TST: More old issues (#41712)

Author: mroeschke

pandas/tests/frame/indexing/test_setitem.py

@@ -638,6 +638,19 @@ def test_setitem_dtypes_bytes_type_to_object(self):
         expected = Series([np.uint32, object, object, np.uint8], index=list("abcd"))
         tm.assert_series_equal(result, expected)
 
+    def test_boolean_mask_nullable_int64(self):
+        # GH 28928
+        result = DataFrame({"a": [3, 4], "b": [5, 6]}).astype(
+            {"a": "int64", "b": "Int64"}
+        )
+        mask = Series(False, index=result.index)
+        result.loc[mask, "a"] = result["a"]
+        result.loc[mask, "b"] = result["b"]
+        expected = DataFrame({"a": [3, 4], "b": [5, 6]}).astype(
+            {"a": "int64", "b": "Int64"}
+        )
+        tm.assert_frame_equal(result, expected)
+
 
 class TestSetitemTZAwareValues:
     @pytest.fixture

pandas/tests/frame/methods/test_append.py

@@ -238,3 +238,22 @@ def test_append_numpy_bug_1681(self, dtype):
 
         result = df.append(other)
         assert (result["B"] == index).all()
+
+    @pytest.mark.filterwarnings("ignore:The values in the array:RuntimeWarning")
+    def test_multiindex_column_append_multiple(self):
+        # GH 29699
+        df = DataFrame(
+            [[1, 11], [2, 12], [3, 13]],
+            columns=pd.MultiIndex.from_tuples(
+                [("multi", "col1"), ("multi", "col2")], names=["level1", None]
+            ),
+        )
+        df2 = df.copy()
+        for i in range(1, 10):
+            df[i, "colA"] = 10
+            df = df.append(df2, ignore_index=True)
+            result = df["multi"]
+            expected = DataFrame(
+                {"col1": [1, 2, 3] * (i + 1), "col2": [11, 12, 13] * (i + 1)}
+            )
+            tm.assert_frame_equal(result, expected)

pandas/tests/frame/methods/test_drop.py

@@ -502,3 +502,9 @@ def test_drop_inplace_no_leftover_column_reference(self):
         tm.assert_index_equal(df.columns, Index([], dtype="object"))
         a -= a.mean()
         tm.assert_index_equal(df.columns, Index([], dtype="object"))
+
+    def test_drop_level_missing_label_multiindex(self):
+        # GH 18561
+        df = DataFrame(index=MultiIndex.from_product([range(3), range(3)]))
+        with pytest.raises(KeyError, match="labels \\[5\\] not found in level"):
+            df.drop(5, level=0)

pandas/tests/frame/methods/test_reindex.py

@@ -60,6 +60,24 @@ def test_set_reset_index_intervalindex(self):
 
         df = df.reset_index()
 
+    def test_setitem_reset_index_dtypes(self):
+        # GH 22060
+        df = DataFrame(columns=["a", "b", "c"]).astype(
+            {"a": "datetime64[ns]", "b": np.int64, "c": np.float64}
+        )
+        df1 = df.set_index(["a"])
+        df1["d"] = []
+        result = df1.reset_index()
+        expected = DataFrame(columns=["a", "b", "c", "d"], index=range(0)).astype(
+            {"a": "datetime64[ns]", "b": np.int64, "c": np.float64, "d": np.float64}
+        )
+        tm.assert_frame_equal(result, expected)
+
+        df2 = df.set_index(["a", "b"])
+        df2["d"] = []
+        result = df2.reset_index()
+        tm.assert_frame_equal(result, expected)
+
 
 class TestDataFrameSelectReindex:
     # These are specific reindex-based tests; other indexing tests should go in

pandas/tests/frame/methods/test_sort_index.py

@@ -775,6 +775,16 @@ def test_sort_index_ascending_bad_value_raises(self, ascending):
         with pytest.raises(ValueError, match=match):
             df.sort_index(axis=0, ascending=ascending, na_position="first")
 
+    def test_sort_index_use_inf_as_na(self):
+        # GH 29687
+        expected = DataFrame(
+            {"col1": [1, 2, 3], "col2": [3, 4, 5]},
+            index=pd.date_range("2020", periods=3),
+        )
+        with pd.option_context("mode.use_inf_as_na", True):
+            result = expected.sort_index()
+        tm.assert_frame_equal(result, expected)
+
 
 class TestDataFrameSortIndexKey:
     def test_sort_multi_index_key(self):

pandas/tests/frame/test_repr_info.py

@@ -322,3 +322,11 @@ def test_frame_to_string_with_periodindex(self):
 
         # it works!
         frame.to_string()
+
+    def test_datetime64tz_slice_non_truncate(self):
+        # GH 30263
+        df = DataFrame({"x": date_range("2019", periods=10, tz="UTC")})
+        expected = repr(df)
+        df = df.iloc[:, :5]
+        result = repr(df)
+        assert result == expected

pandas/tests/groupby/test_groupby.py

@@ -2338,3 +2338,24 @@ def test_groupby_filtered_df_std():
         index=Index([True], name="groupby_col"),
     )
     tm.assert_frame_equal(result, expected)
+
+
+def test_datetime_categorical_multikey_groupby_indices():
+    # GH 26859
+    df = DataFrame(
+        {
+            "a": Series(list("abc")),
+            "b": Series(
+                to_datetime(["2018-01-01", "2018-02-01", "2018-03-01"]),
+                dtype="category",
+            ),
+            "c": Categorical.from_codes([-1, 0, 1], categories=[0, 1]),
+        }
+    )
+    result = df.groupby(["a", "b"]).indices
+    expected = {
+        ("a", Timestamp("2018-01-01 00:00:00")): np.array([0]),
+        ("b", Timestamp("2018-02-01 00:00:00")): np.array([1]),
+        ("c", Timestamp("2018-03-01 00:00:00")): np.array([2]),
+    }
+    assert result == expected

