WIP: multi-timezone handling for array_to_datetime

pandas/_libs/tslib.pyx

@@ -32,7 +32,9 @@ from tslibs.np_datetime import OutOfBoundsDatetime
 from tslibs.parsing import parse_datetime_string
 
 from tslibs.timedeltas cimport cast_from_unit
-from tslibs.timezones cimport is_utc, is_tzlocal, get_dst_info
+from tslibs.timezones cimport (
+    is_utc, is_tzlocal, get_dst_info, tz_cache_key, get_utcoffset,
+    is_fixed_offset, tz_compare, get_timezone)
 from tslibs.timezones import UTC
 from tslibs.conversion cimport (tz_convert_single, _TSObject,
                                 convert_datetime_to_tsobject,
@@ -459,6 +461,26 @@ def array_with_unit_to_datetime(ndarray values, object unit,
     return oresult
 
 
+cdef get_key(tz):
+    if tz is None:
+        return None
+    if is_fixed_offset(tz):
+        # TODO: these should all be mapped together
+        try:
+            # pytz
+            return str(tz._minutes)  # pytz specific?
+        except AttributeError:
+            try:
+                # dateutil.tz.tzoffset
+                return str(tz._offset.total_seconds())
+            except AttributeError:
+                return str(tz)
+    if is_utc(tz):
+        return 'UTC'
+    return tz_cache_key(tz)
+
+
+
 @cython.wraparound(False)
 @cython.boundscheck(False)
 cpdef array_to_datetime(ndarray[object] values, str errors='raise',
@@ -506,16 +528,14 @@ cpdef array_to_datetime(ndarray[object] values, str errors='raise',
         bint seen_integer = 0
         bint seen_string = 0
         bint seen_datetime = 0
-        bint seen_datetime_offset = 0
         bint is_raise = errors=='raise'
         bint is_ignore = errors=='ignore'
         bint is_coerce = errors=='coerce'
         bint is_same_offsets
         _TSObject _ts
         int64_t value
         int out_local=0, out_tzoffset=0
-        float offset_seconds, tz_offset
-        set out_tzoffset_vals = set()
+        dict out_tzinfos = {}
 
     # specify error conditions
     assert is_raise or is_ignore or is_coerce
@@ -533,27 +553,18 @@ cpdef array_to_datetime(ndarray[object] values, str errors='raise',
 
                 elif PyDateTime_Check(val):
                     seen_datetime = 1
-                    if val.tzinfo is not None:
-                        if utc_convert:
-                            _ts = convert_datetime_to_tsobject(val, None)
-                            iresult[i] = _ts.value
-                        else:
-                            raise ValueError('Tz-aware datetime.datetime '
-                                             'cannot be converted to '
-                                             'datetime64 unless utc=True')
-                    else:
-                        iresult[i] = pydatetime_to_dt64(val, &dts)
-                        if not PyDateTime_CheckExact(val):
-                            # i.e. a Timestamp object
-                            iresult[i] += val.nanosecond
-                        check_dts_bounds(&dts)
+                    out_tzinfos[get_key(val.tzinfo)] = val.tzinfo
+                    _ts = convert_datetime_to_tsobject(val, None)
+                    iresult[i] = _ts.value
 
                 elif PyDate_Check(val):
+                    # Treating as either naive or UTC
                     seen_datetime = 1
                     iresult[i] = pydate_to_dt64(val, &dts)
                     check_dts_bounds(&dts)
 
                 elif is_datetime64_object(val):
+                    # Treating as either naive or UTC
                     seen_datetime = 1
                     iresult[i] = get_datetime64_nanos(val)
 
@@ -592,6 +603,8 @@ cpdef array_to_datetime(ndarray[object] values, str errors='raise',
                         # A ValueError at this point is a _parsing_ error
                         # specifically _not_ OutOfBoundsDatetime
                         if _parse_today_now(val, &iresult[i]):
+                            # TODO: Do we treat this as local?
+                            #  "now" is UTC, "today" is local
                             continue
                         elif require_iso8601:
                             # if requiring iso8601 strings, skip trying
@@ -619,16 +632,7 @@ cpdef array_to_datetime(ndarray[object] values, str errors='raise',
                         # If the dateutil parser returned tzinfo, capture it
                         # to check if all arguments have the same tzinfo
                         tz = py_dt.utcoffset()
-                        if tz is not None:
-                            seen_datetime_offset = 1
-                            # dateutil timezone objects cannot be hashed, so
-                            # store the UTC offsets in seconds instead
-                            out_tzoffset_vals.add(tz.total_seconds())
-                        else:
-                            # Add a marker for naive string, to track if we are
-                            # parsing mixed naive and aware strings
-                            out_tzoffset_vals.add('naive')
-
+                        out_tzinfos[get_key(py_dt.tzinfo)] = py_dt.tzinfo
                         _ts = convert_datetime_to_tsobject(py_dt, None)
                         iresult[i] = _ts.value
                     except:
@@ -642,17 +646,17 @@ cpdef array_to_datetime(ndarray[object] values, str errors='raise',
                         # where we left off
                         value = dtstruct_to_dt64(&dts)
                         if out_local == 1:
-                            seen_datetime_offset = 1
                             # Store the out_tzoffset in seconds
                             # since we store the total_seconds of
                             # dateutil.tz.tzoffset objects
-                            out_tzoffset_vals.add(out_tzoffset * 60.)
                             tz = pytz.FixedOffset(out_tzoffset)
+                            out_tzinfos[get_key(tz)] = tz
                             value = tz_convert_single(value, tz, UTC)
                         else:
                             # Add a marker for naive string, to track if we are
                             # parsing mixed naive and aware strings
-                            out_tzoffset_vals.add('naive')
+                            out_tzinfos[None] = None
+
                         iresult[i] = value
                         check_dts_bounds(&dts)
 
