def test_as_discrete(self):
table = self.data
domain = table.domain
tr = AsCategorical()
dtr = []
for v in domain.variables:
vtr = apply_reinterpret(v, tr, table_column_data(table, v))
dtr.append(vtr)
tdomain = Domain(dtr)
ttable = table.transform(tdomain)
assert_array_equal(
ttable.X,
np.array([
[0, 2, 2, 1],
[1, 1, 3, 2],
[2, 0, 1, 3],
[1, 0, 0, 0],
], dtype=float)
)
self.assertEqual(tdomain["A"].values, ("a", "b", "c"))
self.assertEqual(tdomain["B"].values, ("0", "1", "2"))
self.assertEqual(tdomain["C"].values, ("0.0", "0.2", "0.25", "1.25"))
self.assertEqual(
tdomain["D"].values,
("1970-01-01 00:00:00", "1970-01-01 00:03:00",
"1970-01-01 00:06:00", "1970-01-01 00:12:00")
)
def test_reinterpret_string(self):
table = self.data_str
domain = table.domain
tvars = []
for v in domain.metas:
for i, tr in enumerate(
[AsContinuous(),
AsCategorical(),
AsTime(),
AsString()]):
vtr = apply_reinterpret(v, tr, table_column_data(
table, v)).renamed(f"{v.name}_{i}")
if isinstance(tr, AsTime):
strp = StrpTime("Detect automatically", None, 1, 1)
vtr = apply_transform_var(vtr, [strp])
tvars.append(vtr)
tdomain = Domain([], metas=tvars)
ttable = table.transform(tdomain)
assert_array_nanequal(
ttable.metas,
np.array([
[0.1, 0., np.nan, "0.1", 2010., 0., 1262304000., "2010"],
[1.0, 1., np.nan, "1.0", 2020., 1., 1577836800., "2020"],
],
dtype=object))
def test_reinterpret_string(self):
table = self.data_str
domain = table.domain
tvars = []
for v in domain.metas:
for tr in [AsContinuous(), AsCategorical(), AsTime(), AsString()]:
tr = apply_reinterpret(v, tr, table_column_data(table, v))
tvars.append(tr)
tdomain = Domain([], metas=tvars)
ttable = table.transform(tdomain)
assert_array_nanequal(
ttable.metas,
np.array([
[0.1, 0., np.nan, "0.1", 2010., 0., 1262304000., "2010"],
[1.0, 1., np.nan, "1.0", 2020., 1., 1577836800., "2020"],
],
dtype=object))
def test_reinterpret(self):
var = String("T", ())
for tr in (AsContinuous(), AsCategorical(), AsTime()):
t = report_transform(var, [tr])
self.assertIn("→ (", t)