''' Plot feature for XOM '''
for i, fcFunc in enumerate(lfcFeatures[:-1]):
plt.clf()
plt.subplot(211)
plt.title( fcFunc.__name__ )
plt.plot( dfPrice.index, dfPrice['XOM'].values, 'r-' )
plt.subplot(212)
plt.plot( dfPrice.index, ldfFeatures[i]['XOM'].values, 'g-' )
plt.show()
''' Pick Test and Training Points '''
lSplit = int(len(ldtTimestamps) * 0.7)
dtStartTrain = ldtTimestamps[0]
dtEndTrain = ldtTimestamps[lSplit]
dtStartTest = ldtTimestamps[lSplit+1]
dtEndTest = ldtTimestamps[-1]
''' Stack all information into one Numpy array '''
naFeatTrain = ftu.stackSyms( ldfFeatures, dtStartTrain, dtEndTrain )
naFeatTest = ftu.stackSyms( ldfFeatures, dtStartTest, dtEndTest )
''' Normalize features, use same normalization factors for testing data as training data '''
ltWeights = ftu.normFeatures( naFeatTrain, -1.0, 1.0, False )
''' Normalize query points with same weights that come from test data '''
ftu.normQuery( naFeatTest[:,:-1], ltWeights )
learnerTest( naFeatTrain, naFeatTest )
''' Generate a list of DataFrames, one for each feature, with the same index/column structure as price data '''
ldfFeaturesTrain = ftu.applyFeatures(dDataTrain, lfcFeatures, ldArgs,
'$SPX')
ldfFeaturesTest = ftu.applyFeatures(dDataTest, lfcFeatures, ldArgs, '$SPX')
''' Pick Test and Training Points '''
dtStartTrain = dt.datetime(2008, 01, 01)
dtEndTrain = dt.datetime(2009, 12, 31)
dtStartTest = dt.datetime(2010, 01, 01)
dtEndTest = dt.datetime(2010, 12, 31)
''' Stack all information into one Numpy array '''
naFeatTrain = ftu.stackSyms(ldfFeaturesTrain, dtStartTrain, dtEndTrain)
naFeatTest = ftu.stackSyms(ldfFeaturesTest, dtStartTest, dtEndTest)
''' Normalize features, use same normalization factors for testing data as training data '''
ltWeights = ftu.normFeatures(naFeatTrain, -1.0, 1.0, False)
''' Normalize query points with same weights that come from test data '''
ftu.normQuery(naFeatTest[:, :-1], ltWeights)
lFeatures = range(0, len(lfcFeatures) - 1)
classLabelIndex = len(lfcFeatures) - 1
funccall = sys.argv[
1] + '(naFeatTrain,naFeatTest,lFeatures,classLabelIndex)'
timestart = time.time()
clockstart = time.clock()
eval(funccall)
clockend = time.clock()
timeend = time.time()
sys.stdout.write('\n\nclock diff: ' + str(clockend - clockstart) + 'sec\n')
sys.stdout.write('time diff: ' + str(timeend - timestart) + 'sec\n')
def main():
# symbols = np.loadtxt('./Examples/Features/symbols.txt',dtype='S10',comments='#')
symbols = [
"AA",
"AXP",
"BA",
"BAC",
"CAT",
"CSCO",
"CVX",
"DD",
"DIS",
"GE",
"HD",
"HPQ",
"IBM",
"INTC",
"JNJ",
"JPM",
"KFT",
"KO",
"MCD",
"MMM",
"MRK",
"MSFT",
"PFE",
"PG",
"T",
"TRV",
"UTX",
"VZ",
"WMT",
"XOM",
]
# symbols = ['XOM']
# This is the start and end dates for the entire train and test data combined
alldatastartday = dt.datetime(2007, 1, 1)
alldataendday = dt.datetime(2010, 6, 30)
timeofday = dt.timedelta(hours=16)
timestamps = du.getNYSEdays(alldatastartday, alldataendday, timeofday)
dataobj = da.DataAccess("Norgate")
voldata = dataobj.get_data(timestamps, symbols, "volume", verbose=True)
voldata = (voldata.fillna()).fillna(method="backfill")
close = dataobj.get_data(timestamps, symbols, "close", verbose=True)
close = (close.fillna()).fillna(method="backfill")
featureList = [
featMA,
featMA,
featRSI,
featRSI,
featDrawDown,
featRunUp,
featVolumeDelta,
featVolumeDelta,
featAroon,
classFutRet,
]
featureListArgs = [
{"lLookback": 10, "bRel": True},
{"lLookback": 20},
{"lLookback": 10},
{"lLookback": 20},
{},
{},
{"lLookback": 10},
{"lLookback": 20},
{"bDown": False},
{"lLookforward": 5},
]
# print 'Applying Features'
#
# John Cornwell's featuretest.py was consulted for figuring out the syntax of ftu.applyFeatures() methods and ftu.stackSyms() methods
#
allfeatureValues = ftu.applyFeatures(close, voldata, featureList, featureListArgs)
trainstartday = dt.datetime(2007, 1, 1)
trainendday = dt.datetime(2009, 12, 31)
traintimestamps = du.getNYSEdays(trainstartday, trainendday, timeofday)
# print 'Stack Syms for Training'
trainingData = ftu.stackSyms(allfeatureValues, traintimestamps[0], traintimestamps[-1])
# print 'Norm Features for Training'
scaleshiftvalues = ftu.normFeatures(trainingData, -1.0, 1.0, False)
teststartday = dt.datetime(2010, 1, 1)
testendday = dt.datetime(2010, 6, 30)
