CLN: assorted cleanups (#30473)

Author: jbrockmendel

.binstar.yml

@@ -580,8 +580,8 @@ or ``matplotlib.Axes.plot``. See :ref:`plotting.formatters` for more.
 - :meth:`Series.where` with ``Categorical`` dtype (or :meth:`DataFrame.where` with ``Categorical`` column) no longer allows setting new categories (:issue:`24114`)
 - :class:`DatetimeIndex`, :class:`TimedeltaIndex`, and :class:`PeriodIndex` constructors no longer allow ``start``, ``end``, and ``periods`` keywords, use :func:`date_range`, :func:`timedelta_range`, and :func:`period_range` instead (:issue:`23919`)
 - :class:`DatetimeIndex` and :class:`TimedeltaIndex` constructors no longer have a ``verify_integrity`` keyword argument (:issue:`23919`)
-- ``pandas.core.internals.blocks.make_block`` no longer accepts the "fastpath" keyword(:issue:`19265`)
-- :meth:`Block.make_block_same_class` no longer accepts the "dtype" keyword(:issue:`19434`)
+- ``pandas.core.internals.blocks.make_block`` no longer accepts the "fastpath" keyword (:issue:`19265`)
+- :meth:`Block.make_block_same_class` no longer accepts the "dtype" keyword (:issue:`19434`)
 - Removed the previously deprecated :meth:`ExtensionArray._formatting_values`. Use :attr:`ExtensionArray._formatter` instead. (:issue:`23601`)
 - Removed the previously deprecated :meth:`MultiIndex.to_hierarchical` (:issue:`21613`)
 - Removed the previously deprecated :attr:`MultiIndex.labels`, use :attr:`MultiIndex.codes` instead (:issue:`23752`)

doc/source/whatsnew/v1.0.0.rst

@@ -28,7 +28,7 @@ def unstack(reshape_t[:, :] values, uint8_t[:] mask,
             Py_ssize_t stride, Py_ssize_t length, Py_ssize_t width,
             reshape_t[:, :] new_values, uint8_t[:, :] new_mask):
     """
-    transform long sorted_values to wide new_values
+    Transform long values to wide new_values.
 
     Parameters
     ----------

pandas/_libs/reshape.pyx

@@ -802,8 +802,8 @@ def _add_offset(self, offset):
                 PerformanceWarning,
             )
             result = self.astype("O") + offset
-            if len(self) == 0:
-                # _from_sequence won't be able to infer self.tz
+            if not len(self):
+                # GH#30336 _from_sequence won't be able to infer self.tz
                 return type(self)._from_sequence(result).tz_localize(self.tz)
 
         return type(self)._from_sequence(result, freq="infer")

pandas/core/arrays/datetimes.py

@@ -741,16 +741,17 @@ def copy(self, deep=True):
 
         Parameters
         ----------
-        deep : boolean o rstring, default True
+        deep : bool or string, default True
             If False, return shallow copy (do not copy data)
             If 'all', copy data and a deep copy of the index
 
         Returns
         -------
-        copy : BlockManager
+        BlockManager
         """
         # this preserves the notion of view copying of axes
         if deep:
+            # hit in e.g. tests.io.json.test_pandas
 
             def copy_func(ax):
                 if deep == "all":
@@ -761,6 +762,7 @@ def copy_func(ax):
             new_axes = [copy_func(ax) for ax in self.axes]
         else:
             new_axes = list(self.axes)
+
         res = self.apply("copy", deep=deep)
         res.axes = new_axes
         return res

pandas/core/internals/managers.py

@@ -2204,8 +2204,6 @@ class PythonParser(ParserBase):
     def __init__(self, f, **kwds):
         """
         Workhorse function for processing nested list into DataFrame
-
-        Should be replaced by np.genfromtxt eventually?
         """
         ParserBase.__init__(self, kwds)
 

pandas/io/parsers.py

@@ -241,12 +241,6 @@ def _iter_data(self, data=None, keep_index=False, fillna=None):
         if fillna is not None:
             data = data.fillna(fillna)
 
-        # TODO: unused?
-        # if self.sort_columns:
-        #     columns = com.try_sort(data.columns)
-        # else:
-        #     columns = data.columns
-
         for col, values in data.items():
             if keep_index is True:
                 yield col, values

pandas/plotting/_matplotlib/core.py

@@ -1206,25 +1206,33 @@ def test_truediv(self):
         ex = "s / 1"
         d = {"s": s}  # noqa
 
-        res = self.eval(ex, truediv=False)
+        # FutureWarning: The `truediv` parameter in pd.eval is deprecated and will be
+        # removed in a future version.
+        with tm.assert_produces_warning(FutureWarning):
+            res = self.eval(ex, truediv=False)
         tm.assert_numpy_array_equal(res, np.array([1.0]))
 
