# https://quantpedia.com/strategies/earnings-announcement-premium/
#
# The investment universe consists of all stocks from the CRSP database. At the beginning of every calendar month, stocks are ranked in ascending 
# order on the basis of the volume concentration ratio, which is defined as the volume of the previous 16 announcement months divided by the total
# volume in the previous 48 months. The ranked stocks are assigned to one of 5 quintile portfolios. Within each quintile, stocks are assigned to
# one of two portfolios (expected announcers and expected non-announcers) using the predicted announcement based on the previous year. All stocks
# are value-weighted within a given portfolio, and portfolios are rebalanced every calendar month to maintain value weights. The investor invests
# in a long-short portfolio, which is a zero-cost portfolio that holds the portfolio of high volume expected announcers and sells short the 
# portfolio of high volume expected non-announcers.

import fk_tools
from collections import deque

class EarningsAnnouncementPremium(QCAlgorithm):

    def Initialize(self):
        self.SetStartDate(2003, 1, 1)
        self.SetCash(100000) 

        self.symbol = 'SPY'
        self.AddEquity(self.symbol, Resolution.Daily)
        
        self.period = 21
        self.month_period = 48

        # Volume daily data.
        self.data = {}

        # Volume monthly data.
        self.monthly_volume = {}

        self.course_count = 1000
        self.weight = {}
        
        self.selection_flag = False
        self.rebalance_flag = False
        self.UniverseSettings.Resolution = Resolution.Daily
        self.AddUniverse(self.CoarseSelectionFunction, self.FineSelectionFunction)
        
        self.Schedule.On(self.DateRules.MonthStart(self.symbol), self.TimeRules.AfterMarketOpen(self.symbol), self.Selection)

    def OnSecuritiesChanged(self, changes):
        for security in changes.AddedSecurities:
            security.SetFeeModel(fk_tools.CustomFeeModel(self))
        
    def CoarseSelectionFunction(self, coarse):
        if not self.selection_flag:
            return Universe.Unchanged
        
        self.selection_flag = False
        
        selected = sorted([x for x in coarse if x.HasFundamentalData and x.Market == 'usa' and x.Price > 5],
            key=lambda x: x.DollarVolume, reverse=True)
        
        return [x.Symbol for x in selected[:self.course_count]]

    def FineSelectionFunction(self, fine):
        fine = [x for x in fine if x.EarningReports.BasicAverageShares.ThreeMonths > 0 and x.EarningReports.BasicEPS.TwelveMonths > 0 and x.ValuationRatios.PERatio > 0]
        
        # Ratio/market cap pair.
        volume_concentration_ratio_market_cap = {}
        for stock in fine:
            symbol = stock.Symbol
            
            # Store daily price and volume data.
            if symbol not in self.data:
                self.data[symbol] = deque(maxlen = self.period)

            # Month worth of daily data is ready.    
            if len(self.data[symbol]) == self.data[symbol].maxlen:
                # Store last month volume.
                if symbol not in self.monthly_volume:
                    self.monthly_volume[symbol] = deque(maxlen = self.month_period)
                
                monthly_vol = sum([x for x in self.data[symbol]])
                last_month_date = self.Time - timedelta(days=self.Time.day)
                last_file_date = stock.FinancialStatements.FileDate
                was_announcement_month = (last_file_date.year == last_month_date.year and last_file_date.month == last_month_date.month)    # Last month was announcement date.
                self.monthly_volume[symbol].append(VolumeData(last_month_date, monthly_vol, was_announcement_month))
                
                # 48 months of volume data is ready.
                if len(self.monthly_volume[symbol]) == self.monthly_volume[symbol].maxlen:
                    # Volume concentration ratio calc.
                    announcement_months_volume = sum([x.Volume for x in self.monthly_volume[symbol] if x.Was_announcement_month][-16:])
                    total_volume = sum([x.Volume for x in self.monthly_volume[symbol]])
                    
                    if announcement_months_volume != 0 and total_volume != 0:
                        # Market cap calc.
                        market_cap =  float(stock.EarningReports.BasicAverageShares.ThreeMonths * (stock.EarningReports.BasicEPS.TwelveMonths*stock.ValuationRatios.PERatio))
                        
                        # Store ratio, market cap pair.
                        volume_concentration_ratio = announcement_months_volume / total_volume
                        volume_concentration_ratio_market_cap[symbol] = [volume_concentration_ratio, market_cap]

        fine_symbols = [x.Symbol for x in fine]
        
