@pytest.fixture def n_rows(): return 20

@pytest.fixture def n_cols(): return 10

@pytest.fixture def x_norm(n_rows, n_cols): return np.random.randn(n_rows, n_cols)

# At this point, the data is loaded into memory on the workers and you don't # need to attack disk again, so this operation is very fast messages.filter(lambda x: x.find("php") > -1).count()