library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 3.5.2 ✔ tibble 3.2.1
## ✔ lubridate 1.9.4 ✔ tidyr 1.3.1
## ✔ purrr 1.0.4
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(randomForest)
## 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
library(caret)
## Loading required package: lattice
##
## Attaching package: 'caret'
##
## The following object is masked from 'package:purrr':
##
## lift
library(readxl)
library(randomForest) #for random forest
library(e1071) # for SVM
library(rpart) # for decision tree
data_train <- read_excel("D:/file kuliah/datatraining.xlsx")
data_test <- read_excel("D:/file kuliah/datatesting.xlsx")
str(data_train)
## 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 : chr [1:200] "0" "0" "0" "1" ...
## $ 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 : chr [1:200] "1" "2" "2" "3" ...
## $ fasilitas_belajar : chr [1:200] "2" "3" "1" "2" ...
## $ 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: chr [1:200] "2" "2" "1" "3" ...
## $ kesulitan_ekonomi : chr [1:200] "0" "1" "1" "1" ...
## $ 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 : chr [1:200] "1" "2" "1" "2" ...
str(data_test)
## 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 : chr [1:15] "1" "0" "0" "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 : chr [1:15] "2" "1" "2" "3" ...
## $ fasilitas_belajar : chr [1:15] "2" "1" "3" "1" ...
## $ 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: chr [1:15] "2" "3" "1" "1" ...
## $ kesulitan_ekonomi : chr [1:15] "1" "0" "0" "0" ...
## $ 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 ...
# Ubah tipe kolom yang sesuai
factor_cols <- c("jenis_kelamin", "dukungan_orang_tua", "fasilitas_belajar",
"minat_pada_pelajaran", "kesulitan_ekonomi", "motivasi_belajar")
data_train[factor_cols] <- lapply(data_train[factor_cols], as.factor)
# Untuk data testing, tanpa motivasi_belajar
factor_cols_test <- setdiff(factor_cols, "motivasi_belajar")
data_test[factor_cols_test] <- lapply(data_test[factor_cols_test], as.factor)
# Konfirmasi perubahan
str(data_train)
## 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 ...
library(randomForest)
# Latih model dengan semua variabel kecuali motivasi_belajar sebagai target
model_rf <- randomForest(motivasi_belajar ~ ., data = data_train, ntree = 100, importance = TRUE)
# Lihat ringkasan model
print(model_rf)
##
## Call:
## randomForest(formula = motivasi_belajar ~ ., data = data_train, ntree = 100, importance = TRUE)
## Type of random forest: classification
## Number of trees: 100
## No. of variables tried at each split: 3
##
## OOB estimate of error rate: 29%
## Confusion matrix:
## 1 2 3 class.error
## 1 55 26 0 0.3209877
## 2 17 87 1 0.1714286
## 3 0 14 0 1.0000000
library(e1071)
# Latih model SVM dengan kernel radial (default)
model_svm <- svm(motivasi_belajar ~ ., data = data_train, kernel = "radial")
# Lihat ringkasan model
summary(model_svm)
##
## Call:
## svm(formula = motivasi_belajar ~ ., data = data_train, kernel = "radial")
##
##
## Parameters:
## SVM-Type: C-classification
## SVM-Kernel: radial
## cost: 1
##
## Number of Support Vectors: 177
##
## ( 69 94 14 )
##
##
## Number of Classes: 3
##
## Levels:
## 1 2 3
library(rpart)
# Latih model decision tree
model_dt <- rpart(motivasi_belajar ~ ., data = data_train, method = "class")
# Lihat ringkasan model
printcp(model_dt)
##
## Classification tree:
## rpart(formula = motivasi_belajar ~ ., data = data_train, method = "class")
##
## Variables actually used in tree construction:
## [1] dukungan_orang_tua fasilitas_belajar jam_belajar_per_hari
## [4] kehadiran_persen kesulitan_ekonomi nilai_rata_rata
##
## Root node error: 95/200 = 0.475
##
## n= 200
##
## CP nsplit rel error xerror xstd
## 1 0.178947 0 1.00000 1.00000 0.074339
## 2 0.115789 1 0.82105 1.07368 0.074417
## 3 0.052632 2 0.70526 0.84211 0.072928
## 4 0.042105 3 0.65263 0.88421 0.073473
## 5 0.015789 4 0.61053 0.89474 0.073590
## 6 0.010526 6 0.57895 0.88421 0.073473
## 7 0.010000 8 0.55789 0.88421 0.073473
# Visualisasi opsional
library(rpart.plot)
rpart.plot(model_dt)
# Mengubah kolom kategorikal menjadi factor
kategori_vars <- c("jenis_kelamin", "dukungan_orang_tua", "fasilitas_belajar",
"minat_pada_pelajaran", "kesulitan_ekonomi", "motivasi_belajar")
data_train[kategori_vars] <- lapply(data_train[kategori_vars], as.factor)
data_test[kategori_vars[-6]] <- lapply(data_test[kategori_vars[-6]], as.factor) # Tanpa motivasi_belajar
model_rf <- randomForest(motivasi_belajar ~ ., data = data_train, ntree = 100)
pred_rf <- predict(model_rf, newdata = data_test)
# Pastikan target adalah faktor
library(e1071)
model_svm <- svm(motivasi_belajar ~ ., data = data_train, kernel = "radial")
pred_svm <- predict(model_svm, newdata = data_test)
library(rpart)
model_dt <- rpart(motivasi_belajar ~ ., data = data_train, method = "class")
pred_dt <- predict(model_dt, newdata = data_test, type = "class")
hasil_prediksi <- data_test
hasil_prediksi$pred_rf <- pred_rf
hasil_prediksi$pred_svm <- pred_svm
hasil_prediksi$pred_dt <- pred_dt
# Tampilkan
print(hasil_prediksi[, c("pred_rf", "pred_svm", "pred_dt")])
## # A tibble: 15 × 3
## pred_rf pred_svm pred_dt
## <fct> <fct> <fct>
## 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 2 1
## 10 2 2 2
## 11 1 1 2
## 12 1 1 1
## 13 2 2 1
## 14 2 1 2
## 15 1 1 1