29b533feef93e61a61d4a935805ae1563583de2f,matutils.py,MmReader,__iter__,#MmReader#,138

Before Change

                prevId = docId
                document = []
            // add (termId, weight) pair to the document
            document.append((int(termId) - 1, float(val),)) // -1 because matrix market indexes are 1-based => convert to 0-based
        if prevId is not None: // handle the last document, as a special case
            yield prevId, document
//endclass MmReader

After Change

                                
                // return implicit (empty) documents between previous id and new id 
                // too, to keep consistent document numbering and corpus length
                for prevId in xrange(prevId + 1, docId):
                    yield prevId, []
                
                // from now on start adding fields to a new document, with a new id
                prevId = docId
                document = []
            
            document.append((termId, val,)) // add another field to the current document

Instances