CLN/TST: address FIXMEs (#44637)

Author: jbrockmendel

pandas/_testing/_warnings.py

@@ -151,8 +151,8 @@ def _assert_caught_no_extra_warnings(
             if actual_warning.category == ResourceWarning and unclosed in str(
                 actual_warning.message
             ):
-                # FIXME: kludge because pytest.filterwarnings does not
-                #  suppress these, xref GH#38630
+                # FIXME(GH#38630): kludge because pytest.filterwarnings does not
+                #  suppress these
                 continue
 
             extra_warnings.append(

pandas/core/arrays/interval.py

@@ -1195,15 +1195,7 @@ def length(self):
         Return an Index with entries denoting the length of each Interval in
         the IntervalArray.
         """
-        try:
-            return self.right - self.left
-        except TypeError as err:
-            # length not defined for some types, e.g. string
-            msg = (
-                "IntervalArray contains Intervals without defined length, "
-                "e.g. Intervals with string endpoints"
-            )
-            raise TypeError(msg) from err
+        return self.right - self.left
 
     @property
     def mid(self):

pandas/tests/base/test_unique.py

@@ -1,12 +1,7 @@
 import numpy as np
 import pytest
 
-from pandas._libs import iNaT
-
-from pandas.core.dtypes.common import (
-    is_datetime64tz_dtype,
-    needs_i8_conversion,
-)
+from pandas.core.dtypes.common import is_datetime64tz_dtype
 
 import pandas as pd
 from pandas import NumericIndex
@@ -49,11 +44,8 @@ def test_unique_null(null_obj, index_or_series_obj):
     elif isinstance(obj, pd.MultiIndex):
         pytest.skip(f"MultiIndex can't hold '{null_obj}'")
 
-    values = obj.values
-    if needs_i8_conversion(obj.dtype):
-        values[0:2] = iNaT
-    else:
-        values[0:2] = null_obj
+    values = obj._values
+    values[0:2] = null_obj
 
     klass = type(obj)
     repeated_values = np.repeat(values, range(1, len(values) + 1))

pandas/tests/extension/base/constructors.py

@@ -3,10 +3,7 @@
 
 import pandas as pd
 from pandas.api.extensions import ExtensionArray
-from pandas.core.internals.blocks import (
-    DatetimeTZBlock,
-    ExtensionBlock,
-)
+from pandas.core.internals.blocks import EABackedBlock
 from pandas.tests.extension.base.base import BaseExtensionTests
 
 
@@ -29,14 +26,14 @@ def test_series_constructor(self, data):
         assert result.dtype == data.dtype
         assert len(result) == len(data)
         if hasattr(result._mgr, "blocks"):
-            assert isinstance(result._mgr.blocks[0], (ExtensionBlock, DatetimeTZBlock))
+            assert isinstance(result._mgr.blocks[0], EABackedBlock)
         assert result._mgr.array is data
 
         # Series[EA] is unboxed / boxed correctly
         result2 = pd.Series(result)
         assert result2.dtype == data.dtype
         if hasattr(result._mgr, "blocks"):
-            assert isinstance(result2._mgr.blocks[0], (ExtensionBlock, DatetimeTZBlock))
+            assert isinstance(result2._mgr.blocks[0], EABackedBlock)
 
     def test_series_constructor_no_data_with_index(self, dtype, na_value):
         result = pd.Series(index=[1, 2, 3], dtype=dtype)
@@ -71,15 +68,15 @@ def test_dataframe_constructor_from_dict(self, data, from_series):
         assert result.dtypes["A"] == data.dtype
         assert result.shape == (len(data), 1)
         if hasattr(result._mgr, "blocks"):
-            assert isinstance(result._mgr.blocks[0], (ExtensionBlock, DatetimeTZBlock))
+            assert isinstance(result._mgr.blocks[0], EABackedBlock)
         assert isinstance(result._mgr.arrays[0], ExtensionArray)
 
     def test_dataframe_from_series(self, data):
         result = pd.DataFrame(pd.Series(data))
         assert result.dtypes[0] == data.dtype
         assert result.shape == (len(data), 1)
         if hasattr(result._mgr, "blocks"):
-            assert isinstance(result._mgr.blocks[0], (ExtensionBlock, DatetimeTZBlock))
+            assert isinstance(result._mgr.blocks[0], EABackedBlock)
         assert isinstance(result._mgr.arrays[0], ExtensionArray)
 
     def test_series_given_mismatched_index_raises(self, data):

pandas/tests/extension/test_datetime.py

@@ -108,10 +108,6 @@ class TestGetitem(BaseDatetimeTests, base.BaseGetitemTests):
 
 
 class TestMethods(BaseDatetimeTests, base.BaseMethodsTests):
-    @pytest.mark.skip(reason="Incorrect expected")
-    def test_value_counts(self, all_data, dropna):
-        pass
-
     def test_combine_add(self, data_repeated):
         # Timestamp.__add__(Timestamp) not defined
         pass
@@ -140,23 +136,23 @@ def test_arith_frame_with_scalar(self, data, all_arithmetic_operators):
 
