REF: remove always-UTC arg from tz_convert, tz_convert_single (#35154)

Author: jbrockmendel

asv_bench/benchmarks/tslibs/tz_convert.py

@@ -1,16 +1,23 @@
 import numpy as np
 from pytz import UTC
 
-from pandas._libs.tslibs.tzconversion import tz_convert, tz_localize_to_utc
+from pandas._libs.tslibs.tzconversion import tz_localize_to_utc
 
 from .tslib import _sizes, _tzs
 
+try:
+    old_sig = False
+    from pandas._libs.tslibs.tzconversion import tz_convert_from_utc
+except ImportError:
+    old_sig = True
+    from pandas._libs.tslibs.tzconversion import tz_convert as tz_convert_from_utc
+
 
 class TimeTZConvert:
-    params = (
+    params = [
         _sizes,
         [x for x in _tzs if x is not None],
-    )
+    ]
     param_names = ["size", "tz"]
 
     def setup(self, size, tz):
@@ -21,7 +28,13 @@ def time_tz_convert_from_utc(self, size, tz):
         # effectively:
         #  dti = DatetimeIndex(self.i8data, tz=tz)
         #  dti.tz_localize(None)
-        tz_convert(self.i8data, UTC, tz)
+        if size >= 10 ** 6 and str(tz) == "tzlocal()":
+            # asv fill will because each call takes 8+seconds
+            return
+        if old_sig:
+            tz_convert_from_utc(self.i8data, UTC, tz)
+        else:
+            tz_convert_from_utc(self.i8data, tz)
 
     def time_tz_localize_to_utc(self, size, tz):
         # effectively:

pandas/_libs/tslibs/__init__.py

@@ -19,7 +19,7 @@
     "ints_to_pytimedelta",
     "get_resolution",
     "Timestamp",
-    "tz_convert_single",
+    "tz_convert_from_utc_single",
     "to_offset",
     "Tick",
     "BaseOffset",
@@ -34,7 +34,7 @@
 from .resolution import Resolution
 from .timedeltas import Timedelta, delta_to_nanoseconds, ints_to_pytimedelta
 from .timestamps import Timestamp
-from .tzconversion import tz_convert_single
+from .tzconversion import tz_convert_from_utc_single
 from .vectorized import (
     dt64arr_to_periodarr,
     get_resolution,

pandas/_libs/tslibs/offsets.pyx

@@ -46,8 +46,7 @@ from pandas._libs.tslibs.np_datetime cimport (
     dt64_to_dtstruct,
     pydate_to_dtstruct,
 )
-from pandas._libs.tslibs.timezones cimport utc_pytz as UTC
-from pandas._libs.tslibs.tzconversion cimport tz_convert_single
+from pandas._libs.tslibs.tzconversion cimport tz_convert_from_utc_single
 
 from .dtypes cimport PeriodDtypeCode
 from .timedeltas cimport delta_to_nanoseconds
@@ -264,7 +263,7 @@ cdef _to_dt64D(dt):
         #  equiv `Timestamp(dt).value` or `dt.timestamp() * 10**9`
         nanos = getattr(dt, "nanosecond", 0)
         i8 = convert_datetime_to_tsobject(dt, tz=None, nanos=nanos).value
-        dt = tz_convert_single(i8, UTC, dt.tzinfo)
+        dt = tz_convert_from_utc_single(i8, dt.tzinfo)
         dt = np.int64(dt).astype('datetime64[ns]')
     else:
         dt = np.datetime64(dt)

pandas/_libs/tslibs/timestamps.pyx

@@ -59,7 +59,7 @@ from pandas._libs.tslibs.timezones cimport (
     get_timezone, tz_compare,
 )
 from pandas._libs.tslibs.tzconversion cimport (
-    tz_convert_single,
+    tz_convert_from_utc_single,
     tz_localize_to_utc_single,
 )
 
@@ -1309,7 +1309,7 @@ default 'raise'
         else:
             if tz is None:
                 # reset tz
-                value = tz_convert_single(self.value, UTC, self.tz)
+                value = tz_convert_from_utc_single(self.value, self.tz)
                 return Timestamp(value, tz=tz, freq=self.freq)
             else:
                 raise TypeError(
@@ -1391,7 +1391,7 @@ default 'raise'
         tzobj = self.tzinfo
         value = self.value
         if tzobj is not None:
-            value = tz_convert_single(value, UTC, tzobj)
+            value = tz_convert_from_utc_single(value, tzobj)
 
