<\/p>\n
Hareketli ortalama,<\/strong> verilerdeki “g\u00fcr\u00fclt\u00fcy\u00fc” azaltmak ve kal\u0131plar\u0131 ve e\u011filimleri daha kolay belirlemek amac\u0131yla zaman serisi verilerini yumu\u015fatmak i\u00e7in kullan\u0131labilecek bir tekniktir.<\/span><\/p>\n Hareketli ortalaman\u0131n arkas\u0131ndaki fikir, belirli bir d\u00f6nem i\u00e7in “hareketli ortalamaya” ula\u015fmak i\u00e7in \u00f6nceki d\u00f6nemlerin ortalamas\u0131n\u0131 almakt\u0131r.<\/span><\/p>\n Bu e\u011fitimde Python’da hareketli ortalamalar\u0131n nas\u0131l hesaplanaca\u011f\u0131 a\u00e7\u0131klanmaktad\u0131r.<\/span><\/p>\n Belirli bir \u015firketin 10 d\u00f6nem i\u00e7indeki toplam sat\u0131\u015flar\u0131n\u0131 g\u00f6steren a\u015fa\u011f\u0131daki tabloya sahip oldu\u011fumuzu varsayal\u0131m:<\/span><\/p>\n Y\u00f6ntem 1: cumsum() i\u015flevini kullan\u0131n.<\/strong><\/span><\/p>\n Hareketli ortalamay\u0131 hesaplaman\u0131n bir yolu cumsum() fonksiyonunu kullanmakt\u0131r:<\/span><\/p>\n Sonucun nas\u0131l yorumlanaca\u011f\u0131 a\u015fa\u011f\u0131da a\u00e7\u0131klanm\u0131\u015ft\u0131r:<\/span><\/p>\n Ve benzeri.<\/span><\/p>\n Y\u00f6ntem 2: Pandalar\u0131 kullan\u0131n.<\/strong><\/span><\/p>\n Hareketli ortalamay\u0131 hesaplaman\u0131n ba\u015fka bir yolu da pandalara dayal\u0131 bir fonksiyon yazmakt\u0131r:<\/span><\/p>\n Bu y\u00f6ntem \u00f6nceki y\u00f6ntemle tamamen ayn\u0131 sonu\u00e7lar\u0131 \u00fcretir ancak daha b\u00fcy\u00fck dizilerde daha h\u0131zl\u0131 \u00e7al\u0131\u015fma e\u011filimindedir.<\/span><\/p>\n Hareketli ortalama hesaplamas\u0131nda kullanmak \u00fczere istedi\u011finiz say\u0131da \u00f6nceki d\u00f6nemi de belirtebilece\u011finizi unutmay\u0131n. \u00d6rne\u011fin, n=5 kullanmay\u0131 tercih edebilirsiniz:<\/span><\/p>\n Hareketli ortalamay\u0131 hesaplamak i\u00e7in ne kadar \u00e7ok d\u00f6nem kullan\u0131rsan\u0131z, hareketli ortalama \u00e7izgisi o kadar “d\u00fczeltilir”.<\/span><\/p>\n","protected":false},"excerpt":{"rendered":" Hareketli ortalama, verilerdeki “g\u00fcr\u00fclt\u00fcy\u00fc” azaltmak ve kal\u0131plar\u0131 ve e\u011filimleri daha kolay belirlemek amac\u0131yla zaman serisi verilerini yumu\u015fatmak i\u00e7in kullan\u0131labilecek bir tekniktir. Hareketli ortalaman\u0131n arkas\u0131ndaki fikir, belirli bir d\u00f6nem i\u00e7in “hareketli ortalamaya” ula\u015fmak i\u00e7in \u00f6nceki d\u00f6nemlerin ortalamas\u0131n\u0131 almakt\u0131r. Bu e\u011fitimde Python’da hareketli ortalamalar\u0131n nas\u0131l hesaplanaca\u011f\u0131 a\u00e7\u0131klanmaktad\u0131r. \u00d6rnek: Python’da Hareketli Ortalamalar Belirli bir \u015firketin 10 d\u00f6nem i\u00e7indeki […]<\/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-860","post","type-post","status-publish","format-standard","hentry","category-rehber"],"yoast_head":"\n \u00d6rnek: Python’da Hareketli Ortalamalar<\/strong><\/span><\/h3>\n
x = [50, 55, 36, 49, 84, 75, 101, 86, 80, 104]\n<\/strong><\/pre>\n
import<\/span> numpy as<\/span> np\n\n#define moving average function<\/span>\ndef<\/span> moving_avg(x, n):\n cumsum = np.cumsum(np.insert(x, 0, 0)) \n return<\/span> (cumsum[n:] - cumsum[:-n]) \/ float(n)\n\n#calculate moving average using previous 3 time periods\n<\/span>n = 3\nmoving_avg(x, n):\n\narray([47, 46.67, 56.33, 69.33, 86.67, 87.33, 89, 90])\n<\/strong><\/pre>\n\n
import<\/span> pandas as<\/span> pd\n\n#define array to use and number of previous periods to use in calculation<\/span>\nx = [50, 55, 36, 49, 84, 75, 101, 86, 80, 104]\nn=3\n\n#calculate moving average<\/span>\npd.Series(x).rolling(window=n).mean().iloc[n-1:].values\n\narray([47, 46.67, 56.33, 69.33, 86.67, 87.33, 89, 90])\n<\/strong><\/pre>\n #use 5 previous periods to calculate moving average<\/span>\nn=5\n\n#calculate moving average<\/span>\npd.Series(x).rolling(window=n).mean().iloc[n-1:].values\n\narray([54.8, 59.8, 69., 79., 85.2, 89.2])<\/strong><\/pre>\n