TST: Add test for old issues (pandas-dev#41431)

Author: mroeschke

pandas/tests/arrays/sparse/test_array.py

@@ -1313,6 +1313,14 @@ def test_dropna(fill_value):
     tm.assert_equal(df.dropna(), expected_df)
 
 
+def test_drop_duplicates_fill_value():
+    # GH 11726
+    df = pd.DataFrame(np.zeros((5, 5))).apply(lambda x: SparseArray(x, fill_value=0))
+    result = df.drop_duplicates()
+    expected = pd.DataFrame({i: SparseArray([0.0], fill_value=0) for i in range(5)})
+    tm.assert_frame_equal(result, expected)
+
+
 class TestMinMax:
     plain_data = np.arange(5).astype(float)
     data_neg = plain_data * (-1)

pandas/tests/frame/methods/test_to_dict.py

@@ -304,3 +304,10 @@ def test_to_dict_scalar_constructor_orient_dtype(self, data, expected_dtype):
         d = df.to_dict(orient="records")
         result = type(d[0]["a"])
         assert result is expected_dtype
+
+    def test_to_dict_mixed_numeric_frame(self):
+        # GH 12859
+        df = DataFrame({"a": [1.0], "b": [9.0]})
+        result = df.reset_index().to_dict("records")
+        expected = [{"index": 0, "a": 1.0, "b": 9.0}]
+        assert result == expected

pandas/tests/groupby/test_apply.py

@@ -1121,3 +1121,27 @@ def test_apply_dropna_with_indexed_same():
     )
 
     tm.assert_frame_equal(result, expected)
+
+
+@pytest.mark.parametrize(
+    "as_index, expected",
+    [
+        [
+            False,
+            DataFrame(
+                [[1, 1, 1], [2, 2, 1]], columns=Index(["a", "b", None], dtype=object)
+            ),
+        ],
+        [
+            True,
+            Series(
+                [1, 1], index=MultiIndex.from_tuples([(1, 1), (2, 2)], names=["a", "b"])
+            ),
+        ],
+    ],
+)
+def test_apply_as_index_constant_lambda(as_index, expected):
+    # GH 13217
+    df = DataFrame({"a": [1, 1, 2, 2], "b": [1, 1, 2, 2], "c": [1, 1, 1, 1]})
+    result = df.groupby(["a", "b"], as_index=as_index).apply(lambda x: 1)
+    tm.assert_equal(result, expected)

pandas/tests/groupby/test_apply_mutate.py

@@ -68,3 +68,63 @@ def fn(x):
         name="col2",
     )
     tm.assert_series_equal(result, expected)
+
+
+def test_apply_mutate_columns_multiindex():
+    # GH 12652
+    df = pd.DataFrame(
+        {
+            ("C", "julian"): [1, 2, 3],
+            ("B", "geoffrey"): [1, 2, 3],
+            ("A", "julian"): [1, 2, 3],
+            ("B", "julian"): [1, 2, 3],
+            ("A", "geoffrey"): [1, 2, 3],
+            ("C", "geoffrey"): [1, 2, 3],
+        },
+        columns=pd.MultiIndex.from_tuples(
+            [
+                ("A", "julian"),
+                ("A", "geoffrey"),
+                ("B", "julian"),
+                ("B", "geoffrey"),
+                ("C", "julian"),
+                ("C", "geoffrey"),
+            ]
+        ),
+    )
+
+    def add_column(grouped):
+        name = grouped.columns[0][1]
+        grouped["sum", name] = grouped.sum(axis=1)
+        return grouped
+
+    result = df.groupby(level=1, axis=1).apply(add_column)
+    expected = pd.DataFrame(
+        [
+            [1, 1, 1, 3, 1, 1, 1, 3],
+            [2, 2, 2, 6, 2, 2, 2, 6],
+            [
+                3,
+                3,
+                3,
+                9,
+                3,
+                3,
+                3,
+                9,
+            ],
+        ],
+        columns=pd.MultiIndex.from_tuples(
+            [
+                ("geoffrey", "A", "geoffrey"),
+                ("geoffrey", "B", "geoffrey"),
+                ("geoffrey", "C", "geoffrey"),
+                ("geoffrey", "sum", "geoffrey"),
+                ("julian", "A", "julian"),
+                ("julian", "B", "julian"),
+                ("julian", "C", "julian"),
+                ("julian", "sum", "julian"),
+            ]
+        ),
+    )
+    tm.assert_frame_equal(result, expected)

