Merge remote-tracking branch 'upstream/master' into dtype-only

Author: TomAugspurger

doc/source/whatsnew/v0.24.0.rst

@@ -1076,6 +1076,7 @@ Deprecations
 - Timezone converting a tz-aware ``datetime.datetime`` or :class:`Timestamp` with :class:`Timestamp` and the ``tz`` argument is now deprecated. Instead, use :meth:`Timestamp.tz_convert` (:issue:`23579`)
 - :func:`pandas.types.is_period` is deprecated in favor of `pandas.types.is_period_dtype` (:issue:`23917`)
 - :func:`pandas.types.is_datetimetz` is deprecated in favor of `pandas.types.is_datetime64tz` (:issue:`23917`)
+- Creating a :class:`TimedeltaIndex` or :class:`DatetimeIndex` by passing range arguments `start`, `end`, and `periods` is deprecated in favor of :func:`timedelta_range` and :func:`date_range` (:issue:`23919`)
 
 .. _whatsnew_0240.deprecations.datetimelike_int_ops:
 

pandas/_libs/tslibs/timestamps.pyx

@@ -377,13 +377,15 @@ cdef class _Timestamp(datetime):
             neg_other = -other
             return self + neg_other
 
+        typ = getattr(other, '_typ', None)
+
         # a Timestamp-DatetimeIndex -> yields a negative TimedeltaIndex
-        elif getattr(other, '_typ', None) == 'datetimeindex':
+        if typ in ('datetimeindex', 'datetimearray'):
             # timezone comparison is performed in DatetimeIndex._sub_datelike
             return -other.__sub__(self)
 
         # a Timestamp-TimedeltaIndex -> yields a negative TimedeltaIndex
-        elif getattr(other, '_typ', None) == 'timedeltaindex':
+        elif typ in ('timedeltaindex', 'timedeltaarray'):
             return (-other).__add__(self)
 
         elif other is NaT:

pandas/core/arrays/timedeltas.py

@@ -7,7 +7,7 @@
 
 import numpy as np
 
-from pandas._libs import tslibs
+from pandas._libs import algos, tslibs
 from pandas._libs.tslibs import NaT, Timedelta, Timestamp, iNaT
 from pandas._libs.tslibs.fields import get_timedelta_field
 from pandas._libs.tslibs.timedeltas import (
@@ -24,7 +24,7 @@
 from pandas.core.dtypes.missing import isna
 
 from pandas.core import ops
-from pandas.core.algorithms import checked_add_with_arr
+from pandas.core.algorithms import checked_add_with_arr, unique1d
 import pandas.core.common as com
 
 from pandas.tseries.frequencies import to_offset
@@ -162,15 +162,29 @@ def _simple_new(cls, values, freq=None, dtype=_TD_DTYPE):
         result._freq = freq
         return result
 
-    def __new__(cls, values, freq=None, dtype=_TD_DTYPE):
+    def __new__(cls, values, freq=None, dtype=_TD_DTYPE, copy=False):
 
         freq, freq_infer = dtl.maybe_infer_freq(freq)
 
-        values = np.array(values, copy=False)
-        if values.dtype == np.object_:
-            values = array_to_timedelta64(values)
+        values, inferred_freq = sequence_to_td64ns(
+            values, copy=copy, unit=None)
+        if inferred_freq is not None:
+            if freq is not None and freq != inferred_freq:
+                raise ValueError('Inferred frequency {inferred} from passed '
+                                 'values does not conform to passed frequency '
+                                 '{passed}'
+                                 .format(inferred=inferred_freq,
+                                         passed=freq.freqstr))
+            elif freq is None:
+                freq = inferred_freq
+                freq_infer = False
 
         result = cls._simple_new(values, freq=freq)
+        # check that we are matching freqs
+        if inferred_freq is None and len(result) > 0:
+            if freq is not None and not freq_infer:
+                cls._validate_frequency(result, freq)
+
         if freq_infer:
             result.freq = to_offset(result.inferred_freq)
 
@@ -227,6 +241,21 @@ def _validate_fill_value(self, fill_value):
                              "Got '{got}'.".format(got=fill_value))
         return fill_value
 
+    # monotonicity/uniqueness properties are called via frequencies.infer_freq,
+    #  see GH#23789
+
+    @property
+    def _is_monotonic_increasing(self):
+        return algos.is_monotonic(self.asi8, timelike=True)[0]
+
+    @property
+    def _is_monotonic_decreasing(self):
+        return algos.is_monotonic(self.asi8, timelike=True)[1]
+
+    @property
+    def _is_unique(self):
+        return len(unique1d(self.asi8)) == len(self)
+
     # ----------------------------------------------------------------
     # Arithmetic Methods
 
