Bu e\u011fitimde Python’da k\u00fcbik regresyonun nas\u0131l ger\u00e7ekle\u015ftirilece\u011fi a\u00e7\u0131klanmaktad\u0131r.<\/span><\/p>\n \u0130ki de\u011fi\u015fken (x ve y) i\u00e7eren a\u015fa\u011f\u0131daki panda DataFrame’e sahip oldu\u011fumuzu varsayal\u0131m:<\/span><\/p>\n Bu verinin basit bir da\u011f\u0131l\u0131m grafi\u011fini \u00e7\u0131kar\u0131rsak iki de\u011fi\u015fken aras\u0131ndaki ili\u015fkinin do\u011frusal olmad\u0131\u011f\u0131n\u0131 g\u00f6rebiliriz:<\/span> <\/p>\n X’in de\u011feri artt\u0131k\u00e7a y de belli bir noktaya kadar artar, sonra azal\u0131r, sonra tekrar artar.<\/span><\/p>\n \u00c7izimde iki “e\u011fri” bulunan bu model, iki de\u011fi\u015fken aras\u0131ndaki k\u00fcbik ili\u015fkinin bir g\u00f6stergesidir.<\/span><\/p>\n Bu, k\u00fcbik regresyon modelinin iki de\u011fi\u015fken aras\u0131ndaki ili\u015fkiyi \u00f6l\u00e7mek i\u00e7in iyi bir aday oldu\u011fu anlam\u0131na gelir.<\/span><\/p>\n K\u00fcbik regresyon ger\u00e7ekle\u015ftirmek i\u00e7in numpy.polyfit()<\/a> i\u015flevini<\/span> kullanarak derece 3’e sahip bir polinom regresyon modeli yerle\u015ftirebiliriz:<\/span> <\/p>\n Uygun k\u00fcbik regresyon denklemini model katsay\u0131lar\u0131n\u0131 yazd\u0131rarak elde edebiliriz:<\/span><\/p>\n Uygun k\u00fcbik regresyon denklemi \u015f\u00f6yledir:<\/span><\/p>\n y = 0,003302(x) 3<\/sup> \u2013 0,3214(x) 2<\/sup> + 9,832x \u2013 30,01<\/strong><\/span><\/p>\n Bu denklemi x’in de\u011ferine ba\u011fl\u0131 olarak y’nin beklenen de\u011ferini hesaplamak i\u00e7in kullanabiliriz.<\/span><\/p>\n \u00d6rne\u011fin, x 30 ise y’nin beklenen de\u011feri 64,844’t\u00fcr:<\/span><\/p>\n y = 0,003302(30) 3<\/sup> \u2013 0,3214(30) 2<\/sup> + 9,832(30) \u2013 30,01 = 64,844<\/span><\/p>\n Ayr\u0131ca, yorday\u0131c\u0131 de\u011fi\u015fkenler taraf\u0131ndan a\u00e7\u0131klanabilen yan\u0131t de\u011fi\u015fkenindeki varyans\u0131n oran\u0131 olan modelin R-karesini elde etmek i\u00e7in k\u0131sa bir fonksiyon da yazabiliriz.<\/span><\/p>\n Bu \u00f6rnekte modelin R karesi 0,9632’dir<\/strong> .<\/span><\/p>\n Bu, yan\u0131t de\u011fi\u015fkenindeki de\u011fi\u015fimin %96,32’sinin yorday\u0131c\u0131 de\u011fi\u015fken taraf\u0131ndan a\u00e7\u0131klanabilece\u011fi anlam\u0131na gelmektedir.<\/span><\/p>\n Bu de\u011ferin \u00e7ok y\u00fcksek olmas\u0131 bize k\u00fcbik regresyon modelinin iki de\u011fi\u015fken aras\u0131ndaki ili\u015fkiyi iyi \u00f6l\u00e7t\u00fc\u011f\u00fcn\u00fc s\u00f6yler.<\/span><\/p>\n \u0130lgili:<\/strong> \u0130yi bir R-kare de\u011feri nedir?