lsi.py 文件源码

def _getCscMatrix(self):#compressed sparse column matrix
        if self._cscMatrix is not None:
            return self._cscMatrix
        # data and indices are parallel arrays,
        # data storing values (ie tf*idf) and indices storing values
        num_nnz, data, indices, indptr = 0, [], [], [0]
        for termVector in self._termVectors:
            newIndices = [i for i in termVector[1].keys()]
            newValues = [v for v in termVector[1].values()]
            indices.extend(newIndices)
            data.extend(newValues)
            num_nnz += len(newValues)
            indptr.append(num_nnz)
        data = numpy.asarray(data)
        indices = numpy.asarray(indices)
        # compressed sparse column matrix
        # Rows terms, column docs
        #
        #        doc1   doc2   doc3
        # 'the'    1      1     1
        # 'cat'    1      0     2
        self._cscMatrix = scipy.sparse.csc_matrix((data, indices, indptr),
                shape=(self.numTerms, self.numDocs))
        return self._cscMatrix