def predict(self, Xtest):
testSize = Xtest.shape[0]
ytest = np.zeros(testSize)
for index in range(testSize):
testData = Xtest[index, 0:self.lastCol]
prob0 = 0
prob1 = 0
for ft in range(self.lastCol):
try:
prob0 += log(
utils.calculateprob(Xtest[index,
ft], self.class0Mean[ft, ],
self.class0Std[ft, ]))
prob1 += log(
utils.calculateprob(Xtest[index,
ft], self.class1Mean[ft, ],
self.class1Std[ft, ]))
except ValueError:
if utils.calculateprob(Xtest[index,
ft], self.class0Mean[ft, ],
self.class0Std[ft, ]) == 0:
prob0 += 0
elif utils.calculateprob(Xtest[index,
ft], self.class1Mean[ft, ],
self.class1Std[ft, ]) == 0:
prob1 += 0
ytest[index] = np.float64(0) if prob0 > prob1 else np.float(1)
return ytest
def predict(self, Xtest):
if self.params['notusecolumnones']:
Xtest = Xtest[:, np.array(xrange(Xtest.shape[1] - 1))]
#ttemp=self.skGNB.predict(Xtest)
'''
print self.skGNB.theta_
print self.sigma
print ""
print ""
print self.skGNB.sigma_
print self.variance
'''
dim = [Xtest.shape[0], Xtest.shape[1]]
probNB1 = [[
utils.calculateprob(Xtest[r, c], self.sigma[1][c],
math.sqrt(self.variance[1][c]))
for c in xrange(dim[1])
] for r in xrange(dim[0])]
#print "Shape Of probNB1",len(probNB1),len(probNB1[0])
probNB0 = [[
utils.calculateprob(Xtest[r, c], self.sigma[0][c],
math.sqrt(self.variance[0][c]))
for c in xrange(dim[1])
] for r in xrange(dim[0])]
NB1MLPR = (np.prod(probNB1, axis=1)) * self.probY[1]
#print "Shape of NB1MLPR",len(NB1MLPR)
#print NB1MLPR
NB0MLPR = (np.prod(probNB0, axis=1)) * self.probY[0]
ytest = [1 if NB1MLPR[x] > NB0MLPR[x] else 0 for x in xrange(dim[0])]
return ytest
def predict(self, Xtest):
# noOfFeatures = Xtest.shape[1]
if not self.getparams()['usecolumnones']:
Xtest = Xtest[:, :-1]
ytest = np.zeros(Xtest.shape[0])
for i in range(0, Xtest.shape[0]):
prob_Class0 = self.ymean_Class0
prob_Class1 = self.ymean_Class1
for j in range(0, len(self.mean_Class0)):
prob_Class0 = prob_Class0 * utils.calculateprob(Xtest[i][j], self.mean_Class0[j], self.std_Class0[j])
prob_Class1 = prob_Class1 * utils.calculateprob(Xtest[i][j], self.mean_Class1[j], self.std_Class1[j])
if prob_Class0 < prob_Class1:
ytest[i] = 1
return ytest
def predict(self, Xtest):
Xtest = Xtest[:,0:self.features]
numsamples = Xtest.shape[0]
ytest = np.empty(numsamples)
for i in xrange(numsamples):
zeroprobs = self.priozero
oneprobs = self.prioone
for f in xrange(self.features):
zeroprobs = zeroprobs * utils.calculateprob(Xtest[i,f], self.meanstdev[0,0,f], self.meanstdev[0,1,f])
oneprobs = oneprobs * utils.calculateprob(Xtest[i,f], self.meanstdev[1,0,f], self.meanstdev[1,1,f])
if (zeroprobs <= oneprobs):
ytest[i] = 1
else:
ytest[i] = 0
return ytest
def likelihoodcal(self, dpt, distparams, featurelength):
if featurelength >= 0:
mu = distparams[featurelength]['mu']
sigma = distparams[featurelength]['sigma']
j = utils.calculateprob(dpt[featurelength], mu, sigma)
return j * self.likelihoodcal(dpt, distparams, featurelength-1)
else:
return 1
def likelihoodcal(self, dpt, distparams, featurelength):
if featurelength >= 0:
mu = distparams[featurelength]['mu']
sigma = distparams[featurelength]['sigma']
j = utils.calculateprob(dpt[featurelength], mu, sigma)
return j * self.likelihoodcal(dpt, distparams, featurelength - 1)
else:
return 1
def probbydivide(self, dividedDS, Xtest):
prob = {}
for val, var in dividedDS.items():
prob[val] = 1
for i in range(len(var)):
mean, stdev = var[i]
x = Xtest[i]
probability = utils.calculateprob(x, mean, stdev)
prob[val] = prob[val] * probability
return prob
def probbydivide(self,dividedDS, Xtest):
prob = {}