pandas/tests/groupby/test_nth.py

@@ -663,3 +663,29 @@ def test_first_categorical_and_datetime_data_nat():
     )
     expected.index = Index(["first", "second", "third"], name="group")
     tm.assert_frame_equal(result, expected)
+
+
+def test_first_multi_key_groupbby_categorical():
+    # GH 22512
+    df = DataFrame(
+        {
+            "A": [1, 1, 1, 2, 2],
+            "B": [100, 100, 200, 100, 100],
+            "C": ["apple", "orange", "mango", "mango", "orange"],
+            "D": ["jupiter", "mercury", "mars", "venus", "venus"],
+        }
+    )
+    df = df.astype({"D": "category"})
+    result = df.groupby(by=["A", "B"]).first()
+    expected = DataFrame(
+        {
+            "C": ["apple", "mango", "mango"],
+            "D": Series(["jupiter", "mars", "venus"]).astype(
+                pd.CategoricalDtype(["jupiter", "mars", "mercury", "venus"])
+            ),
+        }
+    )
+    expected.index = MultiIndex.from_tuples(
+        [(1, 100), (1, 200), (2, 100)], names=["A", "B"]
+    )
+    tm.assert_frame_equal(result, expected)

pandas/tests/indexing/test_iloc.py

@@ -13,6 +13,7 @@
 import pandas.util._test_decorators as td
 
 from pandas import (
+    NA,
     Categorical,
     CategoricalDtype,
     DataFrame,
@@ -1340,3 +1341,10 @@ def test_iloc_setitem_pure_position_based(self):
         ser1.iloc[1:3] = ser2.iloc[1:3]
         expected = Series([1, 5, 6])
         tm.assert_series_equal(ser1, expected)
+
+    def test_iloc_nullable_int64_size_1_nan(self):
+        # GH 31861
+        result = DataFrame({"a": ["test"], "b": [np.nan]})
+        result.loc[:, "b"] = result.loc[:, "b"].astype("Int64")
+        expected = DataFrame({"a": ["test"], "b": array([NA], dtype="Int64")})
+        tm.assert_frame_equal(result, expected)

pandas/tests/reshape/merge/test_merge.py

@@ -2479,3 +2479,11 @@ def test_merge_string_float_column_result():
         [[9, 10, 1, 2], [11, 12, 3, 4]], columns=pd.Index(["x", "y", "a", 114.0])
     )
     tm.assert_frame_equal(result, expected)
+
+
+def test_mergeerror_on_left_index_mismatched_dtypes():
+    # GH 22449
+    df_1 = DataFrame(data=["X"], columns=["C"], index=[22])
+    df_2 = DataFrame(data=["X"], columns=["C"], index=[999])
+    with pytest.raises(MergeError, match="Can only pass argument"):
+        merge(df_1, df_2, on=["C"], left_index=True)

pandas/tests/series/methods/test_sort_values.py

@@ -199,6 +199,13 @@ def test_sort_values_pos_args_deprecation(self):
         expected = Series([1, 2, 3])
         tm.assert_series_equal(result, expected)
 
+    def test_mergesort_decending_stability(self):
+        # GH 28697
+        s = Series([1, 2, 1, 3], ["first", "b", "second", "c"])
+        result = s.sort_values(ascending=False, kind="mergesort")
+        expected = Series([3, 2, 1, 1], ["c", "b", "first", "second"])
+        tm.assert_series_equal(result, expected)
+
 
 class TestSeriesSortingKey:
     def test_sort_values_key(self):

pandas/tests/tseries/offsets/test_offsets.py

@@ -870,3 +870,21 @@ def test_dateoffset_immutable(attribute):
     msg = "DateOffset objects are immutable"
     with pytest.raises(AttributeError, match=msg):
         setattr(offset, attribute, 5)
+
+
+@pytest.mark.parametrize(
+    "weekmask, expected_time, mult",
+    [
+        ["Mon Tue Wed Thu Fri Sat", "2018-11-10 09:00:00", 10],
+        ["Tue Wed Thu Fri Sat", "2018-11-13 08:00:00", 18],
+    ],
+)
+def test_custom_businesshour_weekmask_and_holidays(weekmask, expected_time, mult):
+    # GH 23542
+    holidays = ["2018-11-09"]
+    bh = CustomBusinessHour(
+        start="08:00", end="17:00", weekmask=weekmask, holidays=holidays
+    )
+    result = Timestamp("2018-11-08 08:00") + mult * bh
+    expected = Timestamp(expected_time)
+    assert result == expected

pandas/tests/window/test_rolling.py

@@ -1411,3 +1411,11 @@ def test_rolling_sum_all_nan_window_floating_artifacts():
     result = df.rolling(3, min_periods=0).sum()
     expected = DataFrame([0.002, 0.010, 0.015, 0.013, 0.005, 0.0])
     tm.assert_frame_equal(result, expected)
+
+
+def test_rolling_zero_window():
+    # GH 22719
+    s = Series(range(1))
+    result = s.rolling(0).min()
+    expected = Series([np.nan])
+    tm.assert_series_equal(result, expected)