library(readxl)## Warning: package 'readxl' was built under R version 4.4.3library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionlibrary(caret)## Warning: package 'caret' was built under R version 4.4.3## Loading required package: ggplot2## Loading required package: latticelibrary(e1071)
library(randomForest)## Warning: package 'randomForest' was built under R version 4.4.3## randomForest 4.7-1.2## Type rfNews() to see new features/changes/bug fixes.##
## Attaching package: 'randomForest'## The following object is masked from 'package:ggplot2':
##
## margin## The following object is masked from 'package:dplyr':
##
## combinelibrary(rpart)datatraining <- read_excel("D:/kuliah/Data Mining/UAS/datatraining.xlsx")
datatesting <- read_excel("D:/kuliah/Data Mining/UAS/datatesting.xlsx")
summary(datatraining)## usia jenis_kelamin nilai_rata_rata dukungan_orang_tua
## Min. :15.00 Length:200 Min. : 41.50 Length:200
## 1st Qu.:16.00 Class :character 1st Qu.: 66.95 Class :character
## Median :18.00 Mode :character Median : 74.40 Mode :character
## Mean :17.78 Mean : 74.14
## 3rd Qu.:20.00 3rd Qu.: 80.78
## Max. :21.00 Max. :100.00
## fasilitas_belajar jam_belajar_per_hari kehadiran_persen minat_pada_pelajaran
## Length:200 Min. :1.000 Min. : 66.30 Length:200
## Class :character 1st Qu.:2.900 1st Qu.: 79.70 Class :character
## Mode :character Median :4.050 Median : 86.10 Mode :character
## Mean :4.095 Mean : 85.53
## 3rd Qu.:5.100 3rd Qu.: 90.80
## Max. :8.800 Max. :100.00
## kesulitan_ekonomi jarak_rumah_sekolah motivasi_belajar
## Length:200 Min. : 1.000 Length:200
## Class :character 1st Qu.: 5.475 Class :character
## Mode :character Median : 8.300 Mode :character
## Mean : 8.315
## 3rd Qu.:11.300
## Max. :20.500summary(datatesting)## usia jenis_kelamin nilai_rata_rata dukungan_orang_tua
## Min. :15.00 Length:15 Min. :62.00 Length:15
## 1st Qu.:16.50 Class :character 1st Qu.:68.85 Class :character
## Median :17.00 Mode :character Median :79.50 Mode :character
## Mean :17.87 Mean :76.85
## 3rd Qu.:19.50 3rd Qu.:83.75
## Max. :21.00 Max. :90.20
## fasilitas_belajar jam_belajar_per_hari kehadiran_persen minat_pada_pelajaran
## Length:15 Min. :1.400 Min. : 64.90 Length:15
## Class :character 1st Qu.:1.900 1st Qu.: 77.15 Class :character
## Mode :character Median :2.900 Median : 84.50 Mode :character
## Mean :3.287 Mean : 83.64
