Script R

8.1 Permutation Variable Importance Program 8.1 rumah = read.csv("rumah.csv") set.seed(50) ambil = sample(1:nrow(rumah), 40) datalatih = rumah[ambil,] datauji = rumah[-ambil,] modellengkap = lm(harga ~ luasbangunan + umur + kamarmandi + dekattol, data=datalatih) RMSEPasli = sqrt(mean((predict(modellengkap, datauji) – datauji$harga)^2)) n.uji = nrow(datauji) permutasi1 = datauji permutasi1$luasbangunan = permutasi1[sample(1:n.uji, n.uji),]$luasbangunan RMSEP1 = sqrt(mean((predict(modellengkap, permutasi1) – datauji$harga)^2)) permutasi2 … Read more

7.1 LASSO Program 7.1 rumah = read.csv("rumah.csv") library(glmnet) x = as.matrix(rumah[,2:7]) y = rumah[,8] model1 <- glmnet(x, y, alpha = 1, lambda = 1) model2 <- glmnet(x, y, alpha = 1, lambda = 3) model3 <- glmnet(x, y, alpha = 1, lambda = 5) matrix(cbind(coef(model1), coef(model2), coef(model3)), ncol=3) Output 7.1 ## [,1] [,2] [,3] ## … Read more

6.2 Best Subset Program 6.1 best = leaps(x=rumah[,2:7], y=rumah[,8], method="adjr2", nbest=2) hasil = data.frame(size=best$size-1, best$which, adjr2=best$adjr2*100) hasil = hasil[order(hasil[,8], decreasing=TRUE),] row.names(hasil) = 1:nrow(hasil) hasil Output 6.1 ## size X1 X2 X3 X4 X5 X6 adjr2 ## 1 3 FALSE TRUE TRUE FALSE FALSE TRUE 84.56957 ## 2 4 FALSE TRUE TRUE FALSE TRUE TRUE 84.37513 … Read more

5.1 Statistik Uji ANOVA Program 5.1 promo <- read.csv("promo.csv") promo2 <- promo[,-c(1,2,4)] promo2$X12 <- promo2$frekuensi.fashion*promo2$nilai.fashion promo2$X13 <- promo2$frekuensi.footwear*promo2$nilai.footwear promo2$X14 <- promo2$frekuensi.lainnya*promo2$nilai.lainnya promo2$X15 <- promo2$total.nilai.tunai/(promo2$X12 + promo2$X13 + promo2$X14) hasil = NULL for(i in c(1:9, 11:14)){ y = promo2[,i] x = promo2$promo F = oneway.test(y ~ x)$statistic hasil = rbind(hasil, c(i, F)) } namavar = colnames(promo2)[-10] … Read more

4.2 Variance Threshold Program 4.1 data <- read.csv("data sapi.csv") data <- data[,-1] head(format(data, digits=6)) ## X1pjg_badan X2ttg_badan X3lkr_badan X4pjg_ekor X5pjg_tanduk Ybbt_badan ## 1 118.488 118.634 191.772 36.1714 15.99607 2836.12 ## 2 170.237 127.834 174.372 35.6906 14.27944 3058.19 ## 3 157.333 155.058 171.637 31.5397 11.45499 3153.16 ## 4 116.805 151.166 194.035 30.3483 10.04847 2923.64 ## 5 … Read more

3.1 Regresi Logistik Program 3.1 # mengimpor data dataEHR <- read.csv("data-EHR.csv", sep=",") # Mengubah peubah “SOURCE” dan “AGE” menjadi factor. library(dplyr) dataEHR <- dataEHR %>% mutate_at(c(10,11),factor) # Memisahkan data menjadi 80% data latih dan 20% data uji. set.seed(123) n <- round(0.2*nrow(dataEHR),0) contoh <- sample(nrow(dataEHR), n, replace = FALSE) EHRlatih <- dataEHR[-contoh,] EHRuji <- dataEHR[contoh,] # … Read more

2.1 Regresi Linier Program 2.1 data <- read.csv("data sapi.csv") data <- data[,-1] regresi <- lm(Ybbt_badan ~ ., data=data) regresi Output 2.1 ## ## Call: ## lm(formula = Ybbt_badan ~ ., data = data) ## ## Coefficients: ## (Intercept) X1pjg_badan X2ttg_badan X3lkr_badan X4pjg_ekor ## 118.8305 6.1877 4.5001 7.4794 1.1279 ## X5pjg_tanduk ## 0.1448 Program 2.2 data … Read more