         # setup components
         dt64_to_dtstruct(value, &dts)

pandas/_libs/tslibs/tzconversion.pxd

@@ -3,7 +3,7 @@ from numpy cimport int64_t
 
 
 cdef int64_t tz_convert_utc_to_tzlocal(int64_t utc_val, tzinfo tz, bint* fold=*)
-cpdef int64_t tz_convert_single(int64_t val, tzinfo tz1, tzinfo tz2)
+cpdef int64_t tz_convert_from_utc_single(int64_t val, tzinfo tz)
 cdef int64_t tz_localize_to_utc_single(
     int64_t val, tzinfo tz, object ambiguous=*, object nonexistent=*
 ) except? -1

pandas/_libs/tslibs/tzconversion.pyx

@@ -366,93 +366,69 @@ cdef int64_t tz_convert_utc_to_tzlocal(int64_t utc_val, tzinfo tz, bint* fold=NU
     return _tz_convert_tzlocal_utc(utc_val, tz, to_utc=False, fold=fold)
 
 
-cpdef int64_t tz_convert_single(int64_t val, tzinfo tz1, tzinfo tz2):
+cpdef int64_t tz_convert_from_utc_single(int64_t val, tzinfo tz):
     """
-    Convert the val (in i8) from timezone1 to timezone2
+    Convert the val (in i8) from UTC to tz
 
-    This is a single timezone version of tz_convert
+    This is a single value version of tz_convert_from_utc.
 
     Parameters
     ----------
     val : int64
-    tz1 : tzinfo
-    tz2 : tzinfo
+    tz : tzinfo
 
     Returns
     -------
     converted: int64
     """
     cdef:
         int64_t arr[1]
-        bint to_utc = is_utc(tz2)
-        tzinfo tz
-
-    # See GH#17734 We should always be converting either from UTC or to UTC
-    assert is_utc(tz1) or to_utc
 
     if val == NPY_NAT:
         return val
 
-    if to_utc:
-        tz = tz1
-    else:
-        tz = tz2
-
     if is_utc(tz):
         return val
     elif is_tzlocal(tz):
-        return _tz_convert_tzlocal_utc(val, tz, to_utc=to_utc)
+        return _tz_convert_tzlocal_utc(val, tz, to_utc=False)
     else:
         arr[0] = val
-        return _tz_convert_dst(arr, tz, to_utc=to_utc)[0]
+        return _tz_convert_dst(arr, tz)[0]
 
 
-def tz_convert(int64_t[:] vals, tzinfo tz1, tzinfo tz2):
+def tz_convert_from_utc(int64_t[:] vals, tzinfo tz):
     """
-    Convert the values (in i8) from timezone1 to timezone2
+    Convert the values (in i8) from UTC to tz
 
     Parameters
     ----------
     vals : int64 ndarray
-    tz1 : tzinfo
-    tz2 : tzinfo
+    tz : tzinfo
 
     Returns
     -------
     int64 ndarray of converted
     """
     cdef:
         int64_t[:] converted
-        bint to_utc = is_utc(tz2)
-        tzinfo tz
-
-    # See GH#17734 We should always be converting from UTC; otherwise
-    #  should use tz_localize_to_utc.
-    assert is_utc(tz1)
 
     if len(vals) == 0:
         return np.array([], dtype=np.int64)
 
-    if to_utc:
-        tz = tz1
-    else:
-        tz = tz2
-
-    converted = _tz_convert_one_way(vals, tz, to_utc=to_utc)
+    converted = _tz_convert_from_utc(vals, tz)
     return np.array(converted, dtype=np.int64)
 
 
 @cython.boundscheck(False)
 @cython.wraparound(False)
-cdef int64_t[:] _tz_convert_one_way(int64_t[:] vals, tzinfo tz, bint to_utc):
+cdef int64_t[:] _tz_convert_from_utc(int64_t[:] vals, tzinfo tz):
     """
     Convert the given values (in i8) either to UTC or from UTC.
 
     Parameters
     ----------
     vals : int64 ndarray
-    tz1 : tzinfo
-    to_utc : bool
+    tz : tzinfo
 
     Returns
     -------
@@ -472,9 +448,9 @@ cdef int64_t[:] _tz_convert_one_way(int64_t[:] vals, tzinfo tz, bint to_utc):
             if val == NPY_NAT:
                 converted[i] = NPY_NAT
             else:
-                converted[i] = _tz_convert_tzlocal_utc(val, tz, to_utc)
+                converted[i] = _tz_convert_tzlocal_utc(val, tz, to_utc=False)
     else:
-        converted = _tz_convert_dst(vals, tz, to_utc)
+        converted = _tz_convert_dst(vals, tz)
 
     return converted
 
@@ -565,9 +541,7 @@ cdef int64_t _tz_convert_tzlocal_utc(int64_t val, tzinfo tz, bint to_utc=True,
 
 @cython.boundscheck(False)
 @cython.wraparound(False)
-cdef int64_t[:] _tz_convert_dst(
-    const int64_t[:] values, tzinfo tz, bint to_utc=True,
-):
+cdef int64_t[:] _tz_convert_dst(const int64_t[:] values, tzinfo tz):
     """
     tz_convert for non-UTC non-tzlocal cases where we have to check
     DST transitions pointwise.
@@ -576,8 +550,6 @@ cdef int64_t[:] _tz_convert_dst(
     ----------
     values : ndarray[int64_t]
     tz : tzinfo
-    to_utc : bool
-        True if converting _to_ UTC, False if converting _from_ utc
 
