DOC: Clarify documentation of 'ambiguous' parameter (pandas-dev#23408)

bartaelterman · Pingviinituutti · commit 62f44099bdd6 · 2019-02-28T10:26:56.000+02:00
* Add documentation line with example for the ambiguous parameter of tz_locaclize * Updating 'ambiguous'-param doc + update it on Timestamp, DatetimeIndex and NaT This is following the discussion at pandas-dev#23408 (comment)
diff --git a/pandas/_libs/tslibs/conversion.pyx b/pandas/_libs/tslibs/conversion.pyx
@@ -844,7 +844,20 @@ def tz_localize_to_utc(ndarray[int64_t] vals, object tz, object ambiguous=None,
     vals : ndarray[int64_t]
     tz : tzinfo or None
     ambiguous : str, bool, or arraylike
-        If arraylike, must have the same length as vals
+        When clocks moved backward due to DST, ambiguous times may arise.
+        For example in Central European Time (UTC+01), when going from 03:00
+        DST to 02:00 non-DST, 02:30:00 local time occurs both at 00:30:00 UTC
+        and at 01:30:00 UTC. In such a situation, the `ambiguous` parameter
+        dictates how ambiguous times should be handled.
+
+        - 'infer' will attempt to infer fall dst-transition hours based on
+          order
+        - bool-ndarray where True signifies a DST time, False signifies a
+          non-DST time (note that this flag is only applicable for ambiguous
+          times, but the array must have the same length as vals)
+        - bool if True, treat all vals as DST. If False, treat them as non-DST
+        - 'NaT' will return NaT where there are ambiguous times
+
     nonexistent : str
         If arraylike, must have the same length as vals
 
diff --git a/pandas/_libs/tslibs/nattype.pyx b/pandas/_libs/tslibs/nattype.pyx
@@ -593,6 +593,13 @@ class NaTType(_NaT):
             None will remove timezone holding local time.
 
         ambiguous : bool, 'NaT', default 'raise'
+            When clocks moved backward due to DST, ambiguous times may arise.
+            For example in Central European Time (UTC+01), when going from
+            03:00 DST to 02:00 non-DST, 02:30:00 local time occurs both at
+            00:30:00 UTC and at 01:30:00 UTC. In such a situation, the
+            `ambiguous` parameter dictates how ambiguous times should be
+            handled.
+
             - bool contains flags to determine if time is dst or not (note
               that this flag is only applicable for ambiguous fall dst dates)
             - 'NaT' will return NaT for an ambiguous time
diff --git a/pandas/_libs/tslibs/timestamps.pyx b/pandas/_libs/tslibs/timestamps.pyx
@@ -1026,6 +1026,13 @@ class Timestamp(_Timestamp):
             None will remove timezone holding local time.
 
         ambiguous : bool, 'NaT', default 'raise'
+            When clocks moved backward due to DST, ambiguous times may arise.
+            For example in Central European Time (UTC+01), when going from
+            03:00 DST to 02:00 non-DST, 02:30:00 local time occurs both at
+            00:30:00 UTC and at 01:30:00 UTC. In such a situation, the
+            `ambiguous` parameter dictates how ambiguous times should be
+            handled.
+
             - bool contains flags to determine if time is dst or not (note
               that this flag is only applicable for ambiguous fall dst dates)
             - 'NaT' will return NaT for an ambiguous time
diff --git a/pandas/core/arrays/datetimes.py b/pandas/core/arrays/datetimes.py
@@ -614,6 +614,12 @@ def tz_localize(self, tz, ambiguous='raise', nonexistent='raise',
             Time zone to convert timestamps to. Passing ``None`` will
             remove the time zone information preserving local time.
         ambiguous : 'infer', 'NaT', bool array, default 'raise'
+            When clocks moved backward due to DST, ambiguous times may arise.
+            For example in Central European Time (UTC+01), when going from
+            03:00 DST to 02:00 non-DST, 02:30:00 local time occurs both at
+            00:30:00 UTC and at 01:30:00 UTC. In such a situation, the
+            `ambiguous` parameter dictates how ambiguous times should be
+            handled.
 
