R’de bir karar a\u011fac\u0131 \u00e7izmenin en kolay yolu rpart.plot<\/strong> paketindeki prp()<\/strong> fonksiyonunu kullanmakt\u0131r.<\/span><\/span><\/p>\n A\u015fa\u011f\u0131daki \u00f6rnekte bu fonksiyonun pratikte nas\u0131l kullan\u0131laca\u011f\u0131 g\u00f6sterilmektedir.<\/span><\/p>\n Bu \u00f6rnek i\u00e7in, 263 profesyonel beyzbol oyuncusu hakk\u0131nda \u00e7e\u015fitli bilgiler i\u00e7eren ISLR<\/strong> paketindeki Hitters<\/strong> veri setini kullanaca\u011f\u0131z.<\/span><\/p>\n Bu veri setini, belirli bir oyuncunun maa\u015f\u0131n\u0131 tahmin etmek i\u00e7in say\u0131 say\u0131s\u0131n\u0131 ve oynanan y\u0131llar\u0131 kullanan bir regresyon a\u011fac\u0131 olu\u015fturmak i\u00e7in kullanaca\u011f\u0131z.<\/span><\/p>\n A\u015fa\u011f\u0131daki kod, bu regresyon a\u011fac\u0131n\u0131n nas\u0131l s\u0131\u011fd\u0131r\u0131laca\u011f\u0131n\u0131 ve a\u011fac\u0131 \u00e7izmek i\u00e7in prp()<\/strong> fonksiyonunun nas\u0131l kullan\u0131laca\u011f\u0131n\u0131 g\u00f6sterir:<\/span> <\/p>\n prp<\/strong> () i\u015flevindeki faclen<\/strong> , extra<\/strong> , roundint<\/strong> ve rakam<\/strong> ba\u011f\u0131ms\u0131z de\u011fi\u015fkenlerini kullanarak karar a\u011fac\u0131n\u0131n g\u00f6r\u00fcn\u00fcm\u00fcn\u00fc de \u00f6zelle\u015ftirebilece\u011fimizi unutmay\u0131n:<\/span> <\/p>\n A\u011fac\u0131n alt\u0131 terminal d\u00fc\u011f\u00fcm\u00fcne sahip oldu\u011funu g\u00f6rebiliriz.<\/span><\/p>\n Her terminal d\u00fc\u011f\u00fcm\u00fc, o d\u00fc\u011f\u00fcmdeki oyuncular\u0131n tahmini maa\u015f\u0131n\u0131n yan\u0131 s\u0131ra, orijinal veri k\u00fcmesinden o derecelendirmeye ait olan g\u00f6zlem say\u0131s\u0131n\u0131 da g\u00f6r\u00fcnt\u00fcler.<\/span><\/p>\n \u00d6rne\u011fin, orijinal veri setinde 4,5 y\u0131ldan az deneyime sahip 90 oyuncunun bulundu\u011funu ve ortalama maa\u015flar\u0131n\u0131n 225,83 bin dolar<\/strong> oldu\u011funu g\u00f6rebiliyoruz.<\/span> <\/p>\n A\u011fac\u0131 ayn\u0131 zamanda belirli bir oyuncunun maa\u015f\u0131n\u0131, y\u0131llar\u0131n deneyimine ve ortalama say\u0131lar\u0131na dayanarak tahmin etmek i\u00e7in de kullanabiliriz.<\/span><\/p>\n \u00d6rne\u011fin, 7 y\u0131ll\u0131k tecr\u00fcbeye sahip ve ortalama 4 home run yapan bir oyuncunun beklenen maa\u015f\u0131 502,81 bin dolar<\/strong> .<\/span> <\/p>\n Karar a\u011fac\u0131 kullanman\u0131n avantajlar\u0131ndan biri de budur: Sonu\u00e7lar\u0131 kolayca g\u00f6rselle\u015ftirip yorumlayabiliriz.<\/span><\/p>\n A\u015fa\u011f\u0131daki e\u011fitimler karar a\u011fa\u00e7lar\u0131 hakk\u0131nda ek bilgi sa\u011flar:<\/span><\/p>\n S\u0131n\u0131fland\u0131rma ve regresyon a\u011fa\u00e7lar\u0131na giri\u015f<\/a> Makine \u00f6\u011freniminde karar a\u011fac\u0131 , bir yan\u0131t de\u011fi\u015fkeninin de\u011ferini tahmin eden bir karar a\u011fac\u0131 olu\u015fturmak i\u00e7in bir dizi tahmin de\u011fi\u015fkeni kullanan bir model t\u00fcr\u00fcd\u00fcr. R’de bir karar a\u011fac\u0131 \u00e7izmenin en kolay yolu rpart.plot paketindeki prp() fonksiyonunu kullanmakt\u0131r. A\u015fa\u011f\u0131daki \u00f6rnekte bu fonksiyonun pratikte nas\u0131l kullan\u0131laca\u011f\u0131 g\u00f6sterilmektedir. \u00d6rnek: R’de bir karar a\u011fac\u0131 \u00e7izmek Bu \u00f6rnek i\u00e7in, 263 […]<\/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-3504","post","type-post","status-publish","format-standard","hentry","category-rehber"],"yoast_head":"\n \u00d6rnek: R’de bir karar a\u011fac\u0131 \u00e7izmek<\/strong><\/span><\/h2>\n
library<\/span> (ISLR)\nlibrary<\/span> (rpart)\nlibrary<\/span> (rpart.plot)\n\n#build the initial decision tree\n<\/span>tree <- rpart(Salary ~ Years + HmRun, data=Hitters, control=rpart. control<\/span> (cp= .0001<\/span> ))\n<\/span><\/span><\/strong>\n<\/span>#identify best cp value to use\nbest <- tree$cptable[which. min<\/span> (tree$cptable[,\" xerror<\/span> \"]),\" CP<\/span> \"]\n\n#produce a pruned tree based on the best cp value\n<\/span>pruned_tree <- prune<\/span> (tree, cp=best)\n\n#plot the pruned tree\n<\/span>prp(pruned_tree)\n<\/span><\/span><\/span><\/strong><\/pre>\n![\"\"](\"https:\/\/statorials.org\/wp-content\/uploads\/2023\/08\/decision1.jpg\")
<\/p>\n #plot decision tree using custom arguments<\/span>\nprp(pruned_tree,\n faclen= 0<\/span> , #use full names for factor labels<\/span>\n extra= 1<\/span> , #display number of observations for each terminal node<\/span>\n roundint= F<\/span> , #don't round to integers in output<\/span>\n digits= 5<\/span> ) #display 5 decimal places in output<\/span><\/span><\/span><\/span><\/strong> <\/pre>\n![\"R'de](\"https:\/\/statorials.org\/wp-content\/uploads\/2023\/08\/decision2.jpg\")
<\/p>\n![\"R'de](\"https:\/\/statorials.org\/wp-content\/uploads\/2023\/08\/arbre4.png\")
<\/p>\n![\"R'deki](\"https:\/\/statorials.org\/wp-content\/uploads\/2023\/08\/arbre5.png\")
<\/p>\n Ek kaynaklar<\/span><\/strong><\/span><\/h2>\n
Karar a\u011fac\u0131 ve rastgele ormanlar: fark nedir?<\/a>
R’ye s\u0131n\u0131fland\u0131rma ve regresyon a\u011fa\u00e7lar\u0131 nas\u0131l s\u0131\u011fd\u0131r\u0131l\u0131r<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"