Remove offset/DTI caching (disabled since 0.14 (#23118)

* Remove offset/DTI caching (disabled since 0.14

* remove unused import

* remove cached_range tests

* fixup remove unused imports

* whatsnew

Author: jbrockmendel

doc/source/whatsnew/v0.24.0.txt

@@ -688,6 +688,7 @@ Other API Changes
 - :meth:`DataFrame.corr` and :meth:`Series.corr` now raise a ``ValueError`` along with a helpful error message instead of a ``KeyError`` when supplied with an invalid method (:issue:`22298`)
 - :meth:`shift` will now always return a copy, instead of the previous behaviour of returning self when shifting by 0 (:issue:`22397`)
 - Slicing a single row of a DataFrame with multiple ExtensionArrays of the same type now preserves the dtype, rather than coercing to object (:issue:`22784`)
+- :class:`DateOffset` attribute `_cacheable` and method `_should_cache` have been removed (:issue:`23118`)
 
 .. _whatsnew_0240.deprecations:
 

pandas/_libs/tslibs/offsets.pyx

@@ -282,11 +282,6 @@ class ApplyTypeError(TypeError):
     pass
 
 
-# TODO: unused.  remove?
-class CacheableOffset(object):
-    _cacheable = True
-
-
 # ---------------------------------------------------------------------
 # Base Classes
 
@@ -296,8 +291,6 @@ class _BaseOffset(object):
     and will (after pickle errors are resolved) go into a cdef class.
     """
     _typ = "dateoffset"
-    _normalize_cache = True
-    _cacheable = False
     _day_opt = None
     _attributes = frozenset(['n', 'normalize'])
 
@@ -386,10 +379,6 @@ class _BaseOffset(object):
         # that allows us to use methods that can go in a `cdef class`
         return self * 1
 
-    # TODO: this is never true.  fix it or get rid of it
-    def _should_cache(self):
-        return self.isAnchored() and self._cacheable
-
     def __repr__(self):
         className = getattr(self, '_outputName', type(self).__name__)
 

pandas/core/arrays/datetimes.py

@@ -13,7 +13,7 @@
     resolution as libresolution)
 
 from pandas.util._decorators import cache_readonly
-from pandas.errors import PerformanceWarning, AbstractMethodError
+from pandas.errors import PerformanceWarning
 from pandas import compat
 
 from pandas.core.dtypes.common import (
@@ -268,27 +268,22 @@ def _generate_range(cls, start, end, periods, freq, tz=None,
                 end, end.tz, start.tz, freq, tz
             )
         if freq is not None:
-            if cls._use_cached_range(freq, _normalized, start, end):
-                # Currently always False; never hit
-                # Should be reimplemented as a part of GH#17914
-                index = cls._cached_range(start, end, periods=periods,
-                                          freq=freq)
-            else:
-                index = _generate_regular_range(cls, start, end, periods, freq)
-
-                if tz is not None and getattr(index, 'tz', None) is None:
-                    arr = conversion.tz_localize_to_utc(
-                        ensure_int64(index.values),
-                        tz, ambiguous=ambiguous)
-
-                    index = cls(arr)
-
-                    # index is localized datetime64 array -> have to convert
-                    # start/end as well to compare
-                    if start is not None:
-                        start = start.tz_localize(tz).asm8
-                    if end is not None:
-                        end = end.tz_localize(tz).asm8
+            # TODO: consider re-implementing _cached_range; GH#17914
+            index = _generate_regular_range(cls, start, end, periods, freq)
+
+            if tz is not None and getattr(index, 'tz', None) is None:
+                arr = conversion.tz_localize_to_utc(
+                    ensure_int64(index.values),
+                    tz, ambiguous=ambiguous)
+
+                index = cls(arr)
+
+                # index is localized datetime64 array -> have to convert
+                # start/end as well to compare
+                if start is not None:
+                    start = start.tz_localize(tz).asm8
+                if end is not None:
+                    end = end.tz_localize(tz).asm8
         else:
             # Create a linearly spaced date_range in local time
             arr = np.linspace(start.value, end.value, periods)
@@ -303,16 +298,6 @@ def _generate_range(cls, start, end, periods, freq, tz=None,
 
         return cls._simple_new(index.values, freq=freq, tz=tz)
 