-        res = self.eval(ex, truediv=True)
+        with tm.assert_produces_warning(FutureWarning):
+            res = self.eval(ex, truediv=True)
         tm.assert_numpy_array_equal(res, np.array([1.0]))
 
-        res = self.eval("1 / 2", truediv=True)
+        with tm.assert_produces_warning(FutureWarning):
+            res = self.eval("1 / 2", truediv=True)
         expec = 0.5
         assert res == expec
 
-        res = self.eval("1 / 2", truediv=False)
+        with tm.assert_produces_warning(FutureWarning):
+            res = self.eval("1 / 2", truediv=False)
         expec = 0.5
         assert res == expec
 
-        res = self.eval("s / 2", truediv=False)
+        with tm.assert_produces_warning(FutureWarning):
+            res = self.eval("s / 2", truediv=False)
         expec = 0.5
         assert res == expec
 
-        res = self.eval("s / 2", truediv=True)
+        with tm.assert_produces_warning(FutureWarning):
+            res = self.eval("s / 2", truediv=True)
         expec = 0.5
         assert res == expec
 

pandas/tests/computation/test_eval.py

@@ -4,6 +4,7 @@
 
 """
 import collections
+from collections import namedtuple
 from datetime import date, datetime, time, timedelta
 from decimal import Decimal
 from fractions import Fraction
@@ -1123,18 +1124,13 @@ def test_is_string_array(self):
     def test_to_object_array_tuples(self):
         r = (5, 6)
         values = [r]
-        result = lib.to_object_array_tuples(values)
+        lib.to_object_array_tuples(values)
 
-        try:
-            # make sure record array works
-            from collections import namedtuple
-
-            record = namedtuple("record", "x y")
-            r = record(5, 6)
-            values = [r]
-            result = lib.to_object_array_tuples(values)  # noqa
-        except ImportError:
-            pass
+        # make sure record array works
+        record = namedtuple("record", "x y")
+        r = record(5, 6)
+        values = [r]
+        lib.to_object_array_tuples(values)
 
     def test_object(self):
 
@@ -1174,8 +1170,6 @@ def test_is_period(self):
     def test_categorical(self):
 
         # GH 8974
-        from pandas import Categorical, Series
-
         arr = Categorical(list("abc"))
         result = lib.infer_dtype(arr, skipna=True)
         assert result == "categorical"

pandas/tests/dtypes/test_inference.py

@@ -51,7 +51,7 @@ def data_missing(allow_in_pandas, dtype):
     if dtype.numpy_dtype == "object":
         if _np_version_under1p16:
             raise pytest.skip("Skipping for NumPy <1.16")
-        return PandasArray(np.array([np.nan, (1,)]))
+        return PandasArray(np.array([np.nan, (1,)], dtype=object))
     return PandasArray(np.array([np.nan, 1.0]))
 
 
@@ -78,7 +78,7 @@ def data_for_sorting(allow_in_pandas, dtype):
     if dtype.numpy_dtype == "object":
         # Use an empty tuple for first element, then remove,
         # to disable np.array's shape inference.
-        return PandasArray(np.array([(), (2,), (3,), (1,)])[1:])
+        return PandasArray(np.array([(), (2,), (3,), (1,)], dtype=object)[1:])
     return PandasArray(np.array([1, 2, 0]))
 
 
@@ -90,7 +90,7 @@ def data_missing_for_sorting(allow_in_pandas, dtype):
     A < B and NA missing.
     """
     if dtype.numpy_dtype == "object":
-        return PandasArray(np.array([(1,), np.nan, (0,)]))
+        return PandasArray(np.array([(1,), np.nan, (0,)], dtype=object))
     return PandasArray(np.array([1, np.nan, 0]))
 
 
@@ -106,7 +106,9 @@ def data_for_grouping(allow_in_pandas, dtype):
         a, b, c = (1,), (2,), (3,)
     else:
         a, b, c = np.arange(3)
-    return PandasArray(np.array([b, b, np.nan, np.nan, a, a, b, c]))
+    return PandasArray(
+        np.array([b, b, np.nan, np.nan, a, a, b, c], dtype=dtype.numpy_dtype)
+    )
 
 
 @pytest.fixture

pandas/tests/extension/test_numpy.py

@@ -74,7 +74,7 @@ def test_to_records_with_unicode_index(self):
         tm.assert_almost_equal(result, expected)
 
     def test_to_records_with_unicode_column_names(self):
-        # xref GH#2407
+        # xref issue: https://github.com/numpy/numpy/issues/2407
         # Issue GH#11879. to_records used to raise an exception when used
         # with column names containing non-ascii characters in Python 2
         result = DataFrame(data={"accented_name_é": [1.0]}).to_records()