pandas/tests/indexes/object/__init__.py

@@ -1366,7 +1366,7 @@ async def test_tab_complete_warning(self, ip):
         pytest.importorskip("IPython", minversion="6.0.0")
         from IPython.core.completer import provisionalcompleter
 
-        code = "import pandas as pd; idx = Index([1, 2])"
+        code = "import pandas as pd; idx = pd.Index([1, 2])"
         await ip.run_code(code)
 
         # GH 31324 newer jedi version raises Deprecation warning;
@@ -1720,3 +1720,21 @@ def test_validate_1d_input():
     ser = Series(0, range(4))
     with pytest.raises(ValueError, match=msg):
         ser.index = np.array([[2, 3]] * 4)
+
+
+@pytest.mark.parametrize(
+    "klass, extra_kwargs",
+    [
+        [Index, {}],
+        [Int64Index, {}],
+        [Float64Index, {}],
+        [DatetimeIndex, {}],
+        [TimedeltaIndex, {}],
+        [PeriodIndex, {"freq": "Y"}],
+    ],
+)
+def test_construct_from_memoryview(klass, extra_kwargs):
+    # GH 13120
+    result = klass(memoryview(np.arange(2000, 2005)), **extra_kwargs)
+    expected = klass(range(2000, 2005), **extra_kwargs)
+    tm.assert_index_equal(result, expected)

pandas/tests/indexes/test_base.py

@@ -2446,3 +2446,14 @@ def test_merge_duplicate_columns_with_suffix_causing_another_duplicate():
         result = merge(left, right, on="a")
     expected = DataFrame([[1, 1, 1, 1, 2]], columns=["a", "b_x", "b_x", "b_x", "b_y"])
     tm.assert_frame_equal(result, expected)
+
+
+def test_merge_string_float_column_result():
+    # GH 13353
+    df1 = DataFrame([[1, 2], [3, 4]], columns=pd.Index(["a", 114.0]))
+    df2 = DataFrame([[9, 10], [11, 12]], columns=["x", "y"])
+    result = merge(df2, df1, how="inner", left_index=True, right_index=True)
+    expected = DataFrame(
+        [[9, 10, 1, 2], [11, 12, 3, 4]], columns=pd.Index(["x", "y", "a", 114.0])
+    )
+    tm.assert_frame_equal(result, expected)

pandas/tests/reshape/merge/test_merge.py

@@ -662,3 +662,11 @@ def test_getitem_categorical_str():
 def test_slice_can_reorder_not_uniquely_indexed():
     ser = Series(1, index=["a", "a", "b", "b", "c"])
     ser[::-1]  # it works!
+
+
+@pytest.mark.parametrize("index_vals", ["aabcd", "aadcb"])
+def test_duplicated_index_getitem_positional_indexer(index_vals):
+    # GH 11747
+    s = Series(range(5), index=list(index_vals))
+    result = s[3]
+    assert result == 3

pandas/tests/series/indexing/test_getitem.py

@@ -286,6 +286,13 @@ def test_setitem_with_bool_mask_and_values_matching_n_trues_in_length(self):
         expected = Series([None] * 3 + list(range(5)) + [None] * 2).astype("object")
         tm.assert_series_equal(result, expected)
 
+    def test_setitem_nan_with_bool(self):
+        # GH 13034
+        result = Series([True, False, True])
+        result[0] = np.nan
+        expected = Series([np.nan, False, True], dtype=object)
+        tm.assert_series_equal(result, expected)
+
 
 class TestSetitemViewCopySemantics:
     def test_setitem_invalidates_datetime_index_freq(self):