def featBeta( dData, lLookback=14, sMarket='$SPX', b_human=False ):
'''
@summary: Calculate beta relative to a given stock/index.
@param dData: Dictionary of data to use
@param sStock: Stock to calculate beta relative to
@param b_human: if true return dataframe to plot
@return: DataFrame array containing feature values
'''
dfPrice = dData['close']
#''' Calculate returns '''
dfRets = dfPrice.copy()
tsu.returnize1(dfRets.values)
tsMarket = dfRets[sMarket]
dfRet = pand.rolling_cov(tsMarket, dfRets, lLookback)
dfRet /= dfRet[sMarket]
if b_human:
for sym in dData['close']:
x=1000/dData['close'][sym][0]
dData['close'][sym]=dData['close'][sym]*x
return dData['close']
return dfRet
def featBeta(dData, lLookback=14, sMarket='$SPX', b_human=False):
'''
@summary: Calculate beta relative to a given stock/index.
@param dData: Dictionary of data to use
@param sStock: Stock to calculate beta relative to
@param b_human: if true return dataframe to plot
@return: DataFrame array containing feature values
'''
dfPrice = dData['close']
#''' Calculate returns '''
dfRets = dfPrice.copy()
tsu.returnize1(dfRets.values)
tsMarket = dfRets[sMarket]
dfRet = pand.rolling_cov(tsMarket, dfRets, lLookback)
dfRet /= dfRet[sMarket]
if b_human:
for sym in dData['close']:
x = 1000 / dData['close'][sym][0]
dData['close'][sym] = dData['close'][sym] * x
return dData['close']
return dfRet
def featBeta(dData, lLookback=14, sMarket='$SPX', b_human=False):
'''
@summary: Calculate beta relative to a given stock/index.
@param dData: Dictionary of data to use
@param sStock: Stock to calculate beta relative to
@param b_human: if true return dataframe to plot
@return: DataFrame array containing feature values
'''
dfPrice = dData['close']
#''' Calculate returns '''
naRets = dfPrice.values.copy()
tsu.returnize1(naRets)
dfHistReturns = pand.DataFrame(
index=dfPrice.index, columns=dfPrice.columns, data=naRets)
#''' Feature DataFrame will be 1:1, we can use the price as a template '''
dfRet = pand.DataFrame(
index=dfPrice.index,
columns=dfPrice.columns,
data=np.zeros(dfPrice.shape))
#''' Loop through stocks '''
for sStock in dfHistReturns.columns:
tsHistReturns = dfHistReturns[sStock]
tsMarket = dfHistReturns[sMarket]
tsRet = dfRet[sStock]
#''' Loop over time '''
for i in range(len(tsRet.index)):
#''' NaN if not enough data to do lookback '''
if i < lLookback - 1:
tsRet[i] = float('nan')
continue
naStock = tsHistReturns[i - (lLookback - 1):i + 1]
naMarket = tsMarket[i - (lLookback - 1):i + 1]
#''' Beta is the slope the line, with market returns on X, stock returns on Y '''
try:
fBeta, unused = np.polyfit(naMarket, naStock, 1)
tsRet[i] = fBeta
except:
#'Numpy Error featBeta'
tsRet[i] = float('NaN')
if b_human:
for sym in dData['close']:
x = 1000 / dData['close'][sym][0]
dData['close'][sym] = dData['close'][sym] * x
return dData['close']
return dfRet
def featBeta(dData, lLookback=14, sMarket='$SPX', b_human=False):
'''
@summary: Calculate beta relative to a given stock/index.