-    @classmethod
-    def _use_cached_range(cls, freq, _normalized, start, end):
-        # DatetimeArray is mutable, so is not cached
-        return False
-
-    @classmethod
-    def _cached_range(cls, start=None, end=None,
-                      periods=None, freq=None, **kwargs):
-        raise AbstractMethodError(cls)
-
     # -----------------------------------------------------------------
     # Descriptive Properties
 

pandas/core/indexes/datetimes.py

@@ -40,7 +40,7 @@
     DatelikeOps, TimelikeOps, DatetimeIndexOpsMixin,
     wrap_field_accessor, wrap_array_method)
 from pandas.tseries.offsets import (
-    generate_range, CDay, prefix_mapping)
+    CDay, prefix_mapping)
 
 from pandas.core.tools.timedeltas import to_timedelta
 from pandas.util._decorators import Appender, cache_readonly, Substitution
@@ -326,13 +326,6 @@ def _generate_range(cls, start, end, periods, name=None, freq=None,
         out.name = name
         return out
 
-    @classmethod
-    def _use_cached_range(cls, freq, _normalized, start, end):
-        # Note: This always returns False
-        return (freq._should_cache() and
-                not (freq._normalize_cache and not _normalized) and
-                _naive_in_cache_range(start, end))
-
     def _convert_for_op(self, value):
         """ Convert value to be insertable to ndarray """
         if self._has_same_tz(value):
@@ -410,71 +403,6 @@ def nbytes(self):
         # for TZ-aware
         return self._ndarray_values.nbytes
 
-    @classmethod
-    def _cached_range(cls, start=None, end=None, periods=None, freq=None,
-                      name=None):
-        if start is None and end is None:
-            # I somewhat believe this should never be raised externally
-            raise TypeError('Must specify either start or end.')
-        if start is not None:
-            start = Timestamp(start)
-        if end is not None:
-            end = Timestamp(end)
-        if (start is None or end is None) and periods is None:
-            raise TypeError(
-                'Must either specify period or provide both start and end.')
-
-        if freq is None:
-            # This can't happen with external-facing code
-            raise TypeError('Must provide freq.')
-
-        drc = _daterange_cache
-        if freq not in _daterange_cache:
-            xdr = generate_range(offset=freq, start=_CACHE_START,
-                                 end=_CACHE_END)
-
-            arr = tools.to_datetime(list(xdr), box=False)
-
-            cachedRange = DatetimeIndex._simple_new(arr)
-            cachedRange.freq = freq
-            cachedRange = cachedRange.tz_localize(None)
-            cachedRange.name = None
-            drc[freq] = cachedRange
-        else:
-            cachedRange = drc[freq]
-
-        if start is None:
-            if not isinstance(end, Timestamp):
-                raise AssertionError('end must be an instance of Timestamp')
-
-            end = freq.rollback(end)
-
-            endLoc = cachedRange.get_loc(end) + 1
-            startLoc = endLoc - periods
-        elif end is None:
-            if not isinstance(start, Timestamp):
-                raise AssertionError('start must be an instance of Timestamp')
-
-            start = freq.rollforward(start)
-
-            startLoc = cachedRange.get_loc(start)
-            endLoc = startLoc + periods
-        else:
-            if not freq.onOffset(start):
-                start = freq.rollforward(start)
-
-            if not freq.onOffset(end):
-                end = freq.rollback(end)
-
-            startLoc = cachedRange.get_loc(start)
-            endLoc = cachedRange.get_loc(end) + 1
-
-        indexSlice = cachedRange[startLoc:endLoc]
-        indexSlice.name = name
-        indexSlice.freq = freq
-
-        return indexSlice
-
     def _mpl_repr(self):
         # how to represent ourselves to matplotlib
         return libts.ints_to_pydatetime(self.asi8, self.tz)
@@ -832,22 +760,19 @@ def _fast_union(self, other):
         else:
             left, right = other, self
 
-        left_start, left_end = left[0], left[-1]
+        left_end = left[-1]
         right_end = right[-1]
 
