implement deprecation portion of pandas-dev#23675 (pandas-dev#23937)

Author: jbrockmendel

doc/source/whatsnew/v0.24.0.rst

@@ -1043,6 +1043,7 @@ Deprecations
   `use_threads` to reflect the changes in pyarrow 0.11.0. (:issue:`23053`)
 - :func:`pandas.read_excel` has deprecated accepting ``usecols`` as an integer. Please pass in a list of ints from 0 to ``usecols`` inclusive instead (:issue:`23527`)
 - Constructing a :class:`TimedeltaIndex` from data with ``datetime64``-dtyped data is deprecated, will raise ``TypeError`` in a future version (:issue:`23539`)
+- Constructing a :class:`DatetimeIndex` from data with ``timedelta64``-dtyped data is deprecated, will raise ``TypeError`` in a future version (:issue:`23675`)
 - The ``keep_tz=False`` option (the default) of the ``keep_tz`` keyword of
   :meth:`DatetimeIndex.to_series` is deprecated (:issue:`17832`).
 - 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`)

pandas/core/arrays/datetimes.py

@@ -15,8 +15,9 @@
 from pandas.util._decorators import Appender, cache_readonly
 
 from pandas.core.dtypes.common import (
-    _NS_DTYPE, is_datetime64_dtype, is_datetime64tz_dtype, is_int64_dtype,
-    is_object_dtype)
+    _NS_DTYPE, is_datetime64_dtype, is_datetime64tz_dtype, is_extension_type,
+    is_float_dtype, is_int64_dtype, is_object_dtype, is_period_dtype,
+    is_timedelta64_dtype)
 from pandas.core.dtypes.dtypes import DatetimeTZDtype
 from pandas.core.dtypes.generic import ABCIndexClass, ABCSeries
 from pandas.core.dtypes.missing import isna
@@ -1421,6 +1422,83 @@ def to_julian_date(self):
 DatetimeArrayMixin._add_datetimelike_methods()
 
 
+# -------------------------------------------------------------------
+# Constructor Helpers
+
+def maybe_infer_tz(tz, inferred_tz):
+    """
+    If a timezone is inferred from data, check that it is compatible with
+    the user-provided timezone, if any.
+
+    Parameters
+    ----------
+    tz : tzinfo or None
+    inferred_tz : tzinfo or None
+
+    Returns
+    -------
+    tz : tzinfo or None
+
+    Raises
+    ------
+    TypeError : if both timezones are present but do not match
+    """
+    if tz is None:
+        tz = inferred_tz
+    elif inferred_tz is None:
+        pass
+    elif not timezones.tz_compare(tz, inferred_tz):
+        raise TypeError('data is already tz-aware {inferred_tz}, unable to '
+                        'set specified tz: {tz}'
+                        .format(inferred_tz=inferred_tz, tz=tz))
+    return tz
+
+
+def maybe_convert_dtype(data, copy):
+    """
+    Convert data based on dtype conventions, issuing deprecation warnings
+    or errors where appropriate.
+     Parameters
+    ----------
+    data : np.ndarray or pd.Index
+    copy : bool
+     Returns
+    -------
+    data : np.ndarray or pd.Index
+    copy : bool
+     Raises
+    ------
+    TypeError : PeriodDType data is passed
+    """
+    if is_float_dtype(data):
+        # Note: we must cast to datetime64[ns] here in order to treat these
+        #  as wall-times instead of UTC timestamps.
+        data = data.astype(_NS_DTYPE)
+        copy = False
+        # TODO: deprecate this behavior to instead treat symmetrically
+        #  with integer dtypes.  See discussion in GH#23675
+
+    elif is_timedelta64_dtype(data):
+        warnings.warn("Passing timedelta64-dtype data is deprecated, will "
+                      "raise a TypeError in a future version",
+                      FutureWarning, stacklevel=3)
+        data = data.view(_NS_DTYPE)
+
+    elif is_period_dtype(data):
+        # Note: without explicitly raising here, PeriondIndex
+        #  test_setops.test_join_does_not_recur fails
+        raise TypeError("Passing PeriodDtype data is invalid.  "
+                        "Use `data.to_timestamp()` instead")
+
+    elif is_extension_type(data) and not is_datetime64tz_dtype(data):
+        # Includes categorical
+        # TODO: We have no tests for these
+        data = np.array(data, dtype=np.object_)
+        copy = False
+
+    return data, copy
+
+
 def _generate_regular_range(cls, start, end, periods, freq):
     """
     Generate a range of dates with the spans between dates described by