## 3rd Qu.:4.500 3rd Qu.: 89.85
## Max. :5.500 Max. :100.00
## kesulitan_ekonomi jarak_rumah_sekolah
## Length:15 Min. : 3.100
## Class :character 1st Qu.: 5.050
## Mode :character Median : 8.000
## Mean : 7.667
## 3rd Qu.:10.050
## Max. :12.500glimpse(datatraining)## Rows: 200
## Columns: 11
## $ usia <dbl> 15, 19, 15, 15, 16, 18, 16, 16, 15, 21, 21, 18, 1…
## $ jenis_kelamin <chr> "0", "0", "0", "1", "1", "1", "1", "0", "1", "1",…
## $ nilai_rata_rata <dbl> 85.2, 60.9, 60.5, 78.6, 66.2, 85.9, 45.2, 91.6, 7…
## $ dukungan_orang_tua <chr> "1", "2", "2", "3", "2", "2", "1", "2", "2", "3",…
## $ fasilitas_belajar <chr> "2", "3", "1", "2", "1", "1", "3", "2", "1", "3",…
## $ jam_belajar_per_hari <dbl> 4.1, 3.8, 6.1, 5.1, 5.5, 3.7, 2.8, 6.2, 4.6, 3.0,…
## $ kehadiran_persen <dbl> 79.7, 89.8, 86.7, 78.5, 81.0, 85.4, 78.9, 78.1, 9…
## $ minat_pada_pelajaran <chr> "2", "2", "1", "3", "1", "2", "1", "2", "2", "3",…
## $ kesulitan_ekonomi <chr> "0", "1", "1", "1", "1", "1", "0", "0", "0", "1",…
## $ jarak_rumah_sekolah <dbl> 11.5, 6.3, 15.9, 9.8, 3.5, 1.0, 6.4, 4.9, 6.5, 9.…
## $ motivasi_belajar <chr> "1", "2", "1", "2", "1", "1", "1", "2", "1", "3",…glimpse(datatesting)## Rows: 15
## Columns: 10
## $ usia <dbl> 15, 19, 17, 20, 16, 21, 21, 19, 17, 18, 16, 15, 1…
## $ jenis_kelamin <chr> "1", "0", "0", "1", "1", "0", "0", "1", "0", "0",…
## $ nilai_rata_rata <dbl> 90.2, 79.6, 66.9, 85.6, 65.9, 70.8, 86.3, 84.3, 7…
## $ dukungan_orang_tua <chr> "2", "1", "2", "3", "3", "2", "3", "3", "2", "1",…
## $ fasilitas_belajar <chr> "2", "1", "3", "1", "1", "3", "2", "3", "2", "2",…
## $ jam_belajar_per_hari <dbl> 5.4, 4.6, 2.9, 3.9, 5.3, 1.9, 4.4, 1.5, 2.0, 5.5,…
## $ kehadiran_persen <dbl> 78.3, 88.2, 76.3, 89.4, 74.0, 100.0, 100.0, 92.1,…
## $ minat_pada_pelajaran <chr> "2", "3", "1", "1", "1", "1", "1", "1", "3", "3",…
## $ kesulitan_ekonomi <chr> "1", "0", "0", "0", "1", "1", "0", "0", "0", "0",…
## $ jarak_rumah_sekolah <dbl> 4.7, 10.8, 11.8, 5.7, 3.1, 7.1, 8.2, 5.4, 4.2, 10…datatraining[c("jenis_kelamin", "dukungan_orang_tua", "fasilitas_belajar", "minat_pada_pelajaran", "kesulitan_ekonomi", "motivasi_belajar")] <-
lapply(datatraining[c("jenis_kelamin", "dukungan_orang_tua", "fasilitas_belajar", "minat_pada_pelajaran", "kesulitan_ekonomi", "motivasi_belajar")] , as.factor)
str(datatraining)## tibble [200 × 11] (S3: tbl_df/tbl/data.frame)
