def train(self, trainData, trainLabels,iteration):
for k in range(iteration):
for i in range(len(trainLabels)):
truth = trainLabels[i]
feature = features.featuresExtract(trainData[i],self.f)
predict = self.learnWeights(feature)
if predict != truth:
wt = self.weights[truth] + feature
wp = self.weights[predict] - feature
self.weights[truth] = wt
self.weights[predict] = wp
def train(self, trainData, trainLabels,iteration):
for k in range(iteration):
for i in range(len(trainLabels)):
truth = trainLabels[i]
feature = features.featuresExtract(trainData[i],self.f)
predict = self.learnWeights(feature)
if predict != truth:
wt = self.weights[truth] + feature
wp = self.weights[predict] - feature
self.weights[truth] = wt
self.weights[predict] = wp
def calConditionalProbabilities(self, data, labels):
"calculate P(F_i|Y)"
occurrence = {}
"first count the occurrence of all labels "
for i in range(len(labels)):
l = labels[i]
feature = features.featuresExtract(data[i],self.f)
if l not in occurrence:
occurrence[l] = np.array(feature)
else:
occurrence[l] += np.array(feature)
self.conds = {}
"then estimate the conditional probabilities with Adaptive Smoothing"
for l in labels:
self.conds[l] = np.divide(occurrence[l] + self.k, float(self.dist[l] + self.k * 2))
return self.conds
def calLogJointProbabilities(self, datum):
logJoint = {}
feature = features.featuresExtract(datum, self.f)
for l in self.dist.keys():
logConds = np.log(self.conds[l])
logCondsC = np.log(1 - self.conds[l])
logJoint[l] = np.sum(np.array(feature) * logConds, dtype=float)
logJoint[l] += np.sum((1 - np.array(feature)) * logCondsC,
dtype=float)
logJoint[l] += math.log(self.prior[l])
return logJoint
def calConditionalProbabilities(self, data, labels):
"calculate P(F_i|Y)"
occurrence = {}
"first count the occurrence of all labels "
for i in range(len(labels)):
l = labels[i]
feature = features.featuresExtract(data[i],self.f)
if l not in occurrence:
occurrence[l] = np.array(feature)
else:
occurrence[l] += np.array(feature)
self.conds = {}
"then estimate the conditional probabilities with Adaptive Smoothing"
for l in labels:
self.conds[l] = np.divide(occurrence[l] + self.k, float(self.dist[l] + self.k * 2))
return self.conds
def calConditionalProbabilities(self, data, labels):
occurrence = {}
for i in range(len(labels)):
l = labels[i]
feature = features.featuresExtract(data[i], self.f)
if l not in occurrence:
occurrence[l] = np.array(feature)
else:
occurrence[l] += np.array(feature)
self.conds = {}
for l in labels:
self.conds[l] = np.divide(occurrence[l] + self.k,
float(self.dist[l] + self.k * 2))
return self.conds
def calLogJointProbabilities(self, datum):
"calculate the log of joint probability"
logJoint = {}
feature = features.featuresExtract(datum,self.f)
for l in self.dist.keys():
"the log of P(f_i=1|Y=y)"
logConds = np.log(self.conds[l])
"the log of P(f_i=0|Y=y)"
logCondsC = np.log(1 - self.conds[l])
"""
feature is an Indicator array of which features equal to 1
1-feature is an Indicator array of which features equal to 0
sum of dot product between Indicator array and logP(f_i|Y=y) calculates total
"""
logJoint[l] = np.sum(np.array(feature) * logConds, dtype=float)
logJoint[l] += np.sum((1 - np.array(feature)) * logCondsC, dtype=float)
"adding up the log of P(Y=y)"
logJoint[l] += math.log(self.prior[l])
return logJoint
def calLogJointProbabilities(self, datum):
"calculate the log of joint probability"
logJoint = {}
feature = features.featuresExtract(datum,self.f)
for l in self.dist.keys():
"the log of P(f_i=1|Y=y)"
logConds = np.log(self.conds[l])
"the log of P(f_i=0|Y=y)"
logCondsC = np.log(1 - self.conds[l])
"""
feature is an Indicator array of which features equal to 1
1-feature is an Indicator array of which features equal to 0
sum of dot product between Indicator array and logP(f_i|Y=y) calculates total
"""
logJoint[l] = np.sum(np.array(feature) * logConds, dtype=float)
logJoint[l] += np.sum((1 - np.array(feature)) * logCondsC, dtype=float)
"adding up the log of P(Y=y)"
logJoint[l] += math.log(self.prior[l])
return logJoint
def classify(self, testData):
guess = []
for datum in testData:
feature = features.featuresExtract(datum,self.f)
guess.append(self.learnWeights(feature))
return guess
def classify(self, testData):
guess = []
for datum in testData:
feature = features.featuresExtract(datum,self.f)
guess.append(self.learnWeights(feature))
return guess
