import numpy as np
from scipy.optimize import minimize

sp100_stocks = ['AAPL','MSFT','AMZN','FB','BRKB','GOOGL','GOOG','JPM','JNJ','V','PG','XOM','UNH','BAC','MA','T','DIS','INTC','HD','VZ','MRK','PFE','CVX','KO','CMCSA','CSCO','PEP','WFC','C','BA','ADBE','WMT','CRM','MCD','MDT','BMY','ABT','NVDA','NFLX','AMGN','PM','PYPL','TMO','COST','ABBV','ACN','HON','NKE','UNP','UTX','NEE','IBM','TXN','AVGO','LLY','ORCL','LIN','SBUX','AMT','LMT','GE','MMM','DHR','QCOM','CVS','MO','LOW','FIS','AXP','BKNG','UPS','GILD','CHTR','CAT','MDLZ','GS','USB','CI','ANTM','BDX','TJX','ADP','TFC','CME','SPGI','COP','INTU','ISRG','CB','SO','D','FISV','PNC','DUK','SYK','ZTS','MS','RTN','AGN','BLK']

def MonthDiff(d1, d2):
    return (d1.year - d2.year) * 12 + d1.month - d2.month

def Return(values):
    return (values[-1] - values[0]) / values[0]
    
def Volatility(values):
    values = np.array(values)
    returns = (values[1:] - values[:-1]) / values[:-1]
    return np.std(returns)  

def GetFutureMulitpliers(algorithm):
    symbol_multiplier = {}
    
    csv_string_file = algorithm.Download('data.quantpedia.com/backtesting_data/futures/contract_multiplier.csv')
    mulitpliers_lines = csv_string_file.split('\r\n')
    for line in mulitpliers_lines:
        symbol, multiplier = line.split(';')
        symbol_multiplier[symbol] = multiplier
    
    return symbol_multiplier

# Custom fee model
class CustomFeeModel(FeeModel):
    def GetOrderFee(self, parameters):
        fee = parameters.Security.Price * parameters.Order.AbsoluteQuantity * 0.00005
        return OrderFee(CashAmount(fee, "USD"))

# Quandl free data
class QuandlFutures(PythonQuandl):
    def __init__(self):
        self.ValueColumnName = "settle"

# Quandl short interest data.
class QuandlFINRA_ShortVolume(PythonQuandl):
    def __init__(self):
        self.ValueColumnName = 'SHORTVOLUME'    # also 'TOTALVOLUME' is accesible

# Quantpedia data.
# NOTE: IMPORTANT: Data order must be ascending (datewise)
class QuantpediaFutures(PythonData):
    def GetSource(self, config, date, isLiveMode):
        return SubscriptionDataSource("data.quantpedia.com/backtesting_data/futures/{0}.csv".format(config.Symbol.Value), SubscriptionTransportMedium.RemoteFile, FileFormat.Csv)

    def Reader(self, config, line, date, isLiveMode):
        data = QuantpediaFutures()
        data.Symbol = config.Symbol
        
        if not line[0].isdigit(): return None
        split = line.split(';')
        
        data.Time = datetime.strptime(split[0], "%d.%m.%Y") + timedelta(days=1)
        data['back_adjusted'] = float(split[1])
        data['spliced'] = float(split[2])
        data.Value = float(split[1])

        return data

# Commitments of Traders data.
# NOTE: IMPORTANT: Data order must be ascending (datewise).
# Data source: https://commitmentsoftraders.org/cot-data/
# Data description: https://commitmentsoftraders.org/wp-content/uploads/Static/CoTData/file_key.html
class CommitmentsOfTraders(PythonData):
    def GetSource(self, config, date, isLiveMode):
        return SubscriptionDataSource("data.quantpedia.com/backtesting_data/futures/cot/{0}.PRN".format(config.Symbol.Value), SubscriptionTransportMedium.RemoteFile, FileFormat.Csv)

    # File example.
    # DATE   OPEN     HIGH        LOW       CLOSE     VOLUME   OI
    # ----   ----     ----        ---       -----     ------   --
    # DATE   LARGE    SPECULATOR  COMMERCIAL HEDGER   SMALL TRADER
    #        LONG     SHORT       LONG      SHORT     LONG     SHORT
    def Reader(self, config, line, date, isLiveMode):
        data = CommitmentsOfTraders()
        data.Symbol = config.Symbol
        
        if not line[0].isdigit(): return None
        split = line.split(',')
        
        # Prevent lookahead bias.
        data.Time = datetime.strptime(split[0], "%Y%m%d") + timedelta(days=1)
        
        data['LARGE_SPECULATOR_LONG'] = int(split[1])
        data['LARGE_SPECULATOR_SHORT'] = int(split[2])
        data['COMMERCIAL_HEDGER_LONG'] = int(split[3])
        data['COMMERCIAL_HEDGER_SHORT'] = int(split[4])
        data['SMALL_TRADER_LONG'] = int(split[5])
        data['SMALL_TRADER_SHORT'] = int(split[6])

        data.Value = int(split[1])

        return data
        
# NOTE: Manager for new trades. It's represented by certain count of equally weighted brackets for long and short positions.
# If there's a place for new trade, it will be managed for time of holding period.
class TradeManager():
    def __init__(self, algorithm, long_size, short_size, holding_period):
        self.algorithm = algorithm  # algorithm to execute orders in.
        
        self.long_size = long_size
        self.short_size = short_size
        
        self.long_len = 0
        self.short_len = 0
    
        # Arrays of ManagedSymbols
        self.symbols = []
        
        self.holding_period = holding_period    # Days of holding.
    
