39 lines
1.3 KiB
R
39 lines
1.3 KiB
R
# Install necessary packages
|
|
if(!require(tidyverse)) install.packages("tidyverse")
|
|
if(!require(caret)) install.packages("caret")
|
|
|
|
# Load Libraries
|
|
library(tidyverse)
|
|
library(caret)
|
|
|
|
# Download data
|
|
url <- "https://archive.ics.uci.edu/ml/machine-learning-databases/00526/data.zip"
|
|
dest_file <- "data/data.zip"
|
|
if(!dir.exists("data"))dir.create("data")
|
|
if(!file.exists(dest_file))download.file(url, destfile = dest_file)
|
|
|
|
# Unzip
|
|
if(!file.exists("data/BitcoinHeistData.csv"))unzip(dest_file, "BitcoinHeistData.csv", exdir="data")
|
|
|
|
# Import data from CSV
|
|
ransomware <- read_csv("data/BitcoinHeistData.csv")
|
|
|
|
# Turn labels into factors, bw is a binary factor for ransomware/non-ransomware
|
|
ransomware <- ransomware %>% mutate(label=as.factor(label), bw=as.factor(ifelse(label=="white", "white", "black")))
|
|
|
|
# Validation set made from 50% of BitcoinHeist data, reduce later if possible. Binary outcomes (bw)
|
|
test_index <- createDataPartition(y = ransomware$bw, times = 1, p = .5, list = FALSE)
|
|
|
|
workset <- ransomware[-test_index,]
|
|
validation <- ransomware[test_index,]
|
|
|
|
# Split the working set into a training set and a test set @ 50%, reduce later if possible. Binary outcomes (bw)
|
|
test_index <- createDataPartition(y = workset$bw, times = 1, p = .5, list = FALSE)
|
|
|
|
train_set <- workset[-test_index,]
|
|
test_set <- workset[test_index,]
|
|
|
|
# Clean up environment
|
|
rm(dest_file, url)
|
|
|