Esempio n. 1
0
    def join(self, other, numPartitions=None):
        """
        Return an RDD containing all pairs of elements with matching keys in
        C{self} and C{other}.

        Each pair of elements will be returned as a (k, (v1, v2)) tuple, where
        (k, v1) is in C{self} and (k, v2) is in C{other}.

        Performs a hash join across the cluster.

        >>> x = sc.parallelize([("a", 1), ("b", 4)])
        >>> y = sc.parallelize([("a", 2), ("a", 3)])
        >>> sorted(x.join(y).collect())
        [('a', (1, 2)), ('a', (1, 3))]
        """
        return python_join(self, other, numPartitions)
Esempio n. 2
0
    def join(self, other, numPartitions=None):
        """
        Return an RDD containing all pairs of elements with matching keys in
        C{self} and C{other}.

        Each pair of elements will be returned as a (k, (v1, v2)) tuple, where
        (k, v1) is in C{self} and (k, v2) is in C{other}.

        Performs a hash join across the cluster.

        >>> x = sc.parallelize([("a", 1), ("b", 4)])
        >>> y = sc.parallelize([("a", 2), ("a", 3)])
        >>> sorted(x.join(y).collect())
        [('a', (1, 2)), ('a', (1, 3))]
        """
        return python_join(self, other, numPartitions)