def get_relative_features(dDataRelative, sym):
sma = ft.featMA(dDataRelative, lLookback = 20)
sma1 = ft.featMA(dDataRelative, lLookback = 10)
sma2 = ft.featMA(dDataRelative, lLookback = 5)
sma3 = ft.featMA(dDataRelative, lLookback = 80)
sma4 = ft.featMA(dDataRelative, lLookback = 40)
rsi = ft.featRSI(dDataRelative, lLookback = 20)
rsi1 = ft.featRSI(dDataRelative, lLookback = 10)
rsi2 = ft.featRSI(dDataRelative, lLookback = 5)
rsi3 = ft.featRSI(dDataRelative, lLookback = 80)
rsi4 = ft.featRSI(dDataRelative, lLookback = 40)
#volumeDelta = ft.featVolumeDelta(dDataRelative, lLookback = 20)
aroon = ft.featAroon(dDataRelative, lLookback = 20)
aroon1 = ft.featAroon(dDataRelative, lLookback = 10)
aroon2 = ft.featAroon(dDataRelative, lLookback = 5)
aroon3 = ft.featAroon(dDataRelative, lLookback = 80)
aroon4 = ft.featAroon(dDataRelative, lLookback = 40)
bollinger = ft.featBollinger(dDataRelative, lLookback = 20)
bollinger1 = ft.featBollinger(dDataRelative, lLookback = 10)
bollinger2 = ft.featBollinger(dDataRelative, lLookback = 5)
bollinger3 = ft.featBollinger(dDataRelative, lLookback = 80)
bollinger4 = ft.featBollinger(dDataRelative, lLookback = 40)
#stochastics = ft.featStochastic(dDataRelative, lLookback = 20)
dfX = pd.DataFrame( index=dDataRelative['close'].index,
columns=['SMA', 'RSI', 'AROON', 'BOLL'],
data=np.zeros((len(dDataRelative['close'].index), 4)))
dfX['SMA'] = sma[sym]
dfX['SMA1'] = sma1[sym]
dfX['SMA2'] = sma2[sym]
dfX['SMA3'] = sma3[sym]
dfX['SMA4'] = sma4[sym]
dfX['RSI'] = rsi[sym]
dfX['RSI1'] = rsi1[sym]
dfX['RSI2'] = rsi2[sym]
dfX['RSI3'] = rsi3[sym]
dfX['RSI4'] = rsi4[sym]
dfX['AROON'] = aroon[sym]
dfX['AROON1'] = aroon1[sym]
dfX['AROON2'] = aroon2[sym]
dfX['AROON3'] = aroon3[sym]
dfX['AROON4'] = aroon4[sym]
dfX['BOLL'] = bollinger[sym]
dfX['BOLL1'] = bollinger1[sym]
dfX['BOLL2'] = bollinger2[sym]
dfX['BOLL3'] = bollinger3[sym]
dfX['BOLL4'] = bollinger4[sym]
return dfX
def findEvents(symbols, startday,endday, marketSymbol,verbose=False):
# Reading the Data for the list of Symbols.
timeofday=dt.timedelta(hours=16)
timestamps = du.getNYSEdays(startday,endday,timeofday)
dataobj = da.DataAccess('Yahoo')
if verbose:
print __name__ + " reading data"
# Reading the Data
close = dataobj.get_data(timestamps, symbols, closefield)
# Completing the Data - Removing the NaN values from the Matrix
close = (close.fillna(method='ffill')).fillna(method='backfill')
#CLOSE_UNCHANGED!!!!
close_unchanged = dataobj.get_data(timestamps, symbols, closefield)
close_unchanged = (close.fillna(method='ffill')).fillna(method='backfill')
# Calculating Daily Returns for the Market
tsu.returnize0(close.values)
SPYValues=close[marketSymbol]
# Calculating the Returns of the Stock Relative to the Market
# So if a Stock went up 5% and the Market rised 3%. The the return relative to market is 2%
mktneutDM = close - close[marketSymbol]
np_eventmat = copy.deepcopy(mktneutDM)
for sym in symbols:
for time in timestamps:
np_eventmat[sym][time]=np.NAN
if verbose:
print __name__ + " finding events"
# Generating the Event Matrix
# Event described is : Market falls more than 3% plus the stock falls 5% more than the Market
# Suppose : The market fell 3%, then the stock should fall more than 8% to mark the event.
# And if the market falls 5%, then the stock should fall more than 10% to mark the event.
with open (args.orders, "w") as outFile:
writer = csv.writer(outFile)
for symbol in symbols:
for i in range(1,len(mktneutDM[symbol])):
if SPYValues[i]<-0.03 and mktneutDM[symbol][i] < -0.05 :
ft.featAroon(close_unchanged[symbol][i], bDown=False)
writer.writerow([timestamps[i].year,timestamps[i].month,timestamps[i].day, symbol, "Buy", 100])
writer.writerow([timestamps[i+5].year,timestamps[i+5].month,timestamps[i+5].day, symbol, "Sell", 100])
def get_features_old(self):
feats = pd.DataFrame( index=self.relative_data['close'].index)
periods = self.default_periods
for x in periods:
feats['SMA' + str(x)] = ft.featMA(self.relative_data, lLookback = x)[self.stock_period.symbol]
for x in periods:
feats['RSI' + str(x)] = ft.featRSI(self.relative_data, lLookback = x)[self.stock_period.symbol]
for x in periods:
feats['AROON' + str(x)] = ft.featAroon(self.relative_data, lLookback = x)[self.stock_period.symbol]
for x in periods:
feats['BOLL' + str(x)] = ft.featBollinger(self.relative_data, lLookback = x)[self.stock_period.symbol]
for x in periods:
feats['MOM' + str(x)] = ft.featMomentum(self.relative_data, lLookback = x)[self.stock_period.symbol]
for x in periods:
feats['EMA' + str(x)] = ft.featEMA(self.relative_data, lLookback = x)[self.stock_period.symbol]
#for x in periods:
# feats['STD' + str(x)] = ft.featSTD(self.relative_data, lLookback = x)[self.stock_period.symbol]
#for x in periods:
# feats['VOLD' + str(x)] = ft.featVolumeDelta(self.relative_data, lLookback = x)[self.stock_period.symbol]
return feats