def test_infer_categories(self):
"""
Test that categories are inferred in sorted order if they're not
explicitly passed.
"""
arr1d = LabelArray(self.strs, missing_value='')
codes1d = arr1d.as_int_array()
self.assertEqual(arr1d.shape, self.strs.shape)
self.assertEqual(arr1d.shape, codes1d.shape)
categories = arr1d.categories
unique_rowvalues = set(self.rowvalues)
# There should be an entry in categories for each unique row value, and
# each integer stored in the data array should be an index into
# categories.
self.assertEqual(list(categories), sorted(set(self.rowvalues)))
self.assertEqual(
set(codes1d.ravel()),
set(range(len(unique_rowvalues)))
)
for idx, value in enumerate(arr1d.categories):
check_arrays(
self.strs == value,
arr1d.as_int_array() == idx,
)
# It should be equivalent to pass the same set of categories manually.
arr1d_explicit_categories = LabelArray(
self.strs,
missing_value='',
categories=arr1d.categories,
)
check_arrays(arr1d, arr1d_explicit_categories)
for shape in (9, 3), (3, 9), (3, 3, 3):
strs2d = self.strs.reshape(shape)
arr2d = LabelArray(strs2d, missing_value='')
codes2d = arr2d.as_int_array()
self.assertEqual(arr2d.shape, shape)
check_arrays(arr2d.categories, categories)
for idx, value in enumerate(arr2d.categories):
check_arrays(strs2d == value, codes2d == idx)
def test_infer_categories(self):
"""
Test that categories are inferred in sorted order if they're not
explicitly passed.
"""
arr1d = LabelArray(self.strs, missing_value='')
codes1d = arr1d.as_int_array()
self.assertEqual(arr1d.shape, self.strs.shape)
self.assertEqual(arr1d.shape, codes1d.shape)
categories = arr1d.categories
unique_rowvalues = set(self.rowvalues)
# There should be an entry in categories for each unique row value, and
# each integer stored in the data array should be an index into
# categories.
self.assertEqual(list(categories), sorted(set(self.rowvalues)))
self.assertEqual(
set(codes1d.ravel()),
set(range(len(unique_rowvalues)))
)
for idx, value in enumerate(arr1d.categories):
check_arrays(
self.strs == value,
arr1d.as_int_array() == idx,
)
# It should be equivalent to pass the same set of categories manually.
arr1d_explicit_categories = LabelArray(
self.strs,
missing_value='',
categories=arr1d.categories,
)
check_arrays(arr1d, arr1d_explicit_categories)
for shape in (9, 3), (3, 9), (3, 3, 3):
strs2d = self.strs.reshape(shape)
arr2d = LabelArray(strs2d, missing_value='')
codes2d = arr2d.as_int_array()
self.assertEqual(arr2d.shape, shape)
check_arrays(arr2d.categories, categories)
for idx, value in enumerate(arr2d.categories):
check_arrays(strs2d == value, codes2d == idx)
def test_string_not_equal(self, compval, missing, labelarray_dtype):
compval = labelarray_dtype.type(compval)
class C(Classifier):
dtype = categorical_dtype
missing_value = missing
inputs = ()
window_length = 0
c = C()
# There's no significance to the values here other than that they
# contain a mix of the comparison value and other values.
data = LabelArray(
np.asarray(
[
["", "a", "ab", "ba"],
["z", "ab", "a", "ab"],
["aa", "ab", "", "ab"],
["aa", "a", "ba", "ba"],
],
dtype=labelarray_dtype,
),
missing_value=missing,
)
expected = (data.as_int_array() != data.reverse_categories.get(
compval, -1)) & (data.as_int_array() !=
data.reverse_categories[C.missing_value])
self.check_terms(
terms={
"ne": c != compval,
},
expected={
"ne": expected,
},
initial_workspace={c: data},
mask=self.build_mask(self.ones_mask(shape=data.shape)),
)
def test_string_not_equal(self, compval, missing, labelarray_dtype):
compval = labelarray_dtype.type(compval)
class C(Classifier):
dtype = categorical_dtype
missing_value = missing
inputs = ()
window_length = 0
c = C()
# There's no significance to the values here other than that they
# contain a mix of the comparison value and other values.
data = LabelArray(
np.asarray(
[['', 'a', 'ab', 'ba'],
['z', 'ab', 'a', 'ab'],
['aa', 'ab', '', 'ab'],
['aa', 'a', 'ba', 'ba']],
dtype=labelarray_dtype,
),
missing_value=missing,
)
expected = (
(data.as_int_array() != data.reverse_categories.get(compval, -1)) &
(data.as_int_array() != data.reverse_categories[C.missing_value])
)
self.check_terms(
terms={
'ne': c != compval,
},
expected={
'ne': expected,
},
initial_workspace={c: data},
mask=self.build_mask(self.ones_mask(shape=data.shape)),
)