pandas/core/indexes/datetimes.py

@@ -16,16 +16,17 @@
 
 from pandas.core.dtypes.common import (
     _INT64_DTYPE, _NS_DTYPE, ensure_int64, is_datetime64_dtype,
-    is_datetime64_ns_dtype, is_datetimetz, is_dtype_equal, is_float,
-    is_integer, is_integer_dtype, is_list_like, is_period_dtype, is_scalar,
-    is_string_like, pandas_dtype)
+    is_datetime64_ns_dtype, is_datetime64tz_dtype, is_datetimetz,
+    is_dtype_equal, is_float, is_integer, is_integer_dtype, is_list_like,
+    is_period_dtype, is_scalar, is_string_like, pandas_dtype)
 import pandas.core.dtypes.concat as _concat
 from pandas.core.dtypes.generic import ABCSeries
 from pandas.core.dtypes.missing import isna
 
 from pandas.core.arrays import datetimelike as dtl
 from pandas.core.arrays.datetimes import (
-    DatetimeArrayMixin as DatetimeArray, _to_m8)
+    DatetimeArrayMixin as DatetimeArray, _to_m8, maybe_convert_dtype,
+    maybe_infer_tz)
 from pandas.core.base import _shared_docs
 import pandas.core.common as com
 from pandas.core.indexes.base import Index, _index_shared_docs
@@ -246,50 +247,49 @@ def __new__(cls, data=None,
             name = data.name
 
         freq, freq_infer = dtl.maybe_infer_freq(freq)
+        if freq is None and hasattr(data, "freq"):
+            # i.e. DatetimeArray/Index
+            freq = data.freq
+            verify_integrity = False
 
         # if dtype has an embedded tz, capture it
         tz = dtl.validate_tz_from_dtype(dtype, tz)
 
-        if not isinstance(data, (np.ndarray, Index, ABCSeries, DatetimeArray)):
-            # other iterable of some kind
-            if not isinstance(data, (list, tuple)):
+        if not hasattr(data, "dtype"):
+            # e.g. list, tuple
+            if np.ndim(data) == 0:
+                # i.e. generator
                 data = list(data)
-            data = np.asarray(data, dtype='O')
+            data = np.asarray(data)
+            copy = False
         elif isinstance(data, ABCSeries):
             data = data._values
 
-        # data must be Index or np.ndarray here
+        # By this point we are assured to have either a numpy array or Index
+        data, copy = maybe_convert_dtype(data, copy)
+
         if not (is_datetime64_dtype(data) or is_datetimetz(data) or
                 is_integer_dtype(data) or lib.infer_dtype(data) == 'integer'):
             data = tools.to_datetime(data, dayfirst=dayfirst,
                                      yearfirst=yearfirst)
 
-        if isinstance(data, DatetimeArray):
-            if tz is None:
-                tz = data.tz
-            elif data.tz is None:
-                data = data.tz_localize(tz, ambiguous=ambiguous)
-            else:
-                # the tz's must match
-                if not timezones.tz_compare(tz, data.tz):
-                    msg = ('data is already tz-aware {0}, unable to '
-                           'set specified tz: {1}')
-                    raise TypeError(msg.format(data.tz, tz))
-
+        if is_datetime64tz_dtype(data):
+            tz = maybe_infer_tz(tz, data.tz)
             subarr = data._data
 
