3fd9809dfdfcf47bf34a9f9a780277abaae76105,docsim.py,SimilarityABC,__iter__,#SimilarityABC#,47

Before Change

        
        for docNo, doc in enumerate(self.corpus):
            // compute cosine similarity against every other document in the collection
            allSims = self[doc]
            
            // return either all similarities as a list, or only self.numBest most similar, depending on settings from the constructor
            if self.numBest is None:
                yield allSims
            else:
                tops = [(docNo, sim) for docNo, sim in enumerate(allSims) if sim > 0]
                tops = sorted(tops, key = lambda item: -item[1]) // sort by -sim => highest cossim first
                yield tops[ : self.numBest] // return at most numBest top 2-tuples (docId, docSim)
//endclass SimilarityABC
        

class Similarity(SimilarityABC):
    
    Compute cosine similary against a corpus of documents. This is done by a full 
    sequential scan of the corpus. If your corpus is reasonably small (fits in RAM), 

After Change

        and yield the result.
        
        for docNo, doc in enumerate(self.corpus):
            yield self[doc]
//endclass SimilarityABC
        

class Similarity(SimilarityABC):

Instances