BUG: constructing DTA/TDA from xarray/dask/pandasarray

pandas/core/arrays/datetimes.py

@@ -59,17 +59,18 @@
     pandas_dtype,
 )
 from pandas.core.dtypes.dtypes import DatetimeTZDtype
-from pandas.core.dtypes.generic import (
-    ABCIndex,
-    ABCPandasArray,
-    ABCSeries,
-)
+from pandas.core.dtypes.generic import ABCMultiIndex
 from pandas.core.dtypes.missing import isna
 
 from pandas.core.algorithms import checked_add_with_arr
-from pandas.core.arrays import datetimelike as dtl
+from pandas.core.arrays import (
+    ExtensionArray,
+    datetimelike as dtl,
+)
 from pandas.core.arrays._ranges import generate_regular_range
+from pandas.core.arrays.integer import IntegerArray
 import pandas.core.common as com
+from pandas.core.construction import extract_array
 
 from pandas.tseries.frequencies import get_period_alias
 from pandas.tseries.offsets import (
@@ -239,8 +240,9 @@ class DatetimeArray(dtl.TimelikeOps, dtl.DatelikeOps):
     _freq = None
 
     def __init__(self, values, dtype=DT64NS_DTYPE, freq=None, copy=False):
-        if isinstance(values, (ABCSeries, ABCIndex)):
-            values = values._values
+        values = extract_array(values, extract_numpy=True)
+        if isinstance(values, IntegerArray):
+            values = values.to_numpy("int64", na_value=iNaT)
 
         inferred_freq = getattr(values, "_freq", None)
 
@@ -266,7 +268,7 @@ def __init__(self, values, dtype=DT64NS_DTYPE, freq=None, copy=False):
         if not isinstance(values, np.ndarray):
             raise ValueError(
                 f"Unexpected type '{type(values).__name__}'. 'values' must be "
-                "a DatetimeArray ndarray, or Series or Index containing one of those."
+                "a DatetimeArray, ndarray, or Series or Index containing one of those."
             )
         if values.ndim not in [1, 2]:
             raise ValueError("Only 1-dimensional input arrays are supported.")
@@ -1975,30 +1977,29 @@ def sequence_to_dt64ns(
     dtype = _validate_dt64_dtype(dtype)
     tz = timezones.maybe_get_tz(tz)
 
+    # if dtype has an embedded tz, capture it
+    tz = validate_tz_from_dtype(dtype, tz)
+
     if not hasattr(data, "dtype"):
         # e.g. list, tuple
         if np.ndim(data) == 0:
             # i.e. generator
             data = list(data)
         data = np.asarray(data)
         copy = False
-    elif isinstance(data, ABCSeries):
-        data = data._values
-    if isinstance(data, ABCPandasArray):
-        data = data.to_numpy()
-
-    if hasattr(data, "freq"):
-        # i.e. DatetimeArray/Index
-        inferred_freq = data.freq
+    elif isinstance(data, ABCMultiIndex):
+        raise TypeError("Cannot create a DatetimeArray from a MultiIndex.")
+    else:
+        data = extract_array(data, extract_numpy=True)
 
-    # if dtype has an embedded tz, capture it
-    tz = validate_tz_from_dtype(dtype, tz)
+    if isinstance(data, IntegerArray):
+        data = data.to_numpy("int64", na_value=iNaT)
+    elif not isinstance(data, (np.ndarray, ExtensionArray)):
+        # GH#24539 e.g. xarray, dask object
+        data = np.asarray(data)
 
-    if isinstance(data, ABCIndex):
-        if data.nlevels > 1:
-            # Without this check, data._data below is None
-            raise TypeError("Cannot create a DatetimeArray from a MultiIndex.")
-        data = data._data
+    if isinstance(data, DatetimeArray):
+        inferred_freq = data.freq
 
     # By this point we are assured to have either a numpy array or Index
     data, copy = maybe_convert_dtype(data, copy)
@@ -2042,13 +2043,14 @@ def sequence_to_dt64ns(
     if is_datetime64tz_dtype(data_dtype):
         # DatetimeArray -> ndarray
         tz = _maybe_infer_tz(tz, data.tz)
-        result = data._data
+        result = data._ndarray
 
     elif is_datetime64_dtype(data_dtype):
         # tz-naive DatetimeArray or ndarray[datetime64]
-        data = getattr(data, "_data", data)
+        data = getattr(data, "_ndarray", data)
         if data.dtype != DT64NS_DTYPE:
             data = conversion.ensure_datetime64ns(data)
+            copy = False
 
         if tz is not None:
             # Convert tz-naive to UTC
@@ -2085,7 +2087,7 @@ def sequence_to_dt64ns(
 
 
 def objects_to_datetime64ns(
-    data,
+    data: np.ndarray,
     dayfirst,
     yearfirst,
     utc=False,