        # Remove old data, so we only store consecutive data.
        symbols_to_remove = []
        for symbol in self.monthly_volume:
            if symbol not in fine_symbols:
                symbols_to_remove.append(symbol)
        for symbol in symbols_to_remove:
            del self.monthly_volume[symbol]
            
            # NOTE: Do we want ot remove symbol from daily data also? This way we save memory dramatically. - storing only self.course_count of symbols and its history compared to expanding dict of symbols with its history.
            # Therefore we only store actually selected symbols and delete those, which are not in self.course_count-long selection.
            # Otherwise, we would be storing whole lot of data which will not be used anymore. But those may appear in self.course_count-long selection later.
            # It appears to be minor difference in final equity and only 70 trades more has been opened with every peace of daily data stored.
            # 
            # Storing every data throughout the backtest is more precise tho and it depends on use case and backtested strategy I guess.
            # del self.data[symbol]
        
        if len(volume_concentration_ratio_market_cap) == 0: return fine_symbols
        
        # Volume sorting.
        sorted_by_volume = sorted(volume_concentration_ratio_market_cap.items(), key = lambda x: x[1][0], reverse = True)
        quintile = int(len(sorted_by_volume) / 5)
        high_volume = [x for x in sorted_by_volume[:quintile]]
        
        # Filering announcers and non-announcers.
        month_to_lookup = self.Time.month
        year_to_lookup = self.Time.year - 1
        
        long = []
        short = []
        for data in high_volume:
            symbol = data[0]
            announcement_dates = [[x.Date.year, x.Date.month] for x in self.monthly_volume[symbol] if x.Was_announcement_month]
            if [year_to_lookup, month_to_lookup] in announcement_dates:
                long.append(data)
            else:
                short.append(data)
        
        # Market cap weighting.
        total_market_cap = sum([x[1][1] for x in long + short])        
        long_symbols = [x[0] for x in long]
        for symbol, volume_concentration_ratio_market_cap in long + short:
            if symbol in long_symbols:
                self.weight[symbol] = volume_concentration_ratio_market_cap[1] / total_market_cap
            else:
                self.weight[symbol] = - volume_concentration_ratio_market_cap[1] / total_market_cap
                
        self.rebalance_flag = True
        
        return fine_symbols
    
    def OnData(self, data):
        # Store daily volume data.
        
        # for symbol in self.data:
        for symbol in self.Securities.Keys:
            if symbol.Value == 'SPY': continue

            if self.Securities.ContainsKey(symbol):
                volume = self.Securities[symbol].Volume
                if volume != 0:
                    self.data[symbol].append(volume)
                else:
                    # Append latest price as a next one in case there's 0 as price.
                    if len(self.data[symbol]) > 0:
                        last_data = self.data[symbol][-1]
                        self.data[symbol].append(last_data)

        # Rabalance.
        if not self.rebalance_flag:
            return
        self.rebalance_flag = False
        
        # Trade execution
        count = len(self.weight)
        if count == 0: return
        
        stocks_invested = [x.Key for x in self.Portfolio if x.Value.Invested]
        symbols_to_rebalance = [x[0] for x in self.weight.items()]
        for symbol in stocks_invested:
            if symbol not in symbols_to_rebalance:
                self.Liquidate(symbol)

        # self.Liquidate()

        for symbol, w in self.weight.items():
            if self.Securities[symbol].Price != 0:  # Prevent error message.
                self.SetHoldings(symbol, 0.9 * w)
        
        self.weight.clear()
        
    def Selection(self):
        self.selection_flag = True

# Monthly volume data.
class VolumeData():
    def __init__(self, date, monthly_volume, was_announcement_month):
        self.Date = date
        self.Volume = monthly_volume
        self.Was_announcement_month = was_announcement_month

import numpy as np
from scipy.optimize import minimize

sp100_stocks = ['AAPL','MSFT','AMZN','FB','BRK.B','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)  

# 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['settle'] = float(split[1])
        data.Value = float(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.weight = 1 / (self.long_size + self.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, self.weight)
                self.long_len += 1
        # Open new short trade.
        else:
            # If there's a place for it.
            if self.long_len < self.short_size:
                self.symbols.append(managed_symbol)
                self.algorithm.SetHoldings(symbol, - self.weight)
                self.short_len += 1
    
    # 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)

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