@param dData: Dictionary of data to use
@param sStock: Stock to calculate beta relative to
@param b_human: if true return dataframe to plot
@return: DataFrame array containing feature values
'''
dfPrice = dData['close']
#''' Calculate returns '''
naRets = dfPrice.values.copy()
tsu.returnize1(naRets)
dfHistReturns = pand.DataFrame(index=dfPrice.index,
columns=dfPrice.columns,
data=naRets)
#''' Feature DataFrame will be 1:1, we can use the price as a template '''
dfRet = pand.DataFrame(index=dfPrice.index,
columns=dfPrice.columns,
data=np.zeros(dfPrice.shape))
#''' Loop through stocks '''
for sStock in dfHistReturns.columns:
tsHistReturns = dfHistReturns[sStock]
tsMarket = dfHistReturns[sMarket]
tsRet = dfRet[sStock]
#''' Loop over time '''
for i in range(len(tsRet.index)):
#''' NaN if not enough data to do lookback '''
if i < lLookback - 1:
tsRet[i] = float('nan')
continue
naStock = tsHistReturns[i - (lLookback - 1):i + 1]
naMarket = tsMarket[i - (lLookback - 1):i + 1]
#''' Beta is the slope the line, with market returns on X, stock returns on Y '''
try:
fBeta, unused = np.polyfit(naMarket, naStock, 1)
tsRet[i] = fBeta
except:
#'Numpy Error featBeta'
tsRet[i] = float('NaN')
if b_human:
for sym in dData['close']:
x = 1000 / dData['close'][sym][0]
dData['close'][sym] = dData['close'][sym] * x
return dData['close']
return dfRet
def featCorrelation(dData, lLookback=20, sRel='$SPX', b_human=False):
'''
@summary: Calculate correlation of two stocks.
@param dData: Dictionary of data to use
@param lLookback: Number of days to calculate moving average over
@param b_human: if true return dataframe to plot
@return: DataFrame array containing feature values
'''
dfPrice = dData['close']
if sRel not in dfPrice.columns:
raise KeyError("%s not found in data provided to featCorrelation" %
sRel)
#''' Calculate returns '''
naRets = dfPrice.values.copy()
tsu.returnize1(naRets)
dfHistReturns = pand.DataFrame(index=dfPrice.index,
columns=dfPrice.columns,
data=naRets)
#''' Feature DataFrame will be 1:1, we can use the price as a template '''
dfRet = pand.DataFrame(index=dfPrice.index,
columns=dfPrice.columns,
data=np.zeros(dfPrice.shape))
#''' Loop through stocks '''
for sStock in dfHistReturns.columns:
tsHistReturns = dfHistReturns[sStock]
tsRelativeReturns = dfHistReturns[sRel]
tsRet = dfRet[sStock]
#''' Loop over time '''
for i in range(len(tsHistReturns.index)):
#''' NaN if not enough data to do lookback '''
if i < lLookback - 1:
tsRet[i] = float('nan')
continue
naCorr = np.corrcoef(tsHistReturns[i - (lLookback - 1):i + 1],
tsRelativeReturns[i - (lLookback - 1):i + 1])
tsRet[i] = naCorr[0, 1]
if b_human:
for sym in dData['close']:
x = 1000 / dData['close'][sym][0]
dData['close'][sym] = dData['close'][sym] * x
return dData['close']
return dfRet
def featCorrelation(dData, lLookback=20, sRel='$SPX', b_human=False):
'''
@summary: Calculate correlation of two stocks.
@param dData: Dictionary of data to use
@param lLookback: Number of days to calculate moving average over
@param b_human: if true return dataframe to plot
@return: DataFrame array containing feature values
'''
dfPrice = dData['close']
if sRel not in dfPrice.columns:
raise KeyError(
"%s not found in data provided to featCorrelation" % sRel)
#''' Calculate returns '''
naRets = dfPrice.values.copy()
tsu.returnize1(naRets)
dfHistReturns = pand.DataFrame(
index=dfPrice.index, columns=dfPrice.columns, data=naRets)
#''' Feature DataFrame will be 1:1, we can use the price as a template '''
dfRet = pand.DataFrame(
index=dfPrice.index,
columns=dfPrice.columns,
data=np.zeros(dfPrice.shape))
#''' Loop through stocks '''
for sStock in dfHistReturns.columns:
tsHistReturns = dfHistReturns[sStock]
tsRelativeReturns = dfHistReturns[sRel]
tsRet = dfRet[sStock]
#''' Loop over time '''
for i in range(len(tsHistReturns.index)):
#''' NaN if not enough data to do lookback '''
if i < lLookback - 1:
tsRet[i] = float('nan')
continue