pandas/core/arrays/timedeltas.py

@@ -53,15 +53,13 @@
     pandas_dtype,
 )
 from pandas.core.dtypes.dtypes import DatetimeTZDtype
-from pandas.core.dtypes.generic import (
-    ABCSeries,
-    ABCTimedeltaIndex,
-)
+from pandas.core.dtypes.generic import ABCMultiIndex
 from pandas.core.dtypes.missing import isna
 
 from pandas.core import nanops
 from pandas.core.algorithms import checked_add_with_arr
 from pandas.core.arrays import (
+    ExtensionArray,
     IntegerArray,
     datetimelike as dtl,
 )
@@ -170,7 +168,9 @@ def dtype(self) -> np.dtype:
     _freq = None
 
     def __init__(self, values, dtype=TD64NS_DTYPE, freq=lib.no_default, copy=False):
-        values = extract_array(values)
+        values = extract_array(values, extract_numpy=True)
+        if isinstance(values, IntegerArray):
+            values = values.to_numpy("int64", na_value=tslibs.iNaT)
 
         inferred_freq = getattr(values, "_freq", None)
         explicit_none = freq is None
@@ -190,7 +190,7 @@ def __init__(self, values, dtype=TD64NS_DTYPE, freq=lib.no_default, copy=False):
         if not isinstance(values, np.ndarray):
             msg = (
                 f"Unexpected type '{type(values).__name__}'. 'values' must be a "
-                "TimedeltaArray ndarray, or Series or Index containing one of those."
+                "TimedeltaArray, ndarray, or Series or Index containing one of those."
             )
             raise ValueError(msg)
         if values.ndim not in [1, 2]:
@@ -950,20 +950,23 @@ def sequence_to_td64ns(
             # i.e. generator
             data = list(data)
         data = np.array(data, copy=False)
-    elif isinstance(data, ABCSeries):
-        data = data._values
-    elif isinstance(data, ABCTimedeltaIndex):
-        inferred_freq = data.freq
-        data = data._data._ndarray
-    elif isinstance(data, TimedeltaArray):
-        inferred_freq = data.freq
-        data = data._ndarray
-    elif isinstance(data, IntegerArray):
-        data = data.to_numpy("int64", na_value=tslibs.iNaT)
+    elif isinstance(data, ABCMultiIndex):
+        raise TypeError("Cannot create a DatetimeArray from a MultiIndex.")
+    else:
+        data = extract_array(data, extract_numpy=True)
+
+    if isinstance(data, IntegerArray):
+        data = data.to_numpy("int64", na_value=iNaT)
+    elif not isinstance(data, (np.ndarray, ExtensionArray)):
+        # GH#24539 e.g. xarray, dask object
+        data = np.asarray(data)
     elif is_categorical_dtype(data.dtype):
         data = data.categories.take(data.codes, fill_value=NaT)._values
         copy = False
 
+    if isinstance(data, TimedeltaArray):
+        inferred_freq = data.freq
+
     # Convert whatever we have into timedelta64[ns] dtype
     if is_object_dtype(data.dtype) or is_string_dtype(data.dtype):
         # no need to make a copy, need to convert if string-dtyped

pandas/tests/arrays/test_datetimelike.py

@@ -13,6 +13,7 @@
     Timestamp,
 )
 from pandas.compat import np_version_under1p18
+import pandas.util._test_decorators as td
 
 import pandas as pd
 from pandas import (
@@ -28,6 +29,8 @@
     PeriodArray,
     TimedeltaArray,
 )
+from pandas.core.arrays.datetimes import sequence_to_dt64ns
+from pandas.core.arrays.timedeltas import sequence_to_td64ns
 
 
 # TODO: more freq variants
@@ -224,7 +227,7 @@ def test_unbox_scalar(self):
         result = arr._unbox_scalar(NaT)
         assert isinstance(result, expected)
 
-        msg = f"'value' should be a {self.dtype.__name__}."
+        msg = f"'value' should be a {self.scalar_type.__name__}."
         with pytest.raises(ValueError, match=msg):
             arr._unbox_scalar("foo")
 
@@ -614,11 +617,21 @@ def test_median(self, arr1d):
         result = arr2.median(axis=1, skipna=False)
         tm.assert_equal(result, arr)
 
+    def test_from_integer_array(self):
+        arr = np.array([1, 2, 3], dtype=np.int64)
+        expected = self.array_cls(arr, dtype=self.example_dtype)
+
+        data = pd.array(arr, dtype="Int64")
+        result = self.array_cls(data, dtype=self.example_dtype)
+
+        tm.assert_extension_array_equal(result, expected)
+
 
 class TestDatetimeArray(SharedTests):
     index_cls = DatetimeIndex
     array_cls = DatetimeArray
-    dtype = Timestamp
+    scalar_type = Timestamp
+    example_dtype = "M8[ns]"
 
