def print_industry_coer(fund_ts, ostream):
"""
@summary prints standard deviation of returns for a fund
@param fund_ts: pandas fund time series
@param years: list of years to print out
@param ostream: stream to print to
"""
industries = [['$DJUSBM', 'Materials'],
['$DJUSNC', 'Goods'],
['$DJUSCY', 'Services'],
['$DJUSFN', 'Financials'],
['$DJUSHC', 'Health'],
['$DJUSIN', 'Industrial'],
['$DJUSEN', 'Oil & Gas'],
['$DJUSTC', 'Technology'],
['$DJUSTL', 'TeleComm'],
['$DJUSUT', 'Utilities']]
for i in range(0, len(industries) ):
if(i%2==0):
ostream.write("\n")
#load data
norObj = de.DataAccess('mysql')
ldtTimestamps = du.getNYSEdays( fund_ts.index[0], fund_ts.index[-1], dt.timedelta(hours=16) )
ldfData = norObj.get_data( ldtTimestamps, [industries[i][0]], ['close'] )
#get corelation
ldfData[0]=ldfData[0].fillna(method='pad')
ldfData[0]=ldfData[0].fillna(method='bfill')
a=np.corrcoef(np.ravel(tsu.daily(ldfData[0][industries[i][0]])),np.ravel(tsu.daily(fund_ts.values)))
b=np.ravel(tsu.daily(ldfData[0][industries[i][0]]))
f=np.ravel(tsu.daily(fund_ts))
fBeta, unused = np.polyfit(b,f,1)
ostream.write("%10s(%s):%+6.2f, %+6.2f " % (industries[i][1], industries[i][0], a[0,1], fBeta))
def print_industry_coer(fund_ts, ostream):
"""
@summary prints standard deviation of returns for a fund
@param fund_ts: pandas fund time series
@param years: list of years to print out
@param ostream: stream to print to
"""
industries = [['$DJUSBM', 'Materials'], ['$DJUSNC', 'Goods'],
['$DJUSCY', 'Services'], ['$DJUSFN', 'Financials'],
['$DJUSHC', 'Health'], ['$DJUSIN', 'Industrial'],
['$DJUSEN', 'Oil & Gas'], ['$DJUSTC', 'Technology'],
['$DJUSTL', 'TeleComm'], ['$DJUSUT', 'Utilities']]
for i in range(0, len(industries)):
if (i % 2 == 0):
ostream.write("\n")
#load data
norObj = de.DataAccess('mysql')
ldtTimestamps = du.getNYSEdays(fund_ts.index[0], fund_ts.index[-1],
dt.timedelta(hours=16))
ldfData = norObj.get_data(ldtTimestamps, [industries[i][0]], ['close'])
#get corelation
ldfData[0] = ldfData[0].fillna(method='pad')
ldfData[0] = ldfData[0].fillna(method='bfill')
a = np.corrcoef(np.ravel(tsu.daily(ldfData[0][industries[i][0]])),
np.ravel(tsu.daily(fund_ts.values)))
b = np.ravel(tsu.daily(ldfData[0][industries[i][0]]))
f = np.ravel(tsu.daily(fund_ts))
fBeta, unused = np.polyfit(b, f, 1)
ostream.write("%10s(%s):%+6.2f, %+6.2f " %
(industries[i][1], industries[i][0], a[0, 1], fBeta))
def fundsAnalysisToPNG(funds,output_file):
plt.clf()
if(type(funds)!=type(list())):
print 'fundsmatrix only contains one timeseries, not able to analyze.'