@@ -704,20 +708,25 @@ cpdef array_to_datetime(ndarray[object] values, str errors='raise',
             return array_to_datetime_object(values, is_raise,
                                             dayfirst, yearfirst)
 
-    if seen_datetime_offset and not utc_convert:
+    # TODO: File bug report with cython.  it raises
+    #  Closures Not Supported
+    #  error when I tried to use
+    #  `if any(key is not None for key in out_tzinfos)`
+    keys = out_tzinfos.keys()
+    nnkeys = [x for x in keys if x is not None]
+    if len(nnkeys) and not utc_convert:
         # GH#17697
         # 1) If all the offsets are equal, return one offset for
         #    the parsed dates to (maybe) pass to DatetimeIndex
         # 2) If the offsets are different, then force the parsing down the
         #    object path where an array of datetimes
         #    (with individual dateutil.tzoffsets) are returned
-        is_same_offsets = len(out_tzoffset_vals) == 1
+        is_same_offsets = len(out_tzinfos) == 1
         if not is_same_offsets:
             return array_to_datetime_object(values, is_raise,
                                             dayfirst, yearfirst)
         else:
-            tz_offset = out_tzoffset_vals.pop()
-            tz_out = pytz.FixedOffset(tz_offset / 60.)
+            tz_out = list(out_tzinfos.values())[0]
     return result, tz_out
 
 

pandas/_libs/tslibs/conversion.pyx

@@ -40,7 +40,7 @@ from timezones import UTC
 from parsing import parse_datetime_string
 
 from nattype import nat_strings
-from nattype cimport NPY_NAT, checknull_with_nat, c_NaT as NaT
+from nattype cimport NPY_NAT, c_NaT as NaT
 
 # ----------------------------------------------------------------------
 # Constants
@@ -68,6 +68,9 @@ cdef inline int64_t get_datetime64_nanos(object val) except? -1:
 
     unit = get_datetime64_unit(val)
 
+    if ival == NPY_NAT:
+        return ival
+
     if unit != NPY_FR_ns:
         pandas_datetime_to_datetimestruct(ival, unit, &dts)
         check_dts_bounds(&dts)
@@ -146,58 +149,6 @@ def ensure_timedelta64ns(arr: ndarray, copy: bool=True):
     # TODO: check for overflows when going from a lower-resolution to nanos
 
 
-@cython.boundscheck(False)
-@cython.wraparound(False)
-def datetime_to_datetime64(values: object[:]):
-    """
-    Convert ndarray of datetime-like objects to int64 array representing
-    nanosecond timestamps.
-
-    Parameters
-    ----------
-    values : ndarray[object]
-
-    Returns
-    -------
-    result : ndarray[int64_t]
-    inferred_tz : tzinfo or None
-    """
-    cdef:
-        Py_ssize_t i, n = len(values)
-        object val, inferred_tz = None
-        int64_t[:] iresult
-        npy_datetimestruct dts
-        _TSObject _ts
-
-    result = np.empty(n, dtype='M8[ns]')
-    iresult = result.view('i8')
-    for i in range(n):
-        val = values[i]
-        if checknull_with_nat(val):
-            iresult[i] = NPY_NAT
-        elif PyDateTime_Check(val):
-            if val.tzinfo is not None:
-                if inferred_tz is not None:
-                    if not tz_compare(val.tzinfo, inferred_tz):
-                        raise ValueError('Array must be all same time zone')
-                else:
-                    inferred_tz = get_timezone(val.tzinfo)
-
-                _ts = convert_datetime_to_tsobject(val, None)
-                iresult[i] = _ts.value
-                check_dts_bounds(&_ts.dts)
-            else:
-                if inferred_tz is not None:
-                    raise ValueError('Cannot mix tz-aware with '
-                                     'tz-naive values')
-                iresult[i] = pydatetime_to_dt64(val, &dts)
-                check_dts_bounds(&dts)
-        else:
-            raise TypeError('Unrecognized value type: %s' % type(val))
-
-    return result, inferred_tz
-
-
 cdef inline maybe_datetimelike_to_i8(object val):
     """
     Try to convert to a nanosecond timestamp.  Fall back to returning the

pandas/_libs/tslibs/timezones.pxd

@@ -6,11 +6,13 @@ cdef bint is_tzlocal(object tz)
 cdef bint treat_tz_as_pytz(object tz)
 cdef bint treat_tz_as_dateutil(object tz)
 
