def validateByFrequency(self, x, y, model):
totalCorrect = 0
for i in range(self.k):
(foldTrainX, foldTrainY, foldValidationX, foldValidationY) = self.__splitDataFold(x, y, i)
frequencyTable = FeatureSelection.byFrequency(foldTrainX)
words = [word for word,_ in frequencyTable[:10]]
print('For fold %d/%d, choose words:' % (i + 1, self.k))
print(words)
(xNewTrain, xNewValidation) = FeatureSelection.Featurize(foldTrainX, foldValidationX, words)
model.fit(xNewTrain, foldTrainY)
totalCorrect += self.__countCorrect(model.predict(xNewValidation), foldValidationY)
accuracy = totalCorrect / len(x)
return accuracy
testAccuracy = EvaluationsStub.Accuracy(yTest, yTestPredicted)
print("Test Set Accuracy is %f" % (testAccuracy))
print("Train with all 5 features")
model.fit(xTrain, yTrain, iterations=50000, step=0.01)
yTestPredicted = model.predict(xTest)
testAccuracy = EvaluationsStub.Accuracy(yTest, yTestPredicted)
print("Test Set Accuracy is %f" % (testAccuracy))
############################
import FeatureSelection
print('### Get the Frequency Table')
frequencyTable = FeatureSelection.byFrequency(xTrainRaw)
print('Top 10')
for i in range(10):
print(frequencyTable[i])
#############################
print('### Get the Mutual Information Table')
mutualInformationTable = FeatureSelection.byMutualInformation(
xTrainRaw, yTrain)
print('Top 10')
for i in range(10):
print(mutualInformationTable[i])
#############################