#convert to daily returns
count=list()
dates=list()
sum=list()
for i in range(0,len(funds)):
ret=tsu.daily(funds[i].values)
for j in range(0, len(ret)):
if (funds[i].index[j] in dates):
sum[dates.index(funds[i].index[j])]+=ret[j]
count[dates.index(funds[i].index[j])]+=1
else:
dates.append(funds[i].index[j])
count.append(1)
sum.append(ret[j])
#compute average
tot_ret=deepcopy(sum)
for i in range(0,len(sum)):
tot_ret[i]=sum[i]/count[i]
#compute std
std=zeros(len(sum))
for i in range(0,len(funds)):
temp=tsu.daily(funds[i].values)
for j in range(0,len(temp)):
std[dates.index(funds[i].index[j])]=0
std[dates.index(funds[i].index[j])]+=math.pow(temp[j]-tot_ret[dates.index(funds[i].index[j])],2)
for i in range(1, len(std)):
# std[i]=math.sqrt(std[i]/count[i])+std[i-1]
std[i]=math.sqrt(std[i]/count[i])
#compute total returns
lower=deepcopy(tot_ret)
upper=deepcopy(tot_ret)
tot_ret[0]=funds[0].values[0]
lower[0]=funds[0].values[0]
upper[0]=lower[0]
# for i in range(1,len(tot_ret)):
# tot_ret[i]=tot_ret[i-1]+(tot_ret[i])*tot_ret[i-1]
# lower[i]=tot_ret[i-1]-(std[i])*tot_ret[i-1]
# upper[i]=tot_ret[i-1]+(std[i])*tot_ret[i-1]
for i in range(1,len(tot_ret)):
lower[i]=(tot_ret[i]-std[i]+1)*lower[i-1]
upper[i]=(tot_ret[i]+std[i]+1)*upper[i-1]
tot_ret[i]=(tot_ret[i]+1)*tot_ret[i-1]
plt.clf()
plt.plot(dates,tot_ret)
plt.plot(dates,lower)
plt.plot(dates,upper)
plt.legend(('Tot_Ret','Lower','Upper'),loc='upper left')
plt.ylabel('Fund Total Return')
plt.ylim(ymin=0,ymax=2*tot_ret[0])
plt.draw()
savefig(output_file, format='png')
def print_other_coer(fund_ts, ostream):
"""
@summary prints standard deviation of returns for a fund
@param fund_ts: pandas fund time series
@param years: list of years to print out
@param ostream: stream to print to
"""
industries = [['$SPX', ' S&P Index'], ['$DJI', ' Dow Jones'],
['$DJUSEN', 'Oil & Gas'], ['$DJGSP', ' Metals']]
for i in range(0, len(industries)):
if (i % 2 == 0):
ostream.write("\n")
#load data
norObj = de.DataAccess('mysql')
ldtTimestamps = du.getNYSEdays(fund_ts.index[0], fund_ts.index[-1],
dt.timedelta(hours=16))
ldfData = norObj.get_data(ldtTimestamps, [industries[i][0]], ['close'])
#get corelation
ldfData[0] = ldfData[0].fillna(method='pad')
ldfData[0] = ldfData[0].fillna(method='bfill')
a = np.corrcoef(np.ravel(tsu.daily(ldfData[0][industries[i][0]])),
np.ravel(tsu.daily(fund_ts.values)))
b = np.ravel(tsu.daily(ldfData[0][industries[i][0]]))
f = np.ravel(tsu.daily(fund_ts))
fBeta, unused = np.polyfit(b, f, 1)
ostream.write("%10s(%s):%+6.2f, %+6.2f " %
(industries[i][1], industries[i][0], a[0, 1], fBeta))
def print_other_coer(fund_ts, ostream):
"""
@summary prints standard deviation of returns for a fund
@param fund_ts: pandas fund time series
@param years: list of years to print out
@param ostream: stream to print to
"""
industries = [['$SPX', ' S&P Index'],
['$DJI', ' Dow Jones'],
['$DJUSEN', 'Oil & Gas'],
['$DJGSP', ' Metals']]
for i in range(0, len(industries) ):
if(i%2==0):
ostream.write("\n")
#load data
norObj =de.DataAccess('mysql')
ldtTimestamps = du.getNYSEdays( fund_ts.index[0], fund_ts.index[-1], dt.timedelta(hours=16) )
ldfData = norObj.get_data( ldtTimestamps, [industries[i][0]], ['close'] )
#get corelation
ldfData[0]=ldfData[0].fillna(method='pad')
ldfData[0]=ldfData[0].fillna(method='bfill')
a=np.corrcoef(np.ravel(tsu.daily(ldfData[0][industries[i][0]])),np.ravel(tsu.daily(fund_ts.values)))
b=np.ravel(tsu.daily(ldfData[0][industries[i][0]]))
f=np.ravel(tsu.daily(fund_ts))