     @pytest.fixture
     def arr1d(self, tz_naive_fixture, freqstr):
@@ -918,7 +931,8 @@ def test_strftime_nat(self):
 class TestTimedeltaArray(SharedTests):
     index_cls = TimedeltaIndex
     array_cls = TimedeltaArray
-    dtype = pd.Timedelta
+    scalar_type = pd.Timedelta
+    example_dtype = "m8[ns]"
 
     def test_from_tdi(self):
         tdi = TimedeltaIndex(["1 Day", "3 Hours"])
@@ -1037,7 +1051,8 @@ def test_take_fill_valid(self, timedelta_index):
 class TestPeriodArray(SharedTests):
     index_cls = PeriodIndex
     array_cls = PeriodArray
-    dtype = Period
+    scalar_type = Period
+    example_dtype = PeriodIndex([], freq="W").dtype
 
     @pytest.fixture
     def arr1d(self, period_index):
@@ -1305,3 +1320,100 @@ def test_period_index_construction_from_strings(klass):
     result = PeriodIndex(data, freq="Q")
     expected = PeriodIndex([Period(s) for s in strings])
     tm.assert_index_equal(result, expected)
+
+
+@pytest.mark.parametrize("dtype", ["M8[ns]", "m8[ns]"])
+def test_from_pandas_array(dtype):
+    # GH#24615
+    data = np.array([1, 2, 3], dtype=dtype)
+    arr = PandasArray(data)
+
+    cls = {"M8[ns]": DatetimeArray, "m8[ns]": TimedeltaArray}[dtype]
+
+    result = cls(arr)
+    expected = cls(data)
+    tm.assert_extension_array_equal(result, expected)
+
+    result = cls._from_sequence(arr)
+    expected = cls._from_sequence(data)
+    tm.assert_extension_array_equal(result, expected)
+
+    func = {"M8[ns]": sequence_to_dt64ns, "m8[ns]": sequence_to_td64ns}[dtype]
+    result = func(arr)[0]
+    expected = func(data)[0]
+    tm.assert_equal(result, expected)
+
+    func = {"M8[ns]": pd.to_datetime, "m8[ns]": pd.to_timedelta}[dtype]
+    result = func(arr).array
+    expected = func(data).array
+    tm.assert_equal(result, expected)
+
+    # Let's check the Indexes while we're here
+    idx_cls = {"M8[ns]": DatetimeIndex, "m8[ns]": TimedeltaIndex}[dtype]
+    result = idx_cls(arr)
+    expected = idx_cls(data)
+    tm.assert_index_equal(result, expected)
+
+
+@pytest.fixture(
+    params=[
+        "memoryview",
+        "array",
+        pytest.param("dask", marks=td.skip_if_no("dask.array")),
+        pytest.param("xarray", marks=td.skip_if_no("xarray")),
+    ]
+)
+def array_likes(request):
+    # GH#24539 recognize e.g xarray, dask, ...
+    arr = np.array([1, 2, 3], dtype=np.int64)
+
+    name = request.param
+    if name == "memoryview":
+        data = memoryview(arr)
+    elif name == "array":
+        # stdlib array
+        from array import array
+
+        data = array("i", arr)
+    elif name == "dask":
+        import dask.array
+
+        data = dask.array.array(arr)
+    elif name == "xarray":
+        import xarray as xr
+
+        data = xr.DataArray(arr)
+
+    return arr, data
+
+
+@pytest.mark.parametrize("dtype", ["M8[ns]", "m8[ns]"])
+def test_from_obscure_array(dtype, array_likes):
+    # GH#24539 recognize e.g xarray, dask, ...
+    # Note: we dont do this for PeriodArray bc _from_sequence won't accept
+    #  an array of integers
+    # TODO: could check with arraylike of Period objects
+    arr, data = array_likes
+
+    cls = {"M8[ns]": DatetimeArray, "m8[ns]": TimedeltaArray}[dtype]
+
+    expected = cls(arr)
+    result = cls._from_sequence(data)
+    tm.assert_extension_array_equal(result, expected)
+
+    func = {"M8[ns]": sequence_to_dt64ns, "m8[ns]": sequence_to_td64ns}[dtype]
+    result = func(arr)[0]
+    expected = func(data)[0]
+    tm.assert_equal(result, expected)
+
+    # FIXME: dask and memoryview both break on these
+    # func = {"M8[ns]": pd.to_datetime, "m8[ns]": pd.to_timedelta}[dtype]
+    # result = func(arr).array
+    # expected = func(data).array
+    # tm.assert_equal(result, expected)
+
+    # Let's check the Indexes while we're here
+    idx_cls = {"M8[ns]": DatetimeIndex, "m8[ns]": TimedeltaIndex}[dtype]
+    result = idx_cls(arr)
+    expected = idx_cls(data)
+    tm.assert_index_equal(result, expected)