111 lines
3.8 KiB
R
111 lines
3.8 KiB
R
install.packages(c("e1071","caret","randomForest","ggplot2","pROC"), dependencies = TRUE)
|
|
|
|
suppressPackageStartupMessages({
|
|
library(e1071) # for svm/tune.svm
|
|
library(caret) # for metrics
|
|
library(randomForest) # alternative classifier
|
|
library(ggplot2)
|
|
})
|
|
|
|
set.seed(42)
|
|
|
|
read_wine <- function() {
|
|
df <- read.csv("wine.data", header = FALSE)
|
|
colnames(df) <- c("Class",
|
|
"Alcohol","Malic.acid","Ash","Alcalinity.of.ash","Magnesium",
|
|
"Total.phenols","Flavanoids","Nonflavanoid.phenols","Proanthocyanins",
|
|
"Color.intensity","Hue","OD280.OD315","Proline")
|
|
df$Class <- factor(df$Class)
|
|
df
|
|
}
|
|
|
|
df <- read_wine()
|
|
|
|
# split into train/test
|
|
idx <- createDataPartition(df$Class, p = 0.8, list = FALSE)
|
|
train <- df[idx, ]
|
|
test <- df[-idx, ]
|
|
|
|
# choose a subset of features based on ANOVA F-test
|
|
# I picked this sbuset before the runs:
|
|
# alcohol, flavanoids, color intensity, od280/od315, proline, total phenols
|
|
features <- c("Alcohol","Flavanoids","Color.intensity","OD280.OD315","Proline","Total.phenols")
|
|
x_train <- train[, features]
|
|
y_train <- train$Class
|
|
x_test <- test[, features]
|
|
y_test <- test$Class
|
|
|
|
# scale features
|
|
pp <- preProcess(x_train, method = c("center","scale"))
|
|
x_train_s <- predict(pp, x_train)
|
|
x_test_s <- predict(pp, x_test)
|
|
|
|
# 1) linear kernel svm with hyperparameter tuning (C)
|
|
set.seed(42)
|
|
lin_grid <- data.frame(cost = c(0.1, 1, 10, 100))
|
|
tune_lin <- tune.svm(x = x_train_s, y = y_train,
|
|
kernel = "linear",
|
|
cost = lin_grid$cost,
|
|
tunecontrol = tune.control(cross = 5))
|
|
lin_best <- tune_lin$best.model
|
|
|
|
# 2) rbf kernel svm with tuning (C, gamma)
|
|
set.seed(42)
|
|
rbf_grid_cost <- c(0.1, 1, 10, 100, 1000)
|
|
rbf_grid_gamma <- c(0.001, 0.01, 0.1, 1)
|
|
tune_rbf <- tune.svm(x = x_train_s, y = y_train,
|
|
kernel = "radial",
|
|
cost = rbf_grid_cost,
|
|
gamma = rbf_grid_gamma,
|
|
tunecontrol = tune.control(cross = 5))
|
|
rbf_best <- tune_rbf$best.model
|
|
|
|
# 3) alternative classifier: random forest (same features)
|
|
set.seed(42)
|
|
rf_fit <- randomForest(x = x_train, y = y_train, ntree = 500, mtry = 2, importance = TRUE)
|
|
|
|
# evaluation helper
|
|
eval_model <- function(model, x_test_s, y_test, name) {
|
|
pred <- predict(model, x_test_s)
|
|
cm <- confusionMatrix(pred, y_test)
|
|
pr <- data.frame(model = name,
|
|
accuracy = cm$overall["Accuracy"],
|
|
precision_macro = mean(cm$byClass[,"Precision"], na.rm=TRUE),
|
|
recall_macro = mean(cm$byClass[,"Recall"], na.rm=TRUE),
|
|
f1_macro = mean(cm$byClass[,"F1"], na.rm=TRUE))
|
|
list(cm = cm, pr = pr)
|
|
}
|
|
|
|
# eval svm models (use scaled features)
|
|
lin_eval <- eval_model(lin_best, x_test_s, y_test, "svm_linear")
|
|
rbf_eval <- eval_model(rbf_best, x_test_s, y_test, "svm_rbf")
|
|
|
|
# evaluate random forest (no scaling)
|
|
rf_pred <- predict(rf_fit, x_test)
|
|
rf_cm <- confusionMatrix(rf_pred, y_test)
|
|
|
|
rf_pr <- data.frame(model = "random_forest",
|
|
accuracy = rf_cm$overall["Accuracy"],
|
|
precision_macro = mean(rf_cm$byClass[,"Precision"], na.rm=TRUE),
|
|
recall_macro = mean(rf_cm$byClass[,"Recall"], na.rm=TRUE),
|
|
f1_macro = mean(rf_cm$byClass[,"F1"], na.rm=TRUE))
|
|
|
|
perf <- rbind(lin_eval$pr, rbf_eval$pr, rf_pr)
|
|
|
|
# print
|
|
cat("best params (linear svm): C =", lin_best$cost, "\n")
|
|
cat("best params (rbf svm): C =", rbf_best$cost, " gamma =", rbf_best$gamma, "\n\n")
|
|
print(perf)
|
|
|
|
# macro-f1 comparison
|
|
ggplot(perf, aes(x = model, y = f1_macro)) +
|
|
geom_col() +
|
|
labs(title = "macro-F1 by model (wine test set)")
|
|
|
|
# save outputs
|
|
write.table(perf, file = "lab5_performance_table.txt", sep = "\t", row.names = FALSE, quote = FALSE)
|
|
sink("lab5_confusion_matrices.txt")
|
|
cat("=== svm linear ===\n"); print(lin_eval$cm)
|
|
cat("\n=== svm rbf ===\n"); print(rbf_eval$cm)
|
|
cat("\n=== random forest ===\n"); print(rf_cm)
|
|
sink() |