From 7517dd0f4905f533209e31354f31c0e0268afea8 Mon Sep 17 00:00:00 2001
From: Tom Augspurger <tom.w.augspurger@gmail.com>
Date: Mon, 28 Jan 2019 17:46:05 -0600
Subject: [PATCH 1/2] DOC: Document breaking change to read_csv

Closes https://github.com/pandas-dev/pandas/issues/24987
---
 doc/source/user_guide/io.rst    | 30 +++++++++++++++++++++
 doc/source/whatsnew/v0.24.0.rst | 46 +++++++++++++++++++++++++++++++++
 pandas/io/parsers.py            | 11 +++++---
 3 files changed, 84 insertions(+), 3 deletions(-)

diff --git a/doc/source/user_guide/io.rst b/doc/source/user_guide/io.rst
index 58e1b2370c7c8..b23a0f10e9e2b 100644
--- a/doc/source/user_guide/io.rst
+++ b/doc/source/user_guide/io.rst
@@ -989,6 +989,36 @@ a single date rather than the entire array.
 
    os.remove('tmp.csv')
 
+
+.. _io.csv.mixed_timezones:
+
+Parsing a CSV with mixed Timezones
+++++++++++++++++++++++++++++++++++
+
+Pandas cannot natively represent a column or index with mixed timezones. If your CSV
+file contains columns with a mixture of timezones, the default result will be
+an object-dtype column with strings, even with ``parse_dates``.
+
+
+.. ipython:: python
+
+   content = """\
+   a
+   2000-01-01T00:00:00+05:00
+   2000-01-01T00:00:00+06:00"""
+   df = pd.read_csv(StringIO(content), parse_dates=['a'])
+   df['a']
+
+To parse the mixed-timezone values as a datetime column, pass a partially-applied
+:func:`to_datetime` with ``utc=True`` as the ``date_parser``.
+
+.. ipython:: python
+
+   df = pd.read_csv(StringIO(content), parse_dates=['a'],
+                    date_parser=lambda col: pd.to_datetime(col, utc=True))
+   df['a']
+
+
 .. _io.dayfirst:
 
 
diff --git a/doc/source/whatsnew/v0.24.0.rst b/doc/source/whatsnew/v0.24.0.rst
index 16319a3b83ca4..da7bb631550db 100644
--- a/doc/source/whatsnew/v0.24.0.rst
+++ b/doc/source/whatsnew/v0.24.0.rst
@@ -648,6 +648,52 @@ that the dates have been converted to UTC
     pd.to_datetime(["2015-11-18 15:30:00+05:30",
                     "2015-11-18 16:30:00+06:30"], utc=True)
 
+
+.. _whatsnew_0240.api_breaking.read_csv_mixed_tz:
+
+Parsing mixed-timezones with :func:`read_csv`
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+:func:`read_csv` no longer silently converts mixed-timezone columns to UTC (:issue:`24987`).
+
+*Previous Behavior*
+
+.. code-block:: python
+
+   >>> import io
+   >>> content = """\
+   ... a
+   ... 2000-01-01T00:00:00+05:00
+   ... 2000-01-01T00:00:00+06:00"""
+   >>> df = pd.read_csv(io.StringIO(content), parse_dates=['a'])
+   >>> df.a
+   0   1999-12-31 19:00:00
+   1   1999-12-31 18:00:00
+   Name: a, dtype: datetime64[ns]
+
+*New Behavior*
+
+.. ipython:: python
+
+   import io
+   content = """\
+   a
+   2000-01-01T00:00:00+05:00
+   2000-01-01T00:00:00+06:00"""
+   df = pd.read_csv(io.StringIO(content), parse_dates=['a'])
+   df.a
+
+As can be seen, the ``dtype`` is object; each value in the column is a string.
+To convert the strings to an array of datetimes, the ``date_parser`` argument
+
+.. ipython:: python
+
+   df = pd.read_csv(io.StringIO(content), parse_dates=['a'],
+                    date_parser=lambda col: pd.to_datetime(col, utc=True)
+   df.a
+
+See :ref:`whatsnew_0240.api.timezone_offset_parsing` for more.
+
 .. _whatsnew_0240.api_breaking.period_end_time:
 
 Time values in ``dt.end_time`` and ``to_timestamp(how='end')``
diff --git a/pandas/io/parsers.py b/pandas/io/parsers.py
index b31d3f665f47f..4163a571df800 100755
--- a/pandas/io/parsers.py
+++ b/pandas/io/parsers.py
@@ -203,9 +203,14 @@
     * dict, e.g. {{'foo' : [1, 3]}} -> parse columns 1, 3 as date and call
       result 'foo'
 
-    If a column or index contains an unparseable date, the entire column or
-    index will be returned unaltered as an object data type. For non-standard
-    datetime parsing, use ``pd.to_datetime`` after ``pd.read_csv``
+    If a column or index cannot be represented as an array of datetimes,
+    say because of an unparseable value or a mixture of timezones, the column
+    or index will be returned unaltered as an object data type. For
+    non-standard datetime parsing, use ``pd.to_datetime`` after
+    ``pd.read_csv``. To parse an index or column with a mixture of timezones,
+    specify ``date_parser`` to be a partially-applied
+    :func:`pandas.to_datetime` with ``utc=True``. See
+    :ref:`io.csv.mixed_timezones` for more.
 
     Note: A fast-path exists for iso8601-formatted dates.
 infer_datetime_format : bool, default False

From c26684d955c83c233d218e2e5bea4bd0fc6813a3 Mon Sep 17 00:00:00 2001
From: Tom Augspurger <tom.w.augspurger@gmail.com>
Date: Mon, 28 Jan 2019 20:48:06 -0600
Subject: [PATCH 2/2] missing paren

---
 doc/source/whatsnew/v0.24.0.rst | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/doc/source/whatsnew/v0.24.0.rst b/doc/source/whatsnew/v0.24.0.rst
index da7bb631550db..a49ea2cf493a6 100644
--- a/doc/source/whatsnew/v0.24.0.rst
+++ b/doc/source/whatsnew/v0.24.0.rst
@@ -689,7 +689,7 @@ To convert the strings to an array of datetimes, the ``date_parser`` argument
 .. ipython:: python
 
    df = pd.read_csv(io.StringIO(content), parse_dates=['a'],
-                    date_parser=lambda col: pd.to_datetime(col, utc=True)
+                    date_parser=lambda col: pd.to_datetime(col, utc=True))
    df.a
 
 See :ref:`whatsnew_0240.api.timezone_offset_parsing` for more.