## $ usia : num [1:200] 15 19 15 15 16 18 16 16 15 21 ...
## $ jenis_kelamin : Factor w/ 2 levels "0","1": 1 1 1 2 2 2 2 1 2 2 ...
## $ nilai_rata_rata : num [1:200] 85.2 60.9 60.5 78.6 66.2 85.9 45.2 91.6 74.1 88.2 ...
## $ dukungan_orang_tua : Factor w/ 3 levels "1","2","3": 1 2 2 3 2 2 1 2 2 3 ...
## $ fasilitas_belajar : Factor w/ 3 levels "1","2","3": 2 3 1 2 1 1 3 2 1 3 ...
## $ jam_belajar_per_hari: num [1:200] 4.1 3.8 6.1 5.1 5.5 3.7 2.8 6.2 4.6 3 ...
## $ kehadiran_persen : num [1:200] 79.7 89.8 86.7 78.5 81 85.4 78.9 78.1 96.8 82.1 ...
## $ minat_pada_pelajaran: Factor w/ 3 levels "1","2","3": 2 2 1 3 1 2 1 2 2 3 ...
## $ kesulitan_ekonomi : Factor w/ 2 levels "0","1": 1 2 2 2 2 2 1 1 1 2 ...
## $ jarak_rumah_sekolah : num [1:200] 11.5 6.3 15.9 9.8 3.5 1 6.4 4.9 6.5 9.5 ...
## $ motivasi_belajar : Factor w/ 3 levels "1","2","3": 1 2 1 2 1 1 1 2 1 3 ...datatesting[c("jenis_kelamin", "dukungan_orang_tua", "fasilitas_belajar", "minat_pada_pelajaran", "kesulitan_ekonomi")] <-
lapply(datatesting[c("jenis_kelamin", "dukungan_orang_tua", "fasilitas_belajar", "minat_pada_pelajaran", "kesulitan_ekonomi")], as.factor)
str(datatesting)## tibble [15 × 10] (S3: tbl_df/tbl/data.frame)
## $ usia : num [1:15] 15 19 17 20 16 21 21 19 17 18 ...
## $ jenis_kelamin : Factor w/ 2 levels "0","1": 2 1 1 2 2 1 1 2 1 1 ...
## $ nilai_rata_rata : num [1:15] 90.2 79.6 66.9 85.6 65.9 70.8 86.3 84.3 79.5 74.4 ...
## $ dukungan_orang_tua : Factor w/ 3 levels "1","2","3": 2 1 2 3 3 2 3 3 2 1 ...
## $ fasilitas_belajar : Factor w/ 3 levels "1","2","3": 2 1 3 1 1 3 2 3 2 2 ...
## $ jam_belajar_per_hari: num [1:15] 5.4 4.6 2.9 3.9 5.3 1.9 4.4 1.5 2 5.5 ...
## $ kehadiran_persen : num [1:15] 78.3 88.2 76.3 89.4 74 100 100 92.1 84.5 90.3 ...
## $ minat_pada_pelajaran: Factor w/ 3 levels "1","2","3": 2 3 1 1 1 1 1 1 3 3 ...
## $ kesulitan_ekonomi : Factor w/ 2 levels "0","1": 2 1 1 1 2 2 1 1 1 1 ...
## $ jarak_rumah_sekolah : num [1:15] 4.7 10.8 11.8 5.7 3.1 7.1 8.2 5.4 4.2 10.7 ...numeric_vars <- c("usia", "nilai_rata_rata", "jam_belajar_per_hari",
"kehadiran_persen", "jarak_rumah_sekolah")
train <- datatraining
test <- datatesting
preProc <- preProcess(datatraining[, numeric_vars], method = c("center", "scale"))
train_svm <- datatraining
test_svm <- datatesting
train_svm[, numeric_vars] <- predict(preProc, datatraining[, numeric_vars])
test_svm[, numeric_vars] <- predict(preProc, datatesting[, numeric_vars])svm_model <- svm(motivasi_belajar ~ ., data = train_svm)
svm_pred <- predict(svm_model, newdata = test_svm)rf_model <- randomForest(motivasi_belajar ~ ., data = train, ntree = 100)
rf_pred <- predict(rf_model, newdata = test)dt_model <- rpart(motivasi_belajar ~ ., data = train, method = "class")
dt_pred <- predict(dt_model, newdata = test, type = "class")results <- data.frame(
SVM = svm_pred,
RandomForest = rf_pred,
DecisionTree = dt_pred
)
print(results)## SVM RandomForest DecisionTree
## 1 2 2 2
## 2 2 2 2
## 3 1 1 1
## 4 2 2 2
## 5 1 1 1
## 6 2 2 2
## 7 2 2 2
## 8 2 2 3
## 9 2 1 1
## 10 2 2 2
## 11 1 1 2
## 12 1 1 1
## 13 2 2 1
## 14 1 2 2
## 15 1 1 1