def avg(data, column):
global __is_aggregate
__is_aggregate = True
vals = [row[column] for row in data]
data = parallel.run(parallel.map(
lambda chunk: [(sum([int(line) for line in chunk]), len(chunk))]),
vals,
'avg()'
)
dividend = parallel.run(parallel.reduce(lambda data: sum([d[0] for d in data], 0.0)), data)
divisor = parallel.run(parallel.reduce(lambda data: sum([d[1] for d in data])), data)
return sum(dividend)/sum(divisor)
def simple_test():
data = [i for i in range(1, 5)]
expected = [i * i for i in data]
def f(x):
z = x * x
l = list(z)
d = dict(x=z, y=z)
s = str(d)
return z
result = parallel.map(f, data)
print(result)
def simple_test():
data = [ i for i in range(1, 5) ]
expected = [ i*i for i in data ]
def f(x):
z = x * x
l = list(z)
d = dict(x=z, y=z)
s = str(d)
return z
result = parallel.map(f, data)
print(result)