CLN: Follow-ups to #24024 (#24573)

Author: jbrockmendel

pandas/core/algorithms.py

@@ -350,9 +350,6 @@ def unique(values):
     if is_extension_array_dtype(values):
         # Dispatch to extension dtype's unique.
         return values.unique()
-    elif is_datetime64tz_dtype(values):
-        # TODO: merge this check into the previous one following #24024
-        return values.unique()
 
     original = values
     htable, _, values, dtype, ndtype = _get_hashtable_algo(values)

pandas/core/arrays/datetimelike.py

@@ -47,10 +47,6 @@ def cmp_method(self, other):
         if isinstance(other, ABCDataFrame):
             return NotImplemented
 
-        if isinstance(other, (np.ndarray, ABCIndexClass, ABCSeries, cls)):
-            if other.ndim > 0 and len(self) != len(other):
-                raise ValueError('Lengths must match to compare')
-
         if needs_i8_conversion(self) and needs_i8_conversion(other):
             # we may need to directly compare underlying
             # representations
@@ -586,10 +582,6 @@ def view(self, dtype=None):
 
     # ------------------------------------------------------------------
     # ExtensionArray Interface
-    # TODO:
-    #   * _from_sequence
-    #   * argsort / _values_for_argsort
-    #   * _reduce
 
     def unique(self):
         result = unique1d(self.asi8)

pandas/core/arrays/datetimes.py

@@ -280,8 +280,7 @@ def __init__(self, values, dtype=_NS_DTYPE, freq=None, copy=False):
             )
             raise ValueError(msg.format(values.dtype))
 
-        dtype = pandas_dtype(dtype)
-        _validate_dt64_dtype(dtype)
+        dtype = _validate_dt64_dtype(dtype)
 
         if freq == "infer":
             msg = (

pandas/core/generic.py

@@ -3082,7 +3082,7 @@ def _box_item_values(self, key, values):
     def _maybe_cache_changed(self, item, value):
         """The object has called back to us saying maybe it has changed.
         """
-        self._data.set(item, value, check=False)
+        self._data.set(item, value)
 
     @property
     def _is_cached(self):

pandas/core/indexes/base.py

@@ -68,8 +68,7 @@ def cmp_method(self, other):
             if other.ndim > 0 and len(self) != len(other):
                 raise ValueError('Lengths must match to compare')
 
-        from .multi import MultiIndex
-        if is_object_dtype(self) and not isinstance(self, MultiIndex):
+        if is_object_dtype(self) and not isinstance(self, ABCMultiIndex):
             # don't pass MultiIndex
             with np.errstate(all='ignore'):
                 result = ops._comp_method_OBJECT_ARRAY(op, self.values, other)
@@ -1307,8 +1306,7 @@ def set_names(self, names, level=None, inplace=False):
                    names=['species', 'year'])
         """
 
-        from .multi import MultiIndex
-        if level is not None and not isinstance(self, MultiIndex):
+        if level is not None and not isinstance(self, ABCMultiIndex):
             raise ValueError('Level must be None for non-MultiIndex')
 
         if level is not None and not is_list_like(level) and is_list_like(
@@ -3145,9 +3143,8 @@ def _reindex_non_unique(self, target):
     @Appender(_index_shared_docs['join'])
     def join(self, other, how='left', level=None, return_indexers=False,
              sort=False):
-        from .multi import MultiIndex
-        self_is_mi = isinstance(self, MultiIndex)
-        other_is_mi = isinstance(other, MultiIndex)
+        self_is_mi = isinstance(self, ABCMultiIndex)
+        other_is_mi = isinstance(other, ABCMultiIndex)
 
         # try to figure out the join level
         # GH3662
@@ -4394,8 +4391,7 @@ def groupby(self, values):
 
         # TODO: if we are a MultiIndex, we can do better
         # that converting to tuples
-        from .multi import MultiIndex
-        if isinstance(values, MultiIndex):
+        if isinstance(values, ABCMultiIndex):
             values = values.values
         values = ensure_categorical(values)
         result = values._reverse_indexer()

pandas/core/indexes/datetimelike.py

@@ -31,23 +31,24 @@
 _index_doc_kwargs = dict(ibase._index_doc_kwargs)
 
 
-def ea_passthrough(name):
+def ea_passthrough(array_method):
     """
     Make an alias for a method of the underlying ExtensionArray.
 
