06e94610dc2d71997ca567b45df02f5ea7613a81,apps/analyzer/classifier.py,Classifier,get_features,#Classifier#Any#,15

Before Change

        self.feed = feed

    def get_features(self, doc):
        splitter=re.compile("\\W*")
        // Split the words by non-alpha characters
        words=[s.lower() for s in splitter.split(doc) 
              if len(s)>2 and len(s)<20]
  
        // Return the unique set of words only
        return dict([(w,1) for w in words])
        
    def increment_feature(self, feature, category):
        count = self.feature_count(feature,category)

After Change

    def get_features(self, doc):
        found = {}
        
        for phrase in self.phrases:
            if phrase in doc:
                if phrase in found:
                    found[phrase] += 1
                else:
                    found[phrase] = 1

        return found
        
    def increment_feature(self, feature, category):
        count = self.feature_count(feature,category)

Instances