{"id":477,"date":"2023-07-29T19:05:27","date_gmt":"2023-07-29T19:05:27","guid":{"rendered":"https:\/\/statorials.org\/cn\/%e5%a4%9a%e9%a1%b9%e5%bc%8f%e5%9b%9e%e5%bd%92-r\/"},"modified":"2023-07-29T19:05:27","modified_gmt":"2023-07-29T19:05:27","slug":"%e5%a4%9a%e9%a1%b9%e5%bc%8f%e5%9b%9e%e5%bd%92-r","status":"publish","type":"post","link":"https:\/\/statorials.org\/cn\/%e5%a4%9a%e9%a1%b9%e5%bc%8f%e5%9b%9e%e5%bd%92-r\/","title":{"rendered":"R \u4e2d\u7684\u591a\u9879\u5f0f\u56de\u5f52\uff08\u9010\u6b65\uff09"},"content":{"rendered":"

<\/p>\n

\n

\u5f53\u9884\u6d4b\u53d8\u91cf\u548c\u54cd\u5e94\u53d8\u91cf<\/a>\u4e4b\u95f4\u7684\u5173\u7cfb\u662f\u975e\u7ebf\u6027\u65f6\uff0c\u53ef\u4ee5\u4f7f\u7528\u591a\u9879\u5f0f\u56de\u5f52<\/a>\u6280\u672f\u3002<\/span><\/p>\n

\u8fd9\u79cd\u7c7b\u578b\u7684\u56de\u5f52\u91c7\u7528\u4ee5\u4e0b\u5f62\u5f0f\uff1a<\/span><\/p>\n

Y = \u03b2 0<\/sub> +<\/sup> \u03b2 1<\/sub> X + \u03b2 2<\/sub> X 2<\/sup> + \u2026 + \u03b2 h<\/sub><\/span><\/p>\n

\u5176\u4e2dh<\/em>\u662f\u591a\u9879\u5f0f\u7684\u201c\u6b21\u6570\u201d\u3002<\/span><\/p>\n

\u672c\u6559\u7a0b\u63d0\u4f9b\u4e86\u5982\u4f55\u5728 R \u4e2d\u6267\u884c\u591a\u9879\u5f0f\u56de\u5f52\u7684\u5206\u6b65\u793a\u4f8b\u3002<\/span><\/p>\n

\u7b2c 1 \u6b65\uff1a\u521b\u5efa\u6570\u636e<\/strong><\/span><\/h3>\n

\u5728\u6b64\u793a\u4f8b\u4e2d\uff0c\u6211\u4eec\u5c06\u521b\u5efa\u4e00\u4e2a\u6570\u636e\u96c6\uff0c\u5176\u4e2d\u5305\u542b 50 \u540d\u5b66\u751f\u7684\u73ed\u7ea7\u7684\u5b66\u4e60\u5c0f\u65f6\u6570\u548c\u671f\u672b\u8003\u8bd5\u6210\u7ee9\uff1a<\/span><\/p>\n

 #make this example reproducible<\/span>\nset.seed(1)\n\n#create dataset\n<\/span>df <- data.frame(hours = runif<\/span> (50, 5, 15), score=50)\ndf$score = df$score + df$hours^3\/150 + df$hours* runif<\/span> (50, 1, 2)\n\n#view first six rows of data\n<\/span>head(data)\n\n      hours score\n1 7.655087 64.30191\n2 8.721239 70.65430\n3 10.728534 73.66114\n4 14.082078 86.14630\n5 7.016819 59.81595\n6 13.983897 83.60510\n<\/strong><\/pre>\n
\u7b2c 2 \u6b65\uff1a\u53ef\u89c6\u5316\u6570\u636e<\/strong><\/span><\/h3>\n
\u5728\u5c06\u56de\u5f52\u6a21\u578b\u62df\u5408\u5230\u6570\u636e\u4e4b\u524d\uff0c\u6211\u4eec\u9996\u5148\u521b\u5efa\u4e00\u4e2a\u6563\u70b9\u56fe\u6765\u53ef\u89c6\u5316\u5b66\u4e60\u65f6\u95f4\u548c\u8003\u8bd5\u6210\u7ee9\u4e4b\u95f4\u7684\u5173\u7cfb\uff1a<\/span> <\/p>\n
 library<\/span> (ggplot2)\n\nggplot(df, aes<\/span> (x=hours, y=score)) +\n  geom_point()<\/strong> <\/pre>\n
\"\"<\/p>\n
\u6211\u4eec\u53ef\u4ee5\u770b\u5230\u6570\u636e\u5177\u6709\u8f7b\u5fae\u7684\u4e8c\u6b21\u5173\u7cfb\uff0c\u8868\u660e\u591a\u9879\u5f0f\u56de\u5f52\u53ef\u80fd\u6bd4\u7b80\u5355\u7ebf\u6027\u56de\u5f52\u66f4\u597d\u5730\u62df\u5408\u6570\u636e\u3002<\/span><\/p>\n
\u6b65\u9aa4 3\uff1a\u62df\u5408\u591a\u9879\u5f0f\u56de\u5f52\u6a21\u578b<\/span><\/strong><\/h3>\n
\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u5c06\u62df\u5408\u4e94\u4e2a\u4e0d\u540c\u7684\u591a\u9879\u5f0f\u56de\u5f52\u6a21\u578b\uff0c\u5176\u6b21\u6570h<\/em> = 1\u20265\uff0c\u5e76\u4f7f\u7528 k = 10 \u6b21\u7684 k \u500d\u4ea4\u53c9\u9a8c\u8bc1\u6765\u8ba1\u7b97\u6bcf\u4e2a\u6a21\u578b\u7684 MSE \u68c0\u9a8c\uff1a<\/span><\/p>\n
 #randomly shuffle data\n<\/span>df.shuffled <- df[ sample<\/span> ( nrow<\/span> (df)),]\n\n#define number of folds to use for k-fold cross-validation\n<\/span>K <- 10 \n\n#define degree of polynomials to fit\n<\/span>degree <- 5\n\n#create k equal-sized folds\n<\/span>folds <- cut( seq<\/span> (1, nrow<\/span> (df.shuffled)), breaks=K, labels= FALSE<\/span> )\n\n#create object to hold MSE's of models\n<\/span>mse = matrix(data=NA,nrow=K,ncol=degree)\n\n#Perform K-fold cross validation\n<\/span>for<\/span> (i in<\/span> 1:K){\n    \n#define training and testing data\n<\/span>testIndexes <- which<\/span> (folds==i,arr.ind= TRUE<\/span> )\n    testData <- df.shuffled[testIndexes, ]\n    trainData <- df.shuffled[-testIndexes, ]\n    \n#use k-fold cv to evaluate models\n<\/span>for (j in 1:degree){\n        fit.train = lm<\/span> (score ~ poly<\/span> (hours,d), data=trainData)\n        fit.test = predict<\/span> (fit.train, newdata=testData)\n        mse[i,j] = mean<\/span> ((fit.test-testData$score)^2) \n    }\n}\n\n#find MSE for each degree \n<\/span>colMeans(mse)\n\n[1] 9.802397 8.748666 9.601865 10.592569 13.545547\n<\/strong><\/span><\/pre>\n
\u4ece\u7ed3\u679c\u4e2d\u6211\u4eec\u53ef\u4ee5\u770b\u5230\u6bcf\u4e2a\u6a21\u578b\u7684MSE\u6d4b\u8bd5\uff1a<\/span><\/p>\n