# 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, grey is a binary factor for ransomware/non-ransomware
ransomware <- ransomware %>% mutate(label=as.factor(label), 
                                    grey=as.factor(ifelse(label=="white", "white", "black")), 
                                    address=as.factor(address))

# Sample every other row (keeping it simple for now)
#ransomware <- ransomware[seq(1, nrow(ransomware), 2), ]

# Validation set made from 50% of BitcoinHeist data, reduce later if possible. Binary outcomes (grey)
test_index <- createDataPartition(y = ransomware$grey, times = 1, p = .5, list = FALSE)

# Validation set made from 50% of BitcoinHeist data, reduce later if possible. Categorical outcomes
#test_index <- createDataPartition(y = ransomware$label, times = 1, p = .5, list = FALSE)

workset <- ransomware[-test_index,]
temp <- ransomware[test_index,]

# Make sure addresses in validation set are also in working set...
# validation <- temp %>% 
#  semi_join(workset, by = "address")

# Add rows removed from validation set back into working set...
#removed <- anti_join(temp, validation)
#workset <- rbind(workset, removed)

# ... Or not
validation <- temp

# Split the working set into a training set and a test set @ 50%, reduce later if possible. Binary outcomes (grey)
test_index <- createDataPartition(y = workset$grey, times = 1, p = .5, list = FALSE)

# Split the working set into a training set and a test set @ 50%, reduce later if possible. Categorical outcomes
#test_index <- createDataPartition(y = workset$label, times = 1, p = .5, list = FALSE)

train_set <- workset[-test_index,]
temp <- workset[test_index,]

# Make sure addresses in validation set are also in working set....
#test_set <- temp %>% 
#  semi_join(train_set, by = "address")

# Add rows removed from validation set back into working set....
#removed <- anti_join(temp, test_set)
#train_set <- rbind(train_set, removed)

# ....Or not
test_set <- temp

# Clean up environment
rm(dest_file, url, temp)

# Inspect data frames
#test_set %>% str()
#test_set %>% head()
#train_set %>% str()
#train_set %>% head()

## Data preparation is done, now focusing on Self Organizing Maps as our method