TST: skip fewer tests (#44918)

Author: jbrockmendel

ci/deps/actions-38-db.yaml

@@ -12,7 +12,7 @@ dependencies:
   - pytest-cov>=2.10.1  # this is only needed in the coverage build, ref: GH 35737
 
   # pandas dependencies
-  - aiobotocore<2.0.0
+  - aiobotocore<2.0.0  # GH#44311 pinned to fix docbuild
   - beautifulsoup4
   - boto3
   - botocore>=1.11

environment.yml

@@ -105,7 +105,7 @@ dependencies:
 
   - pytables>=3.6.1  # pandas.read_hdf, DataFrame.to_hdf
   - s3fs>=0.4.0  # file IO when using 's3://...' path
-  - aiobotocore<2.0.0
+  - aiobotocore<2.0.0  # GH#44311 pinned to fix docbuild
   - fsspec>=0.7.4  # for generic remote file operations
   - gcsfs>=0.6.0  # file IO when using 'gcs://...' path
   - sqlalchemy  # pandas.read_sql, DataFrame.to_sql

pandas/conftest.py

@@ -559,6 +559,21 @@ def index_flat(request):
 index_flat2 = index_flat
 
 
+@pytest.fixture(
+    params=[
+        key
+        for key in indices_dict
+        if not isinstance(indices_dict[key], MultiIndex) and indices_dict[key].is_unique
+    ]
+)
+def index_flat_unique(request):
+    """
+    index_flat with uniqueness requirement.
+    """
+    key = request.param
+    return indices_dict[key].copy()
+
+
 @pytest.fixture(
     params=[
         key

pandas/core/arrays/categorical.py

@@ -2377,7 +2377,7 @@ def describe(self):
 
         return result
 
-    def isin(self, values) -> np.ndarray:
+    def isin(self, values) -> npt.NDArray[np.bool_]:
         """
         Check whether `values` are contained in Categorical.
 
@@ -2394,7 +2394,7 @@ def isin(self, values) -> np.ndarray:
 
         Returns
         -------
-        isin : numpy.ndarray (bool dtype)
+        np.ndarray[bool]
 
         Raises
         ------

pandas/tests/base/test_fillna.py

@@ -6,26 +6,26 @@
 import numpy as np
 import pytest
 
-from pandas.core.dtypes.generic import ABCMultiIndex
-
-from pandas import Index
+from pandas import MultiIndex
 import pandas._testing as tm
 from pandas.tests.base.common import allow_na_ops
 
 
 def test_fillna(index_or_series_obj):
     # GH 11343
     obj = index_or_series_obj
-    if isinstance(obj, ABCMultiIndex):
-        pytest.skip("MultiIndex doesn't support isna")
+
+    if isinstance(obj, MultiIndex):
+        msg = "isna is not defined for MultiIndex"
+        with pytest.raises(NotImplementedError, match=msg):
+            obj.fillna(0)
+        return
 
     # values will not be changed
     fill_value = obj.values[0] if len(obj) > 0 else 0
     result = obj.fillna(fill_value)
-    if isinstance(obj, Index):
-        tm.assert_index_equal(obj, result)
-    else:
-        tm.assert_series_equal(obj, result)
+
+    tm.assert_equal(obj, result)
 
     # check shallow_copied
     assert obj is not result
@@ -41,7 +41,7 @@ def test_fillna_null(null_obj, index_or_series_obj):
         pytest.skip(f"{klass} doesn't allow for NA operations")
     elif len(obj) < 1:
         pytest.skip("Test doesn't make sense on empty data")
-    elif isinstance(obj, ABCMultiIndex):
+    elif isinstance(obj, MultiIndex):
         pytest.skip(f"MultiIndex can't hold '{null_obj}'")
 
     values = obj._values

pandas/tests/base/test_unique.py

@@ -123,6 +123,6 @@ def test_unique_bad_unicode(index_or_series):
 @pytest.mark.parametrize("dropna", [True, False])
 def test_nunique_dropna(dropna):
     # GH37566
-    s = pd.Series(["yes", "yes", pd.NA, np.nan, None, pd.NaT])
-    res = s.nunique(dropna)
+    ser = pd.Series(["yes", "yes", pd.NA, np.nan, None, pd.NaT])
+    res = ser.nunique(dropna)
     assert res == 1 if dropna else 5

pandas/tests/extension/base/dim2.py

@@ -150,10 +150,7 @@ def test_fillna_2d_method(self, data_missing, method):
         self.assert_extension_array_equal(result, expected)
 
