def test_read_csv():
import nums
from nums.core import settings
settings.system_name = "serial"
filename = settings.pj(settings.project_root, "tests", "core", "storage", "test.csv")
ba = nums.read_csv(filename, has_header=True)
assert np.allclose(ba[0].get(), [123, 4, 5])
assert np.allclose(ba[-1].get(), [1.2, 3.4, 5.6])
def test_modin(nps_app_inst):
import nums
import nums.numpy as nps
import modin.pandas as mpd
from nums.core import settings
from nums.core.systems.systems import RaySystem
if not isinstance(nps_app_inst.cm.system, RaySystem):
return
filename = settings.pj(settings.project_root, "tests", "core", "storage",
"test.csv")
ba1 = nums.read_csv(filename, has_header=True)
df = mpd.read_csv(filename)
ba2: BlockArray = nums.from_modin(df)
assert nps.allclose(ba1, ba2)
dtype=nps.int.__name__,
),
cm,
)
for grid_entry in X.grid.get_entry_iterator():
i = grid_entry[0]
X_block: Block = X.blocks[grid_entry]
r_block: Block = result.blocks[i]
syskwargs = {
"grid_entry": grid_entry,
"grid_shape": X.grid.grid_shape
}
r_block.oid = cm.call("xgb_predict",
model_block.oid,
X_block.oid,
syskwargs=syskwargs)
return result
if __name__ == "__main__":
from nums.core import settings
import nums
filename = settings.pj(settings.project_root, "tests", "core", "storage",
"test.csv")
X: BlockArray = nums.read_csv(filename, has_header=True)
y: BlockArray = nps.random.random_sample(X.shape[0])
model = XGBClassifier()
model.fit(X, y)
print(model.predict(X).get())