    # Add stock symbol object
    def Add(self, symbol, long_flag):
        # Open new long trade.
        managed_symbol = ManagedSymbol(symbol, self.holding_period, long_flag)
        
        if long_flag:
            # If there's a place for it.
            if self.long_len < self.long_size:
                self.symbols.append(managed_symbol)
                self.algorithm.SetHoldings(symbol, 1 / self.long_size)
                self.long_len += 1
            else:
                self.algorithm.Log("There's not place for additional trade.")

        # Open new short trade.
        else:
            # If there's a place for it.
            if self.short_len < self.short_size:
                self.symbols.append(managed_symbol)
                self.algorithm.SetHoldings(symbol, - 1 / self.short_size)
                self.short_len += 1
            else:
                self.algorithm.Log("There's not place for additional trade.")
   
    # Decrement holding period and liquidate symbols.
    def TryLiquidate(self):
        symbols_to_delete = []
        for managed_symbol in self.symbols:
            managed_symbol.days_to_liquidate -= 1
            
            # Liquidate.
            if managed_symbol.days_to_liquidate == 0:
                symbols_to_delete.append(managed_symbol)
                self.algorithm.Liquidate(managed_symbol.symbol)
                
                if managed_symbol.long_flag: self.long_len -= 1
                else: self.short_len -= 1

        # Remove symbols from management.
        for managed_symbol in symbols_to_delete:
            self.symbols.remove(managed_symbol)
    
    def LiquidateTicker(self, ticker):
        symbol_to_delete = None
        for managed_symbol in self.symbols:
            if managed_symbol.symbol.Value == ticker:
                self.algorithm.Liquidate(managed_symbol.symbol)
                symbol_to_delete = managed_symbol
                if managed_symbol.long_flag: self.long_len -= 1
                else: self.short_len -= 1
                
                break
        
        if symbol_to_delete: self.symbols.remove(symbol_to_delete)
        else: self.algorithm.Debug("Ticker is not held in portfolio!")
    
class ManagedSymbol():
    def __init__(self, symbol, days_to_liquidate, long_flag):
        self.symbol = symbol
        self.days_to_liquidate = days_to_liquidate
        self.long_flag = long_flag
        
class PortfolioOptimization(object):
    def __init__(self, df_return, risk_free_rate, num_assets):
        self.daily_return = df_return
        self.risk_free_rate = risk_free_rate
        self.n = num_assets # numbers of risk assets in portfolio
        self.target_vol = 0.05

    def annual_port_return(self, weights):
        # calculate the annual return of portfolio
        return np.sum(self.daily_return.mean() * weights) * 252

    def annual_port_vol(self, weights):
        # calculate the annual volatility of portfolio
        return np.sqrt(np.dot(weights.T, np.dot(self.daily_return.cov() * 252, weights)))

    def min_func(self, weights):
        # method 1: maximize sharp ratio
        return - self.annual_port_return(weights) / self.annual_port_vol(weights)
        
        # method 2: maximize the return with target volatility
        #return - self.annual_port_return(weights) / self.target_vol

    def opt_portfolio(self):
        # maximize the sharpe ratio to find the optimal weights
        cons = ({'type': 'eq', 'fun': lambda x: np.sum(x) - 1})
        bnds = tuple((0, 1) for x in range(2)) + tuple((0, 0.25) for x in range(self.n - 2))
        opt = minimize(self.min_func,                               # object function
                       np.array(self.n * [1. / self.n]),            # initial value
                       method='SLSQP',                              # optimization method
                       bounds=bnds,                                 # bounds for variables 
                       constraints=cons)                            # constraint conditions
                      
        opt_weights = opt['x']
 
        return opt_weights

# https://quantpedia.com/strategies/pairs-trading-with-stocks/
#
# The investment universe consists of stocks from NYSE, AMEX, and NASDAQ, while illiquid stocks are removed from the investment universe. Cumulative
# total return index is then created for each stock (dividends included), and the starting price during the formation period is set to $1 (price normalization). 
# Pairs are formed over twelve months (formation period) and are then traded in the next six-month period (trading period). The matching partner for each stock
# is found by looking for the security that minimizes the sum of squared deviations between two normalized price series. Top 20 pairs with the smallest historical 
# distance measure are then traded, and a long-short position is opened when pair prices have diverged by two standard deviations, and the position is closed
# when prices revert.