     @pytest.mark.parametrize("method", ["mean", "median", "var", "std", "sum", "prod"])
-    def test_reductions_2d_axis_none(self, data, method, request):
-        if not hasattr(data, method):
-            pytest.skip("test is not applicable for this type/dtype")
-
+    def test_reductions_2d_axis_none(self, data, method):
         arr2d = data.reshape(1, -1)
 
         err_expected = None
@@ -178,10 +175,7 @@ def test_reductions_2d_axis_none(self, data, method, request):
         assert is_matching_na(result, expected) or result == expected
 
     @pytest.mark.parametrize("method", ["mean", "median", "var", "std", "sum", "prod"])
-    def test_reductions_2d_axis0(self, data, method, request):
-        if not hasattr(data, method):
-            pytest.skip("test is not applicable for this type/dtype")
-
+    def test_reductions_2d_axis0(self, data, method):
         arr2d = data.reshape(1, -1)
 
         kwargs = {}
@@ -231,10 +225,7 @@ def get_reduction_result_dtype(dtype):
         # punt on method == "var"
 
     @pytest.mark.parametrize("method", ["mean", "median", "var", "std", "sum", "prod"])
-    def test_reductions_2d_axis1(self, data, method, request):
-        if not hasattr(data, method):
-            pytest.skip("test is not applicable for this type/dtype")
-
+    def test_reductions_2d_axis1(self, data, method):
         arr2d = data.reshape(1, -1)
 
         try:

pandas/tests/indexes/test_common.py

@@ -244,13 +244,17 @@ def test_unique(self, index_flat):
             result = i.unique()
             tm.assert_index_equal(result, expected)
 
-    def test_searchsorted_monotonic(self, index_flat):
+    def test_searchsorted_monotonic(self, index_flat, request):
         # GH17271
         index = index_flat
         # not implemented for tuple searches in MultiIndex
         # or Intervals searches in IntervalIndex
         if isinstance(index, pd.IntervalIndex):
-            pytest.skip("Skip check for MultiIndex/IntervalIndex")
+            mark = pytest.mark.xfail(
+                reason="IntervalIndex.searchsorted does not support Interval arg",
+                raises=NotImplementedError,
+            )
+            request.node.add_marker(mark)
 
         # nothing to test if the index is empty
         if index.empty:

pandas/tests/indexes/test_setops.py

@@ -272,13 +272,11 @@ def test_symmetric_difference(self, index):
             (None, None, None),
         ],
     )
-    def test_corner_union(self, index_flat, fname, sname, expected_name):
+    def test_corner_union(self, index_flat_unique, fname, sname, expected_name):
         # GH#9943, GH#9862
         # Test unions with various name combinations
         # Do not test MultiIndex or repeats
-        index = index_flat
-        if not index.is_unique:
-            pytest.skip("Not for MultiIndex or repeated indices")
+        index = index_flat_unique
 
         # Test copy.union(copy)
         first = index.copy().set_names(fname)
@@ -318,10 +316,8 @@ def test_corner_union(self, index_flat, fname, sname, expected_name):
             (None, None, None),
         ],
     )
-    def test_union_unequal(self, index_flat, fname, sname, expected_name):
-        index = index_flat
-        if not index.is_unique:
-            pytest.skip("Not for MultiIndex or repeated indices")
+    def test_union_unequal(self, index_flat_unique, fname, sname, expected_name):
+        index = index_flat_unique
 
         # test copy.union(subset) - need sort for unicode and string
         first = index.copy().set_names(fname)
@@ -340,12 +336,10 @@ def test_union_unequal(self, index_flat, fname, sname, expected_name):
             (None, None, None),
         ],
     )
-    def test_corner_intersect(self, index_flat, fname, sname, expected_name):
+    def test_corner_intersect(self, index_flat_unique, fname, sname, expected_name):
         # GH#35847
         # Test intersections with various name combinations
-        index = index_flat
-        if not index.is_unique:
-            pytest.skip("Not for MultiIndex or repeated indices")
+        index = index_flat_unique
 
         # Test copy.intersection(copy)
         first = index.copy().set_names(fname)
@@ -385,10 +379,8 @@ def test_corner_intersect(self, index_flat, fname, sname, expected_name):
             (None, None, None),
         ],
     )
-    def test_intersect_unequal(self, index_flat, fname, sname, expected_name):
-        index = index_flat
-        if not index.is_unique:
-            pytest.skip("Not for MultiIndex or repeated indices")
+    def test_intersect_unequal(self, index_flat_unique, fname, sname, expected_name):
+        index = index_flat_unique
 
