cat(system('curl -sL https://gitlab.aicrowd.com/snippets/34123/raw > aicrowd.R', intern=TRUE), sep='\n')
cat(system('pip3 install -q -U aicrowd-cli', intern=TRUE), sep='\n')
cat(system('pip install -q -U aicrowd-cli', intern=TRUE), sep='\n')

source("aicrowd.R")

# You can get your API key from https://www.aicrowd.com/participants/me

# Please use the absolute for the location of the dataset.
AICROWD_DATASET_PATH = Sys.getenv("DATASET_PATH", "/ds_shared_drive/validation.csv")
AICROWD_PREDICTIONS_PATH = Sys.getenv("PREDICTIONS_PATH", "predictions.csv")

# Use this directory to store any assets needed
AICROWD_ASSETS_DIR = "assets"

#install.packages("ggplot2", repos='http://cran.ma.imperial.ac.uk')
#install.packages("dplyr", repos='http://cran.ma.imperial.ac.uk')
#install.packages("stringr", repos='http://cran.ma.imperial.ac.uk')
cat(system('conda install --quiet --yes -c conda-forge r-xgboost', intern=TRUE), sep='\n')

library(ggplot2)
library(dplyr)
library(stringr)
library(xgboost)

##########################################################################################################
#
# $$\   $$\ $$$$$$$$\ $$\       $$\       $$$$$$\  
# $$ |  $$ |$$  _____|$$ |      $$ |     $$  __$$\ 
# $$ |  $$ |$$ |      $$ |      $$ |     $$ /  $$ |
# $$$$$$$$ |$$$$$\    $$ |      $$ |     $$ |  $$ |
# $$  __$$ |$$  __|   $$ |      $$ |     $$ |  $$ |
# $$ |  $$ |$$ |      $$ |      $$ |     $$ |  $$ |
# $$ |  $$ |$$$$$$$$\ $$$$$$$$\ $$$$$$$$\ $$$$$$  |
# \__|  \__|\________|\________|\________|\______/  
# 
#
# Hello R user! 
# I wanted to share a starter kit for R users...  are there any in the competition? :)  
#
# Below you will find:  
# 
#   - light Exploratory Data Analysis
#   - small Feature Engineering
#   - Model Training
#   - Prediction Generating
#   - Working Submission (Leaderboard Log Loss of )
#
#
# I hope this can inspire you, and more importantly, help you debug any issues you might encounter!  
#
# Don't hesitate to comment below.  
# 
# Stay safe, enjoy!
#
# Michaël
#
##########################################################################################################

# Looking at the data, there is quite a few NAs.
#
# However, it appears most of the time that whenever there's a NA, it looks like 0 could be a good proxy.
#
# As an example, for the length of the clock hand.
#  - If the clock hand is absent, it is identified as NA.
#  - But we could reasonably also call it a length of 0.
#
# Therefore, in order to produce the correlation chart, I will replace all NAs with 0.

# names(td)[sapply(td, anyNA)]  #to see variables with NAs

preprocess <- function(df){ 
 
    # Remove the ID variable
    df <- df[, !names(df) %in% c("row_id")]
    
    #Converting character variables to factors
    df$intersection_pos_rel_centre <- as.factor(df$intersection_pos_rel_centre)
    
    
    # Feature Engineering
    df$count_NA <- rowSums( is.na( df[,] ))    # count the number of NA
    
    #Cleaning
    df[is.na(df)] <- 0  # imputing 0 to missing
    
    # Feature Enineering
    df$ellipse_area = 3.1451926 * df$double_major * df$double_minor / 2    # surface area of the clock
   
    return(df)
}

td = read.csv(str_replace(AICROWD_DATASET_PATH,"validation","train"))

td$diagnosis <- as.factor(td$diagnosis)

# The target variable is a multi-class, with 3 levels. 
#
#    normal
#    pre_alzheimer
#    post_alzheimer
#
# We will look at how behaves each feature variable in the context of the three classes to predict.

# Remove the ID variable
td <- td[, !names(td) %in% c("row_id")]

# Number of graphs to produce, and their name
nvar = ncol(td)
#nvar = 5
var_list = combn(names(td)[1:nvar], 1, simplify=FALSE)

# Make plots.
for (i in 1:nvar) {
  p = ggplot(td, aes_string(x=var_list[[i]][1], color=td$diagnosis)) +
            geom_density(alpha=0, na.rm=TRUE)
  print(p)
}

# Correlation
#
# Creating a numerical version of the diagnosis
# tds <- td %>% mutate(diag.normal = ifelse(diagnosis == "normal",1,0)) %>% 
#              mutate(diag.pre    = ifelse(diagnosis == "pre_alzheimer",1,0)) %>% 
#               mutate(diag.post   = ifelse(diagnosis == "post_alzheimer",1,0)) 

# What's correlated with a normal condition?
#  td_normal <- tds %>% select(-diagnosis,-diag.pre,-diag.post)
#  corr_var(td_normal, # name of dataset
#         diag.normal, # name of variable to focus on
#         top = 30 # display top correlations
#)   

# This wonderful correlation function is within the "lares" package.
# Unfortunately, I wasn't able to install it.  
#   Not available on CRAN.
#   VMs can't install from github
#   VM wasn't able to install from raw zip file.
#   Conda copy is outdated.
#
# I still recommend this package, look it up!

# Applying my preprocessing
#   Cleaning and Feature Engineering

td_clean <- preprocess(td)



# Creating data set to feed xgboost

x_data <- td_clean %>% select(-diagnosis)
y_data <- td_clean %>% select( diagnosis)
y_label = as.integer(y_data$diagnosis) -1

mat_train = as.matrix(sapply(x_data,as.numeric))

xgb_train_data = xgb.DMatrix(data= mat_train , label = y_label)

# Defining the parameters

params_multi = list(
  booster = "gbtree",
  eta = 0.01,
  max_depth = 6,
  gamma = 0,
  subsample = 0.55,
  colsample_bytree = 0.55,
  min_child_weight= 10,
  objective = "multi:softprob",
  eval_metric="mlogloss",
  num_class = 3
)

# Fit

xgb_multi = xgb.train(
  params = params_multi,
  data = xgb_train_data,
  nrounds = 250,
  verbose = 1
)

# Importance of the features
names <- dimnames(xgb_train_data)[[2]]
imp <- xgb.importance(names, model=xgb_multi)
imp

xgb.plot.importance(imp, top_n = 10)

xgb.save(xgb_multi, file.path(AICROWD_ASSETS_DIR,"xgb_multi_file"))

xgb_multi <- xgb.load(file.path(AICROWD_ASSETS_DIR,"xgb_multi_file"))

test_data = read.csv(AICROWD_DATASET_PATH)
head(test_data)
row_id = test_data$row_id

test_data <- preprocess(test_data)
mat_test = as.matrix(sapply(test_data,as.numeric))

xgb_pred = as.data.frame(predict(xgb_multi, mat_test, reshape=T))
colnames(xgb_pred) = c("normal","post_alzheimer","pre_alzheimer")
summary(xgb_pred)

predictions <- data.frame(
    row_id = row_id,
    normal_diagnosis_probability = xgb_pred$normal,
    post_alzheimer_diagnosis_probability = xgb_pred$post_alzheimer,
    pre_alzheimer_diagnosis_probability = xgb_pred$pre_alzheimer
)


write.csv(predictions, AICROWD_PREDICTIONS_PATH, row.names=FALSE)

aicrowd_login(AICROWD_API_KEY)
aicrowd_submit(AICROWD_ASSETS_DIR, "addi-alzheimers-detection-challenge", dataset_dir = AICROWD_DATASET_PATH)