def runRegressionModelTest(featureSet, valueVector, model):
output = ''
clf = 0
if model == 1:
print "\nLINEAR REGRESSION\n"
clf = linear_regression_fit(featureSet, valueVector)
elif model == 2:
print "\nSVR\n"
clf = SVR_fit(featureSet, valueVector)
elif model == 4:
print "\nSTOCHASTIC\n"
clf = SGD_r_fit(featureSet, valueVector)
joblib.dump(clf, 'sgd.pkl')
elif model == 5:
print "\nNEIGHBOURS\n"
clf = neighbours_fit(featureSet, valueVector)
elif model == 6:
print "\nLOGISTIC\n"
clf = log_regression_fit(featureSet, valueVector)
elif model == 7:
print "\nBAYESIANRIDGE\n"
clf = bayesian_ridge_fit(featureSet, valueVector)
elif model == 8:
print "\nRIDGE\n"
clf = ridge_fit(featureSet, valueVector)
elif model == 9:
print "\nELASTIC NET\n"
clf = elastic_fit(featureSet, valueVector)
elif model == 10:
print "\nLASSO\n"
clf = lasso_fit(featureSet, valueVector)
else:
print 'Invalid choice\n'
return clf
def runRegressionModelTest(featureSet, valueVector, X_test, y_test, model):
output = ''
score = 0
clf = 0
if model == 1:
output += "\nLINEAR REGRESSION\n"
clf = linear_regression_fit(featureSet, valueVector)
elif model == 2:
output += "\nSVR\n"
clf = SVR_fit(featureSet, valueVector)
elif model == 3:
output += "\nEXTREME LEARNING MACHINE\n"
clf = elm.ELMRegressor()
clf.fit(featureSet, valueVector)
joblib.dump(clf, 'elm.pkl')
elif model == 4:
output += "\nSTOCHASTIC\n"
clf = SGD_r_fit(featureSet, valueVector)
joblib.dump(clf, 'sgd.pkl')
elif model == 5:
output += "\nNEIGHBOURS\n"
clf = neighbours_fit(featureSet, valueVector)
elif model == 6:
output += "\nLOGISTIC\n"
clf = log_regression_fit(featureSet, valueVector)
elif model == 7:
output += "\nBAYESIANRIDGE\n"
clf = bayesian_ridge_fit(featureSet, valueVector)
else:
output += 'Invalid choice\n'
score = mean_squared_error(y_test, clf.predict(X_test))
score2 = r2_score(y_test, clf.predict(X_test))
cv = cross_validation.ShuffleSplit(featureSet.shape[0],
n_iter=50,
test_size=0.25,
random_state=0)
a = cross_validation.cross_val_score(clf, featureSet, valueVector, cv=cv)
a = a[a > 0]
output += 'Cross V score: :' + ' '.join("%10.3f" % x for x in a) + '\n'
output += ('Mean Score: %.3f\n' % np.mean(a))
output += ('Mean Squared Error: %.3f\n' % score)
output += ('R^2: %.3f\n' % score2)
return output
def runRegressionModelTest(featureSet, valueVector, X_test, y_test, model):
output = ''
score = 0
clf = 0
if model == 1:
output += "\nLINEAR REGRESSION\n"
clf = linear_regression_fit(featureSet, valueVector)
elif model == 2:
output += "\nSVR\n"
clf = SVR_fit(featureSet, valueVector)
elif model == 3:
output += "\nEXTREME LEARNING MACHINE\n"
clf = elm.ELMRegressor()
clf.fit(featureSet, valueVector)
joblib.dump(clf, 'elm.pkl')
elif model == 4:
output += "\nSTOCHASTIC\n"
clf = SGD_r_fit(featureSet, valueVector)
joblib.dump(clf, 'sgd.pkl')
elif model == 5:
output += "\nNEIGHBOURS\n"
clf = neighbours_fit(featureSet, valueVector)
elif model == 6:
output += "\nLOGISTIC\n"
clf = log_regression_fit(featureSet, valueVector)
elif model == 7:
output += "\nBAYESIANRIDGE\n"
clf = bayesian_ridge_fit(featureSet, valueVector)
else :
output += 'Invalid choice\n'
score = mean_squared_error(y_test, clf.predict(X_test))
score2 = r2_score(y_test, clf.predict(X_test))
cv = cross_validation.ShuffleSplit(featureSet.shape[0], n_iter=50,test_size=0.25,random_state=0)
a = cross_validation.cross_val_score(clf, featureSet, valueVector, cv=cv)
a = a[a > 0]
output += 'Cross V score: :' + ' '.join("%10.3f" % x for x in a) + '\n'
output += ('Mean Score: %.3f\n' % np.mean(a))
output += ('Mean Squared Error: %.3f\n' % score)
output += ('R^2: %.3f\n' % score2)
return output
def determine_NDGC(X,y,K,cv,clf_min,typev):
dt = getDateTime('timeData.npy')
NDGC = []
tau = []
print "K=",K
print "CV=",cv
for j in np.arange(0,cv):
# Train Classifier
score = 0
while score < clf_min:
shuffle_in_unison(X0,y0)
X,Xt,y,yt = cross_validation.train_test_split(X0,y0, test_size=0.3, random_state=0)
clf = SVR_fit(X,y)
#clf = linear_regression_fit(X, y)
score = r2_score(yt, clf.predict(Xt))
commList = []
N = len(Xt)
predicted = []
recorded = []
for i,row in enumerate(Xt):
predicted.append(clf.predict(row))
recorded.append(yt[i])
tau.append(stats.kendalltau(predicted, recorded)[0])
# bin the recorded values
recorded = binning_tuple(recorded,5)
for i, t in enumerate(recorded):
commList.append((predicted[i], t, dt[i]))
DCG = 0
iDCG = 0
ind = 1
sorted_by_ratio = sorted(commList, key=lambda tup: tup[1])[::-1]
rankedList = []
# Build Ranked List
for i,tup in enumerate(sorted_by_ratio):
rankedList.append((i+1, tup[0], tup[1], tup[2]))
# Sort by predictions
if typev == 1:
print "Classifier"
rankedList = sorted(rankedList, key=lambda tup: tup[1])[::-1]
if typev == 2:
print "TimeStamp"
rankedList = sorted(rankedList, key=lambda tup: tup[3])[::-1]
if typev == 3:
print "Random"
random.shuffle(rankedList)
ind = 1
for tup in rankedList:
fav = N - tup[0] + 1
rank = tup[2]
pow = 2**rank - 1
CG = rank/math.log(ind+1,2)
DCG += CG
if ind == K:
break;
ind += 1
# Sort by community
rankedList = sorted(rankedList, key=lambda tup: tup[2])[::-1]
#print "Ranked ratio List",rankedList
ind = 1
for tup in rankedList:
fav = N - tup[0] + 1
rank = tup[2]
pow = 2**rank - 1
CG = rank/math.log(ind+1,2)
iDCG += CG
if ind == K:
break;
ind += 1
print 'Test',j," - ", DCG/float(iDCG)
NDGC.append(DCG/float(iDCG))
return np.mean(NDGC), np.mean(tau)