     def test_arith_series_with_scalar(self, data, all_arithmetic_operators):
         if all_arithmetic_operators in self.implements:
-            s = pd.Series(data)
-            self.check_opname(s, all_arithmetic_operators, s.iloc[0], exc=None)
+            ser = pd.Series(data)
+            self.check_opname(ser, all_arithmetic_operators, ser.iloc[0], exc=None)
         else:
             # ... but not the rest.
             super().test_arith_series_with_scalar(data, all_arithmetic_operators)
 
     def test_add_series_with_extension_array(self, data):
         # Datetime + Datetime not implemented
-        s = pd.Series(data)
+        ser = pd.Series(data)
         msg = "cannot add DatetimeArray and DatetimeArray"
         with pytest.raises(TypeError, match=msg):
-            s + data
+            ser + data
 
     def test_arith_series_with_array(self, data, all_arithmetic_operators):
         if all_arithmetic_operators in self.implements:
-            s = pd.Series(data)
-            self.check_opname(s, all_arithmetic_operators, s.iloc[0], exc=None)
+            ser = pd.Series(data)
+            self.check_opname(ser, all_arithmetic_operators, ser.iloc[0], exc=None)
         else:
             # ... but not the rest.
             super().test_arith_series_with_scalar(data, all_arithmetic_operators)

pandas/tests/extension/test_sparse.py

@@ -179,12 +179,12 @@ def test_transpose(self, data):
 
 class TestGetitem(BaseSparseTests, base.BaseGetitemTests):
     def test_get(self, data):
-        s = pd.Series(data, index=[2 * i for i in range(len(data))])
-        if np.isnan(s.values.fill_value):
-            assert np.isnan(s.get(4)) and np.isnan(s.iloc[2])
+        ser = pd.Series(data, index=[2 * i for i in range(len(data))])
+        if np.isnan(ser.values.fill_value):
+            assert np.isnan(ser.get(4)) and np.isnan(ser.iloc[2])
         else:
-            assert s.get(4) == s.iloc[2]
-        assert s.get(2) == s.iloc[1]
+            assert ser.get(4) == ser.iloc[2]
+        assert ser.get(2) == ser.iloc[1]
 
     def test_reindex(self, data, na_value):
         self._check_unsupported(data)
@@ -454,8 +454,8 @@ def _compare_other(self, s, data, comparison_op, other):
         tm.assert_series_equal(result, expected)
 
         # series
-        s = pd.Series(data)
-        result = op(s, other)
+        ser = pd.Series(data)
+        result = op(ser, other)
         tm.assert_series_equal(result, expected)
 
 

pandas/tests/frame/indexing/test_indexing.py

@@ -800,20 +800,14 @@ def test_setitem_single_column_mixed_datetime(self):
         assert df["timestamp"].dtype == np.object_
         assert df.loc["b", "timestamp"] == iNaT
 
-        # allow this syntax
+        # allow this syntax (as of GH#3216)
         df.loc["c", "timestamp"] = np.nan
         assert isna(df.loc["c", "timestamp"])
 
         # allow this syntax
         df.loc["d", :] = np.nan
         assert not isna(df.loc["c", :]).all()
 
-        # FIXME: don't leave commented-out
-        # as of GH 3216 this will now work!
-        # try to set with a list like item
-        # pytest.raises(
-        #    Exception, df.loc.__setitem__, ('d', 'timestamp'), [np.nan])
-
     def test_setitem_mixed_datetime(self):
         # GH 9336
         expected = DataFrame(

pandas/tests/frame/methods/test_diff.py

@@ -17,33 +17,31 @@ def test_diff_requires_integer(self):
         with pytest.raises(ValueError, match="periods must be an integer"):
             df.diff(1.5)
 
-    def test_diff_allows_np_integer(self):
-        # np.int64 is OK GH#44572
-        df = DataFrame(np.random.randn(2, 2))
-        res = df.diff(np.int64(1))
-        expected = df.diff(1)
-        tm.assert_frame_equal(res, expected)
-
-    def test_diff(self, datetime_frame):
-        the_diff = datetime_frame.diff(1)
+    # GH#44572 np.int64 is accepted
+    @pytest.mark.parametrize("num", [1, np.int64(1)])
+    def test_diff(self, datetime_frame, num):
+        df = datetime_frame
+        the_diff = df.diff(num)
 
-        tm.assert_series_equal(
-            the_diff["A"], datetime_frame["A"] - datetime_frame["A"].shift(1)
-        )
+        expected = df["A"] - df["A"].shift(num)
+        tm.assert_series_equal(the_diff["A"], expected)
 
+    def test_diff_int_dtype(self):
         # int dtype
         a = 10_000_000_000_000_000
         b = a + 1
-        s = Series([a, b])
+        ser = Series([a, b])
 
-        rs = DataFrame({"s": s}).diff()
+        rs = DataFrame({"s": ser}).diff()
         assert rs.s[1] == 1
 