-        if not self.freq._should_cache():
-            # concatenate dates
-            if left_end < right_end:
-                loc = right.searchsorted(left_end, side='right')
-                right_chunk = right.values[loc:]
-                dates = _concat._concat_compat((left.values, right_chunk))
-                return self._shallow_copy(dates)
-            else:
-                return left
+        # TODO: consider re-implementing freq._should_cache for fastpath
+
+        # concatenate dates
+        if left_end < right_end:
+            loc = right.searchsorted(left_end, side='right')
+            right_chunk = right.values[loc:]
+            dates = _concat._concat_compat((left.values, right_chunk))
+            return self._shallow_copy(dates)
         else:
-            return type(self)(start=left_start,
-                              end=max(left_end, right_end),
-                              freq=left.freq)
+            return left
 
     def _wrap_union_result(self, other, result):
         name = self.name if self.name == other.name else None
@@ -1724,21 +1649,6 @@ def cdate_range(start=None, end=None, periods=None, freq='C', tz=None,
                          closed=closed, **kwargs)
 
 
-_CACHE_START = Timestamp(datetime(1950, 1, 1))
-_CACHE_END = Timestamp(datetime(2030, 1, 1))
-
-_daterange_cache = {}
-
-
-def _naive_in_cache_range(start, end):
-    if start is None or end is None:
-        return False
-    else:
-        if start.tzinfo is not None or end.tzinfo is not None:
-            return False
-        return start > _CACHE_START and end < _CACHE_END
-
-
 def _time_to_micros(time):
     seconds = time.hour * 60 * 60 + 60 * time.minute + time.second
     return 1000000 * seconds + time.microsecond

pandas/tests/indexes/datetimes/test_date_range.py

@@ -616,23 +616,6 @@ def test_naive_aware_conflicts(self):
         with tm.assert_raises_regex(TypeError, msg):
             aware.join(naive)
 
-    def test_cached_range(self):
-        DatetimeIndex._cached_range(START, END, freq=BDay())
-        DatetimeIndex._cached_range(START, periods=20, freq=BDay())
-        DatetimeIndex._cached_range(end=START, periods=20, freq=BDay())
-
-        with tm.assert_raises_regex(TypeError, "freq"):
-            DatetimeIndex._cached_range(START, END)
-
-        with tm.assert_raises_regex(TypeError, "specify period"):
-            DatetimeIndex._cached_range(START, freq=BDay())
-
-        with tm.assert_raises_regex(TypeError, "specify period"):
-            DatetimeIndex._cached_range(end=END, freq=BDay())
-
-        with tm.assert_raises_regex(TypeError, "start or end"):
-            DatetimeIndex._cached_range(periods=20, freq=BDay())
-
     def test_misc(self):
         end = datetime(2009, 5, 13)
         dr = bdate_range(end=end, periods=20)
@@ -693,29 +676,6 @@ def test_constructor(self):
         with tm.assert_raises_regex(TypeError, msg):
             bdate_range('2011-1-1', '2012-1-1', 'C')
 
-    def test_cached_range(self):
-        DatetimeIndex._cached_range(START, END, freq=CDay())
-        DatetimeIndex._cached_range(START, periods=20,
-                                    freq=CDay())
-        DatetimeIndex._cached_range(end=START, periods=20,
-                                    freq=CDay())
-
-        # with pytest.raises(TypeError):
-        with tm.assert_raises_regex(TypeError, "freq"):
-            DatetimeIndex._cached_range(START, END)
-
-        # with pytest.raises(TypeError):
-        with tm.assert_raises_regex(TypeError, "specify period"):
-            DatetimeIndex._cached_range(START, freq=CDay())
-
-        # with pytest.raises(TypeError):
-        with tm.assert_raises_regex(TypeError, "specify period"):
-            DatetimeIndex._cached_range(end=END, freq=CDay())
-
-        # with pytest.raises(TypeError):
-        with tm.assert_raises_regex(TypeError, "start or end"):
-            DatetimeIndex._cached_range(periods=20, freq=CDay())
-
     def test_misc(self):
         end = datetime(2009, 5, 13)
         dr = bdate_range(end=end, periods=20, freq='C')