naCorr = np.corrcoef(tsHistReturns[i - (lLookback - 1):i + 1],
tsRelativeReturns[i - (lLookback - 1):i + 1])
tsRet[i] = naCorr[0, 1]
if b_human:
for sym in dData['close']:
x = 1000 / dData['close'][sym][0]
dData['close'][sym] = dData['close'][sym] * x
return dData['close']
return dfRet
def featSTD( dData, lLookback=20, bRel=True, b_human=False ):
'''
@summary: Calculate standard deviation
@param dData: Dictionary of data to use
@param lLookback: Number of days to look in the past
@param b_human: if true return dataframe to plot
@return: DataFrame array containing values
'''
dfPrice = dData['close'].copy()
tsu.returnize1(dfPrice.values)
dfRet = pand.rolling_std(dfPrice, lLookback)
if bRel:
dfRet = dfRet / dfPrice
if b_human:
for sym in dData['close']:
x=1000/dData['close'][sym][0]
dData['close'][sym]=dData['close'][sym]*x
return dData['close']
return dfRet
def featSTD(dData, lLookback=20, bRel=True, b_human=False):
'''
@summary: Calculate standard deviation
@param dData: Dictionary of data to use
@param lLookback: Number of days to look in the past
@param b_human: if true return dataframe to plot
@return: DataFrame array containing values
'''
dfPrice = dData['close'].copy()
tsu.returnize1(dfPrice.values)
dfRet = pand.rolling_std(dfPrice, lLookback)
if bRel:
dfRet = dfRet / dfPrice
if b_human:
for sym in dData['close']:
x = 1000 / dData['close'][sym][0]
dData['close'][sym] = dData['close'][sym] * x
return dData['close']
return dfRet
dtStart = dtEnd - dt.timedelta(days=365) dtTest = dtEnd + dt.timedelta(days=365) timeofday=dt.timedelta(hours=16) ldtTimestamps = du.getNYSEdays( dtStart, dtEnd, timeofday ) ldtTimestampTest = du.getNYSEdays( dtEnd, dtTest, timeofday ) dmClose = norgateObj.get_data(ldtTimestamps, lsSymbols, "close") dmTest = norgateObj.get_data(ldtTimestampTest, lsSymbols, "close") naData = dmClose.values.copy() naDataTest = dmTest.values.copy() tsu.fillforward(naData) tsu.fillbackward(naData) tsu.returnize1(naData) tsu.fillforward(naDataTest) tsu.fillbackward(naDataTest) tsu.returnize1(naDataTest) lPeriod = 21 ''' Get efficient frontiers ''' (lfReturn, lfStd, lnaPortfolios, naAvgRets, naStd) = getFrontier( naData, lPeriod ) (lfReturnTest, lfStdTest, unused, unused, unused) = getFrontier( naDataTest, lPeriod ) plt.clf() fig = plt.figure() ''' Plot efficient frontiers '''
fundReturns = fundReturns / fundReturns[0]
SPYReturns = SPYvalues /SPYvalues[0,:]
plt.clf()
plt.plot(timestamps, fundReturns)
plt.plot(timestamps, SPYReturns)
plt.legend(["Fund", "SPY"])
plt.ylabel('Normalized Return')
plt.xlabel('Date')
savefig('perf.pdf',format='pdf')
TotalRET = (dailyFund[len(dailyFund)-1] / (dailyFund[0]))
print ("Total Return: " + str(TotalRET))
tsu.returnize1(fundReturns)
print fundReturns
"""
tsu.getSharpeRatio(fundDaily, 0.0)
print ("Sharpe Ratio:")
"""
"""
CODE for QUIZ question
i=0
for time in timestamps:
if ((time.year == 2011) and (time.month == 2) and (time.day == 18)):
print dailyFund[i]
i+=1
dtStart = dtEnd - dt.timedelta(days=365) dtTest = dtEnd + dt.timedelta(days=365) timeofday = dt.timedelta(hours=16) ldtTimestamps = du.getNYSEdays(dtStart, dtEnd, timeofday) ldtTimestampTest = du.getNYSEdays(dtEnd, dtTest, timeofday) dmClose = norgateObj.get_data(ldtTimestamps, lsSymbols, "close") dmTest = norgateObj.get_data(ldtTimestampTest, lsSymbols, "close") naData = dmClose.values.copy() naDataTest = dmTest.values.copy() tsu.fillforward(naData) tsu.fillbackward(naData) tsu.returnize1(naData) tsu.fillforward(naDataTest) tsu.fillbackward(naDataTest) tsu.returnize1(naDataTest) lPeriod = 21 ''' Get efficient frontiers ''' (lfReturn, lfStd, lnaPortfolios, naAvgRets, naStd) = getFrontier(naData, lPeriod) (lfReturnTest, lfStdTest, unused, unused, unused) = getFrontier(naDataTest, lPeriod) plt.clf() fig = plt.figure() ''' Plot efficient frontiers '''
def stratMark(dtStart, dtEnd, dFuncArgs):
"""
@summary Markovitz strategy, generates a curve and then chooses a point on it.
