00fck DataFrame’deki A Tak\u0131m\u0131 oyuncular\u0131n\u0131n oran\u0131yla e\u015fle\u015fti\u011fini unutmay\u0131n.<\/span><\/p>\n Benzer \u015fekilde, katmanl\u0131 \u00f6rnekteki B Tak\u0131m\u0131 oyuncular\u0131n\u0131n oran\u0131 (%75), daha b\u00fcy\u00fck DataFrame’deki B Tak\u0131m\u0131 oyuncular\u0131n\u0131n oran\u0131yla e\u015fle\u015fiyor.<\/span><\/p>\n A\u015fa\u011f\u0131daki e\u011fitimlerde pandalar kullan\u0131larak di\u011fer \u00f6rnek t\u00fcrlerinin nas\u0131l se\u00e7ilece\u011fi a\u00e7\u0131klanmaktad\u0131r:<\/span><\/p>\n Pandalarda k\u00fcme \u00f6rneklemesi nas\u0131l ger\u00e7ekle\u015ftirilir?<\/a> Ara\u015ft\u0131rmac\u0131lar genellikle bir pop\u00fclasyondan\u00f6rnekler al\u0131r ve bu \u00f6rnekteki verileri, bir b\u00fct\u00fcn olarak pop\u00fclasyon hakk\u0131nda sonu\u00e7lar \u00e7\u0131karmak i\u00e7in kullan\u0131r. Yayg\u0131n olarak kullan\u0131lan bir \u00f6rnekleme y\u00f6ntemi, bir pop\u00fclasyonun gruplara ayr\u0131ld\u0131\u011f\u0131 ve her gruptan belirli say\u0131da \u00fcyenin \u00f6rne\u011fe dahil edilmek \u00fczere rastgele se\u00e7ildi\u011fi tabakal\u0131 rastgele \u00f6rneklemedir . Bu e\u011fitimde Python’da katmanl\u0131 rastgele \u00f6rnekleme ger\u00e7ekle\u015ftirmek i\u00e7in iki y\u00f6ntem a\u00e7\u0131klanmaktad\u0131r. […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[11],"tags":[],"class_list":["post-989","post","type-post","status-publish","format-standard","hentry","category-rehber"],"yoast_head":"\n \u00d6rnek 1: Say\u0131mlar kullan\u0131larak katmanl\u0131 \u00f6rnekleme<\/strong><\/h3>\n
import<\/span> pandas as<\/span> pd\n\n#createDataFrame<\/span>\ndf = pd.DataFrame({'team': ['A', 'A', 'A', 'A', 'B', 'B', 'B', 'B'],\n 'position': ['G', 'G', 'F', 'G', 'F', 'F', 'C', 'C'],\n 'assists': [5, 7, 7, 8, 5, 7, 6, 9],\n 'rebounds': [11, 8, 10, 6, 6, 9, 6, 10]})\n\n#view DataFrame\n<\/span>df\n\n team position assists rebounds\n0 A G 5 11\n1 A G 7 8\n2 A F 7 10\n3 A G 8 6\n4 B F 5 6\n5 B F 7 9\n6 B C 6 6\n7 B C 9 10\n<\/strong><\/pre>\n df. groupby<\/span> ('team', group_keys= False<\/span> ). apply<\/span> ( lambda<\/span> x: x.sample<\/span> (2))\n\n team position assists rebounds\n0 A G 5 11\n3 A G 8 6\n6 B C 6 6\n5 B F 7 9\n<\/strong><\/pre>\n \u00d6rnek 2: Oranlar\u0131 Kullanarak Tabakal\u0131 \u00d6rnekleme<\/strong><\/h3>\n
import<\/span> pandas as<\/span> pd\n\n#createDataFrame<\/span>\ndf = pd.DataFrame({'team': ['A', 'A', 'B', 'B', 'B', 'B', 'B', 'B'],\n 'position': ['G', 'G', 'F', 'G', 'F', 'F', 'C', 'C'],\n 'assists': [5, 7, 7, 8, 5, 7, 6, 9],\n 'rebounds': [11, 8, 10, 6, 6, 9, 6, 10]})\n\n#view DataFrame\n<\/span>df\n\n team position assists rebounds\n0 A G 5 11\n1 A G 7 8\n2 A F 7 10\n3 A G 8 6\n4 B F 5 6\n5 B F 7 9\n6 B C 6 6\n7 B C 9 10\n<\/strong><\/pre>\n import<\/span> numpy as np\n\n<\/span>#define total sample size desired<\/span>\nN = 4\n\n#perform stratified random sampling<\/span>\ndf. groupby<\/span> ('team', group_keys= False<\/span> ). apply<\/span> ( lambda<\/span> x: x. sample<\/span> (int(np. rint<\/span> (N* len<\/span> (x)\/ len<\/span> (df))))). sample<\/span> (frac=1). reset_index<\/span> (drop= True<\/span> )\n\n team position assists rebounds\n0 B F 7 9\n1 B G 8 6\n2 B C 6 6\n3 A G 7 8\n<\/strong><\/pre>\n Ek kaynaklar<\/strong><\/span><\/h3>\n
Pandalar aras\u0131nda sistematik \u00f6rnekleme nas\u0131l yap\u0131l\u0131r?<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"