     Returns
     -------
@@ -607,10 +579,7 @@ cdef int64_t[:] _tz_convert_dst(
             if v == NPY_NAT:
                 result[i] = v
             else:
-                if to_utc:
-                    result[i] = v - delta
-                else:
-                    result[i] = v + delta
+                result[i] = v + delta
 
     else:
         # Previously, this search was done pointwise to try and benefit
@@ -629,9 +598,6 @@ cdef int64_t[:] _tz_convert_dst(
                     #  it elsewhere?
                     raise ValueError("First time before start of DST info")
 
-                if to_utc:
-                    result[i] = v - deltas[pos[i]]
-                else:
-                    result[i] = v + deltas[pos[i]]
+                result[i] = v + deltas[pos[i]]
 
     return result

pandas/core/arrays/datetimes.py

@@ -728,7 +728,7 @@ def _local_timestamps(self):
         This is used to calculate time-of-day information as if the timestamps
         were timezone-naive.
         """
-        return tzconversion.tz_convert(self.asi8, timezones.UTC, self.tz)
+        return tzconversion.tz_convert_from_utc(self.asi8, self.tz)
 
     def tz_convert(self, tz):
         """
@@ -960,7 +960,7 @@ def tz_localize(self, tz, ambiguous="raise", nonexistent="raise"):
 
         if self.tz is not None:
             if tz is None:
-                new_dates = tzconversion.tz_convert(self.asi8, timezones.UTC, self.tz)
+                new_dates = tzconversion.tz_convert_from_utc(self.asi8, self.tz)
             else:
                 raise TypeError("Already tz-aware, use tz_convert to convert.")
         else:

pandas/tests/scalar/timestamp/test_timezones.py

@@ -334,7 +334,7 @@ def test_timestamp_to_datetime_tzoffset(self):
     def test_timestamp_constructor_near_dst_boundary(self):
         # GH#11481 & GH#15777
         # Naive string timestamps were being localized incorrectly
-        # with tz_convert_single instead of tz_localize_to_utc
+        # with tz_convert_from_utc_single instead of tz_localize_to_utc
 
         for tz in ["Europe/Brussels", "Europe/Prague"]:
             result = Timestamp("2015-10-25 01:00", tz=tz)

pandas/tests/tslibs/test_api.py

@@ -47,7 +47,7 @@ def test_namespace():
         "delta_to_nanoseconds",
         "ints_to_pytimedelta",
         "localize_pydatetime",
-        "tz_convert_single",
+        "tz_convert_from_utc_single",
         "to_offset",
     ]
 

pandas/tests/tslibs/test_conversion.py

@@ -12,19 +12,16 @@
 
 def _compare_utc_to_local(tz_didx):
     def f(x):
-        return tzconversion.tz_convert_single(x, UTC, tz_didx.tz)
+        return tzconversion.tz_convert_from_utc_single(x, tz_didx.tz)
 
-    result = tzconversion.tz_convert(tz_didx.asi8, UTC, tz_didx.tz)
+    result = tzconversion.tz_convert_from_utc(tz_didx.asi8, tz_didx.tz)
     expected = np.vectorize(f)(tz_didx.asi8)
 
     tm.assert_numpy_array_equal(result, expected)
 
 
 def _compare_local_to_utc(tz_didx, naive_didx):
     # Check that tz_localize behaves the same vectorized and pointwise.
-    def f(x):
-        return tzconversion.tz_convert_single(x, tz_didx.tz, UTC)
-
     err1 = err2 = None
     try:
         result = tzconversion.tz_localize_to_utc(naive_didx.asi8, tz_didx.tz)
@@ -71,7 +68,7 @@ def test_tz_convert_single_matches_tz_convert(tz_aware_fixture, freq):
     ],
 )
 def test_tz_convert_corner(arr):
-    result = tzconversion.tz_convert(arr, UTC, timezones.maybe_get_tz("Asia/Tokyo"))
+    result = tzconversion.tz_convert_from_utc(arr, timezones.maybe_get_tz("Asia/Tokyo"))
     tm.assert_numpy_array_equal(result, arr)
 
 

pandas/tseries/frequencies.py

@@ -21,7 +21,6 @@
 )
 from pandas._libs.tslibs.parsing import get_rule_month
 from pandas._libs.tslibs.resolution import month_position_check
-from pandas._libs.tslibs.timezones import UTC
 from pandas.util._decorators import cache_readonly
 
 from pandas.core.dtypes.common import (
@@ -198,7 +197,9 @@ def __init__(self, index, warn: bool = True):
         # the timezone so they are in local time
         if hasattr(index, "tz"):
             if index.tz is not None:
-                self.i8values = tzconversion.tz_convert(self.i8values, UTC, index.tz)
+                self.i8values = tzconversion.tz_convert_from_utc(
+                    self.i8values, index.tz
+                )
 
         self.warn = warn