CLN: collected cleanups (pandas-dev#44063)

Author: jbrockmendel

pandas/_libs/internals.pyx

@@ -408,7 +408,7 @@ cdef slice indexer_as_slice(intp_t[:] vals):
         int64_t d
 
     if vals is None:
-        raise TypeError("vals must be ndarray")
+        raise TypeError("vals must be ndarray")  # pragma: no cover
 
     n = vals.shape[0]
 
@@ -772,7 +772,7 @@ cdef class BlockManager:
             self.blocks = blocks
             self.axes = axes
 
-        else:
+        else:  # pragma: no cover
             raise NotImplementedError("pre-0.14.1 pickles are no longer supported")
 
         self._post_setstate()

pandas/_libs/join.pyx

@@ -952,12 +952,11 @@ def asof_join_nearest(numeric_t[:] left_values,
                       tolerance=None):
 
     cdef:
-        Py_ssize_t left_size, right_size, i
+        Py_ssize_t left_size, i
         ndarray[intp_t] left_indexer, right_indexer, bli, bri, fli, fri
         numeric_t bdiff, fdiff
 
     left_size = len(left_values)
-    right_size = len(right_values)
 
     left_indexer = np.empty(left_size, dtype=np.intp)
     right_indexer = np.empty(left_size, dtype=np.intp)

pandas/_libs/tslibs/offsets.pyx

@@ -808,9 +808,7 @@ cdef class Tick(SingleConstructorOffset):
     def nanos(self) -> int64_t:
         return self.n * self._nanos_inc
 
-    # FIXME: This should be typed as datetime, but we DatetimeLikeIndex.insert
-    #  checks self.freq.is_on_offset with a Timedelta sometimes.
-    def is_on_offset(self, dt) -> bool:
+    def is_on_offset(self, dt: datetime) -> bool:
         return True
 
     def is_anchored(self) -> bool:

pandas/core/indexes/datetimelike.py

@@ -670,7 +670,11 @@ def _get_insert_freq(self, loc: int, item):
                     freq = self.freq
             else:
                 # Adding a single item to an empty index may preserve freq
-                if self.freq.is_on_offset(item):
+                if isinstance(self.freq, Tick):
+                    # all TimedeltaIndex cases go through here; is_on_offset
+                    #  would raise TypeError
+                    freq = self.freq
+                elif self.freq.is_on_offset(item):
                     freq = self.freq
         return freq
 

pandas/core/internals/construction.py

@@ -155,9 +155,6 @@ def arrays_to_mgr(
             arrays, axes, consolidate=consolidate
         )
     elif typ == "array":
-        if len(columns) != len(arrays):
-            assert len(arrays) == 0
-            arrays = [np.array([], dtype=object) for _ in range(len(columns))]
         return ArrayManager(arrays, [index, columns])
     else:
         raise ValueError(f"'typ' needs to be one of {{'block', 'array'}}, got '{typ}'")

pandas/core/sorting.py

@@ -96,7 +96,9 @@ def get_indexer_indexer(
     return indexer
 
 
-def get_group_index(labels, shape: Shape, sort: bool, xnull: bool):
+def get_group_index(
+    labels, shape: Shape, sort: bool, xnull: bool
+) -> npt.NDArray[np.int64]:
     """
     For the particular label_list, gets the offsets into the hypothetical list
     representing the totally ordered cartesian product of all possible label
@@ -651,7 +653,7 @@ def get_group_index_sorter(
 
 
 def compress_group_index(
-    group_index: np.ndarray, sort: bool = True
+    group_index: npt.NDArray[np.int64], sort: bool = True
 ) -> tuple[npt.NDArray[np.int64], npt.NDArray[np.int64]]:
     """
     Group_index is offsets into cartesian product of all possible labels. This

pandas/tests/base/test_fillna.py

@@ -6,9 +6,6 @@
 import numpy as np
 import pytest
 
-from pandas._libs import iNaT
-
-from pandas.core.dtypes.common import needs_i8_conversion
 from pandas.core.dtypes.generic import ABCMultiIndex
 
 from pandas import Index
@@ -47,24 +44,17 @@ def test_fillna_null(null_obj, index_or_series_obj):
     elif isinstance(obj, ABCMultiIndex):
         pytest.skip(f"MultiIndex can't hold '{null_obj}'")
 
-    values = obj.values
+    values = obj._values
     fill_value = values[0]
     expected = values.copy()
-    if needs_i8_conversion(obj.dtype):
-        values[0:2] = iNaT
-        expected[0:2] = fill_value
-    else:
-        values[0:2] = null_obj
-        expected[0:2] = fill_value
+    values[0:2] = null_obj
+    expected[0:2] = fill_value
 
     expected = klass(expected)
     obj = klass(values)
 
     result = obj.fillna(fill_value)
-    if isinstance(obj, Index):
-        tm.assert_index_equal(result, expected)
-    else:
-        tm.assert_series_equal(result, expected)
+    tm.assert_equal(result, expected)
 
