Closed
Description
pandas: 0.23.4
I experienced the error in a different workflow but was able to narrow it down to a simple scenario.
This works as expected:
Working example
import pandas as pd
iris = pd.read_csv('https://raw.githubusercontent.com/mwaskom/seaborn-data/master/iris.csv')
# iris.loc[:,'species'] = iris.species.astype('category')
iris.where(iris.sepal_width > 2)
However, once we transform one of the columns to a category, it breaks.
Broken example
import pandas as pd
iris = pd.read_csv('https://raw.githubusercontent.com/mwaskom/seaborn-data/master/iris.csv')
iris.loc[:,'species'] = iris.species.astype('category')
iris.where(iris.sepal_width > 2)---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-13-aa56ba330a63> in <module>()
5 iris.loc[:,'species'] = iris.species.astype('category')
6
----> 7 iris.where(iris.sepal_width > 2)
C:\Anaconda3\lib\site-packages\pandas\core\generic.py in where(self, cond, other, inplace, axis, level, errors, try_cast, raise_on_error)
7770 other = com._apply_if_callable(other, self)
7771 return self._where(cond, other, inplace, axis, level,
-> 7772 errors=errors, try_cast=try_cast)
7773
7774 @Appender(_shared_docs['where'] % dict(_shared_doc_kwargs, cond="False",
C:\Anaconda3\lib\site-packages\pandas\core\generic.py in _where(self, cond, other, inplace, axis, level, errors, try_cast)
7630 errors=errors,
7631 try_cast=try_cast, axis=block_axis,
-> 7632 transpose=self._AXIS_REVERSED)
7633
7634 return self._constructor(new_data).__finalize__(self)
C:\Anaconda3\lib\site-packages\pandas\core\internals.py in where(self, **kwargs)
3682
3683 def where(self, **kwargs):
-> 3684 return self.apply('where', **kwargs)
3685
3686 def eval(self, **kwargs):
C:\Anaconda3\lib\site-packages\pandas\core\internals.py in apply(self, f, axes, filter, do_integrity_check, consolidate, **kwargs)
3579
3580 kwargs['mgr'] = self
-> 3581 applied = getattr(b, f)(**kwargs)
3582 result_blocks = _extend_blocks(applied, result_blocks)
3583
C:\Anaconda3\lib\site-packages\pandas\core\internals.py in where(self, other, cond, align, errors, try_cast, axis, transpose, mgr)
1536 result = self._try_cast_result(result)
1537
-> 1538 return self.make_block(result)
1539
1540 # might need to separate out blocks
C:\Anaconda3\lib\site-packages\pandas\core\internals.py in make_block(self, values, placement, ndim)
259 ndim = self.ndim
260
--> 261 return make_block(values, placement=placement, ndim=ndim)
262
263 def make_block_scalar(self, values):
C:\Anaconda3\lib\site-packages\pandas\core\internals.py in make_block(values, placement, klass, ndim, dtype, fastpath)
3203 placement=placement, dtype=dtype)
3204
-> 3205 return klass(values, ndim=ndim, placement=placement)
3206
3207 # TODO: flexible with index=None and/or items=None
C:\Anaconda3\lib\site-packages\pandas\core\internals.py in __init__(self, values, placement, ndim)
2301
2302 super(ObjectBlock, self).__init__(values, ndim=ndim,
-> 2303 placement=placement)
2304
2305 @property
C:\Anaconda3\lib\site-packages\pandas\core\internals.py in __init__(self, values, placement, ndim)
123 raise ValueError(
124 'Wrong number of items passed {val}, placement implies '
--> 125 '{mgr}'.format(val=len(self.values), mgr=len(self.mgr_locs)))
126
127 def _check_ndim(self, values, ndim):
ValueError: Wrong number of items passed 150, placement implies 1Same error when a function is passed instead of a boolean Series.