@param dtStart: Start date for portfolio
@param dtEnd: End date for portfolio
@param dFuncArgs: Dict of function args passed to the function
@return DataFrame corresponding to the portfolio allocations
"""
if not dFuncArgs.has_key('dmPrice'):
print 'Error:', stratMark.__name__, 'requires dmPrice information'
return
if not dFuncArgs.has_key('sPeriod'):
print 'Error:', stratMark.__name__, 'requires rebalancing period'
return
if not dFuncArgs.has_key('lLookback'):
print 'Error:', stratMark.__name__, 'requires lookback'
return
if not dFuncArgs.has_key('sMarkPoint'):
print 'Error:', stratMark.__name__, 'requires markowitz point to choose'
return
''' Optional variables '''
if not dFuncArgs.has_key('bAddAlpha'):
bAddAlpha = False
else:
bAddAlpha = dFuncArgs['bAddAlpha']
dmPrice = dFuncArgs['dmPrice']
sPeriod = dFuncArgs['sPeriod']
lLookback = dFuncArgs['lLookback']
sMarkPoint = dFuncArgs['sMarkPoint']
''' Select rebalancing dates '''
drNewRange = pand.DateRange(dtStart, dtEnd,
timeRule=sPeriod) + pand.DateOffset(hours=16)
dfAlloc = pand.DataMatrix()
''' Go through each rebalance date and calculate an efficient frontier for each '''
for i, dtDate in enumerate(drNewRange):
dtStart = dtDate - pand.DateOffset(days=lLookback)
if (dtStart < dmPrice.index[0]):
print 'Error, not enough data to rebalance'
continue
naRets = dmPrice.ix[dtStart:dtDate].values.copy()
tsu.returnize1(naRets)
tsu.fillforward(naRets)
tsu.fillbackward(naRets)
''' Add alpha to returns '''
if bAddAlpha:
if i < len(drNewRange) - 1:
naFutureRets = dmPrice.ix[dtDate:drNewRange[i +
1]].values.copy()
tsu.returnize1(naFutureRets)
tsu.fillforward(naFutureRets)
tsu.fillbackward(naFutureRets)
naAvg = np.mean(naFutureRets, axis=0)
''' make a mix of past/future rets '''
for i in range(naRets.shape[0]):
naRets[i, :] = (naRets[i, :] + (naAvg * 0.05)) / 1.05
''' Generate the efficient frontier '''
(lfReturn, lfStd, lnaPortfolios) = getFrontier(naRets,
fUpper=0.2,
fLower=0.01)
lInd = 0
'''
plt.clf()
plt.plot( lfStd, lfReturn)'''
if (sMarkPoint == 'Sharpe'):
''' Find portfolio with max sharpe '''
fMax = -1E300
for i in range(len(lfReturn)):
fShrp = (lfReturn[i] - 1) / (lfStd[i])
if fShrp > fMax:
fMax = fShrp
lInd = i
'''
plt.plot( [lfStd[lInd]], [lfReturn[lInd]], 'ro')
plt.draw()
time.sleep(2)
plt.show()'''
elif (sMarkPoint == 'MinVar'):
''' use portfolio with minimum variance '''
fMin = 1E300
for i in range(len(lfReturn)):
if lfStd[i] < fMin:
fMin = lfStd[i]
lInd = i
elif (sMarkPoint == 'MaxRet'):
''' use Portfolio with max returns (not really markovitz) '''
lInd = len(lfReturn) - 1
elif (sMarkPoint == 'MinRet'):
''' use Portfolio with min returns (not really markovitz) '''
lInd = 0
else:
print 'Warning: invalid sMarkPoint' ''
return
''' Generate allocation based on selected portfolio '''
naAlloc = (np.array(lnaPortfolios[lInd]).reshape(1, -1))
dmNew = pand.DataMatrix(index=[dtDate],
data=naAlloc,
columns=(dmPrice.columns))
dfAlloc = dfAlloc.append(dmNew)
dfAlloc['_CASH'] = 0.0
return dfAlloc
def stratMark( dtStart, dtEnd, dFuncArgs ):
"""
@summary Markovitz strategy, generates a curve and then chooses a point on it.