     Parameters
     ----------
-    name : str
+    array_method : method on an Array class
 
     Returns
     -------
     method
     """
+
     def method(self, *args, **kwargs):
-        return getattr(self._eadata, name)(*args, **kwargs)
+        return array_method(self._data, *args, **kwargs)
 
-    method.__name__ = name
-    # TODO: docstrings
+    method.__name__ = array_method.__name__
+    method.__doc__ = array_method.__doc__
     return method
 
 
@@ -67,9 +68,10 @@ class DatetimeIndexOpsMixin(ExtensionOpsMixin):
     _resolution = cache_readonly(DatetimeLikeArrayMixin._resolution.fget)
     resolution = cache_readonly(DatetimeLikeArrayMixin.resolution.fget)
 
-    _box_values = ea_passthrough("_box_values")
-    _maybe_mask_results = ea_passthrough("_maybe_mask_results")
-    __iter__ = ea_passthrough("__iter__")
+    _box_values = ea_passthrough(DatetimeLikeArrayMixin._box_values)
+    _maybe_mask_results = ea_passthrough(
+        DatetimeLikeArrayMixin._maybe_mask_results)
+    __iter__ = ea_passthrough(DatetimeLikeArrayMixin.__iter__)
 
     @property
     def _eadata(self):
@@ -275,9 +277,6 @@ def sort_values(self, return_indexer=False, ascending=True):
             if not ascending:
                 sorted_values = sorted_values[::-1]
 
-            sorted_values = self._maybe_box_as_values(sorted_values,
-                                                      **attribs)
-
             return self._simple_new(sorted_values, **attribs)
 
     @Appender(_index_shared_docs['take'] % _index_doc_kwargs)
@@ -613,14 +612,6 @@ def _concat_same_dtype(self, to_concat, name):
         new_data = type(self._values)._concat_same_type(to_concat).asi8
         return self._simple_new(new_data, **attribs)
 
-    def _maybe_box_as_values(self, values, **attribs):
-        # TODO(DatetimeArray): remove
-        # This is a temporary shim while PeriodArray is an ExtensoinArray,
-        # but others are not. When everyone is an ExtensionArray, this can
-        # be removed. Currently used in
-        # - sort_values
-        return values
-
     @Appender(_index_shared_docs['astype'])
     def astype(self, dtype, copy=True):
         if is_dtype_equal(self.dtype, dtype) and copy is False:

pandas/core/indexes/datetimes.py

@@ -356,36 +356,6 @@ def tz(self, value):
 
     tzinfo = tz
 
-    @property
-    def size(self):
-        # TODO: Remove this when we have a DatetimeTZArray
-        # Necessary to avoid recursion error since DTI._values is a DTI
-        # for TZ-aware
-        return self._ndarray_values.size
-
-    @property
-    def shape(self):
-        # TODO: Remove this when we have a DatetimeTZArray
-        # Necessary to avoid recursion error since DTI._values is a DTI
-        # for TZ-aware
-        return self._ndarray_values.shape
-
-    @property
-    def nbytes(self):
-        # TODO: Remove this when we have a DatetimeTZArray
-        # Necessary to avoid recursion error since DTI._values is a DTI
-        # for TZ-aware
-        return self._ndarray_values.nbytes
-
-    def memory_usage(self, deep=False):
-        # TODO: Remove this when we have a DatetimeTZArray
-        # Necessary to avoid recursion error since DTI._values is a DTI
-        # for TZ-aware
-        result = self._ndarray_values.nbytes
-        # include our engine hashtable
-        result += self._engine.sizeof(deep=deep)
-        return result
-
     @cache_readonly
     def _is_dates_only(self):
         """Return a boolean if we are only dates (and don't have a timezone)"""
@@ -455,11 +425,11 @@ def _mpl_repr(self):
 
     def _format_native_types(self, na_rep='NaT', date_format=None, **kwargs):
         from pandas.io.formats.format import _get_format_datetime64_from_values
-        format = _get_format_datetime64_from_values(self, date_format)
+        fmt = _get_format_datetime64_from_values(self, date_format)
 
         return libts.format_array_from_datetime(self.asi8,
                                                 tz=self.tz,
-                                                format=format,
+                                                format=fmt,
                                                 na_rep=na_rep)
 
     @property
@@ -1142,9 +1112,9 @@ def slice_indexer(self, start=None, end=None, step=None, kind=None):
     is_normalized = cache_readonly(DatetimeArray.is_normalized.fget)
     _resolution = cache_readonly(DatetimeArray._resolution.fget)
 
-    strftime = ea_passthrough("strftime")
-    _has_same_tz = ea_passthrough("_has_same_tz")
-    __array__ = ea_passthrough("__array__")
+    strftime = ea_passthrough(DatetimeArray.strftime)
+    _has_same_tz = ea_passthrough(DatetimeArray._has_same_tz)
+    __array__ = ea_passthrough(DatetimeArray.__array__)
 