@@ -283,7 +312,7 @@ def _add_datetimelike_scalar(self, other):
         result = checked_add_with_arr(i8, other.value,
                                       arr_mask=self._isnan)
         result = self._maybe_mask_results(result)
-        return DatetimeArrayMixin(result, tz=other.tz)
+        return DatetimeArrayMixin(result, tz=other.tz, freq=self.freq)
 
     def _addsub_offset_array(self, other, op):
         # Add or subtract Array-like of DateOffset objects

pandas/core/groupby/ops.py

@@ -7,7 +7,6 @@
 """
 
 import collections
-import copy
 
 import numpy as np
 

pandas/core/indexes/datetimes.py

@@ -50,7 +50,13 @@ def _new_DatetimeIndex(cls, d):
     # so need to localize
     tz = d.pop('tz', None)
 
-    result = cls.__new__(cls, verify_integrity=False, **d)
+    with warnings.catch_warnings():
+        # we ignore warnings from passing verify_integrity=False
+        # TODO: If we knew what was going in to **d, we might be able to
+        #  go through _simple_new instead
+        warnings.simplefilter("ignore")
+        result = cls.__new__(cls, verify_integrity=False, **d)
+
     if tz is not None:
         result = result.tz_localize('UTC').tz_convert(tz)
     return result
@@ -220,10 +226,20 @@ def __new__(cls, data=None,
                 freq=None, start=None, end=None, periods=None, tz=None,
                 normalize=False, closed=None, ambiguous='raise',
                 dayfirst=False, yearfirst=False, dtype=None,
-                copy=False, name=None, verify_integrity=True):
+                copy=False, name=None, verify_integrity=None):
+
+        if verify_integrity is not None:
+            warnings.warn("The 'verify_integrity' argument is deprecated, "
+                          "will be removed in a future version.",
+                          FutureWarning, stacklevel=2)
+        else:
+            verify_integrity = True
 
         if data is None:
-            # TODO: Remove this block and associated kwargs; GH#20535
+            warnings.warn("Creating a DatetimeIndex by passing range "
+                          "endpoints is deprecated.  Use "
+                          "`pandas.date_range` instead.",
+                          FutureWarning, stacklevel=2)
             result = cls._generate_range(start, end, periods,
                                          freq=freq, tz=tz, normalize=normalize,
                                          closed=closed, ambiguous=ambiguous)
@@ -756,8 +772,8 @@ def snap(self, freq='S'):
             snapped[i] = s
 
         # we know it conforms; skip check
-        return DatetimeIndex(snapped, freq=freq, verify_integrity=False)
-        # TODO: what about self.name?  if so, use shallow_copy?
+        return DatetimeIndex._simple_new(snapped, freq=freq)
+        # TODO: what about self.name?  tz? if so, use shallow_copy?
 
     def unique(self, level=None):
         if level is not None:
@@ -1135,6 +1151,11 @@ def slice_indexer(self, start=None, end=None, step=None, kind=None):
     # --------------------------------------------------------------------
     # Wrapping DatetimeArray
 
+    # Compat for frequency inference, see GH#23789
+    _is_monotonic_increasing = Index.is_monotonic_increasing
+    _is_monotonic_decreasing = Index.is_monotonic_decreasing
+    _is_unique = Index.is_unique
+
     _timezone = cache_readonly(DatetimeArray._timezone.fget)
     is_normalized = cache_readonly(DatetimeArray.is_normalized.fget)
     _resolution = cache_readonly(DatetimeArray._resolution.fget)
@@ -1514,9 +1535,13 @@ def date_range(start=None, end=None, periods=None, freq=None, tz=None,
     if freq is None and com._any_none(periods, start, end):
         freq = 'D'
 
-    return DatetimeIndex(start=start, end=end, periods=periods,
-                         freq=freq, tz=tz, normalize=normalize, name=name,
-                         closed=closed, **kwargs)
+    result = DatetimeIndex._generate_range(
+        start=start, end=end, periods=periods,
+        freq=freq, tz=tz, normalize=normalize,
+        closed=closed, **kwargs)
+
+    result.name = name
+    return result
 
 
 def bdate_range(start=None, end=None, periods=None, freq='B', tz=None,
@@ -1602,9 +1627,9 @@ def bdate_range(start=None, end=None, periods=None, freq='B', tz=None,
                'weekmask are passed, got frequency {freq}').format(freq=freq)
         raise ValueError(msg)
 
-    return DatetimeIndex(start=start, end=end, periods=periods,
-                         freq=freq, tz=tz, normalize=normalize, name=name,
-                         closed=closed, **kwargs)
+    return date_range(start=start, end=end, periods=periods,
+                      freq=freq, tz=tz, normalize=normalize, name=name,
+                      closed=closed, **kwargs)
 
 
 def cdate_range(start=None, end=None, periods=None, freq='C', tz=None,
@@ -1661,9 +1686,10 @@ def cdate_range(start=None, end=None, periods=None, freq='C', tz=None,
         holidays = kwargs.pop('holidays', [])
         weekmask = kwargs.pop('weekmask', 'Mon Tue Wed Thu Fri')
         freq = CDay(holidays=holidays, weekmask=weekmask)
-    return DatetimeIndex(start=start, end=end, periods=periods, freq=freq,
-                         tz=tz, normalize=normalize, name=name,
-                         closed=closed, **kwargs)
+
+    return date_range(start=start, end=end, periods=periods, freq=freq,
+                      tz=tz, normalize=normalize, name=name,
+                      closed=closed, **kwargs)
 
