Similarity Metrics - In Parallel.py 文件源码

def parallel_jaccard_similarity(self,x,y):

        p = 16
        pool = mp.Pool(processes= p)

        chunk_X = []
        chunk_Y = []

        for i in range(0, len(x), p):

            chunk_X.append(x[int(i):int((i+1)*p)])
            chunk_Y.append(y[int(i):int((i+1)*p)])

        s = time.clock()

        intersection_cardinality = sum(pool.starmap(self.interc_card_locl, zip(chunk_X,chunk_Y)))
        union_cardinality = sum(pool.starmap(self.union_card_locl, zip(chunk_X,chunk_Y)))
        print(intersection_cardinality, union_cardinality)
        e = time.clock()
        print("Parallel Jaccard Exec Time: ", e-s)
        return intersection_cardinality/float(union_cardinality)