]
type = ['(TEST)', '(TRAIN)']
scaled = ['(PLAIN)', '(NORMALIZED)']
col = 8
valueCol = 4
bincount = 500
values = True
features = False
timeData = False
if __name__ == '__main__':
tempCWD = os.getcwd()
os.chdir('D:\Workspace\NLTK comments\src\RatingPrediction')
X, y, wd, td, out = getDataSets(normalize=False, selected=False)
y = y[:, valueCol]
print np.min(y)
print np.max(y)
print np.mean(y)
print 'Loaded testing data\n'
X_scaled = preprocessing.scale(X)
print "Scaled testing Features\n"
X_binned = binScaling(X[:, col], 10)
print 'Binned Features'
print 'Number of training rows:', len(X)
os.chdir(tempCWD)
break;
ind += 1
print 'Test',j," - ", DCG/float(iDCG)
NDGC.append(DCG/float(iDCG))
return np.mean(NDGC), np.mean(tau)
reg = True
value = 1
feature = 1
if __name__ == '__main__':
X0, y0, wordData,topicData,socialData, out = getDataSets(normalize=True, selected=False)
y0 = y0[:,value]
print out
#test(X,y)
if feature == 0:
X0 = X0
elif feature == 1:
X0 = wordData
elif feature == 2:
X0 = topicData
elif feature == 3:
X0 = np.hstack((X0,wordData))
elif feature == 4:
X0 = np.hstack((X0,topicData))
]
type = ["(TEST)", "(TRAIN)"]
scaled = ["(PLAIN)", "(NORMALIZED)"]
col = 8
valueCol = 4
bincount = 500
values = True
features = False
timeData = False
if __name__ == "__main__":
tempCWD = os.getcwd()
os.chdir("D:\Workspace\NLTK comments\src\RatingPrediction")
X, y, wd, td, out = getDataSets(normalize=False, selected=False)
y = y[:, valueCol]
print np.min(y)
print np.max(y)
print np.mean(y)
print "Loaded testing data\n"
X_scaled = preprocessing.scale(X)
print "Scaled testing Features\n"
X_binned = binScaling(X[:, col], 10)
print "Binned Features"
print "Number of training rows:", len(X)
os.chdir(tempCWD)