from sspark.Context import Context
from operator import add
if __name__ == "__main__":
print("RUNNING...");
sc = Context()
rdd = sc.parallelize([1,2,3,4,5])
rdd.keyBy(lambda x: x*x).collect()
from sspark.Context import Context
from operator import add
if __name__ == "__main__":
print("RUNNING...");
sc = Context()
rdd = sc.parallelize([("a", -1), ("b",0), ("a", 1)])
print(sorted(rdd.countByKey().items()))
from sspark.Context import Context
from operator import add
if __name__ == "__main__":
print("JOIN sample...");
sc = Context()
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))]'''