def getTrainAndTestData(startDate=datetime.date(2018, 1, 1),
endDate=datetime.date.today(),
xSymbols=['SPY'],
ySymbol=['AAPL'],
trainingSize=0.7):
"""
For given period and symbols, generate the training and test data set.
:param startDate: Start date for the entire data set
:param endDate: End date for the entire data set
:param xSymbols: Independent variables symbol tickers
:param ySymbol: Depdendent variable symbol ticker
:param trainingSize: The proportion of data set for training
:return: (xTrain, yTrain, xTest, yTest), in 2-d array format
"""
dataHub = DataHub()
historicalDataBySymbol = dataHub.downloadDataFromYahoo(
startDate, endDate, xSymbols + ySymbol)
df = pd.concat([
historicalDataBySymbol[symbol].loc[:, 'Close']
for symbol in xSymbols + ySymbol
],
axis=1,
join='inner')
splitIdx = int(df.shape[0] * trainingSize)
xTrain = df.iloc[:splitIdx, :-1].values
yTrain = df.iloc[:splitIdx, -1].values
xTest = df.iloc[splitIdx:, :-1].values
yTest = df.iloc[splitIdx:, -1].values
return xTrain, yTrain, xTest, yTest
def main():
"""
Main entry point.
"""
dataHub = DataHub()
startDate = datetime.date(2018,1,1)
endDate = datetime.date.today()
symbols = ['AAPL', 'SPY']
data = dataHub.downloadDataFromYahoo(startDate, endDate, symbols)
ts1 = data.values()[0].loc[:, 'Close'].rename(data.keys()[0])
ts2 = data.values()[1].loc[:, 'Close'].rename(data.keys()[1])
corr = calculateCorrelation(ts1, ts2)
logging.info('Correlation = %.2f', corr)
class VolatilityPricer():
"""
Realized vol:
Same as Black-Scholes, we assume the underlying follows a Geometric Brownian Motion.
Then its log return follows a Normal distribution, with mean as 0.
We take as input the historical daily underlying prices.
Annualization factor is 252.
Degree of Freedom is 0 as we are calculating the exact realized vol for the given historical period.
Implied vol:
Use Black-Scholes to back out the implied volatility from the given market option price.
"""
def __init__(self):
self.historicalDataBySymbol = dict()
self.dataHub = DataHub()
self.realizedVolBySymbol = dict()
def _loadHistoricalUnderlyingData(self, startDate, endDate, symbols):
self.historicalDataBySymbol = self.dataHub.downloadDataFromYahoo(
startDate, endDate, symbols)
def _calculateRealizedVol(self, ts):
""" Calculate the realized vol from given time series """
pctChange = ts.pct_change().dropna()
logReturns = np.log(1 + pctChange)
vol = np.sqrt(np.sum(np.square(logReturns)) / logReturns.size)
annualizedVol = vol * np.sqrt(252)
return annualizedVol
def getRealizedVol(self,
startDate=datetime.date.today() -
datetime.timedelta(days=30),
endDate=datetime.date.today(),
symbols=['SPY']):
""" Calculate the realized volatility from historical market data """
self._loadHistoricalUnderlyingData(startDate, endDate, symbols)
for symbol, df in self.historicalDataBySymbol.iteritems():
# Use daily Close to calculate realized vols
realizedVol = self._calculateRealizedVol(df.loc[:, 'Close'])
self.realizedVolBySymbol[symbol] = realizedVol
return self.realizedVolBySymbol
def getImpliedVol(self,
optionPrice=17.5,
callPut='Call',
spot=586.08,
strike=585.0,
tenor=0.109589,
rate=0.0002):
""" Calculate the implied volatility from option market price """
return blackScholesSolveImpliedVol(optionPrice, callPut, spot, strike,
tenor, rate)
class VolatilityPricer():
def __init__(self):
self.historicalDataBySymbol = dict()
self.dataHub = DataHub()
self.realizedVolBySymbol = dict()
def _loadHistoricalUnderlyingData(self, startDate, endDate, symbols):
self.historicalDataBySymbol = self.dataHub.downloadDataFromYahoo(
startDate, endDate, symbols)
def _calculateRealizedVol(self, ts):
""" Calculate the realized vol from given time series """
pctChange = ts.pct_change().dropna()
logReturns = np.log(1 + pctChange)
vol = np.sqrt(np.sum(np.square(logReturns)) / logReturns.size)
annualizedVol = vol * np.sqrt(252)
return annualizedVol
def getRealizedVol(self,
startDate=datetime.date.today() -
datetime.timedelta(days=30),
endDate=datetime.date.today(),
symbols=['SPY']):
""" Calculate the realized volatility from historical market data """
self._loadHistoricalUnderlyingData(startDate, endDate, symbols)
for symbol, df in self.historicalDataBySymbol.iteritems():
# Use daily Close to calculate realized vols
realizedVol = self._calculateRealizedVol(df.loc[:, 'Close'])
self.realizedVolBySymbol[symbol] = realizedVol
return self.realizedVolBySymbol
def getImpliedVol(self,
optionPrice=17.5,
callPut='Call',
spot=586.08,
strike=585.0,
tenor=0.109589,
rate=0.0002):
""" Calculate the implied volatility from option market price """
return blackScholesSolveImpliedVol(optionPrice, callPut, spot, strike,
tenor, rate)
def __init__(self):
self.historicalDataBySymbol = dict()
self.dataHub = DataHub()
self.realizedVolBySymbol = dict()