Description
I digged into a bit and found that resample by BusinessHour ran into here since the offset is neither string nor Tick:
https://github.com/pydata/pandas/blob/master/pandas/tseries/resample.py#L999
if not isinstance(offset, Tick): # and first.time() != last.time():
# hack!
first = first.normalize()
last = last.normalize()normalize in _get_range_edges cut the time parts off from the offset so it causes the exception.
If I modify the line into following, the resample goes smoothly:
if not isinstance(offset, Tick) and not isinstance(offset, BusinessHour):
# hack!
first = first.normalize()
last = last.normalize()If I made wrong approach, please point me out. I'll make a PR with test.
Reproducible code
In [5]: df = pd.DataFrame(index=pd.date_range(
start='2016-02-11 00:00:00',
end='2016-02-12 23:00:00',
freq='H'))
In [6]: df.resample('BH').count()Traceback
In [6]: df.resample('BH').count()
> /Users/scari/codes/scari/pandas/pandas/tseries/resample.py(988)_get_range_edges()
-> if isinstance(offset, compat.string_types):
(Pdb) c
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-6-0ce6b0e15edc> in <module>()
----> 1 df.resample('BH').count()
/Users/scari/codes/scari/pandas/pandas/tseries/resample.py in f(self, _method)
457
458 def f(self, _method=method):
--> 459 return self._groupby_and_aggregate(None, _method)
460 f.__doc__ = getattr(GroupBy, method).__doc__
461 setattr(Resampler, method, f)
/Users/scari/codes/scari/pandas/pandas/tseries/resample.py in _groupby_and_aggregate(self, grouper, how, *args, **kwargs)
339
340 if grouper is None:
--> 341 self._set_binner()
342 grouper = self.grouper
343
/Users/scari/codes/scari/pandas/pandas/tseries/resample.py in _set_binner(self)
193
194 if self.binner is None:
--> 195 self.binner, self.grouper = self._get_binner()
196
197 def _get_binner(self):
/Users/scari/codes/scari/pandas/pandas/tseries/resample.py in _get_binner(self)
201 """
202
--> 203 binner, bins, binlabels = self._get_binner_for_time()
204 bin_grouper = BinGrouper(bins, binlabels)
205 return binner, bin_grouper
/Users/scari/codes/scari/pandas/pandas/tseries/resample.py in _get_binner_for_time(self)
476 if self.kind == 'period':
477 return self.groupby._get_time_period_bins(self.ax)
--> 478 return self.groupby._get_time_bins(self.ax)
479
480 def _downsample(self, how, **kwargs):
/Users/scari/codes/scari/pandas/pandas/tseries/resample.py in _get_time_bins(self, ax)
879 # general version, knowing nothing about relative frequencies
880 bins = lib.generate_bins_dt64(
--> 881 ax_values, bin_edges, self.closed, hasnans=ax.hasnans)
882
883 if self.closed == 'right':
/Users/scari/codes/scari/pandas/pandas/lib.pyx in pandas.lib.generate_bins_dt64 (pandas/lib.c:20883)()
1160
1161 if values[lenidx-1] > binner[lenbin-1]:
-> 1162 raise ValueError("Values falls after last bin")
1163
1164 bins = np.empty(lenbin - 1, dtype=np.int64)
ValueError: Values falls after last bin
INSTALLED VERSIONS
commit: 8f1a318
python: 3.4.4.final.0
python-bits: 64
OS: Darwin
OS-release: 15.0.0
machine: x86_64
processor: i386
byteorder: little
LC_ALL: ko_KR.UTF-8
LANG: ko_KR.UTF-8
pandas: 0.18.0rc1+8.g8f1a318.dirty
nose: 1.3.7
pip: 7.1.2
setuptools: 19.2
Cython: 0.23.4
numpy: 1.10.2
scipy: 0.16.0
statsmodels: 0.6.1
xarray: None
IPython: 4.0.0
sphinx: 1.3.1
patsy: 0.4.0
dateutil: 2.4.2
pytz: 2015.7
blosc: None
bottleneck: 1.0.0
tables: 3.2.2
numexpr: 2.4.4
matplotlib: 1.4.3
openpyxl: 2.2.6
xlrd: 0.9.4
xlwt: 1.0.0
xlsxwriter: 0.7.7
lxml: 3.4.4
bs4: 4.4.1
html5lib: None
httplib2: 0.9.1
apiclient: None
sqlalchemy: 1.0.9
pymysql: None
psycopg2: None
jinja2: 2.8