install.packages(c("titanic", "caTools", "pROC", "ggplot2"))
library(titanic)
library(caTools)
library(pROC)
library(ggplot2)
data("titanic_train")
df <- na.omit(titanic_train)
df$Survived <- as.factor(df$Survived)
df$Pclass <- as.factor(df$Pclass)
df$Sex <- as.factor(df$Sex)
set.seed(123)
split <- sample.split(df$Survived, SplitRatio = 0.7)
train_data <- subset(df, split == TRUE)
test_data <- subset(df, split == FALSE)
model <- glm(Survived ~ Pclass + Sex + Age + Fare,
data = train_data, family = "binomial")
probs <- predict(model, test_data, type = "response")
roc_obj <- roc(test_data$Survived, probs)
print(paste("AUC Score:", round(auc(roc_obj), 3)))
plot(roc_obj, main ="ROC Curve for Titanic Survival", col = "blue")