-cpdef bint tz_compare(object start, object end)
+cpdef bint tz_compare(object start, object end) except? -1
 cpdef object get_timezone(object tz)
 cpdef object maybe_get_tz(object tz)
 
 cdef get_utcoffset(tzinfo, obj)
 cdef bint is_fixed_offset(object tz)
 
 cdef object get_dst_info(object tz)
+
+cpdef object tz_cache_key(object tz)

pandas/_libs/tslibs/timezones.pyx

@@ -114,7 +114,7 @@ def _p_tz_cache_key(tz):
 dst_cache = {}
 
 
-cdef inline object tz_cache_key(object tz):
+cpdef object tz_cache_key(object tz):
     """
     Return the key in the cache for the timezone info object or None
     if unknown.
@@ -158,8 +158,22 @@ cdef get_utcoffset(tzinfo, obj):
         return tzinfo.utcoffset(obj)
 
 
+cdef get_fixed_offset_total_seconds(tzinfo tz):
+    """
+    For compat between pytz.FixedOffset, dateutil.tz.tzoffset
+    """
+    if hasattr(tz, "_offset"):
+        # dateutil, pytz
+        return tz._offset.total_seconds()
+    else:
+        # TODO: Will it ever want an actual datetime?
+        return tz.utcoffset(None)
+
+
 cdef inline bint is_fixed_offset(object tz):
-    if treat_tz_as_dateutil(tz):
+    if tz is None:
+        return 0
+    elif treat_tz_as_dateutil(tz):
         if len(tz._trans_idx) == 0 and len(tz._trans_list) == 0:
             return 1
         else:
@@ -170,7 +184,9 @@ cdef inline bint is_fixed_offset(object tz):
             return 1
         else:
             return 0
-    return 1
+    if not isinstance(tz, tzinfo):
+        return 0
+    return 1  # TODO: No!
 
 
 cdef object get_utc_trans_times_from_dateutil_tz(object tz):
@@ -295,7 +311,7 @@ def infer_tzinfo(start, end):
     return tz
 
 
-cpdef bint tz_compare(object start, object end):
+cpdef bint tz_compare(object start, object end) except? -1:
     """
     Compare string representations of timezones
 
@@ -321,6 +337,10 @@ cpdef bint tz_compare(object start, object end):
 
     """
     # GH 18523
+    if is_fixed_offset(start) and is_fixed_offset(end):
+        start_seconds = get_fixed_offset_total_seconds(start)
+        end_seconds = get_fixed_offset_total_seconds(end)
+        return start_seconds == end_seconds
     return get_timezone(start) == get_timezone(end)
 
 

pandas/core/dtypes/cast.py

@@ -877,7 +877,7 @@ def maybe_infer_to_datetimelike(value, convert_dates=False):
         return value
 
     shape = v.shape
-    if not v.ndim == 1:
+    if v.ndim != 1:
         v = v.ravel()
 
     if not len(v):
@@ -887,26 +887,18 @@ def try_datetime(v):
         # safe coerce to datetime64
         try:
             # GH19671
-            v = tslib.array_to_datetime(v,
-                                        require_iso8601=True,
-                                        errors='raise')[0]
-        except ValueError:
-
-            # we might have a sequence of the same-datetimes with tz's
-            # if so coerce to a DatetimeIndex; if they are not the same,
-            # then these stay as object dtype, xref GH19671
-            try:
-                from pandas._libs.tslibs import conversion
-                from pandas import DatetimeIndex
-
-                values, tz = conversion.datetime_to_datetime64(v)
-                return DatetimeIndex(values).tz_localize(
-                    'UTC').tz_convert(tz=tz)
-            except (ValueError, TypeError):
-                pass
-
+            v, inferred_tz = tslib.array_to_datetime(v,
+                                                     require_iso8601=True,
+                                                     errors='raise')
         except Exception:
             pass
+        else:
+            if inferred_tz is not None:
+                # TODO: de-duplicate with to_datetime
+                from pandas import DatetimeIndex
+                dti = DatetimeIndex(v).tz_localize('UTC')
+                return dti.tz_convert(tz=inferred_tz)
+                # TODO: possibly reshape?
 
         return v.reshape(shape)
 

pandas/core/series.py

@@ -366,9 +366,11 @@ def _set_axis(self, axis, labels, fastpath=False):
                     # need to set here because we changed the index
                     if fastpath:
                         self._data.set_axis(axis, labels)
-                except (tslibs.OutOfBoundsDatetime, ValueError):
+                except (tslibs.OutOfBoundsDatetime, ValueError, TypeError):
                     # labels may exceeds datetime bounds,
                     # or not be a DatetimeIndex
+                    # GH#24006 TypeError can occur when all entries are
+                    #  datetimes but they do not have matching timezones
                     pass
 
         self._set_subtyp(is_all_dates)