def test_dataset():
ns = {'t': df, 'x': 10}
cache = dict()
d = CachedDataset(ns, cache=cache)
assert discover(d) == discover(ns)
s = symbol('s', discover(d))
compute(s.x * 2, d) == 20
cache == {s.x * 2: 20}
def test_streaming():
seq = [{'name': 'Alice', 'x': 1}, {'name': 'Bob', 'x': 1}]
ns = {'t': seq, 'x': 10}
cache = dict()
d = CachedDataset(ns, cache=cache)
s = symbol('s', discover(d))
expr = s.t.x * 2
result = compute(expr, d)
assert not isinstance(d.cache[expr], Iterator)
assert into(list, d.cache[expr]) == [2, 2]
def test_pre_compute_on_multiple_datasets_is_selective():
from odo import CSV
from blaze import Data
from blaze.cached import CachedDataset
df = pd.DataFrame(
[[1, 'Alice', 100], [2, 'Bob', -200], [3, 'Charlie', 300],
[4, 'Denis', 400], [5, 'Edith', -500]],
columns=['id', 'name', 'amount'])
iris = CSV(example('iris.csv'))
dset = CachedDataset({'df': df, 'iris': iris})
d = Data(dset)
assert str(compute(d.df.amount)) == str(df.amount)