#Load Library
library(caret)## Warning: package 'caret' was built under R version 4.4.3## Loading required package: ggplot2## Warning: package 'ggplot2' was built under R version 4.4.3## Loading required package: latticelibrary(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(e1071)## Warning: package 'e1071' was built under R version 4.4.3library(rpart)## Warning: package 'rpart' 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:dplyr':
##
## combine## The following object is masked from 'package:ggplot2':
##
## margin#Import Data
datatraining <- read_excel("C:/Users/canti/Downloads/datatraining.xlsx")
datatesting <- read_excel("C:/Users/canti/Downloads/datatesting.xlsx")#Preprocessing Data
# Kolom kategorik diubah ke factor
factor_cols <- c("jenis_kelamin", "dukungan_orang_tua", "fasilitas_belajar","minat_pada_pelajaran", "kesulitan_ekonomi", "motivasi_belajar")
datatraining[factor_cols] <- lapply(datatraining[factor_cols], as.factor)
# Kolom numerik ke numeric/int
datatraining$usia <- as.integer(datatraining$usia)
datatraining$nilai_rata_rata <- as.numeric(datatraining$nilai_rata_rata)
datatraining$jam_belajar_per_hari <- as.numeric(datatraining$jam_belajar_per_hari)
datatraining$kehadiran_persen <- as.numeric(datatraining$kehadiran_persen)
datatraining$jarak_rumah_sekolah <- as.numeric(datatraining$jarak_rumah_sekolah)
# Cek struktur
str(datatraining)## tibble [200 × 11] (S3: tbl_df/tbl/data.frame)
## $ usia : int [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 ...# Kolom kategorik diubah ke factor
factor_cols_test <- c("jenis_kelamin", "dukungan_orang_tua", "fasilitas_belajar",
"minat_pada_pelajaran", "kesulitan_ekonomi")
datatesting[factor_cols_test] <- lapply(datatesting[factor_cols_test], as.factor)
# Kolom numerik ke numeric/int
datatesting$usia <- as.integer(datatesting$usia)
datatesting$nilai_rata_rata <- as.numeric(datatesting$nilai_rata_rata)
datatesting$jam_belajar_per_hari <- as.numeric(datatesting$jam_belajar_per_hari)
datatesting$kehadiran_persen <- as.numeric(datatesting$kehadiran_persen)
datatesting$jarak_rumah_sekolah <- as.numeric(datatesting$jarak_rumah_sekolah)
# Cek struktur
str(datatesting)## tibble [15 × 10] (S3: tbl_df/tbl/data.frame)
## $ usia : int [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 ...summary(datatraining)## usia jenis_kelamin nilai_rata_rata dukungan_orang_tua
## Min. :15.00 0: 95 Min. : 41.50 1: 39
## 1st Qu.:16.00 1:105 1st Qu.: 66.95 2:111
## Median :18.00 Median : 74.40 3: 50
## 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
## 1:52 Min. :1.000 Min. : 66.30 1:65
## 2:88 1st Qu.:2.900 1st Qu.: 79.70 2:76
## 3:60 Median :4.050 Median : 86.10 3:59
## 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
## 0:112 Min. : 1.000 1: 81
## 1: 88 1st Qu.: 5.475 2:105
## Median : 8.300 3: 14
## Mean : 8.315
## 3rd Qu.:11.300
## Max. :20.500summary(datatesting)## usia jenis_kelamin nilai_rata_rata dukungan_orang_tua
## Min. :15.00 0:7 Min. :62.00 1:2
## 1st Qu.:16.50 1:8 1st Qu.:68.85 2:6
## Median :17.00 Median :79.50 3:7
## 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
## 1:4 Min. :1.400 Min. : 64.90 1:9
## 2:7 1st Qu.:1.900 1st Qu.: 77.15 2:3
## 3:4 Median :2.900 Median : 84.50 3:3
## 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
## 0:10 Min. : 3.100
## 1: 5 1st Qu.: 5.050
## Median : 8.000
## Mean : 7.667
## 3rd Qu.:10.050
## Max. :12.500colSums(is.na(datatraining))## usia jenis_kelamin nilai_rata_rata
## 0 0 0
## dukungan_orang_tua fasilitas_belajar jam_belajar_per_hari
## 0 0 0
## kehadiran_persen minat_pada_pelajaran kesulitan_ekonomi
## 0 0 0
## jarak_rumah_sekolah motivasi_belajar
## 0 0colSums(is.na(datatesting))## usia jenis_kelamin nilai_rata_rata
## 0 0 0
## dukungan_orang_tua fasilitas_belajar jam_belajar_per_hari
## 0 0 0
## kehadiran_persen minat_pada_pelajaran kesulitan_ekonomi
## 0 0 0
## jarak_rumah_sekolah
## 0# Ubah kolom di testing
factor_cols_test <- setdiff (factor_cols,"motivasi_belajar")
datatesting [factor_cols_test]<-lapply(datatesting [factor_cols_test],as.factor)
# Samakan levels antara training dan testing(
for(col in factor_cols_test){
datatesting [[col]]<-factor(datatesting[[col]],levels=levels(datatraining[[col]]))
}#Training Model
# Decision Tree
model_dt <- rpart(motivasi_belajar~.,data = datatraining,method="class")
# Random Forest
model_rf <- randomForest(motivasi_belajar~.,data = datatraining)
# SVM
model_svm <- svm(motivasi_belajar~.,data = datatraining)#Prediksi
# Decision Tree
pred_dt <- predict(model_dt,datatesting,type="class")
# Random Forest
pred_rf <- predict(model_rf,datatesting)
# SVM
pred_svm <- predict(model_svm,datatesting)
hasil_prediksi <- data.frame(
No = 1: nrow(datatesting),
Prediksi_DecisionTree = pred_dt,
Prediksi_RandomForest = pred_rf,
Prediksi_SVM = pred_svm
)
print(hasil_prediksi)## No Prediksi_DecisionTree Prediksi_RandomForest Prediksi_SVM
## 1 1 2 2 2
## 2 2 2 2 2
## 3 3 1 1 1
## 4 4 2 2 2
## 5 5 1 1 1
## 6 6 2 2 2
## 7 7 2 2 2
## 8 8 3 2 2
## 9 9 1 2 2
## 10 10 2 2 2
## 11 11 2 1 1
## 12 12 1 1 1
## 13 13 1 2 2
## 14 14 2 2 1
## 15 15 1 1 1