@param dtStart: Start date for portfolio
@param dtEnd: End date for portfolio
@param dFuncArgs: Dict of function args passed to the function
@return DataFrame corresponding to the portfolio allocations
"""
if not dFuncArgs.has_key('dmPrice'):
print 'Error:', stratMark.__name__, 'requires dmPrice information'
return
if not dFuncArgs.has_key('sPeriod'):
print 'Error:', stratMark.__name__, 'requires rebalancing period'
return
if not dFuncArgs.has_key('lLookback'):
print 'Error:', stratMark.__name__, 'requires lookback'
return
if not dFuncArgs.has_key('sMarkPoint'):
print 'Error:', stratMark.__name__, 'requires markowitz point to choose'
return
''' Optional variables '''
if not dFuncArgs.has_key('bAddAlpha'):
bAddAlpha = False
else:
bAddAlpha = dFuncArgs['bAddAlpha']
dmPrice = dFuncArgs['dmPrice']
sPeriod = dFuncArgs['sPeriod']
lLookback = dFuncArgs['lLookback']
sMarkPoint = dFuncArgs['sMarkPoint']
''' Select rebalancing dates '''
drNewRange = pand.DateRange(dtStart, dtEnd, timeRule=sPeriod) + pand.DateOffset(hours=16)
dfAlloc = pand.DataMatrix()
''' Go through each rebalance date and calculate an efficient frontier for each '''
for i, dtDate in enumerate(drNewRange):
dtStart = dtDate - pand.DateOffset(days=lLookback)
if( dtStart < dmPrice.index[0] ):
print 'Error, not enough data to rebalance'
continue
naRets = dmPrice.ix[ dtStart:dtDate ].values.copy()
tsu.returnize1(naRets)
tsu.fillforward(naRets)
tsu.fillbackward(naRets)
''' Add alpha to returns '''
if bAddAlpha:
if i < len(drNewRange) - 1:
naFutureRets = dmPrice.ix[ dtDate:drNewRange[i+1] ].values.copy()
tsu.returnize1(naFutureRets)
tsu.fillforward(naFutureRets)
tsu.fillbackward(naFutureRets)
naAvg = np.mean( naFutureRets, axis=0 )
''' make a mix of past/future rets '''
for i in range( naRets.shape[0] ):
naRets[i,:] = (naRets[i,:] + (naAvg*0.05)) / 1.05
''' Generate the efficient frontier '''
(lfReturn, lfStd, lnaPortfolios) = getFrontier( naRets, fUpper=0.2, fLower=0.01 )
lInd = 0
'''
plt.clf()
plt.plot( lfStd, lfReturn)'''
if( sMarkPoint == 'Sharpe'):
''' Find portfolio with max sharpe '''
fMax = -1E300
for i in range( len(lfReturn) ):
fShrp = (lfReturn[i]-1) / (lfStd[i])
if fShrp > fMax:
fMax = fShrp
lInd = i
'''
plt.plot( [lfStd[lInd]], [lfReturn[lInd]], 'ro')
plt.draw()
time.sleep(2)
plt.show()'''
elif( sMarkPoint == 'MinVar'):
''' use portfolio with minimum variance '''
fMin = 1E300
for i in range( len(lfReturn) ):
if lfStd[i] < fMin:
fMin = lfStd[i]
lInd = i
elif( sMarkPoint == 'MaxRet'):
''' use Portfolio with max returns (not really markovitz) '''
lInd = len(lfReturn)-1
elif( sMarkPoint == 'MinRet'):
''' use Portfolio with min returns (not really markovitz) '''
lInd = 0
else:
print 'Warning: invalid sMarkPoint'''
return
''' Generate allocation based on selected portfolio '''
naAlloc = (np.array( lnaPortfolios[lInd] ).reshape(1,-1) )
dmNew = pand.DataMatrix( index=[dtDate], data=naAlloc, columns=(dmPrice.columns) )
dfAlloc = dfAlloc.append( dmNew )
dfAlloc['_CASH'] = 0.0
return dfAlloc
