Random Forest.Rmd

---
title: "Random Forest"
output: html_notebook
---

```{r}
# Remove all variables from the R environment to create a fresh start
rm(list=ls())

# Load datasets
train1 <- read.csv("train_dataset01.csv")
train2 <- read.csv("train_dataset02.csv")
test <- read.csv("test_dataset.csv")

levels(train2$STATUS_PU3) <- c("False", "True")
levels(train2$STATUS_PU5) <- c("False", "True")
levels(train2$STATUS_PU8) <- c("False", "True")
levels(train2$STATUS_PU9) <- c("False", "True")

levels(test$STATUS_PU8) <- c("False", "True")
levels(test$STATUS_PU9) <- c("False", "True")
```

Split
```{r}
library(caTools)
set.seed(100)
spl <-sample.split(train2$ATT_FLAG, SplitRatio =0.7)
attackTrain <- subset(train2, spl == TRUE)
attackTest <- subset(train2, spl == FALSE)
```

Train and validate (CART)
```{r}
# Random Forest
library(randomForest)

# Build the model
attackTrain$DATETIME <- NULL
model1 <- randomForest(ATT_FLAG~., data=attackTrain)
summary(model1)
varImpPlot(model1)

# Prediction
predict1 <- predict(model1, newdata=attackTest)
cm <- table(predict1, attackTest$ATT_FLAG)
cm

precision <- cm[2,2]/sum(cm[2,])
recall <- cm[2,2]/sum(cm[,2])
f1 <- 2 * precision * recall / (precision + recall)

precision
recall
f1
```

Train on whole train2 and predict test
```{r}
# Build the model
train2$DATETIME <- NULL
model2 <- randomForest(ATT_FLAG~., data=train2)
summary(model2)
varImpPlot(model2)

# Prediction
predict2 <- predict(model2, newdata=test)
```

See performance
```{r}
test$ATT_FLAG <- predict2
test.ts <- ts(test)

ignore = c("LEVEL_T5", "FLOW_PU3", "FLOW_PU5", "FLOW_PU9", "STATUS_PU3", "STATUS_PU5", "STATUS_PU8", "STATUS_PU9")
test.small <- test[ , -which(names(test) %in% ignore)]
test.small.ts <- ts(test.small)

for (col in colnames(test.small.ts)) {
  if (col != "DATETIME" & col != "ATT_FLAG") {
    plot.ts(test.small.ts[,col], ylab=col, col=c("black"))
    par(new = TRUE)
    plot.ts(test.small.ts[,"ATT_FLAG"], axes=FALSE, bty = "n", xlab = "", ylab = "", col="red")
  }
}

# section <- test.small.ts[6000:7000, ]
# for (col in colnames(section)) {
#   if (col != "DATETIME" & col != "ATT_FLAG") {
#     plot.ts(section[,col], ylab=col, col=c("black"))
#     par(new = TRUE)
#     plot.ts(section[,"ATT_FLAG"], axes=FALSE, bty = "n", xlab = "", ylab = "", col="red")
#   }
# }

```