def preProcessExamples(self, allExamples): # Duplicates cannot be removed here, as they should only be removed from the training set. This is done # in the classifier. # if "no_duplicates" in self.styles: # count = len(allExamples) # print >> sys.stderr, " Removing duplicates,", # allExamples = ExampleUtils.removeDuplicates(allExamples) # print >> sys.stderr, "removed", count - len(allExamples) if "normalize" in self.styles: print >> sys.stderr, " Normalizing feature vectors" ExampleUtils.normalizeFeatureVectors(allExamples) return allExamples
def preProcessExamples(self, allExamples): if "normalize" in self.styles: print >> sys.stderr, " Normalizing feature vectors" ExampleUtils.normalizeFeatureVectors(allExamples) return allExamples