import numpy as np
from collections import deque
import itertools as it
import fk_tools

class PairsTradingwithStocks(QCAlgorithm):
    
    def Initialize(self):
        self.SetStartDate(2000, 1, 1)
        self.SetCash(100000)
       
        self.symbol = self.AddEquity('SPY', Resolution.Daily).Symbol

        # Daily price data.
        self.history_price = {}
        self.period = 12 * 21
        
        # Equally weighted brackets.
        self.max_traded_pairs = 5
        self.traded_pairs = []
        
        self.coarse_count = 100
        self.month = 6
        self.selection_flag = False
        self.UniverseSettings.Resolution = Resolution.Daily
        self.AddUniverse(self.CoarseSelectionFunction)

        self.Schedule.On(self.DateRules.MonthStart(self.symbol), self.TimeRules.AfterMarketOpen(self.symbol), self.Selection)

    def OnSecuritiesChanged(self, changes):
        for security in changes.AddedSecurities:
            symbol = security.Symbol
            
            security.SetFeeModel(fk_tools.CustomFeeModel(self))
            security.SetLeverage(5)
            
            if symbol not in self.history_price:
                history = self.History(symbol, self.period, Resolution.Daily)
                if len(history) == self.period and 'close' in history:
                    closes = [x for x in history['close']]
                    self.history_price[symbol] = deque(closes, maxlen = self.period)
            
        symbols = [x for x in self.history_price.keys() if x != self.symbol]
        self.symbol_pairs = list(it.combinations(symbols, 2))
        
        distances = {}
        for pair in self.symbol_pairs:
            if len(self.history_price[pair[0]]) == self.period and len(self.history_price[pair[1]]) == self.period:
                distances[pair] = self.Distance(self.history_price[pair[0]], self.history_price[pair[1]])
            
        if len(distances) != 0:
            self.sorted_pairs = sorted(distances.items(), key = lambda x: x[1])[:20]
            self.sorted_pairs = [x[0] for x in self.sorted_pairs]
            self.Liquidate() 

    def CoarseSelectionFunction(self, coarse):
        if self.selection_flag: 
            return Universe.Unchanged
        
        selected = sorted([x for x in coarse if x.HasFundamentalData and x.Price > 5 and x.Market == 'usa'],
            key=lambda x: x.DollarVolume, reverse=True)
        
        return [x.Symbol for x in selected[:self.coarse_count]]
    
    def OnData(self, data):
        # Update the price series everyday.
        for symbol in self.history_price:
            self.history_price[symbol].append(float(self.Securities[symbol].Price)) 
        
        if self.sorted_pairs is None: return
        
        pairs_to_remove = []
        for pair in self.sorted_pairs:
            # Calculate the spread of two price series.
            spread = np.array(self.history_price[pair[0]]) - np.array(self.history_price[pair[1]])
            mean = np.mean(spread)
            std = np.std(spread)
            # ratio = self.Portfolio[pair[0]].Price / self.Portfolio[pair[1]].Price
            
            # Long-short position is opened when pair prices have diverged by two standard deviations.
            weight = 1 / self.max_traded_pairs
            if spread[-1] > mean + 2*std:
                if not self.Portfolio[pair[0]].Invested and not self.Portfolio[pair[1]].Invested:
                    if len(self.traded_pairs) < self.max_traded_pairs:
                        self.SetHoldings(pair[0], -weight)
                        self.SetHoldings(pair[1], weight)
                        
                        if pair not in self.traded_pairs:
                            self.traded_pairs.append(pair)
                            
                elif self.Portfolio[pair[0]].Invested and self.Portfolio[pair[1]].Invested:
                    self.SetHoldings(pair[0], -weight)
                    self.SetHoldings(pair[1], weight)
            
            elif spread[-1] < mean - 2*std:
                if not self.Portfolio[pair[0]].Invested and not self.Portfolio[pair[1]].Invested:
                    if len(self.traded_pairs) < self.max_traded_pairs:
                        self.SetHoldings(pair[0], weight)
                        self.SetHoldings(pair[1], -weight)
    
                        if pair not in self.traded_pairs:
                            self.traded_pairs.append(pair)
                            
                elif self.Portfolio[pair[0]].Invested and self.Portfolio[pair[1]].Invested:
                    self.SetHoldings(pair[0], weight)
                    self.SetHoldings(pair[1], -weight)

            # The position is closed when prices revert back.
            else:
                if self.Portfolio[pair[0]].Invested and self.Portfolio[pair[1]].Invested:
                    self.Liquidate(pair[0]) 
                    self.Liquidate(pair[1])
                    
                    if pair in self.traded_pairs:
                        pairs_to_remove.append(pair)
            
            for pair in pairs_to_remove:
                self.traded_pairs.remove(pair)
            pairs_to_remove.clear()
            
            # self.Log(len(self.traded_pairs))
                
    def Distance(self, price_a, price_b):
        # Calculate the sum of squared deviations between two normalized price series.
        norm_a = np.array(price_a) / price_a[0]
        norm_b = np.array(price_b) / price_b[0]
        return sum((norm_a - norm_b)**2)
        
    def Selection(self):
        if self.month == 6:
            self.selection_flag = True
            
        self.month += 1
        if self.month > 12:
            self.month = 1