/Citadel-Datathon

Citadel Datathon

Primary LanguageHTML

Citadel Datathon

src contains the source code used for this challenge report contains the source code used for the $\Latex$ report

https://v2.overleaf.com/6183192336bcqknxjpwgmt

https://drive.google.com/drive/folders/1epKW_AnAU4EOmpiUduaFQqO1_DC5cc2s?usp=sharing

library(MASS)

# Backward selection
backward_model <- MASS::stepAIC( lm(Prob~., data = dataset1) )

# Forward selection
MASS::stepAIC( lm(Prob~1, data = dataset1), 
               direction = "forward", 
               scope=list(
                upper=lm(Prob~., data = dataset1), 
                lower=lm(Prob~1, data = dataset1)) 
)

set.seed(2)
library(randomForest)
model_rf <- randomForest(Y_train ~ ., data = X_train, importance = TRUE) # Including every variable
model_rf

# Prediction on test set
# No need for cross-validation - out of the bag
prediction_rf <- predict(model_rf, X_test)
table(prediction_rf, Y_test)
result <- prediction_rf==Y_test

# Summary plots
importance(model_rf)    
varImpPlot(model_rf, main = "Random Forests Classifier")

# ROC AUC 
plot(roc(Y_test, as.numeric(prediction_rf=="p"), direction="<" ), print.auc=TRUE, col = 'red', lwd = 3)