testtimestamps = du.getNYSEdays(teststartday, testendday, timeofday)
# print 'Stack Syms for Test'
testData = ftu.stackSyms(allfeatureValues, testtimestamps[0], testtimestamps[-1])
# print 'Norm Features for Test'
ftu.normQuery(testData[:, :-1], scaleshiftvalues)
NUMFEATURES = 9
bestFeatureIndices = []
bestCorrelation = 0.0
fid = open("output.txt", "w")
for iteration in range(NUMFEATURES):
nextFeatureIndexToAdd = -1
for featureIndex in range(NUMFEATURES):
if featureIndex not in bestFeatureIndices:
bestFeatureIndices.append(featureIndex)
fid.write("testing feature set " + str(bestFeatureIndices) + "\n")
print("testing feature set " + str(bestFeatureIndices))
bestFeatureIndices.append(9)
curTrainingData = trainingData[:, bestFeatureIndices]
curTestData = testData[:, bestFeatureIndices]
bestFeatureIndices.remove(9)
kdtlearner = knn.kdtknn(5, "mean", leafsize=100)
kdtlearner.addEvidence(curTrainingData[:, :-1], curTrainingData[:, -1])
testEstimatedValues = kdtlearner.query(curTestData[:, :-1])
testcorrelation = np.corrcoef(testEstimatedValues.T, curTestData[:, -1].T)
curCorrelation = testcorrelation[0, 1]
fid.write("corr coef = %.4f\n" % (curCorrelation))
print("corr coef = %.4f" % (curCorrelation))
if curCorrelation > bestCorrelation:
nextFeatureIndexToAdd = featureIndex
bestCorrelation = curCorrelation
bestFeatureIndices.remove(featureIndex)
if nextFeatureIndexToAdd >= 0:
bestFeatureIndices.append(nextFeatureIndexToAdd)
else:
break
fid.write("best feature set is " + str(bestFeatureIndices) + "\n")
print("best feature set is " + str(bestFeatureIndices))
fid.write("corr coef = %.4f" % (bestCorrelation) + "\n")
print("corr coef = %.4f" % (bestCorrelation))
fid.close()
def find_best_feature(features):
#first for loop gets the first best feature.
hmax = 0
for i in range(0,9):
print 'testing feature set[',i,',9]'
args = []
features = []
global train_data
global test_data
features.append(copyfeatures[i])
features.append(copyfeatures[9])
args.append(copyargs[i])
args.append(copyargs[9])
ldfFeatures_new = ftu.applyFeatures( dfPrice, dfVolume, features, args )
naFeatTrain = ftu.stackSyms( ldfFeatures_new, dtStartTrain, dtEndTrain)
naFeatTest = ftu.stackSyms( ldfFeatures_new, dtStartTest, dtEndTest )
store_train_and_test(naFeatTrain,naFeatTest)
#print naFeatTrain,"NEXT"
#print naFeatTest
ltWeights = ftu.normFeatures( naFeatTrain, -1.0, 1.0, False )
ftu.normQuery( naFeatTest[:,:-1], ltWeights )
corr_of_this = learnerTest(naFeatTrain,naFeatTest)
print 'corr coef = ',corr_of_this[0][1]
if(corr_of_this[0][1] > hmax):
hmax = corr_of_this[0][1]
feature = copyfeatures[i]
best = i
#print "best corr coef",hmax,'for',best
#now all combinations are checked for all other 8 possible ones.
allbest = []
args = []
features = []
features.append(copyfeatures[best])
args.append(copyargs[best])
h = 1
allbest.append(best)
for k in range(0,8):
found = 0
for i in range(0,9):
if(i not in allbest):
global train_data
global test_data
features.append(copyfeatures[i])
h = h+1
features.append(copyfeatures[9])
args.append(copyargs[i])
args.append(copyargs[9])
print 'testing feature set [',allbest,',',i,',9]'
ldfFeatures_new = ftu.applyFeatures( dfPrice, dfVolume, features, args )
naFeatTrain = ftu.stackSyms( ldfFeatures_new, dtStartTrain, dtEndTrain)
naFeatTest = ftu.stackSyms( ldfFeatures_new, dtStartTest, dtEndTest )
store_train_and_test(naFeatTrain,naFeatTest)
#print naFeatTrain,"NEXT"
#print naFeatTest
ltWeights = ftu.normFeatures( naFeatTrain, -1.0, 1.0, False )
ftu.normQuery( naFeatTest[:,:-1], ltWeights )
corr_of_this = learnerTest(naFeatTrain,naFeatTest)
if(corr_of_this[0][1] > hmax):
found = 1
hmax = corr_of_this[0][1]
argument = copyargs[i]
feature = copyfeatures[i]
args.remove(copyargs[i])
features.remove(copyfeatures[i])
args.remove(copyargs[9])
features.remove(copyfeatures[9])
best = i
#allbest.append(best)
print 'corr coef =', hmax
#best = i + best
else:
h = h - 1
print 'corr coef = ',corr_of_this[0][1]
#args.remove(copyargs[i])
args.remove(copyargs[9])
#features.remove(copyfeatures[i])
features.remove(copyfeatures[9])
if found==1:
allbest.append(best)
args.append(argument)
features.append(feature)
else:
break
#for k in range(0,h):
#print 'best is',features[k]
print 'best feature set [',allbest,',9]'
print "corr coef = ",hmax
return
