0cdbd836f44e9351e769b2504d82680af838927f,pliers/extractors/text.py,WordCounterExtractor,_extract,#WordCounterExtractor#Any#,419

Before Change

            
        word_counter = pd.Series(tokens).value_counts()
        
        return ExtractorResult(list(word_counter), stim,
                               self, features=list(word_counter.index)) //still in progress

After Change

            tokens = {k: pos_map[v] if v in pos_map else "n" for k, v in tokens.items()}
            tokens = [lemmatizer.lemmatize(k, pos=v) for k, v in tokens.items()]
        
        word_counter = pd.Series(tokens).groupby(tokens).cumcount()
        
        results = []
        for i, count in enumerate(word_counter):
            results.append(ExtractorResult([count], stims[i], self,
                                features=["word_counter"]))
        return results

Instances