Merge pull request #8699 from jreback/cbd

BUG: incorrect serialization of a CustomBusinessDay in HDF5 (GH8591)

Author: jreback

doc/source/whatsnew/v0.15.1.txt

@@ -1,14 +1,12 @@
 .. _whatsnew_0151:
 
-v0.15.1 (November ??, 2014)
------------------------
+v0.15.1 (November 8, 2014)
+--------------------------
 
-This is a minor release from 0.15.0 and includes a small number of API changes, several new features,
+This is a minor bug-fix release from 0.15.0 and includes a small number of API changes, several new features,
 enhancements, and performance improvements along with a large number of bug fixes. We recommend that all
 users upgrade to this version.
 
-- Highlights include:
-
 - :ref:`Enhancements <whatsnew_0151.enhancements>`
 - :ref:`API Changes <whatsnew_0151.api>`
 - :ref:`Performance Improvements <whatsnew_0151.performance>`
@@ -30,10 +28,10 @@ API changes
 
   .. code-block:: python
 
-     # this was underreported and actually took (in < 0.15.1) about 24008 bytes
+     # this was underreported in prior versions
      In [1]: dfi.memory_usage(index=True)
      Out[1]:
-     Index    8000
+     Index    8000 # took about 24008 bytes in < 0.15.1
      A        8000
      dtype: int64
 
@@ -178,7 +176,7 @@ Experimental
 Bug Fixes
 ~~~~~~~~~
 
-
+- Bug in unpickling  of a ``CustomBusinessDay`` object (:issue:`8591`)
 - Bug in coercing ``Categorical`` to a records array, e.g. ``df.to_records()`` (:issue:`8626`)
 - Bug in ``Categorical`` not created properly with ``Series.to_frame()`` (:issue:`8626`)
 - Bug in coercing in astype of a ``Categorical`` of a passed ``pd.Categorical`` (this now raises ``TypeError`` correctly), (:issue:`8626`)

pandas/io/tests/test_pytables.py

@@ -2047,6 +2047,28 @@ def compare(a,b):
             result = store.select('df')
             assert_frame_equal(result,df)
 
+    def test_calendar_roundtrip_issue(self):
+
+        # 8591
+        # doc example from tseries holiday section
+        weekmask_egypt = 'Sun Mon Tue Wed Thu'
+        holidays = ['2012-05-01', datetime.datetime(2013, 5, 1), np.datetime64('2014-05-01')]
+        bday_egypt = pandas.offsets.CustomBusinessDay(holidays=holidays, weekmask=weekmask_egypt)
+        dt = datetime.datetime(2013, 4, 30)
+        dts = date_range(dt, periods=5, freq=bday_egypt)
+
+        s = (Series(dts.weekday, dts).map(Series('Mon Tue Wed Thu Fri Sat Sun'.split())))
+
+        with ensure_clean_store(self.path) as store:
+
+            store.put('fixed',s)
+            result = store.select('fixed')
+            assert_series_equal(result, s)
+
+            store.append('table',s)
+            result = store.select('table')
+            assert_series_equal(result, s)
+
     def test_append_with_timezones_dateutil(self):
 
         from datetime import timedelta

pandas/tseries/offsets.py

@@ -614,6 +614,14 @@ def __getstate__(self):
         """Return a pickleable state"""
         state = self.__dict__.copy()
         del state['calendar']
+
+        # we don't want to actually pickle the calendar object
+        # as its a np.busyday; we recreate on deserilization
+        try:
+            state['kwds'].pop('calendar')
+        except:
+            pass
+
         return state
 
     def __setstate__(self, state):

pandas/tseries/tests/test_offsets.py

@@ -12,12 +12,13 @@
 from pandas.core.datetools import (
     bday, BDay, CDay, BQuarterEnd, BMonthEnd,
     CBMonthEnd, CBMonthBegin,
-    BYearEnd, MonthEnd, MonthBegin, BYearBegin,
+    BYearEnd, MonthEnd, MonthBegin, BYearBegin, CustomBusinessDay,
     QuarterBegin, BQuarterBegin, BMonthBegin, DateOffset, Week,
     YearBegin, YearEnd, Hour, Minute, Second, Day, Micro, Milli, Nano, Easter,
     WeekOfMonth, format, ole2datetime, QuarterEnd, to_datetime, normalize_date,
     get_offset, get_offset_name, get_standard_freq)
 
+from pandas import Series
 from pandas.tseries.frequencies import _offset_map
 from pandas.tseries.index import _to_m8, DatetimeIndex, _daterange_cache, date_range
 from pandas.tseries.tools import parse_time_string
@@ -867,7 +868,6 @@ def test_pickle_compat_0_14_1(self):
         cday = CDay(holidays=hdays)
         self.assertEqual(cday, cday0_14_1)
 
-
 class CustomBusinessMonthBase(object):
     _multiprocess_can_split_ = True