for val, var in dividedDS.items():
prob[val] = 1
for i in range(len(var)):
mean, stdev = var[i]
x = Xtest[i]
probability=utils.calculateprob(x, mean, stdev)
prob[val]=prob[val]* probability
return prob
def calculate_best(self, x):
probability1 = 1
probability0 = 1
# computing product of all p(x_i|y)
for i in range(0, len(x)):
# probability of zero happening, ignoring the denom and the 1/2 at the beginning since they are the same for both
probability0 *= utils.calculateprob(x[i], self.mv0[i][0],
self.mv0[i][1])
# probability of one happening, ignoring the denom and the 1/2 at the beginning since they are the same for both
probability1 *= utils.calculateprob(x[i], self.mv1[i][0],
self.mv1[i][1])
# now multiplty by p(y)
probability0 *= self.freq0
probability1 *= self.freq1
# pick the larger of the two probabilities
if (probability0 > probability1):
return 0
else:
return 1
def pred(xvec):
p = {}
for Value, groups in self.groupings.iteritems():
#class0: (mean1,stddev1), (mean2,stddev2)....
#class1: (mean1,stddev1), (mean2,stddev2)....
p[Value] = 1
for i in range(len(groups)):
mean, stdev = groups[i]
x = xvec[i]
p[Value] *= utils.calculateprob(x, mean, stdev)
#only for 2 classes
if p[0] > p[1]: return 0
else: return 1
def predict(self, Xtest):
if self.params['usecolumnones'] == False:
Xtest = Xtest[:, :-1]
ytest = []
for row in Xtest:
p_zero = 1
p_one = 1
for datapoint_index in range(row.shape[0]):
p_zero = p_zero * (utils.calculateprob(
row[datapoint_index],
self.Xtrain_Zero_Mean[datapoint_index],
self.Xtrain_Zero_Std[datapoint_index]))
p_one = p_one * (utils.calculateprob(
row[datapoint_index],
self.Xtrain_One_Mean[datapoint_index],
self.Xtrain_One_Std[datapoint_index]))
if p_one >= p_zero:
ytest.append(1)
else:
ytest.append(0)
return ytest
def predict(self, Xtest):
predictions = []
for tt in range(Xtest.shape[0]):
inputVector = Xtest[tt]
probabilities = {}
for classValue, classSummaries in self.summaries.iteritems():
probabilities[classValue] = 1
for i in range(len(classSummaries)):
mean, stdev = classSummaries[i]
x = inputVector[i]
probabilities[classValue] *= utils.calculateprob(x, mean, stdev)
bestLabel, bestProb = None, -1
for classValue, probability in probabilities.iteritems():
if bestLabel is None or probability > bestProb:
bestProb = probability
bestLabel = classValue
predictions.append(bestLabel)
return predictions
def predict(self, Xtest):
predictions = []
for tt in range(Xtest.shape[0]):
inputVector = Xtest[tt]
probabilities = {}
for classValue, classSummaries in self.summaries.iteritems():
probabilities[classValue] = 1
for i in range(len(classSummaries)):
mean, stdev = classSummaries[i]
x = inputVector[i]
probabilities[classValue] *= utils.calculateprob(
x, mean, stdev)
bestLabel, bestProb = None, -1
for classValue, probability in probabilities.iteritems():
if bestLabel is None or probability > bestProb:
bestProb = probability
bestLabel = classValue
predictions.append(bestLabel)
return predictions
def predict(self, Xtest):
ytest = []
for i in range(0, Xtest.shape[0]):
feat_prob_all = []
for k in range(0, 2):
feat_prob = []
for j in range(0, self.nof):
featname = "Feature" + str(j)
mean = self.prob_table[featname][k]["mu"]
stdev = self.prob_table[featname][k]["sig"]
fprob = utils.calculateprob(Xtest[i, j], mean, stdev)
feat_prob.append(fprob)
feat_prob_all.append(feat_prob)
prob_pos = np.prod(np.array(feat_prob_all[0])) * self.prior_prob[0]
prob_neg = np.prod(np.array(feat_prob_all[1])) * self.prior_prob[1]
if prob_pos > prob_neg:
ytest.append(0)
else:
ytest.append(1)
ytest = np.asarray(ytest)
return ytest
