{"id":474,"date":"2023-07-29T19:05:27","date_gmt":"2023-07-29T19:05:27","guid":{"rendered":"https:\/\/statorials.org\/ko\/%e1%84%83%e1%85%a1%e1%84%92%e1%85%a1%e1%86%bc%e1%84%89%e1%85%b5%e1%86%a8-%e1%84%92%e1%85%ac%e1%84%80%e1%85%b1-r\/"},"modified":"2023-07-29T19:05:27","modified_gmt":"2023-07-29T19:05:27","slug":"%e1%84%83%e1%85%a1%e1%84%92%e1%85%a1%e1%86%bc%e1%84%89%e1%85%b5%e1%86%a8-%e1%84%92%e1%85%ac%e1%84%80%e1%85%b1-r","status":"publish","type":"post","link":"https:\/\/statorials.org\/ko\/%e1%84%83%e1%85%a1%e1%84%92%e1%85%a1%e1%86%bc%e1%84%89%e1%85%b5%e1%86%a8-%e1%84%92%e1%85%ac%e1%84%80%e1%85%b1-r\/","title":{"rendered":"R\uc758 \ub2e4\ud56d\uc2dd \ud68c\uadc0(\ub2e8\uacc4\ubcc4)"},"content":{"rendered":"

<\/p>\n

\n

\ub2e4\ud56d\uc2dd \ud68c\uadc0\ub294<\/a> \uc608\uce21 \ubcc0\uc218\uc640 \uc751\ub2f5 \ubcc0\uc218<\/a> \uac04\uc758 \uad00\uacc4\uac00 \ube44\uc120\ud615\uc77c \ub54c \uc0ac\uc6a9\ud560 \uc218 \uc788\ub294 \uae30\uc220\uc785\ub2c8\ub2e4.<\/span><\/p>\n

\uc774\ub7ec\ud55c \uc720\ud615\uc758 \ud68c\uadc0\ub294 \ub2e4\uc74c\uacfc \uac19\uc740 \ud615\uc2dd\uc744 \ucde8\ud569\ub2c8\ub2e4.<\/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

\uc5ec\uae30\uc11c h<\/em> \ub294 \ub2e4\ud56d\uc2dd\uc758 “\ucc28\uc218”\uc785\ub2c8\ub2e4.<\/span><\/p>\n

\uc774 \ud29c\ud1a0\ub9ac\uc5bc\uc5d0\uc11c\ub294 R\uc5d0\uc11c \ub2e4\ud56d\uc2dd \ud68c\uadc0\ub97c \uc218\ud589\ud558\ub294 \ubc29\ubc95\uc5d0 \ub300\ud55c \ub2e8\uacc4\ubcc4 \uc608\ub97c \uc81c\uacf5\ud569\ub2c8\ub2e4.<\/span><\/p>\n

1\ub2e8\uacc4: \ub370\uc774\ud130 \uc0dd\uc131<\/strong><\/span><\/h3>\n

\uc774 \uc608\uc5d0\uc11c\ub294 \ud559\uc0dd 50\uba85\uc5d0 \ub300\ud55c \ud559\uc2b5 \uc2dc\uac04\uacfc \ucd5c\uc885 \uc2dc\ud5d8 \uc131\uc801\uc774 \ud3ec\ud568\ub41c \ub370\uc774\ud130 \uc138\ud2b8\ub97c \ub9cc\ub4ed\ub2c8\ub2e4.<\/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
 2\ub2e8\uacc4: \ub370\uc774\ud130 \uc2dc\uac01\ud654<\/strong><\/span><\/h3>\n
 \ud68c\uadc0 \ubaa8\ub378\uc744 \ub370\uc774\ud130\uc5d0 \ub9de\ucd94\uae30 \uc804\uc5d0 \uba3c\uc800 \uacf5\ubd80 \uc2dc\uac04\uacfc \uc2dc\ud5d8 \uc810\uc218 \uc0ac\uc774\uc758 \uad00\uacc4\ub97c \uc2dc\uac01\ud654\ud558\ub294 \uc0b0\uc810\ub3c4\ub97c \ub9cc\ub4e4\uc5b4 \ubcf4\uaca0\uc2b5\ub2c8\ub2e4.<\/span> <\/p>\n
 library<\/span> (ggplot2)\n\nggplot(df, aes<\/span> (x=hours, y=score)) +\n  geom_point()<\/strong> <\/pre>\n
\"\"<\/p>\n
 \ub370\uc774\ud130\uc5d0 \uc57d\uac04\uc758 2\ucc28 \uad00\uacc4\uac00 \uc788\ub2e4\ub294 \uac83\uc744 \uc54c \uc218 \uc788\ub294\ub370, \uc774\ub294 \ub2e4\ud56d\uc2dd \ud68c\uadc0\uac00 \ub2e8\uc21c \uc120\ud615 \ud68c\uadc0\ubcf4\ub2e4 \ub370\uc774\ud130\uc5d0 \ub354 \uc798 \ub9de\uc744 \uc218 \uc788\uc74c\uc744 \ub098\ud0c0\ub0c5\ub2c8\ub2e4.<\/span><\/p>\n
 3\ub2e8\uacc4: \ub2e4\ud56d \ud68c\uadc0 \ubaa8\ub378 \ud53c\ud305<\/span><\/strong><\/h3>\n
 \ub2e4\uc74c\uc73c\ub85c, \ucc28\uc218 h<\/em> = 1\u20265\uc778 5\uac1c\uc758 \uc11c\ub85c \ub2e4\ub978 \ub2e4\ud56d\uc2dd \ud68c\uadc0 \ubaa8\ub378\uc744 \ud53c\ud305\ud558\uace0 k = 10\ubc88\uc73c\ub85c k\uacb9 \uad50\ucc28 \uac80\uc99d\uc744 \uc0ac\uc6a9\ud558\uc5ec \uac01 \ubaa8\ub378\uc5d0 \ub300\ud55c MSE \ud14c\uc2a4\ud2b8\ub97c \uacc4\uc0b0\ud569\ub2c8\ub2e4.<\/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
 \uacb0\uacfc\uc5d0\uc11c \uac01 \ubaa8\ub378\uc5d0 \ub300\ud55c MSE \ud14c\uc2a4\ud2b8\ub97c \ubcfc \uc218 \uc788\uc2b5\ub2c8\ub2e4.<\/span><\/p>\n