         # test copy.intersection(subset) - need sort for unicode and string
         first = index.copy().set_names(fname)

pandas/tests/io/excel/test_writers.py

@@ -207,14 +207,18 @@ def test_read_excel_multiindex_empty_level(self, ext):
     @pytest.mark.parametrize("c_idx_levels", [1, 3])
     @pytest.mark.parametrize("r_idx_levels", [1, 3])
     def test_excel_multindex_roundtrip(
-        self, ext, c_idx_names, r_idx_names, c_idx_levels, r_idx_levels
+        self, ext, c_idx_names, r_idx_names, c_idx_levels, r_idx_levels, request
     ):
         # see gh-4679
         with tm.ensure_clean(ext) as pth:
-            if c_idx_levels == 1 and c_idx_names:
-                pytest.skip(
-                    "Column index name cannot be serialized unless it's a MultiIndex"
+            if (c_idx_levels == 1 and c_idx_names) and not (
+                r_idx_levels == 3 and not r_idx_names
+            ):
+                mark = pytest.mark.xfail(
+                    reason="Column index name cannot be serialized unless "
+                    "it's a MultiIndex"
                 )
+                request.node.add_marker(mark)
 
             # Empty name case current read in as
             # unnamed levels, not Nones.

pandas/tests/io/formats/test_to_csv.py

@@ -498,9 +498,6 @@ def test_to_csv_compression(self, compression_only, read_infer, to_infer):
         # see gh-15008
         compression = compression_only
 
-        if compression == "zip":
-            pytest.skip(f"{compression} is not supported for to_csv")
-
         # We'll complete file extension subsequently.
         filename = "test."
 

pandas/tests/io/json/test_compression.py

@@ -95,9 +95,6 @@ def test_to_json_compression(compression_only, read_infer, to_infer):
     # see gh-15008
     compression = compression_only
 
-    if compression == "zip":
-        pytest.skip(f"{compression} is not supported for to_csv")
-
     # We'll complete file extension subsequently.
     filename = "test."
 

pandas/tests/io/json/test_pandas.py

@@ -1323,10 +1323,9 @@ def test_to_jsonl(self):
         tm.assert_frame_equal(read_json(result, lines=True), df)
 
     # TODO: there is a near-identical test for pytables; can we share?
+    @pytest.mark.xfail(reason="GH#13774 encoding kwarg not supported", raises=TypeError)
     def test_latin_encoding(self):
         # GH 13774
-        pytest.skip("encoding not implemented in .to_json(), xref #13774")
-
         values = [
             [b"E\xc9, 17", b"", b"a", b"b", b"c"],
             [b"E\xc9, 17", b"a", b"b", b"c"],

pandas/tests/series/methods/test_rank.py

@@ -33,9 +33,9 @@ class TestSeriesRank:
         "dense": np.array([1, 3, 4, 2, np.nan, 2, 1, 5, np.nan, 3]),
     }
 
+    @td.skip_if_no_scipy
     def test_rank(self, datetime_series):
-        pytest.importorskip("scipy.stats.special")
-        rankdata = pytest.importorskip("scipy.stats.rankdata")
+        from scipy.stats import rankdata
 
         datetime_series[::2] = np.nan
         datetime_series[:10][::3] = 4.0
@@ -280,9 +280,9 @@ def test_rank_desc_mix_nans_infs(self):
         exp = Series([3, np.nan, 1, 4, 2], dtype="float64")
         tm.assert_series_equal(result, exp)
 
+    @td.skip_if_no_scipy
     def test_rank_methods_series(self):
-        pytest.importorskip("scipy.stats.special")
-        rankdata = pytest.importorskip("scipy.stats.rankdata")
+        from scipy.stats import rankdata
 
         xs = np.random.randn(9)
         xs = np.concatenate([xs[i:] for i in range(0, 9, 2)])  # add duplicates

pandas/tests/test_algos.py

@@ -509,7 +509,8 @@ def test_on_index_object(self):
     def test_dtype_preservation(self, any_numpy_dtype):
         # GH 15442
         if any_numpy_dtype in (tm.BYTES_DTYPES + tm.STRING_DTYPES):
-            pytest.skip("skip string dtype")
+            data = [1, 2, 2]
+            uniques = [1, 2]
         elif is_integer_dtype(any_numpy_dtype):
             data = [1, 2, 2]
             uniques = [1, 2]
@@ -533,6 +534,9 @@ def test_dtype_preservation(self, any_numpy_dtype):
         result = Series(data, dtype=any_numpy_dtype).unique()
         expected = np.array(uniques, dtype=any_numpy_dtype)
 
+        if any_numpy_dtype in tm.STRING_DTYPES:
+            expected = expected.astype(object)
+
         tm.assert_numpy_array_equal(result, expected)
 
     def test_datetime64_dtype_array_returned(self):