One-hot kodlaman\u0131n temel fikri, orijinal kategorik de\u011ferleri temsil etmek i\u00e7in 0 ve 1 de\u011ferlerini alan yeni de\u011fi\u015fkenler olu\u015fturmakt\u0131r.<\/span><\/p>\n \u00d6rne\u011fin, a\u015fa\u011f\u0131daki g\u00f6r\u00fcnt\u00fc, tak\u0131m adlar\u0131n\u0131 i\u00e7eren kategorik bir de\u011fi\u015fkeni yaln\u0131zca 0 ve 1 de\u011ferleri i\u00e7eren yeni de\u011fi\u015fkenlere d\u00f6n\u00fc\u015ft\u00fcrmek i\u00e7in nas\u0131l s\u0131cak kodlama yapaca\u011f\u0131m\u0131z\u0131 g\u00f6sterir:<\/span> <\/p>\n A\u015fa\u011f\u0131daki ad\u0131m ad\u0131m \u00f6rnek, Python’da bu tam veri k\u00fcmesi i\u00e7in tek ge\u00e7i\u015fli kodlaman\u0131n nas\u0131l ger\u00e7ekle\u015ftirilece\u011fini g\u00f6sterir.<\/span><\/p>\n \u0130lk \u00f6nce a\u015fa\u011f\u0131daki pandalar DataFrame’i olu\u015ftural\u0131m:<\/span><\/p>\n Daha sonra, OneHotEncoder()<\/strong> i\u015flevini sklearn<\/strong> k\u00fct\u00fcphanesinden i\u00e7e aktaral\u0131m ve bunu pandalar DataFrame’deki ‘team’ de\u011fi\u015fkeninde s\u0131cak kodlama ger\u00e7ekle\u015ftirmek i\u00e7in kullanal\u0131m:<\/span><\/p>\n Orijinal “ekip” s\u00fctunu \u00fc\u00e7 benzersiz de\u011fer i\u00e7erdi\u011finden DataFrame’e \u00fc\u00e7 yeni s\u00fctun eklendi\u011fini unutmay\u0131n.<\/span><\/p>\n Not<\/strong> : OneHotEncoder()<\/strong> i\u015flevine ili\u015fkin t\u00fcm belgeleri burada<\/a> bulabilirsiniz.<\/span><\/p>\n Son olarak, art\u0131k ihtiyac\u0131m\u0131z olmad\u0131\u011f\u0131 i\u00e7in orijinal ‘team’ de\u011fi\u015fkenini DataFrame’den kald\u0131rabiliriz:<\/span><\/p>\n \u0130lgili:<\/strong><\/span> Pandalarda S\u00fctunlar Nas\u0131l Silinir (4 Y\u00f6ntem)<\/a><\/p>\n Okunmay\u0131 kolayla\u015ft\u0131rmak i\u00e7in son DataFrame’in s\u00fctunlar\u0131n\u0131 da yeniden adland\u0131rabiliriz:<\/span><\/p>\n One-hot kodlama tamamland\u0131 ve art\u0131k bu pandan\u0131n DataFrame’ini istedi\u011fimiz herhangi bir makine \u00f6\u011frenme algoritmas\u0131na ekleyebiliriz.<\/span><\/p>\n Python’da k\u0131rp\u0131lm\u0131\u015f ortalama nas\u0131l hesaplan\u0131r<\/a> One-hot kodlama, kategorik de\u011fi\u015fkenleri makine \u00f6\u011frenimi algoritmalar\u0131 taraf\u0131ndan kolayl\u0131kla kullan\u0131labilecek bir formata d\u00f6n\u00fc\u015ft\u00fcrmek i\u00e7in kullan\u0131l\u0131r. One-hot kodlaman\u0131n temel fikri, orijinal kategorik de\u011ferleri temsil etmek i\u00e7in 0 ve 1 de\u011ferlerini alan yeni de\u011fi\u015fkenler olu\u015fturmakt\u0131r. \u00d6rne\u011fin, a\u015fa\u011f\u0131daki g\u00f6r\u00fcnt\u00fc, tak\u0131m adlar\u0131n\u0131 i\u00e7eren kategorik bir de\u011fi\u015fkeni yaln\u0131zca 0 ve 1 de\u011ferleri i\u00e7eren yeni de\u011fi\u015fkenlere d\u00f6n\u00fc\u015ft\u00fcrmek i\u00e7in nas\u0131l s\u0131cak kodlama […]<\/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-2237","post","type-post","status-publish","format-standard","hentry","category-rehber"],"yoast_head":"\n![\"\"](\"https:\/\/statorials.org\/wp-content\/uploads\/2023\/08\/unhot1.png\")