     # check shallow_copied
     assert obj is not result

pandas/tests/base/test_unique.py

@@ -96,11 +96,8 @@ def test_nunique_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/base/test_value_counts.py

@@ -5,11 +5,8 @@
 import numpy as np
 import pytest
 
-from pandas._libs import iNaT
 from pandas.compat import np_array_datetime64_compat
 
-from pandas.core.dtypes.common import needs_i8_conversion
-
 import pandas as pd
 from pandas import (
     DatetimeIndex,
@@ -54,11 +51,8 @@ def test_value_counts_null(null_obj, index_or_series_obj):
     elif isinstance(orig, 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/indexes/common.py

@@ -6,7 +6,6 @@
 import numpy as np
 import pytest
 
-from pandas._libs import iNaT
 from pandas._libs.tslibs import Timestamp
 
 from pandas.core.dtypes.common import (
@@ -37,7 +36,6 @@
     Int64Index,
     UInt64Index,
 )
-from pandas.core.indexes.datetimelike import DatetimeIndexOpsMixin
 
 
 class Base:
@@ -548,17 +546,11 @@ def test_fillna(self, index):
                 idx.fillna([idx[0]])
 
             idx = index.copy(deep=True)
-            values = np.asarray(idx.values)
+            values = idx._values
 
-            if isinstance(index, DatetimeIndexOpsMixin):
-                values[1] = iNaT
-            else:
-                values[1] = np.nan
+            values[1] = np.nan
 
-            if isinstance(index, PeriodIndex):
-                idx = type(index)(values, freq=index.freq)
-            else:
-                idx = type(index)(values)
+            idx = type(index)(values)
 
             expected = np.array([False] * len(idx), dtype=bool)
             expected[1] = True

pandas/tests/indexes/test_common.py

@@ -8,12 +8,10 @@
 import numpy as np
 import pytest
 
-from pandas._libs.tslibs import iNaT
 from pandas.compat import IS64
 
 from pandas.core.dtypes.common import (
     is_integer_dtype,
-    is_period_dtype,
     needs_i8_conversion,
 )
 
@@ -173,21 +171,10 @@ def test_unique(self, index_flat):
         if not index._can_hold_na:
             pytest.skip("Skip na-check if index cannot hold na")
 
-        if is_period_dtype(index.dtype):
-            vals = index[[0] * 5]._data
-            vals[0] = pd.NaT
-        elif needs_i8_conversion(index.dtype):
-            vals = index._data._ndarray[[0] * 5]
-            vals[0] = iNaT
-        else:
-            vals = index.values[[0] * 5]
-            vals[0] = np.nan
+        vals = index._values[[0] * 5]
+        vals[0] = np.nan
 
         vals_unique = vals[:2]
-        if index.dtype.kind in ["m", "M"]:
-            # i.e. needs_i8_conversion but not period_dtype, as above
-            vals = type(index._data)(vals, dtype=index.dtype)
-            vals_unique = type(index._data)._simple_new(vals_unique, dtype=index.dtype)
         idx_nan = index._shallow_copy(vals)
         idx_unique_nan = index._shallow_copy(vals_unique)
         assert idx_unique_nan.is_unique is True
@@ -378,26 +365,21 @@ def test_hasnans_isnans(self, index_flat):
         assert idx.hasnans is False
 
         idx = index.copy(deep=True)
-        values = np.asarray(idx.values)
+        values = idx._values
 
         if len(index) == 0:
             return
         elif isinstance(index, NumericIndex) and is_integer_dtype(index.dtype):
             return
-        elif needs_i8_conversion(index.dtype):
-            values[1] = iNaT
-        else:
-            values[1] = np.nan
 
-        if isinstance(index, PeriodIndex):
-            idx = type(index)(values, freq=index.freq)
-        else:
-            idx = type(index)(values)
+        values[1] = np.nan
 
-            expected = np.array([False] * len(idx), dtype=bool)
-            expected[1] = True
-            tm.assert_numpy_array_equal(idx._isnan, expected)
-            assert idx.hasnans is True
+        idx = type(index)(values)
+
+        expected = np.array([False] * len(idx), dtype=bool)
+        expected[1] = True
+        tm.assert_numpy_array_equal(idx._isnan, expected)
+        assert idx.hasnans is True
 
 
 @pytest.mark.parametrize("na_position", [None, "middle"])