<\/a><\/span><\/p>\n A\u015fa\u011f\u0131daki e\u011fitimlerde Python’da di\u011fer genel g\u00f6revlerin nas\u0131l ger\u00e7ekle\u015ftirilece\u011fi a\u00e7\u0131klanmaktad\u0131r:<\/span><\/p>\n Python’da basit do\u011frusal regresyon nas\u0131l ger\u00e7ekle\u015ftirilir<\/a> K\u00fcbik regresyon, de\u011fi\u015fkenler aras\u0131ndaki ili\u015fki do\u011frusal olmad\u0131\u011f\u0131nda, bir yorday\u0131c\u0131 de\u011fi\u015fken ile bir yan\u0131t de\u011fi\u015fkeni aras\u0131ndaki ili\u015fkiyi \u00f6l\u00e7mek i\u00e7in kullanabilece\u011fimiz bir regresyon t\u00fcr\u00fcd\u00fcr. Bu e\u011fitimde Python’da k\u00fcbik regresyonun nas\u0131l ger\u00e7ekle\u015ftirilece\u011fi a\u00e7\u0131klanmaktad\u0131r. \u00d6rnek: Python’da k\u00fcbik regresyon \u0130ki de\u011fi\u015fken (x ve y) i\u00e7eren a\u015fa\u011f\u0131daki panda DataFrame’e sahip oldu\u011fumuzu varsayal\u0131m: import pandas as pd #createDataFrame df = pd. DataFrame […]<\/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-3920","post","type-post","status-publish","format-standard","hentry","category-rehber"],"yoast_head":"\n \u00d6rnek: Python’da k\u00fcbik regresyon<\/span><\/strong><\/h2>\n
import<\/span> pandas as<\/span> pd\n\n#createDataFrame\n<\/span>df = pd. DataFrame<\/span> ({' x<\/span> ': [6, 9, 12, 16, 22, 28, 33, 40, 47, 51, 55, 60],\n ' y<\/span> ': [14, 28, 50, 64, 67, 57, 55, 57, 68, 74, 88, 110]})\n\n#view DataFrame\n<\/span>print<\/span> (df)\n\n xy\n0 6 14\n1 9 28\n2 12 50\n3 16 64\n4 22 67\n5 28 57\n6 33 55\n7 40 57\n8 47 68\n9 51 74\n10 55 88\n11 60 110\n<\/strong><\/pre>\n import matplotlib. pyplot<\/span><\/span> as plt<\/span>\n\n#create scatterplot\n<\/span>plt. scatter<\/span> (df. x<\/span> , df. y<\/span> )<\/span><\/span><\/strong> <\/pre>\n![\"\"](\"https:\/\/statorials.org\/wp-content\/uploads\/2023\/08\/cubique1.jpg\")
<\/p>\n import<\/span> numpy as<\/span> np\n\n#fit cubic regression model\n<\/span>model = np. poly1d<\/span> (np. polyfit<\/span> (df. x<\/span> , df. y<\/span> , 3))<\/span>\n\n#add fitted cubic regression line to scatterplot\n<\/span>polyline = np. linspace<\/span> (1, 60, 50)\nplt. scatter<\/span> (df. x<\/span> , df. y<\/span> )\nplt. plot<\/span> (polyline, model(polyline))\n\n#add axis labels\n<\/span>plt. xlabel<\/span> (' x<\/span> ')\nplt. ylabel<\/span> (' y<\/span> ')\n\n#displayplot\n<\/span>plt. show<\/span> ()<\/strong> <\/pre>\n![\"Python'da](\"https:\/\/statorials.org\/wp-content\/uploads\/2023\/08\/cubique2.jpg\")
<\/p>\n print<\/span> (model)\n\n 3 2\n0.003302x - 0.3214x + 9.832x - 32.01\n<\/strong><\/pre>\n #define function to calculate r-squared<\/span>\ndef<\/span> polyfit(x, y, degree):\n results = {}\n coeffs = np. polyfit<\/span> (x, y, degree)\n p = np. poly1d<\/span> (coeffs)\n #calculate r-squared<\/span>\n yhat = p(x)\n ybar = np. sum<\/span> (y)\/len(y)\n ssreg = np. sum<\/span> ((yhat-ybar) **<\/span> 2)\n sstot = np. sum<\/span> ((y - ybar) **<\/span> 2)\n results[' r_squared<\/span> '] = ssreg \/ sstot\n\n return<\/span> results\n\n#find r-squared of polynomial model with degree = 3\n<\/span>polyfit(df. x<\/span> , df. y<\/span> , 3)\n\n{'r_squared': 0.9632469890057967}\n<\/strong><\/pre>\n Ek kaynaklar<\/strong><\/span><\/h2>\n
Python’da ikinci dereceden regresyon nas\u0131l ger\u00e7ekle\u015ftirilir?<\/a>
Python’da polinom regresyonu nas\u0131l ger\u00e7ekle\u015ftirilir<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"