def ReadData(DataFile, TimeTag, IDTag, FactorTag): #Reading the timestamps from a text file. timestamps=[] file = open(TimeTag, 'r') for onedate in file.readlines(): timestamps.append(dt.datetime.strptime(onedate, "%Y-%m-%d\n")) file.close() symbols=[] file = open(IDTag, 'r') for f in file.readlines(): j = f[:-1] symbols.append(j) file.close() # Reading the Data Values Numpyarray=pickle.load(open( DataFile, 'rb' )) for i in range(0,len(Numpyarray)): tsu.fillforward(Numpyarray[i]) tsu.fillbackward(Numpyarray[i]) featureslist=[] file = open(FactorTag, 'r') for f in file.readlines(): j = f[:-1] featureslist.append(j) file.close() PandasObject= Panel(Numpyarray, items=featureslist, major_axis=timestamps, minor_axis=symbols) featureslist.sort() return (PandasObject, featureslist, symbols, timestamps)
def ReadData(DataFile, TimeTag, IDTag, FactorTag): #Reading the timestamps from a text file. timestamps=[] file = open(TimeTag, 'r') for onedate in file.readlines(): timestamps.append(dt.datetime.strptime(onedate, "%Y-%m-%d\n")) file.close() symbols=[] file = open(IDTag, 'r') for f in file.readlines(): j = f[:-1] symbols.append(j) file.close() # Reading the Data Values Numpyarray=pickle.load(open( DataFile, 'rb' )) for i in range(0,len(Numpyarray)): tsu.fillforward(Numpyarray[i]) tsu.fillbackward(Numpyarray[i]) featureslist=[] file = open(FactorTag, 'r') for f in file.readlines(): j = f[:-1] featureslist.append(j) file.close() PandasObject= Panel(Numpyarray, items=featureslist, major_axis=timestamps, minor_axis=symbols) featureslist.sort() return (PandasObject, featureslist, symbols, timestamps)
sharperatios[sym]['NaNs'] = nans
sharperatios[sym]['sr'] = 0
sharperatios = sharperatios.T
#
# Plot the adjusted close data
#
plt.clf()
newtimestamps = close.index
pricedat = close.values # pull the 2D ndarray out of the pandas object
#normalize nans
for sym in close.columns:
sharperatios['NaNs'][sym] = sharperatios['NaNs'][sym] / len(timestamps)
tsu.fillforward(pricedat)
tsu.fillbackward(pricedat)
dailyrets = (pricedat[1:,:]/pricedat[0:-1,:]) - 1
#print dailyrets
dailyrets = np.insert(dailyrets, 0, np.zeros(dailyrets.shape[1]), 0)
pp = PdfPages('bse-summary2013.pdf')
plt.plot(newtimestamps, dailyrets)
plt.legend(close.columns)
plt.ylabel('dailyrets')
plt.xlabel('Date')
pp.savefig()
for sym in range (0, len(close.columns)):
lYear = 2009 dtEnd = dt.datetime(lYear+1,1,1) 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.returnize0(naData) tsu.fillforward(naDataTest) tsu.fillbackward(naDataTest) tsu.returnize0(naDataTest) ''' Get efficient frontiers ''' (lfReturn, lfStd, lnaPortfolios, naAvgRets, naStd) = getFrontier( naData) (lfReturnTest, lfStdTest, unused, unused, unused) = getFrontier( naDataTest) plt.clf() fig = plt.figure() ''' Plot efficient frontiers '''
# Read the historical data in from our data store # endday = dt.datetime(2011,1,1) startday = endday - dt.timedelta(days=1095) #three years back timeofday=dt.timedelta(hours=16) print "start getNYSEdays" timestamps = du.getNYSEdays(startday,endday,timeofday) print "start read" close = dataobj.get_data(timestamps,portsyms,"close") print "end read" # # Copy, prep, and compute daily returns # rets = close.values.copy() tsu.fillforward(rets) tsu.returnize0(rets) # # Estimate portfolio total returns # portrets = sum(rets*portalloc,axis=1) porttot = cumprod(portrets+1) componenttot = cumprod(rets+1,axis=0) # compute returns for components # # Plot the result # plt.clf() fig = plt.figure() fig.add_subplot(111)
if llValid[i] == llTotal[i]:
lHundred = lHundred + 1
ltBoth.sort()
ltBoth.reverse()
for tRes in ltBoth:
print '%10s: %.02lf%%'%( tRes[1], tRes[0] )
print '\n%i out of %i elemenets non-zero.'%(lNonZero, len(lsItems))
print '%i out of %i elemenets have 100%% participation.'%(lHundred, len(lsItems))
''' Retrieve and plot quarterly earnings per share '''
dmEps = dmKeys = dmValues[ dLabel['EPSPIQ'] ]
naEps = dmEps.values
tsu.fillforward( naEps )
plt.clf()
for i, sStock in enumerate( symbols ):
plt.plot( tsAll, naEps[:,i] )
plt.gcf().autofmt_xdate(rotation=45)
plt.legend( symbols, loc='upper left' )
plt.title('EPS of various stocks')
savefig('tutorial6.pdf',format='pdf')
lYear = 2009 dtEnd = dt.datetime(lYear + 1, 1, 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()
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
