Mengimpor library yang diperlukan
library(randomForest)
## Warning: package 'randomForest' was built under R version 4.2.3
## randomForest 4.7-1.1
## Type rfNews() to see new features/changes/bug fixes.
library(readxl)
library(dplyr)
##
## Attaching package: 'dplyr'
## The following object is masked from 'package:randomForest':
##
## combine
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
library(caret)
## Loading required package: ggplot2
##
## Attaching package: 'ggplot2'
## The following object is masked from 'package:randomForest':
##
## margin
## Loading required package: lattice
Mengimpor dataset
data <- read_excel ("D:/SOBAT KARIER/PORTOFOLIO/Jantung/hearth.xlsx")
head(data)
## # A tibble: 6 × 14
## age sex cp trestbps chol fbs restecg thalach exang oldpeak slope
## <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 69 1 0 160 234 1 2 131 0 0.1 1
## 2 69 0 0 140 239 0 0 151 0 1.8 0
## 3 66 0 0 150 226 0 0 114 0 2.6 2
## 4 65 1 0 138 282 1 2 174 0 1.4 1
## 5 64 1 0 110 211 0 2 144 1 1.8 1
## 6 64 1 0 170 227 0 2 155 0 0.6 1
## # … with 3 more variables: ca <dbl>, thal <dbl>, condition <dbl>
str(data)
## tibble [297 × 14] (S3: tbl_df/tbl/data.frame)
## $ age : num [1:297] 69 69 66 65 64 64 63 61 60 59 ...
## $ sex : num [1:297] 1 0 0 1 1 1 1 1 0 1 ...
## $ cp : num [1:297] 0 0 0 0 0 0 0 0 0 0 ...
## $ trestbps : num [1:297] 160 140 150 138 110 170 145 134 150 178 ...
## $ chol : num [1:297] 234 239 226 282 211 227 233 234 240 270 ...
## $ fbs : num [1:297] 1 0 0 1 0 0 1 0 0 0 ...
## $ restecg : num [1:297] 2 0 0 2 2 2 2 0 0 2 ...
## $ thalach : num [1:297] 131 151 114 174 144 155 150 145 171 145 ...
## $ exang : num [1:297] 0 0 0 0 1 0 0 0 0 0 ...
## $ oldpeak : num [1:297] 0.1 1.8 2.6 1.4 1.8 0.6 2.3 2.6 0.9 4.2 ...
## $ slope : num [1:297] 1 0 2 1 1 1 2 1 0 2 ...
## $ ca : num [1:297] 1 2 0 1 0 0 0 2 0 0 ...
## $ thal : num [1:297] 0 0 0 0 0 2 1 0 0 2 ...
## $ condition: num [1:297] 0 0 0 1 0 0 0 1 0 0 ...
Memisahkan data menjadi fitur (X) dan variabel target (y)
X <- data[, -14] # Mengambil semua kolom kecuali kolom terakhir
y <- data$condition # Kolom terakhir sebagai variabel target
Membagi dataset menjadi data training dan data testing
set.seed(123) # Mengatur seed untuk reproducibility
n <- round(nrow(data) * 0.7) # Jumlah data training (70% dari total data)
sample <- sample(seq_len(nrow(data)), size = n) # Membuat sampel data training
train <- data[sample, ] # Data training
test <- data[-sample, ] # Data testing
# Melakukan proses klasifikasi dengan metode Random Forest
model <- randomForest(factor(condition) ~ ., data = train)
# Menampilkan ringkasan dari model
print(model)
##
## Call:
## randomForest(formula = factor(condition) ~ ., data = train)
## Type of random forest: classification
## Number of trees: 500
## No. of variables tried at each split: 3
##
## OOB estimate of error rate: 20.19%
## Confusion matrix:
## 0 1 class.error
## 0 94 17 0.1531532
## 1 25 72 0.2577320
Melakukan prediksi menggunakan data testing
predictions <- predict(model, newdata = test)
Membuat confusion matrix
# Create a confusion matrix
cm <- confusionMatrix(data = as.factor(predictions), reference = as.factor(test$condition))
# Print the confusion matrix
print(cm)
## Confusion Matrix and Statistics
##
## Reference
## Prediction 0 1
## 0 41 5
## 1 8 35
##
## Accuracy : 0.8539
## 95% CI : (0.7632, 0.9199)
## No Information Rate : 0.5506
## P-Value [Acc > NIR] : 1.077e-09
##
## Kappa : 0.7069
##
## Mcnemar's Test P-Value : 0.5791
##
## Sensitivity : 0.8367
## Specificity : 0.8750
## Pos Pred Value : 0.8913
## Neg Pred Value : 0.8140
## Prevalence : 0.5506
## Detection Rate : 0.4607
## Detection Prevalence : 0.5169
## Balanced Accuracy : 0.8559
##
## 'Positive' Class : 0
##
# Visualize the decision tree
tree <- model$forest[[1]]
plot(tree, main = "Decision Tree", sub = "")
# Load the rpart package for decision tree
library(rpart)
# Train the decision tree model
model <- rpart(condition ~., data = train, method = "class")
# Visualize the decision tree
plot(model)
text(model, use.n = TRUE, all = TRUE, cex = 0.8)
library(rpart)
library(rpart.plot)
## Warning: package 'rpart.plot' was built under R version 4.2.3
# Membangun model pohon keputusan
model <- rpart(condition ~ ., data = train, method = "class")
# Menampilkan pohon keputusan dengan rpart.plot
rpart.plot(model)
