TST: pandas-dev#15752 Add test_drop_duplicates for Categorical dtypes (pandas-dev#18072)

Author: jamestran201-alt

pandas/tests/test_categorical.py

@@ -797,6 +797,97 @@ def test_set_categories_inplace(self):
         cat.set_categories(['a', 'b', 'c', 'd'], inplace=True)
         tm.assert_index_equal(cat.categories, pd.Index(['a', 'b', 'c', 'd']))
 
+    @pytest.mark.parametrize(
+        "dtype",
+        ["int_", "uint", "float_", "unicode_", "timedelta64[h]",
+         pytest.param("datetime64[D]",
+                      marks=pytest.mark.xfail(reason="issue7996"))]
+    )
+    @pytest.mark.parametrize("is_ordered", [True, False])
+    def test_drop_duplicates_non_bool(self, dtype, is_ordered):
+        cat_array = np.array([1, 2, 3, 4, 5], dtype=np.dtype(dtype))
+
+        # Test case 1
+        input1 = np.array([1, 2, 3, 3], dtype=np.dtype(dtype))
+        tc1 = Series(Categorical(input1, categories=cat_array,
+                                 ordered=is_ordered))
+
+        expected = Series([False, False, False, True])
+        tm.assert_series_equal(tc1.duplicated(), expected)
+        tm.assert_series_equal(tc1.drop_duplicates(), tc1[~expected])
+        sc = tc1.copy()
+        sc.drop_duplicates(inplace=True)
+        tm.assert_series_equal(sc, tc1[~expected])
+
+        expected = Series([False, False, True, False])
+        tm.assert_series_equal(tc1.duplicated(keep='last'), expected)
+        tm.assert_series_equal(tc1.drop_duplicates(keep='last'),
+                               tc1[~expected])
+        sc = tc1.copy()
+        sc.drop_duplicates(keep='last', inplace=True)
+        tm.assert_series_equal(sc, tc1[~expected])
+
+        expected = Series([False, False, True, True])
+        tm.assert_series_equal(tc1.duplicated(keep=False), expected)
+        tm.assert_series_equal(tc1.drop_duplicates(keep=False), tc1[~expected])
+        sc = tc1.copy()
+        sc.drop_duplicates(keep=False, inplace=True)
+        tm.assert_series_equal(sc, tc1[~expected])
+
+        # Test case 2
+        input2 = np.array([1, 2, 3, 5, 3, 2, 4], dtype=np.dtype(dtype))
+        tc2 = Series(Categorical(
+            input2, categories=cat_array, ordered=is_ordered)
+        )
+
+        expected = Series([False, False, False, False, True, True, False])
+        tm.assert_series_equal(tc2.duplicated(), expected)
+        tm.assert_series_equal(tc2.drop_duplicates(), tc2[~expected])
+        sc = tc2.copy()
+        sc.drop_duplicates(inplace=True)
+        tm.assert_series_equal(sc, tc2[~expected])
+
+        expected = Series([False, True, True, False, False, False, False])
+        tm.assert_series_equal(tc2.duplicated(keep='last'), expected)
+        tm.assert_series_equal(tc2.drop_duplicates(keep='last'),
+                               tc2[~expected])
+        sc = tc2.copy()
+        sc.drop_duplicates(keep='last', inplace=True)
+        tm.assert_series_equal(sc, tc2[~expected])
+
+        expected = Series([False, True, True, False, True, True, False])
+        tm.assert_series_equal(tc2.duplicated(keep=False), expected)
+        tm.assert_series_equal(tc2.drop_duplicates(keep=False), tc2[~expected])
+        sc = tc2.copy()
+        sc.drop_duplicates(keep=False, inplace=True)
+        tm.assert_series_equal(sc, tc2[~expected])
+
+    @pytest.mark.parametrize("is_ordered", [True, False])
+    def test_drop_duplicates_bool(self, is_ordered):
+        tc = Series(Categorical([True, False, True, False],
+                                categories=[True, False], ordered=is_ordered))
+
+        expected = Series([False, False, True, True])
+        tm.assert_series_equal(tc.duplicated(), expected)
+        tm.assert_series_equal(tc.drop_duplicates(), tc[~expected])
+        sc = tc.copy()
+        sc.drop_duplicates(inplace=True)
+        tm.assert_series_equal(sc, tc[~expected])
+
+        expected = Series([True, True, False, False])
+        tm.assert_series_equal(tc.duplicated(keep='last'), expected)
+        tm.assert_series_equal(tc.drop_duplicates(keep='last'), tc[~expected])
+        sc = tc.copy()
+        sc.drop_duplicates(keep='last', inplace=True)
+        tm.assert_series_equal(sc, tc[~expected])
+
+        expected = Series([True, True, True, True])
+        tm.assert_series_equal(tc.duplicated(keep=False), expected)
+        tm.assert_series_equal(tc.drop_duplicates(keep=False), tc[~expected])
+        sc = tc.copy()
+        sc.drop_duplicates(keep=False, inplace=True)
+        tm.assert_series_equal(sc, tc[~expected])
+
     def test_describe(self):
         # string type
         desc = self.factor.describe()