# Copyright 2024, MetaQuotes Ltd.
# https://www.mql5.com
# imports 
from datetime import datetime
import MetaTrader5 as mt5
import pandas as pd
import numpy  as np
import pytz
import os
from category_encoders import OrdinalEncoder, OneHotEncoder, BinaryEncoder,TargetEncoder, CountEncoder, HashingEncoder, LeaveOneOutEncoder,JamesSteinEncoder

if not mt5.initialize():
    print("initialize() failed ")
    mt5.shutdown()
    exit()
 
#set up timezone infomation   
tz=pytz.timezone("Etc/UTC")

#use time zone to set correct date for history data extraction
startdate = datetime(2023,12,31,hour=23,minute=59,second=59,tzinfo=tz)
stopdate = datetime(2017,12,31,hour=23,minute=59,second=59,tzinfo=tz)

#list the symbol 
symbol = "BTCUSD"

#get price history
prices = pd.DataFrame(mt5.copy_rates_range(symbol,mt5.TIMEFRAME_D1,stopdate,startdate))

if len(prices) < 1:
    print(" Error downloading rates history ")
    mt5.shutdown()
    exit()

#shutdown mt5 tether
mt5.shutdown()

#drop unnecessary columns
prices.drop(labels=["time","tick_volume","spread","real_volume"],axis=1,inplace=True)

#initialize categorical features
prices["bar_type"] = np.where(prices["close"]>=prices["open"],"bullish","bearish")
prices["body_type"] = np.empty((len(prices),),dtype='str')
prices["bar_pattern"] = np.empty((len(prices),),dtype='str')

#set feature values
for i in np.arange(len(prices)):
    bodyratio = np.abs(prices.iloc[i,3]-prices.iloc[i,0])/np.abs(prices.iloc[i,1]-prices.iloc[i,2])
    if bodyratio >= 0.75:
        prices.iloc[i,5] = ">=0.75"
    elif bodyratio < 0.75 and bodyratio >= 0.5:
        prices.iloc[i,5]=">=0.5<0.75"
    elif bodyratio < 0.5 and bodyratio >= 0.25:
        prices.iloc[i,5]=">=0.25<0.5"
    else:
        prices.iloc[i,5]="<0.25"
    if i < 1:
      prices.iloc[i,6] = None
      continue
    if(prices.iloc[i,4]=="bullish" and prices.iloc[i-1,4]=="bullish") and (prices.iloc[i,1]>prices.iloc[i-1,1]) and (prices.iloc[i,2]>prices.iloc[i-1,2]):
        prices.iloc[i,6] = "higherHigh"
    elif(prices.iloc[i,4]=="bearish" and prices.iloc[i-1,4]=="bearish") and (prices.iloc[i,2]<prices.iloc[i-1,2]) and (prices.iloc[i,1]<prices.iloc[i-1,1]):
        prices.iloc[i,6] = "lowerLow"
    else :
        prices.iloc[i,6] = "flat"
 
#calculate target
look_ahead = 1
prices["target"] = np.log(prices["close"])
prices["target"] = prices["target"].diff(look_ahead)
prices["target"] = prices["target"].shift(-look_ahead)              

#drop rows with NA values
prices.dropna(axis=0,inplace=True,ignore_index=True)

print("Full feature matrix \n",prices.head())

#Ordinal encoding
ord_encoder = OrdinalEncoder(cols = ["bar_type","body_type","bar_pattern"])
ordinal_data = ord_encoder.fit_transform(prices)

print(" ordinal encoding\n ", ordinal_data.head())


#One-Hot encoding
onehot_encoder = OneHotEncoder(cols = ["bar_type","body_type","bar_pattern"])
onehot_data = onehot_encoder.fit_transform(prices)

print(" ordinal encoding\n ", onehot_data.head())

#Binary encoding
binary_encoder = BinaryEncoder(cols = ["bar_type","body_type","bar_pattern"])
binary_data = binary_encoder.fit_transform(prices)

print(" binary encoding\n ", binary_data.head())

#Frequency encoding
freq_encoder = CountEncoder(cols = ["bar_type","body_type","bar_pattern"])
freq_data = freq_encoder.fit_transform(prices)

print(" frequency encoding\n ", freq_data.head())

#Hashing encoding
hash_encoder = HashingEncoder(cols = ["bar_type","body_type","bar_pattern"],n_components=3)
hash_data = hash_encoder.fit_transform(prices)

print(" hashing encoding\n ", hash_data.head())

#Target encoding
target_encoder = TargetEncoder(cols = ["bar_type","body_type","bar_pattern"])
target_data = target_encoder.fit_transform(prices[["open","high","low","close","bar_type","body_type","bar_pattern"]], prices["target"])

print(" target encoding\n ", target_data.head())

#LeaveOneOut encoding
oneout_encoder = LeaveOneOutEncoder(cols = ["bar_type","body_type","bar_pattern"])
oneout_data = oneout_encoder.fit_transform(prices[["open","high","low","close","bar_type","body_type","bar_pattern"]], prices["target"])

print(" LeaveOneOut encoding\n ", oneout_data.head())

#James Stein encoding
james_encoder = JamesSteinEncoder(cols = ["bar_type","body_type","bar_pattern"])
james_data = james_encoder.fit_transform(prices[["open","high","low","close","bar_type","body_type","bar_pattern"]], prices["target"])

print(" James Stein encoding\n ", james_data.head())