Method test_infer_categories

tests/test_labelarray.py:251–295

Test that categories are inferred in sorted order if they're not explicitly passed.

(self)

        self.assertIs(sliced.missing_value, arr.missing_value)

    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_reject_ufuncs(self):
        """