def testDataFrameSeries(self, *_):
service_ep = 'http://127.0.0.1:' + self.web_port
scheduler_ep = '127.0.0.1:' + self.scheduler_port
with new_session(service_ep) as sess:
raw1 = pd.Series(np.random.rand(100, ))
data1 = md.Series(raw1, chunk_size=40)
data1.execute(name='series', session=sess)
raw2 = pd.DataFrame(np.random.rand(100, 10))
data2 = mt.tensor(raw2, chunk_size=60)
data2.execute(name='dataframe', session=sess)
with DistributedContext(scheduler_address=scheduler_ep,
session_id=sess.session_id):
t1 = md.named_series(name='series', session=sess)
t2 = md.named_dataframe(name='dataframe', session=sess)
dataset = MarsDataset(t1, t2)
self.assertEqual(len(dataset), 100)
sampler = MarsDistributedSampler(dataset,
num_replicas=1,
rank=0)
indices = sampler.generate_indices()
r1 = np.array(dataset._get_data(indices)[0])
r2 = np.array([dataset[ind][0] for ind in sampler])
np.testing.assert_array_equal(r1, r2)
r1 = np.array(dataset._get_data(indices)[1])
r2 = np.array([dataset[ind][1] for ind in sampler])
np.testing.assert_array_equal(r1, r2)
def testNamed(self):
rs = np.random.RandomState(0)
raw = rs.rand(10, 10)
sess = Session.default_or_local()
# test named tensor
t = mt.tensor(raw, chunk_size=3)
name = 't_name'
r1 = t.execute(name=name, session=sess)
np.testing.assert_array_equal(r1, raw)
t2 = mt.named_tensor(name=name, session=sess)
self.assertEqual(t2.order, TensorOrder.C_ORDER)
r2 = (t2 + 1).execute(session=sess).fetch()
np.testing.assert_array_equal(r2, raw + 1)
# test named series
name = 's_name'
raw = pd.Series([1, 2, 3])
s = md.Series(raw)
r1 = s.execute(name=name, session=sess).fetch()
pd.testing.assert_series_equal(r1, raw)
s2 = md.named_series(name=name, session=sess)
self.assertEqual(s2.dtype, s.dtype)
pd.testing.assert_index_equal(s2.index_value.to_pandas(),
s.index_value.to_pandas())
r2 = s2.execute(session=sess).fetch()
pd.testing.assert_series_equal(r2, raw)
# test dataframe
name = 'd_name'
raw = pd.DataFrame(np.random.rand(10, 3))
d = md.DataFrame(raw, chunk_size=4)
r1 = d.execute(name=name, session=sess).fetch()
pd.testing.assert_frame_equal(r1, raw)
d2 = md.named_dataframe(name=name, session=sess)
pd.testing.assert_series_equal(d2.dtypes, d.dtypes)
pd.testing.assert_index_equal(d2.index_value.to_pandas(),
d.index_value.to_pandas())
pd.testing.assert_index_equal(d2.columns_value.to_pandas(),
d.columns_value.to_pandas())
r2 = d2.execute(session=sess).fetch()
pd.testing.assert_frame_equal(r2, raw)
def testNamed(self):
rs = np.random.RandomState(0)
raw = rs.rand(10, 10)
sess = Session.default_or_local()
# test named tensor
t = mt.tensor(raw, chunk_size=3)
name = 't_name'
r1 = t.execute(name=name, session=sess)
np.testing.assert_array_equal(r1, raw)
t2 = mt.named_tensor(name=name, session=sess)
r2 = (t2 + 1).execute(session=sess).fetch()
np.testing.assert_array_equal(r2, raw + 1)
# test named series
name = 's_name'
raw = pd.Series([1, 2, 3])
s = md.Series(raw)
r1 = s.execute(name=name, session=sess).fetch()
pd.testing.assert_series_equal(r1, raw)
s2 = md.named_series(name=name, session=sess)
r2 = s2.execute(session=sess).fetch()
pd.testing.assert_series_equal(r2, raw)
# test dataframe
name = 'd_name'
raw = pd.DataFrame(np.random.rand(10, 3))
d = md.DataFrame(raw, chunk_size=4)
r1 = d.execute(name=name, session=sess).fetch()
pd.testing.assert_frame_equal(r1, raw)
d2 = md.named_dataframe(name=name, session=sess)
r2 = d2.execute(session=sess).fetch()
pd.testing.assert_frame_equal(r2, raw)