             - 'infer' will attempt to infer fall dst-transition hours based on
               order
@@ -685,6 +691,40 @@ def tz_localize(self, tz, ambiguous='raise', nonexistent='raise',
         DatetimeIndex(['2018-03-01 09:00:00', '2018-03-02 09:00:00',
                        '2018-03-03 09:00:00'],
                       dtype='datetime64[ns]', freq='D')
+
+        Be careful with DST changes. When there is sequential data, pandas can
+        infer the DST time:
+        >>> s = pd.to_datetime(pd.Series([
+        ... '2018-10-28 01:30:00',
+        ... '2018-10-28 02:00:00',
+        ... '2018-10-28 02:30:00',
+        ... '2018-10-28 02:00:00',
+        ... '2018-10-28 02:30:00',
+        ... '2018-10-28 03:00:00',
+        ... '2018-10-28 03:30:00']))
+        >>> s.dt.tz_localize('CET', ambiguous='infer')
+        2018-10-28 01:30:00+02:00    0
+        2018-10-28 02:00:00+02:00    1
+        2018-10-28 02:30:00+02:00    2
+        2018-10-28 02:00:00+01:00    3
+        2018-10-28 02:30:00+01:00    4
+        2018-10-28 03:00:00+01:00    5
+        2018-10-28 03:30:00+01:00    6
+        dtype: int64
+
+        In some cases, inferring the DST is impossible. In such cases, you can
+        pass an ndarray to the ambiguous parameter to set the DST explicitly
+
+        >>> s = pd.to_datetime(pd.Series([
+        ... '2018-10-28 01:20:00',
+        ... '2018-10-28 02:36:00',
+        ... '2018-10-28 03:46:00']))
+        >>> s.dt.tz_localize('CET', ambiguous=np.array([True, True, False]))
+        0   2018-10-28 01:20:00+02:00
+        1   2018-10-28 02:36:00+02:00
+        2   2018-10-28 03:46:00+01:00
+        dtype: datetime64[ns, CET]
+
         """
         if errors is not None:
             warnings.warn("The errors argument is deprecated and will be "
diff --git a/pandas/core/generic.py b/pandas/core/generic.py
@@ -8718,6 +8718,13 @@ def tz_localize(self, tz, axis=0, level=None, copy=True,
         copy : boolean, default True
             Also make a copy of the underlying data
         ambiguous : 'infer', bool-ndarray, 'NaT', default 'raise'
+            When clocks moved backward due to DST, ambiguous times may arise.
+            For example in Central European Time (UTC+01), when going from
+            03:00 DST to 02:00 non-DST, 02:30:00 local time occurs both at
+            00:30:00 UTC and at 01:30:00 UTC. In such a situation, the
+            `ambiguous` parameter dictates how ambiguous times should be
+            handled.
+
             - 'infer' will attempt to infer fall dst-transition hours based on
               order
             - bool-ndarray where True signifies a DST time, False designates
@@ -8745,6 +8752,52 @@ def tz_localize(self, tz, axis=0, level=None, copy=True,
         ------
         TypeError
             If the TimeSeries is tz-aware and tz is not None.
+
+        Examples
+        --------
+
+        Localize local times:
+
+        >>> s = pd.Series([1],
+        ... index=pd.DatetimeIndex(['2018-09-15 01:30:00']))
+        >>> s.tz_localize('CET')
+        2018-09-15 01:30:00+02:00    1
+        dtype: int64
+
+        Be careful with DST changes. When there is sequential data, pandas
+        can infer the DST time:
+
+        >>> s = pd.Series(range(7), index=pd.DatetimeIndex([
+        ... '2018-10-28 01:30:00',
+        ... '2018-10-28 02:00:00',
+        ... '2018-10-28 02:30:00',
+        ... '2018-10-28 02:00:00',
+        ... '2018-10-28 02:30:00',
+        ... '2018-10-28 03:00:00',
+        ... '2018-10-28 03:30:00']))
+        >>> s.tz_localize('CET', ambiguous='infer')
+        2018-10-28 01:30:00+02:00    0
+        2018-10-28 02:00:00+02:00    1
+        2018-10-28 02:30:00+02:00    2
+        2018-10-28 02:00:00+01:00    3
+        2018-10-28 02:30:00+01:00    4
+        2018-10-28 03:00:00+01:00    5
+        2018-10-28 03:30:00+01:00    6
+        dtype: int64
+
+        In some cases, inferring the DST is impossible. In such cases, you can
+        pass an ndarray to the ambiguous parameter to set the DST explicitly
+
+        >>> s = pd.Series(range(3), index=pd.DatetimeIndex([
+        ... '2018-10-28 01:20:00',
+        ... '2018-10-28 02:36:00',
+        ... '2018-10-28 03:46:00']))
+        >>> s.tz_localize('CET', ambiguous=np.array([True, True, False]))
+        2018-10-28 01:20:00+02:00    0
+        2018-10-28 02:36:00+02:00    1
+        2018-10-28 03:46:00+01:00    2
+        dtype: int64
+
         """
         if nonexistent not in ('raise', 'NaT', 'shift'):
             raise ValueError("The nonexistent argument must be one of 'raise',"
diff --git a/pandas/core/indexes/datetimes.py b/pandas/core/indexes/datetimes.py
@@ -99,6 +99,12 @@ class DatetimeIndex(DatetimeArrayMixin, DatelikeOps, TimelikeOps,
         the 'left', 'right', or both sides (None)
     tz : pytz.timezone or dateutil.tz.tzfile
     ambiguous : 'infer', bool-ndarray, 'NaT', default 'raise'
+        When clocks moved backward due to DST, ambiguous times may arise.
+        For example in Central European Time (UTC+01), when going from 03:00
+        DST to 02:00 non-DST, 02:30:00 local time occurs both at 00:30:00 UTC
+        and at 01:30:00 UTC. In such a situation, the `ambiguous` parameter
+        dictates how ambiguous times should be handled.
+
         - 'infer' will attempt to infer fall dst-transition hours based on
           order
         - bool-ndarray where True signifies a DST time, False signifies a
@@ -173,6 +179,7 @@ class DatetimeIndex(DatetimeArrayMixin, DatelikeOps, TimelikeOps,
     TimedeltaIndex : Index of timedelta64 data
     PeriodIndex : Index of Period data
     pandas.to_datetime : Convert argument to datetime
+
     """
     _resolution = cache_readonly(DatetimeArrayMixin._resolution.fget)
     _shallow_copy = Index._shallow_copy