<\/p>\n 1. Ad\u0131m: Verileri olu\u015fturun<\/strong><\/span><\/h3>\n
import<\/span> pandas as<\/span> pd\n\n#createDataFrame\n<\/span>df = pd. DataFrame<\/span> ({' team<\/span> ': ['A', 'A', 'B', 'B', 'B', 'B', 'C', 'C'],\n ' points<\/span> ': [25, 12, 15, 14, 19, 23, 25, 29]})\n\n#view DataFrame\n<\/span>print<\/span> (df)\n\n team points\n0 to 25\n1 to 12\n2 B 15\n3 B 14\n4 B 19\n5 B 23\n6 C 25\n7 C 29<\/strong><\/pre>\n 2. Ad\u0131m: Tek seferde kodlama ger\u00e7ekle\u015ftirin<\/strong><\/span><\/h3>\n
from<\/span> sklearn. preprocessing<\/span> import<\/span> OneHotEncoder\n\n#creating instance of one-hot-encoder\n<\/span>encoder = OneHotEncoder(handle_unknown=' ignore<\/span> ')\n\n#perform one-hot encoding on 'team' column \n<\/span>encoder_df = pd. DataFrame<\/span> ( encoder.fit_transform<\/span> (df[[' team<\/span> ']]). toarray<\/span> ())\n\n#merge one-hot encoded columns back with original DataFrame\n<\/span>final_df = df. join<\/span> (encoder_df)\n\n#view final df\n<\/span>print<\/span> (final_df)\n\n team points 0 1 2\n0 to 25 1.0 0.0 0.0\n1 to 12 1.0 0.0 0.0\n2 B 15 0.0 1.0 0.0\n3 B 14 0.0 1.0 0.0\n4 B 19 0.0 1.0 0.0\n5 B 23 0.0 1.0 0.0\n6 C 25 0.0 0.0 1.0\n7 C 29 0.0 0.0 1.0\n<\/strong><\/pre>\n 3. Ad\u0131m: Orijinal kategorik de\u011fi\u015fkeni kald\u0131r\u0131n<\/strong><\/span><\/h3>\n
#drop 'team' column\n<\/span>final_df. drop<\/span> (' team<\/span> ', axis= 1<\/span> , inplace= True<\/span> )\n\n#view final df\n<\/span>print<\/span> (final_df)\n\n points 0 1 2\n0 25 1.0 0.0 0.0\n1 12 1.0 0.0 0.0\n2 15 0.0 1.0 0.0\n3 14 0.0 1.0 0.0\n4 19 0.0 1.0 0.0\n5 23 0.0 1.0 0.0\n6 25 0.0 0.0 1.0\n7 29 0.0 0.0 1.0\n<\/strong><\/pre>\n #rename columns\n<\/span>final_df. columns<\/span> = ['points', 'teamA', 'teamB', 'teamC']\n\n#view final df<\/span>\nprint<\/span> (final_df)\n\n points teamA teamB teamC\n0 25 1.0 0.0 0.0\n1 12 1.0 0.0 0.0\n2 15 0.0 1.0 0.0\n3 14 0.0 1.0 0.0\n4 19 0.0 1.0 0.0\n5 23 0.0 1.0 0.0\n6 25 0.0 0.0 1.0\n7 29 0.0 0.0 1.0\n<\/strong><\/pre>\n Ek kaynaklar<\/strong><\/span><\/h3>\n
Python’da do\u011frusal regresyon nas\u0131l ger\u00e7ekle\u015ftirilir<\/a>
Python’da Lojistik Regresyon Nas\u0131l Ger\u00e7ekle\u015ftirilir<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"