     @property
     def offset(self):

pandas/core/indexes/multi.py

@@ -1468,9 +1468,9 @@ def to_frame(self, index=True, name=None):
         # Guarantee resulting column order
         result = DataFrame(
             OrderedDict([
-                ((level if name is None else name),
+                ((level if lvlname is None else lvlname),
                  self._get_level_values(level))
-                for name, level in zip(idx_names, range(len(self.levels)))
+                for lvlname, level in zip(idx_names, range(len(self.levels)))
             ]),
             copy=False
         )

pandas/core/indexes/period.py

@@ -357,17 +357,6 @@ def func(x):
                 return Period._from_ordinal(ordinal=x, freq=self.freq)
         return func
 
-    def _maybe_box_as_values(self, values, **attribs):
-        """Box an array of ordinals to a PeriodArray
-
-        This is purely for compatibility between PeriodIndex
-        and Datetime/TimedeltaIndex. Once these are all backed by
-        an ExtensionArray, this can be removed
-        """
-        # TODO(DatetimeArray): remove
-        freq = attribs['freq']
-        return PeriodArray(values, freq=freq)
-
     def _maybe_convert_timedelta(self, other):
         """
         Convert timedelta-like input to an integer multiple of self.freq

pandas/core/indexes/timedeltas.py

@@ -303,11 +303,6 @@ def _format_native_types(self, na_rep='NaT', date_format=None, **kwargs):
     _is_monotonic_decreasing = Index.is_monotonic_decreasing
     _is_unique = Index.is_unique
 
-    _create_comparison_method = DatetimeIndexOpsMixin._create_comparison_method
-    # TODO: make sure we have a test for name retention analogous
-    #  to series.test_arithmetic.test_ser_cmp_result_names;
-    #  also for PeriodIndex which I think may be missing one
-
     @property
     def _box_func(self):
         return lambda x: Timedelta(x, unit='ns')

pandas/core/internals/blocks.py

@@ -338,7 +338,7 @@ def concat_same_type(self, to_concat, placement=None):
     def iget(self, i):
         return self.values[i]
 
-    def set(self, locs, values, check=False):
+    def set(self, locs, values):
         """
         Modify Block in-place with new item value
 
@@ -2416,22 +2416,14 @@ def f(m, v, i):
 
         return blocks
 
-    def set(self, locs, values, check=False):
+    def set(self, locs, values):
         """
         Modify Block in-place with new item value
 
         Returns
         -------
         None
         """
-
-        # GH6026
-        if check:
-            try:
-                if (self.values[locs] == values).all():
-                    return
-            except (IndexError, ValueError):
-                pass
         try:
             self.values[locs] = values
         except (ValueError):
@@ -2902,7 +2894,7 @@ def should_store(self, value):
                 not is_datetime64tz_dtype(value) and
                 not is_extension_array_dtype(value))
 
-    def set(self, locs, values, check=False):
+    def set(self, locs, values):
         """
         Modify Block in-place with new item value
 
@@ -3053,8 +3045,7 @@ def _try_coerce_args(self, values, other):
         elif (is_null_datelike_scalar(other) or
               (lib.is_scalar(other) and isna(other))):
             other = tslibs.iNaT
-        elif isinstance(other, (self._holder, DatetimeArray)):
-            # TODO: DatetimeArray check will be redundant after GH#24024
+        elif isinstance(other, self._holder):
             if other.tz != self.values.tz:
                 raise ValueError("incompatible or non tz-aware value")
             other = _block_shape(other.asi8, ndim=self.ndim)

pandas/core/internals/managers.py

@@ -1009,11 +1009,10 @@ def delete(self, item):
         self._shape = None
         self._rebuild_blknos_and_blklocs()
 
-    def set(self, item, value, check=False):
+    def set(self, item, value):
         """
         Set new item in-place. Does not consolidate. Adds new Block if not
         contained in the current set of items
-        if check, then validate that we are not setting the same data in-place
         """
         # FIXME: refactor, clearly separate broadcasting & zip-like assignment
         #        can prob also fix the various if tests for sparse/categorical
@@ -1065,7 +1064,7 @@ def value_getitem(placement):
             blk = self.blocks[blkno]
             blk_locs = blklocs[val_locs.indexer]
             if blk.should_store(value):
-                blk.set(blk_locs, value_getitem(val_locs), check=check)
+                blk.set(blk_locs, value_getitem(val_locs))
             else:
                 unfit_mgr_locs.append(blk.mgr_locs.as_array[blk_locs])
                 unfit_val_locs.append(val_locs)