def supportFunction(rawX, rawY, rawXTesting, rawYTesting):
X = [elem[0:1] for elem in rawX]
Y = rawY
senses = [elem[2] for elem in rawX]
words = [elem[3] for elem in rawX]
#modelr = svm.SVR()
modelr = sup.SVC(kernel = 'poly', degree = 2, probability = True)
modelr.fit(X,Y)
# This part needs to be changed to sample
sampleX = [elem[0:1] for elem in rawXTesting]
sampleY = rawYTesting
q = modelr.predict_proba(sampleX)
predictedProb = [elem[1] for elem in q]
predictedY = evaluation.getPredictedY(words, senses, predictedProb, rawXTesting, rawYTesting)
return evaluation.evaluationMetrics(sampleY, predictedY)
def supportFunction(rawX, rawY, rawXTesting, rawYTesting):
X = [elem[0:1] for elem in rawX]
Y = rawY
senses = [elem[2] for elem in rawX]
words = [elem[3] for elem in rawX]
#modelr = svm.SVR()
modelr = sup.SVC(kernel='poly', degree=2, probability=True)
modelr.fit(X, Y)
# This part needs to be changed to sample
sampleX = [elem[0:1] for elem in rawXTesting]
sampleY = rawYTesting
q = modelr.predict_proba(sampleX)
predictedProb = [elem[1] for elem in q]
predictedY = evaluation.getPredictedY(words, senses, predictedProb,
rawXTesting, rawYTesting)
return evaluation.evaluationMetrics(sampleY, predictedY)
def kmeansFunction(rawX, rawY, rawXTesting, rawYTesting):
X = [elem[0:1] for elem in rawX]
Y = rawY
senses = [elem[2] for elem in rawX]
words = [elem[3] for elem in rawX]
modelk = cluster.KMeans(n_clusters = 2)
modelk.fit(X)
# This part needs to be changed to sample
sampleX = [elem[0:1] for elem in rawXTesting]
sampleY = rawYTesting
q = modelk.transform(sampleX)
# This gives distance to the new "clusters"
predictedProb = [-elem[1] for elem in q]
# Note we use negative since we want lower distance!
predictedY = evaluation.getPredictedY(words, senses, predictedProb, rawXTesting, rawYTesting)
return evaluation.evaluationMetrics(sampleY, predictedY)
def multinomialNB(rawX, rawY, rawXTesting, rawYTesting): X = np.array([[elem[0], elem[1]] for elem in rawX]) # relatedness and commonness senses = [elem[2] for elem in rawX] # which sense it comes from words = [elem[3] for elem in rawX] # which word it comes from Y = np.array(rawY) clf = BernoulliNB(alpha = 0.0, class_prior = None, fit_prior = True) # clf = MultinomialNB(alpha = 0.1, class_prior = None, fit_prior = True) clf.fit(X, Y) # This part needs to be changed to a sample sampleX = np.array([[elem[0], elem[1]] for elem in rawXTesting]) sampleY = np.array(rawYTesting) q = clf.predict_proba(sampleX) predictedProb = [elem[1] for elem in q] predictedY = evaluation.getPredictedY(words, senses, predictedProb, rawXTesting, rawYTesting) return evaluation.evaluationMetrics(sampleY, predictedY)
def multinomialNB(rawX, rawY, rawXTesting, rawYTesting):
X = np.array([[elem[0], elem[1]]
for elem in rawX]) # relatedness and commonness
senses = [elem[2] for elem in rawX] # which sense it comes from
words = [elem[3] for elem in rawX] # which word it comes from
Y = np.array(rawY)
clf = BernoulliNB(alpha=0.0, class_prior=None, fit_prior=True)
# clf = MultinomialNB(alpha = 0.1, class_prior = None, fit_prior = True)
clf.fit(X, Y)
# This part needs to be changed to a sample
sampleX = np.array([[elem[0], elem[1]] for elem in rawXTesting])
sampleY = np.array(rawYTesting)
q = clf.predict_proba(sampleX)
predictedProb = [elem[1] for elem in q]
predictedY = evaluation.getPredictedY(words, senses, predictedProb,
rawXTesting, rawYTesting)
return evaluation.evaluationMetrics(sampleY, predictedY)