-            if freq is None:
-                freq = data.freq
-                verify_integrity = False
-        elif issubclass(data.dtype.type, np.datetime64):
+        elif is_datetime64_dtype(data):
+            # tz-naive DatetimeArray/Index or ndarray[datetime64]
+            data = getattr(data, "_data", data)
             if data.dtype != _NS_DTYPE:
                 data = conversion.ensure_datetime64ns(data)
+
             if tz is not None:
                 # Convert tz-naive to UTC
                 tz = timezones.maybe_get_tz(tz)
                 data = conversion.tz_localize_to_utc(data.view('i8'), tz,
                                                      ambiguous=ambiguous)
             subarr = data.view(_NS_DTYPE)
+
         else:
             # must be integer dtype otherwise
             # assume this data are epoch timestamps

pandas/core/tools/datetimes.py

@@ -171,6 +171,8 @@ def _convert_listlike_datetimes(arg, box, format, name=None, tz=None,
         - ndarray of Timestamps if box=False
     """
     from pandas import DatetimeIndex
+    from pandas.core.arrays.datetimes import maybe_convert_dtype
+
     if isinstance(arg, (list, tuple)):
         arg = np.array(arg, dtype='O')
 
@@ -208,6 +210,11 @@ def _convert_listlike_datetimes(arg, box, format, name=None, tz=None,
         raise TypeError('arg must be a string, datetime, list, tuple, '
                         '1-d array, or Series')
 
+    # warn if passing timedelta64, raise for PeriodDtype
+    # NB: this must come after unit transformation
+    orig_arg = arg
+    arg, _ = maybe_convert_dtype(arg, copy=False)
+
     arg = ensure_object(arg)
     require_iso8601 = False
 
@@ -231,7 +238,10 @@ def _convert_listlike_datetimes(arg, box, format, name=None, tz=None,
             # shortcut formatting here
             if format == '%Y%m%d':
                 try:
-                    result = _attempt_YYYYMMDD(arg, errors=errors)
+                    # pass orig_arg as float-dtype may have been converted to
+                    # datetime64[ns]
+                    orig_arg = ensure_object(orig_arg)
+                    result = _attempt_YYYYMMDD(orig_arg, errors=errors)
                 except (ValueError, TypeError, tslibs.OutOfBoundsDatetime):
                     raise ValueError("cannot convert the input to "
                                      "'%Y%m%d' date format")

pandas/tests/indexes/datetimes/test_construction.py

@@ -14,11 +14,51 @@
 from pandas import (
     DatetimeIndex, Index, Timestamp, date_range, datetime, offsets,
     to_datetime)
+from pandas.core.arrays import period_array
 import pandas.util.testing as tm
 
 
 class TestDatetimeIndex(object):
 
+    def test_dti_with_period_data_raises(self):
+        # GH#23675
+        data = pd.PeriodIndex(['2016Q1', '2016Q2'], freq='Q')
+
+        with pytest.raises(TypeError, match="PeriodDtype data is invalid"):
+            DatetimeIndex(data)
+
+        with pytest.raises(TypeError, match="PeriodDtype data is invalid"):
+            to_datetime(data)
+
+        with pytest.raises(TypeError, match="PeriodDtype data is invalid"):
+            DatetimeIndex(period_array(data))
+
+        with pytest.raises(TypeError, match="PeriodDtype data is invalid"):
+            to_datetime(period_array(data))
+
+    def test_dti_with_timedelta64_data_deprecation(self):
+        # GH#23675
+        data = np.array([0], dtype='m8[ns]')
+        with tm.assert_produces_warning(FutureWarning):
+            result = DatetimeIndex(data)
+
+        assert result[0] == Timestamp('1970-01-01')
+
+        with tm.assert_produces_warning(FutureWarning, check_stacklevel=False):
+            result = to_datetime(data)
+
+        assert result[0] == Timestamp('1970-01-01')
+
+        with tm.assert_produces_warning(FutureWarning):
+            result = DatetimeIndex(pd.TimedeltaIndex(data))
+
+        assert result[0] == Timestamp('1970-01-01')
+
+        with tm.assert_produces_warning(FutureWarning, check_stacklevel=False):
+            result = to_datetime(pd.TimedeltaIndex(data))
+
+        assert result[0] == Timestamp('1970-01-01')
+
     def test_construction_caching(self):
 
         df = pd.DataFrame({'dt': pd.date_range('20130101', periods=3),