Buram UAS Datmin
Vena Ulya Maulida
2025-05-28
library(caret)## Warning: package 'caret' was built under R version 4.4.3## Loading required package: ggplot2## Loading required package: latticelibrary(readxl)## Warning: package 'readxl' was built under R version 4.4.3library(e1071)
library(rpart)
library(rpart.plot)## Warning: package 'rpart.plot' was built under R version 4.4.3library(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':
##
## margintrain.data <- read_excel("D:/Data Mining/datatraining.xlsx")
test.data <- read_excel("D:/Data Mining/datatesting.xlsx")
print(train.data)## # A tibble: 200 × 11
## usia jenis_kelamin nilai_rata_rata dukungan_orang_tua fasilitas_belajar
## <dbl> <chr> <dbl> <chr> <chr>
## 1 15 0 85.2 1 2
## 2 19 0 60.9 2 3
## 3 15 0 60.5 2 1
## 4 15 1 78.6 3 2
## 5 16 1 66.2 2 1
## 6 18 1 85.9 2 1
## 7 16 1 45.2 1 3
## 8 16 0 91.6 2 2
## 9 15 1 74.1 2 1
## 10 21 1 88.2 3 3
## # ℹ 190 more rows
## # ℹ 6 more variables: jam_belajar_per_hari <dbl>, kehadiran_persen <dbl>,
## # minat_pada_pelajaran <chr>, kesulitan_ekonomi <chr>,
## # jarak_rumah_sekolah <dbl>, motivasi_belajar <chr>print(test.data)## # A tibble: 15 × 10
## usia jenis_kelamin nilai_rata_rata dukungan_orang_tua fasilitas_belajar
## <dbl> <chr> <dbl> <chr> <chr>
## 1 15 1 90.2 2 2
## 2 19 0 79.6 1 1
## 3 17 0 66.9 2 3
## 4 20 1 85.6 3 1
## 5 16 1 65.9 3 1
## 6 21 0 70.8 2 3
## 7 21 0 86.3 3 2
## 8 19 1 84.3 3 3
## 9 17 0 79.5 2 2
## 10 18 0 74.4 1 2
## 11 16 1 76.9 3 2
## 12 15 1 81.9 2 2
## 13 17 1 83.2 3 2
## 14 17 0 65.2 3 3
## 15 20 1 62 2 1
## # ℹ 5 more variables: jam_belajar_per_hari <dbl>, kehadiran_persen <dbl>,
## # minat_pada_pelajaran <chr>, kesulitan_ekonomi <chr>,
## # jarak_rumah_sekolah <dbl>train.data[c("jenis_kelamin", "dukungan_orang_tua", "fasilitas_belajar", "minat_pada_pelajaran", "kesulitan_ekonomi", "motivasi_belajar")] <- lapply(train.data[c("jenis_kelamin", "dukungan_orang_tua", "fasilitas_belajar", "minat_pada_pelajaran", "kesulitan_ekonomi", "motivasi_belajar")], as.factor)
str(train.data)## 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 ...test.data[c("jenis_kelamin", "dukungan_orang_tua", "fasilitas_belajar", "minat_pada_pelajaran", "kesulitan_ekonomi")] <- lapply(test.data[c("jenis_kelamin", "dukungan_orang_tua", "fasilitas_belajar", "minat_pada_pelajaran", "kesulitan_ekonomi")], as.factor)
str(test.data)## 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 ...#Metode SVM
svm_model <- svm(motivasi_belajar ~ ., data = train.data, kernel = "radial")
svm_pred <- predict(svm_model, newdata = test.data)
head(svm_pred, 15)## 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15
## 2 2 1 2 1 2 2 2 2 2 1 1 2 1 1
## Levels: 1 2 3#Random Forest
model_rf <- randomForest(motivasi_belajar ~ ., data = train.data)
pred_rf <- predict(model_rf, newdata = test.data)
head(pred_rf, 15)## 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15
## 2 2 1 2 1 2 2 2 2 2 1 1 2 2 1
## Levels: 1 2 3#Decision Tree
tree_model <- rpart(motivasi_belajar ~ ., data = train.data, method = "class")
tree_pred <- predict(tree_model, newdata = test.data, type = "class")
head(tree_pred, 15)## 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15
## 2 2 1 2 1 2 2 3 1 2 2 1 1 2 1
## Levels: 1 2 3rpart.plot(tree_model, type = 2, extra = 104, fallen.leaves = TRUE, cex = 0.7)