 
 def _time_to_micros(time):

pandas/core/indexes/timedeltas.py

@@ -1,5 +1,6 @@
 """ implement the TimedeltaIndex """
 from datetime import datetime
+import warnings
 
 import numpy as np
 
@@ -132,12 +133,22 @@ def _join_i8_wrapper(joinf, **kwargs):
 
     def __new__(cls, data=None, unit=None, freq=None, start=None, end=None,
                 periods=None, closed=None, dtype=None, copy=False,
-                name=None, verify_integrity=True):
+                name=None, verify_integrity=None):
+
+        if verify_integrity is not None:
+            warnings.warn("The 'verify_integrity' argument is deprecated, "
+                          "will be removed in a future version.",
+                          FutureWarning, stacklevel=2)
+        else:
+            verify_integrity = True
 
         freq, freq_infer = dtl.maybe_infer_freq(freq)
 
         if data is None:
-            # TODO: Remove this block and associated kwargs; GH#20535
+            warnings.warn("Creating a TimedeltaIndex by passing range "
+                          "endpoints is deprecated.  Use "
+                          "`pandas.timedelta_range` instead.",
+                          FutureWarning, stacklevel=2)
             result = cls._generate_range(start, end, periods, freq,
                                          closed=closed)
             result.name = name
@@ -250,6 +261,11 @@ def _format_native_types(self, na_rep=u'NaT', date_format=None, **kwargs):
 
     total_seconds = wrap_array_method(TimedeltaArray.total_seconds, True)
 
+    # Compat for frequency inference, see GH#23789
+    _is_monotonic_increasing = Index.is_monotonic_increasing
+    _is_monotonic_decreasing = Index.is_monotonic_decreasing
+    _is_unique = Index.is_unique
+
     # -------------------------------------------------------------------
 
     @Appender(_index_shared_docs['astype'])
@@ -735,5 +751,8 @@ def timedelta_range(start=None, end=None, periods=None, freq=None,
     if freq is None and com._any_none(periods, start, end):
         freq = 'D'
 
-    return TimedeltaIndex(start=start, end=end, periods=periods,
-                          freq=freq, name=name, closed=closed)
+    freq, freq_infer = dtl.maybe_infer_freq(freq)
+    result = TimedeltaIndex._generate_range(start, end, periods, freq,
+                                            closed=closed)
+    result.name = name
+    return result

pandas/core/resample.py

@@ -26,7 +26,7 @@
 from pandas.core.groupby.ops import BinGrouper
 from pandas.core.indexes.datetimes import DatetimeIndex, date_range
 from pandas.core.indexes.period import PeriodIndex
-from pandas.core.indexes.timedeltas import TimedeltaIndex
+from pandas.core.indexes.timedeltas import TimedeltaIndex, timedelta_range
 
 from pandas.tseries.frequencies import is_subperiod, is_superperiod, to_offset
 from pandas.tseries.offsets import (
@@ -1398,11 +1398,11 @@ def _get_time_bins(self, ax):
         # because replace() will swallow the nanosecond part
         # thus last bin maybe slightly before the end if the end contains
         # nanosecond part and lead to `Values falls after last bin` error
-        binner = labels = DatetimeIndex(freq=self.freq,
-                                        start=first,
-                                        end=last,
-                                        tz=tz,
-                                        name=ax.name)
+        binner = labels = date_range(freq=self.freq,
+                                     start=first,
+                                     end=last,
+                                     tz=tz,
+                                     name=ax.name)
 
         # GH 15549
         # In edge case of tz-aware resapmling binner last index can be
@@ -1484,10 +1484,10 @@ def _get_time_delta_bins(self, ax):
             return binner, [], labels
 
         start, end = ax.min(), ax.max()
-        labels = binner = TimedeltaIndex(start=start,
-                                         end=end,
-                                         freq=self.freq,
-                                         name=ax.name)
+        labels = binner = timedelta_range(start=start,
+                                          end=end,
+                                          freq=self.freq,
+                                          name=ax.name)
 
         end_stamps = labels + self.freq
         bins = ax.searchsorted(end_stamps, side='left')

pandas/io/packers.py

@@ -604,8 +604,8 @@ def decode(obj):
 
     elif typ == u'datetime_index':
         data = unconvert(obj[u'data'], np.int64, obj.get(u'compress'))
-        d = dict(name=obj[u'name'], freq=obj[u'freq'], verify_integrity=False)
-        result = globals()[obj[u'klass']](data, **d)
+        d = dict(name=obj[u'name'], freq=obj[u'freq'])
+        result = DatetimeIndex._simple_new(data, **d)
         tz = obj[u'tz']
 
         # reverse tz conversion