def _test_common(self, var):
tr = [Rename(var.name + "_copy"), Annotate((("A", "1"), ))]
XX = apply_transform_var(var, tr)
self.assertEqual(XX.name, var.name + "_copy")
self.assertEqual(XX.attributes, {"A": 1})
self.assertIsInstance(XX.compute_value, Identity)
self.assertIs(XX.compute_value.variable, var)
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_discrete_reorder(self):
D = DiscreteVariable("D", values=("2", "3", "1", "0"))
DD = apply_transform_var(D, [
CategoriesMapping((("0", "0"), ("1", "1"), ("2", "2"), ("3", "3")))
])
self.assertSequenceEqual(DD.values, ["0", "1", "2", "3"])
self._assertLookupEquals(DD.compute_value,
Lookup(D, np.array([2, 3, 1, 0])))
def test_discrete_merge(self):
D = DiscreteVariable("D", values=("2", "3", "1", "0"))
mapping = (
("0", "x"),
("1", "y"),
("2", "x"),
("3", "y"),
)
tr = [CategoriesMapping(mapping)]
DD = apply_transform_var(D, tr)
self.assertSequenceEqual(DD.values, ["x", "y"])
self._assertLookupEquals(DD.compute_value,
Lookup(D, np.array([0, 1, 1, 0])))
def test_discrete_add_drop(self):
D = DiscreteVariable("D", values=("2", "3", "1", "0"))
mapping = (
("0", None),
("1", "1"),
("2", "2"),
("3", None),
(None, "A"),
)
tr = [CategoriesMapping(mapping)]
DD = apply_transform_var(D, tr)
self.assertSequenceEqual(DD.values, ["1", "2", "A"])
self._assertLookupEquals(DD.compute_value,
Lookup(D, np.array([1, np.nan, 0, np.nan])))
def test_as_time(self):
# this test only test type of format that can be string, continuous and discrete
# correctness of time formats is already tested in TimeVariable module
d = TimeVariable("_").parse_exact_iso
times = (
["07.02.2022", "18.04.2021"], # date only
["07.02.2022 01:02:03", "18.04.2021 01:02:03"], # datetime
["010203", "010203"], # time
["02-07", "04-18"],
)
formats = ["25.11.2021", "25.11.2021 00:00:00", "000000", "11-25"]
expected = [
[d("2022-02-07"), d("2021-04-18")],
[d("2022-02-07 01:02:03"),
d("2021-04-18 01:02:03")],
[d("01:02:03"), d("01:02:03")],
[d("1900-02-07"), d("1900-04-18")],
]
variables = [StringVariable(f"s{i}") for i in range(len(times))]
variables += [
DiscreteVariable(f"d{i}", values=t) for i, t in enumerate(times)
]
domain = Domain([], metas=variables)
metas = [t for t in times] + [list(range(len(x))) for x in times]
table = Table(domain,
np.empty((len(times[0]), 0)),
metas=np.array(metas).transpose())
tr = AsTime()
dtr = []
for v, f in zip(domain.metas, chain(formats, formats)):
strp = StrpTime(f, *TimeVariable.ADDITIONAL_FORMATS[f])
vtr = apply_transform_var(
apply_reinterpret(v, tr, table_column_data(table, v)), [strp])
dtr.append(vtr)
ttable = table.transform(Domain([], metas=dtr))
assert_array_equal(
ttable.metas,
np.array(list(chain(expected, expected)), dtype=float).transpose())
def test_ordered_change(self):
D = DiscreteVariable("D", values=("a", "b"), ordered=True)
Do = apply_transform_var(D, [ChangeOrdered(False)])
self.assertFalse(Do.ordered)
def test_discrete_rename(self):
D = DiscreteVariable("D", values=("a", "b"))
DD = apply_transform_var(D,
[CategoriesMapping((("a", "A"), ("b", "B")))])
self.assertSequenceEqual(DD.values, ["A", "B"])
self.assertIs(DD.compute_value.variable, D)