fBeta, unused = np.polyfit(b,f,1)
ostream.write("%10s(%s):%+6.2f, %+6.2f " % (industries[i][1], industries[i][0], a[0,1], fBeta))
def daily_return(value): # daily_ret = [] # daily_ret.append(0) #the daily_return of the first trading day # for i in range(1,len(value)): # daily_ret.append((value[i]/value[i-1])-1) # return daily_ret return tsu.daily(value)
def daily_return(value):
# daily_ret = []
# daily_ret.append(0) #the daily_return of the first trading day
# for i in range(1,len(value)):
# daily_ret.append((value[i]/value[i-1])-1)
# return daily_ret
return tsu.daily(value)
def get_sharpe_ratio(fund_ts):
"""
@summary Returns daily computed Sharpe ratio of fund time series
@param fund_ts: pandas time series of daily fund values
@return Sharpe ratio of fund time series
"""
return tsu.get_sharpe_ratio(tsu.daily(fund_ts))
def get_winning_days(fund_ts):
"""
@summary Returns percentage of winning days in fund time series
@param fund_ts: pandas time series of daily fund values
@return Percentage of winning days over fund time series
"""
return tsu.get_winning_days(tsu.daily(fund_ts))
def print_benchmark_coer(fund_ts, benchmark_close, sym, ostream):
"""
@summary prints standard deviation of returns for a fund
@param fund_ts: pandas fund time series
@param years: list of years to print out
@param ostream: stream to print to
"""
fund_ts=fund_ts.fillna(method='pad')
fund_ts=fund_ts.fillna(method='bfill')
benchmark_close=benchmark_close.fillna(method='pad')
benchmark_close=benchmark_close.fillna(method='bfill')
faCorr=np.corrcoef(np.ravel(tsu.daily(fund_ts.values)),np.ravel(tsu.daily(benchmark_close)));
b=np.ravel(tsu.daily(benchmark_close))
f=np.ravel(tsu.daily(fund_ts))
fBeta, unused = np.polyfit(b,f, 1);
print_line(sym+"Correlattion","%+6.2f" % faCorr[0,1],i_spacing=3,ostream=ostream)
print_line(sym+"Beta","%+6.2f" % fBeta,i_spacing=3,ostream=ostream)
def get_std_dev(fund_ts):
"""
@summary gets standard deviation of returns for a fund as a string
@param fund_ts: pandas fund time series
@param years: list of years to print out
@param ostream: stream to print to
"""
fund_ts = fund_ts.fillna(method='pad')
fund_ts = fund_ts.fillna(method='bfill')
ret = np.std(tsu.daily(fund_ts.values)) * 10000
return ("%+7.2f bps " % ret)
def get_std_dev(fund_ts):
"""
@summary gets standard deviation of returns for a fund as a string
@param fund_ts: pandas fund time series
@param years: list of years to print out
@param ostream: stream to print to
"""
fund_ts=fund_ts.fillna(method='pad')
fund_ts=fund_ts.fillna(method='bfill')
ret=np.std(tsu.daily(fund_ts.values))*10000
return ("%+7.2f bps " % ret)
def print_benchmark_coer(fund_ts, benchmark_close, sym, ostream):
"""
@summary prints standard deviation of returns for a fund
@param fund_ts: pandas fund time series
@param years: list of years to print out
@param ostream: stream to print to
"""
fund_ts = fund_ts.fillna(method='pad')
fund_ts = fund_ts.fillna(method='bfill')
benchmark_close = benchmark_close.fillna(method='pad')
benchmark_close = benchmark_close.fillna(method='bfill')
faCorr = np.corrcoef(np.ravel(tsu.daily(fund_ts.values)),
np.ravel(tsu.daily(benchmark_close)))
b = np.ravel(tsu.daily(benchmark_close))
f = np.ravel(tsu.daily(fund_ts))
fBeta, unused = np.polyfit(b, f, 1)
print_line(sym + "Correlattion",
"%+6.2f" % faCorr[0, 1],
i_spacing=3,
ostream=ostream)
print_line(sym + "Beta", "%+6.2f" % fBeta, i_spacing=3, ostream=ostream)
def getWinningDays(funds1, funds2, year):
days = []
i = 0
win = 0
tot = 0
