//+------------------------------------------------------------------+
//|        TargetBasedNominalVariableConversionWithDimReduc_demo.mq5 |
//|                                  Copyright 2024, MetaQuotes Ltd. |
//|                                             https://www.mql5.com |
//+------------------------------------------------------------------+
#property copyright "Copyright 2024, MetaQuotes Ltd."
#property link      "https://www.mql5.com"
#property version   "1.00"
#property script_show_inputs
#include<np.mqh>
#include<nom2ord.mqh>
#include<ErrorDescription.mqh>
//--- input parameters
input datetime TrainingSampleStartDate=D'2023.12.31';
input datetime TrainingSampleStopDate=D'2017.12.31';
input ENUM_TIMEFRAMES tf = PERIOD_D1;
input string   SetSymbol="BTCUSD";
//+------------------------------------------------------------------+
//|global integer variables                                          |
//+------------------------------------------------------------------+
int size_insample,                 //training set size
    size_observations,             //size of of both training and testing sets combined
    price_handle=INVALID_HANDLE;   //log prices indicator handle
//+------------------------------------------------------------------+
//|double global variables                                           |
//+------------------------------------------------------------------+

matrix       prices;                   //array for log transformed prices
vector       targets;                  //differenced prices kept here
matrix       predictors;               //flat array arranged as matrix of all predictors ie size_observations by size_predictors
//+------------------------------------------------------------------+
//| Script program start function                                    |
//+------------------------------------------------------------------+
void OnStart()
  {
//get relative shift of is and oos sets
   int trainstart,trainstop;
   trainstart=iBarShift(SetSymbol!=""?SetSymbol:NULL,tf,TrainingSampleStartDate);
   trainstop=iBarShift(SetSymbol!=""?SetSymbol:NULL,tf,TrainingSampleStopDate);
//check for errors from ibarshift calls
   if( trainstart<0 || trainstop<0)
     {
      Print(ErrorDescription(GetLastError()));
      return;
     }
//---set the size of the sample sets
   size_insample=(trainstop - trainstart) + 1;
//---check for input errors
   if(size_insample<=0)
     {
      Print("Invalid inputs ");
      return;
     }
//---
    if(!predictors.Resize(size_insample,3))
     {
      Print("ArrayResize error ",ErrorDescription(GetLastError()));
      return;
     }
//---
   if(!prices.CopyRates(SetSymbol,tf,COPY_RATES_VERTICAL|COPY_RATES_OHLC,TrainingSampleStartDate,TrainingSampleStopDate))
    {
      Print("Copyrates error ",ErrorDescription(GetLastError()));
      return;
    }
//---
   targets = log(prices.Col(3));
   targets = np::diff(targets);
//---
   double bodyratio = 0.0;
   for(ulong i = 0; i<prices.Rows(); i++)
     {
      if(prices[i][3]<prices[i][0])
         predictors[i][0] = 0.0;
      else
         predictors[i][0] = 1.0;

      bodyratio = MathAbs(prices[i][3]-prices[i][0])/MathAbs(prices[i][1]-prices[i][2]);

      if(bodyratio >=0.75)
         predictors[i][1] = 0.0;
      else
         if(bodyratio<0.75 && bodyratio>=0.5)
            predictors[i][1] = 1.0;
         else
            if(bodyratio<0.5 && bodyratio>=0.25)
               predictors[i][1] = 2.0;
            else
               predictors[i][1] = 3.0;

      if(i<1)
        {
         predictors[i][2] = 0.0;
         continue;
        }

      if(predictors[i][0]==1.0 && predictors[i-1][0]==1.0 && prices[i][1]>prices[i-1][1] && prices[i][2]>prices[i-1][2])
         predictors[i][2] = 2.0;
      else
         if(predictors[i][0]==0.0 && predictors[i-1][0]==0.0 && prices[i][2]<prices[i-1][2] && prices[i][1]>prices[i-1][1])
            predictors[i][2] = 1.0;
         else
            predictors[i][2] = 0.0;
     }
    
   targets = np::sliceVector(targets,1);
   
   prices = np::sliceMatrixRows(prices,1,predictors.Rows()-1);
   
   predictors = np::sliceMatrixRows(predictors,1,predictors.Rows()-1);
   
   matrix fullFeatureMatrix(predictors.Rows(),predictors.Cols()+prices.Cols());
   
   if(!np::matrixCopyCols(fullFeatureMatrix,prices,0,prices.Cols()) ||
      !np::matrixCopyCols(fullFeatureMatrix,predictors,prices.Cols()))
    {
     Print("Failed to merge matrices");
     return;
    }
   
   if(predictors.Rows()!=targets.Size())
    {
     Print(" Error in aligning data structures ");
     return;
    }  
   
   CNomOrd enc;
   
   ulong selectedcols[] = {4,5,6};
     
   matrix transformed = enc.fitTransform(fullFeatureMatrix,selectedcols,targets);
   
   Print(" Original predictors \n", fullFeatureMatrix);
   Print(" transformed predictors \n", transformed);
   
   Print(" Probability that predicator  is associated with target ", enc.score(10000,targets));
  }
//+------------------------------------------------------------------+