+    def test_diff_mixed_numeric(self, datetime_frame):
         # mixed numeric
         tf = datetime_frame.astype("float32")
         the_diff = tf.diff(1)
         tm.assert_series_equal(the_diff["A"], tf["A"] - tf["A"].shift(1))
 
+    def test_diff_axis1_nonconsolidated(self):
         # GH#10907
         df = DataFrame({"y": Series([2]), "z": Series([3])})
         df.insert(0, "x", 1)

pandas/tests/frame/methods/test_transpose.py

@@ -115,4 +115,4 @@ def test_transpose_get_view_dt64tzget_view(self):
         assert result._mgr.nblocks == 1
 
         rtrip = result._mgr.blocks[0].values
-        assert np.shares_memory(arr._data, rtrip._data)
+        assert np.shares_memory(arr._ndarray, rtrip._ndarray)

pandas/tests/frame/methods/test_truncate.py

@@ -85,18 +85,16 @@ def test_truncate_nonsortedindex(self, frame_or_series):
             obj.truncate(before=3, after=9)
 
     def test_sort_values_nonsortedindex(self):
-        # TODO: belongs elsewhere?
-
         rng = date_range("2011-01-01", "2012-01-01", freq="W")
         ts = DataFrame(
             {"A": np.random.randn(len(rng)), "B": np.random.randn(len(rng))}, index=rng
         )
 
+        decreasing = ts.sort_values("A", ascending=False)
+
         msg = "truncate requires a sorted index"
         with pytest.raises(ValueError, match=msg):
-            ts.sort_values("A", ascending=False).truncate(
-                before="2011-11", after="2011-12"
-            )
+            decreasing.truncate(before="2011-11", after="2011-12")
 
     def test_truncate_nonsortedindex_axis1(self):
         # GH#17935

pandas/tests/frame/test_block_internals.py

@@ -352,8 +352,7 @@ def test_stale_cached_series_bug_473(self):
             assert pd.isna(Y["g"]["c"])
 
     def test_strange_column_corruption_issue(self):
-        # FIXME: dont leave commented-out
-        # (wesm) Unclear how exactly this is related to internal matters
+        # TODO(wesm): Unclear how exactly this is related to internal matters
         df = DataFrame(index=[0, 1])
         df[0] = np.nan
         wasCol = {}

pandas/tests/indexes/categorical/test_category.py

@@ -264,13 +264,10 @@ def test_ensure_copied_data(self, index):
         #
         # Must be tested separately from other indexes because
         # self.values is not an ndarray.
-        # GH#29918 Index.base has been removed
-        # FIXME: is this test still meaningful?
-        _base = lambda ar: ar if getattr(ar, "base", None) is None else ar.base
 
         result = CategoricalIndex(index.values, copy=True)
         tm.assert_index_equal(index, result)
-        assert _base(index.values) is not _base(result.values)
+        assert not np.shares_memory(result._data._codes, index._data._codes)
 
         result = CategoricalIndex(index.values, copy=False)
         assert result._data._codes is index._data._codes

pandas/tests/indexes/test_base.py

@@ -82,11 +82,6 @@ def test_constructor_copy(self, index):
         arr[0] = "SOMEBIGLONGSTRING"
         assert new_index[0] != "SOMEBIGLONGSTRING"
 
-        # FIXME: dont leave commented-out
-        # what to do here?
-        # arr = np.array(5.)
-        # pytest.raises(Exception, arr.view, Index)
-
     @pytest.mark.parametrize("cast_as_obj", [True, False])
     @pytest.mark.parametrize(
         "index",

pandas/tests/io/pytables/test_append.py

@@ -896,7 +896,6 @@ def test_append_to_multiple_dropna(setup_path):
         tm.assert_index_equal(store.select("df1").index, store.select("df2").index)
 
 
-@pytest.mark.xfail(reason="append_to_multiple_dropna_false is not raising as failed")
 def test_append_to_multiple_dropna_false(setup_path):
     df1 = tm.makeTimeDataFrame()
     df2 = tm.makeTimeDataFrame().rename(columns="{}_2".format)
@@ -910,8 +909,7 @@ def test_append_to_multiple_dropna_false(setup_path):
             {"df1a": ["A", "B"], "df2a": None}, df, selector="df1a", dropna=False
         )
 
-        # TODO Update error message to desired message for this case
-        msg = "Cannot select as multiple after appending with dropna=False"
+        msg = "all tables must have exactly the same nrows!"
         with pytest.raises(ValueError, match=msg):
             store.select_as_multiple(["df1a", "df2a"])
 

pandas/tests/series/test_constructors.py

@@ -1397,12 +1397,6 @@ def test_constructor_dtype_timedelta64(self):
         td = Series([np.timedelta64(1, "s")])
         assert td.dtype == "timedelta64[ns]"
 
-        # FIXME: dont leave commented-out
-        # these are frequency conversion astypes
-        # for t in ['s', 'D', 'us', 'ms']:
-        #    with pytest.raises(TypeError):
-        #        td.astype('m8[%s]' % t)
-
         # valid astype
         with tm.assert_produces_warning(FutureWarning):
             # astype(int64) deprecated