f1ret = tsu.daily(funds1)
f2ret = tsu.daily(funds2)
relf1 = []
relf2 = []
for date in funds1.index:
if (date.year == year):
for date2 in funds2.index:
if (date == date2):
relf1.append(f1ret[i])
relf2.append(f2ret[i])
i += 1
for i in range(0, len(relf1)):
if (f1ret[i] > f2ret[i]):
win += 1
tot += 1
return float(win) / tot
def getWinningDays(funds1,funds2,year): days=[] i=0; win=0 tot=0 f1ret=tsu.daily(funds1) f2ret=tsu.daily(funds2) relf1=[] relf2=[] for date in funds1.index: if(date.year==year): for date2 in funds2.index: if(date==date2): relf1.append(f1ret[i]) relf2.append(f2ret[i]) i+=1 for i in range(0,len(relf1)): if(f1ret[i]>f2ret[i]): win+=1 tot+=1 return float(win)/tot
tick.label.set_fontsize(6)
plt.plot(timestamp, values)
savefig(figureName,format='pdf')
#
# Compute Cumulative Return, Sharpe ratio, std of daily return for the portfolio
#
if debug:
print "-----Before calculate-----"
for v in values:
print v
daily_returns0 = tsu.daily(values)
if debug:
print "-----After calculate-----"
for v in daily_returns0:
print v
final_return = values[len(values)-1]/values[0]-1
print "Total Return:" , final_return
mean = np.average(daily_returns0)
print "Expected Return:", mean
std2 = np.std(daily_returns0)
print "Standard Deviation:", std2
sharp_ratio = tsu.get_sharpe_ratio(daily_returns0)
def analyzeValue(valueFilename=valueFilename, benchmark=benchmark,figureName=figureName, closefield=closefield):
valueCSV = open(valueFilename, 'rU')
reader = csv.reader(valueCSV, delimiter=',')
timestamp = []
values = []
for row in reader:
timestamp.append(dt.date(int(row[0]),int(row[1]),int(row[2])))
values.append(float(row[3]))
#
# Plot portfolio value
plt.clf()
fig = plt.figure()
ax = fig.add_subplot(111)
ax.plot(timestamp, values)
# adjust tick size
for tick in ax.xaxis.get_major_ticks():
tick.label.set_fontsize(6)
plt.plot(timestamp, values)
savefig(figureName,format='pdf')
#
# Compute Cumulative Return, Sharpe ratio, std of daily return for the portfolio
#
if debug:
print "-----Before calculate-----"
for v in values:
print v
daily_returns0 = tsu.daily(values)
if debug:
print "-----After calculate-----"
for v in daily_returns0:
print v
final_return = values[len(values)-1]/values[0]-1
print "Total Return:" , final_return
mean = np.average(daily_returns0)
print "Expected Return:", mean
std2 = np.std(daily_returns0)
print "Standard Deviation:", std2
sharp_ratio = tsu.get_sharpe_ratio(daily_returns0)
print "Calculated Sharpe Ratio:", tsu.sqrt(252) * mean/std2
print "Get Sharpe Ration from QSTK:", sharp_ratio
#
# Calculate Benchmark metrics
#
timeofday = dt.timedelta(hours=h)
timestamps = du.getNYSEdays(timestamp[0],timestamp[len(timestamp)-1],timeofday)
dataobj = da.DataAccess('Yahoo')
print "reading benchmark data...",benchmark
close = dataobj.get_data(timestamps, benchmark, closefield)
if debug:
for time in timestamps:
print time, close[benchmark[0]][time]
close = (close.fillna(method='ffill')).fillna(method='backfill')
bValues = close.values
print
final_return_b = (bValues[len(bValues)-1]/bValues[0])-1
print benchmark,"Total Return:" , final_return_b
# daily returns
b_daily_returns0 = tsu.daily(bValues)
mean = np.average(b_daily_returns0)
print benchmark, "Expected Return:", mean
std2 = np.std(b_daily_returns0)
print benchmark,"Standard Deviation:", std2
sharp_ratio = tsu.get_sharpe_ratio(b_daily_returns0)
print benchmark,"Calculated Sharpe Ratio:", tsu.sqrt(252) * mean/std2
print benchmark,"Get Sharpe Ration from QSTK:", sharp_ratio
