Description
Code Sample, a copy-pastable example if possible
import pandas as pd
import numpy as np
labels = np.array([[0, 0,1,1],
[0, 1, 0, 1]])
columns = pd.MultiIndex(
levels=[["a", "b"], ['%', '#']], labels=labels, names=['', ''])
df = pd.DataFrame(
[[1,-1,1,1],[-1,1,1,1]],
index=["hello", "world"],
columns=columns)
pct_subset = pd.IndexSlice[:, pd.IndexSlice[:, '%':'%']]
def color_negative_red(val):
color = 'red' if val < 0 else 'black'
return 'color: %s' % color
# Works on both 0.22 and 0.24.
df.loc[pct_subset]
# This works on 0.22, but `TypeError: unhashable type` on 0.24!
df.style.applymap(color_negative_red, subset=pct_subset)Problem description
To quote from the docs on the subset keyword argument for Styler.applymap (https://pandas.pydata.org/pandas-docs/stable/user_guide/style.html) :
For row and column slicing, any valid indexer to .loc will work.
The code sample demonstrates an indexer for a dataframe with multindex columns that works with .loc, but doesn't work as the subset argument to applymap. Note that this indexer previously worked in pandas version 0.22, but a regression has been introduced in 0.24.2
Expected Output
Expected the indexer to apply the styling the "%" columns, and not throw an error.
Full Backtrace
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-17-994feb9d52cf> in <module>()
1 df.style.format(
----> 2 '{:.1f}%', subset=pct_subset)
/home/jeremysalwen/.local/lib/python2.7/site-packages/pandas/io/formats/style.pyc in format(self, formatter, subset)
399 subset = subset, self.data.columns
400
--> 401 sub_df = self.data.loc[subset]
402 row_locs = self.data.index.get_indexer_for(sub_df.index)
403 col_locs = self.data.columns.get_indexer_for(sub_df.columns)
/home/jeremysalwen/.local/lib/python2.7/site-packages/pandas/core/indexing.pyc in __getitem__(self, key)
1492 except (KeyError, IndexError, AttributeError):
1493 pass
-> 1494 return self._getitem_tuple(key)
1495 else:
1496 # we by definition only have the 0th axis
/home/jeremysalwen/.local/lib/python2.7/site-packages/pandas/core/indexing.pyc in _getitem_tuple(self, tup)
866 def _getitem_tuple(self, tup):
867 try:
--> 868 return self._getitem_lowerdim(tup)
869 except IndexingError:
870 pass
/home/jeremysalwen/.local/lib/python2.7/site-packages/pandas/core/indexing.pyc in _getitem_lowerdim(self, tup)
967 # we may have a nested tuples indexer here
968 if self._is_nested_tuple_indexer(tup):
--> 969 return self._getitem_nested_tuple(tup)
970
971 # we maybe be using a tuple to represent multiple dimensions here
/home/jeremysalwen/.local/lib/python2.7/site-packages/pandas/core/indexing.pyc in _getitem_nested_tuple(self, tup)
1046
1047 current_ndim = obj.ndim
-> 1048 obj = getattr(obj, self.name)._getitem_axis(key, axis=axis)
1049 axis += 1
1050
/home/jeremysalwen/.local/lib/python2.7/site-packages/pandas/core/indexing.pyc in _getitem_axis(self, key, axis)
1900 raise ValueError('Cannot index with multidimensional key')
1901
-> 1902 return self._getitem_iterable(key, axis=axis)
1903
1904 # nested tuple slicing
/home/jeremysalwen/.local/lib/python2.7/site-packages/pandas/core/indexing.pyc in _getitem_iterable(self, key, axis)
1203 # A collection of keys
1204 keyarr, indexer = self._get_listlike_indexer(key, axis,
-> 1205 raise_missing=False)
1206 return self.obj._reindex_with_indexers({axis: [keyarr, indexer]},
1207 copy=True, allow_dups=True)
/home/jeremysalwen/.local/lib/python2.7/site-packages/pandas/core/indexing.pyc in _get_listlike_indexer(self, key, axis, raise_missing)
1152 if len(ax) or not len(key):
1153 key = self._convert_for_reindex(key, axis)
-> 1154 indexer = ax.get_indexer_for(key)
1155 keyarr = ax.reindex(keyarr)[0]
1156 else:
/home/jeremysalwen/.local/lib/python2.7/site-packages/pandas/core/indexes/base.pyc in get_indexer_for(self, target, **kwargs)
4453 """
4454 if self.is_unique:
-> 4455 return self.get_indexer(target, **kwargs)
4456 indexer, _ = self.get_indexer_non_unique(target, **kwargs)
4457 return indexer
/home/jeremysalwen/.local/lib/python2.7/site-packages/pandas/core/indexes/multi.pyc in get_indexer(self, target, method, limit, tolerance)
2157 method=method,
2158 limit=limit,
-> 2159 tolerance=tolerance)
2160
2161 if not self.is_unique:
/home/jeremysalwen/.local/lib/python2.7/site-packages/pandas/core/indexes/base.pyc in get_indexer(self, target, method, limit, tolerance)
2753 'backfill or nearest reindexing')
2754
-> 2755 indexer = self._engine.get_indexer(target._ndarray_values)
2756
2757 return ensure_platform_int(indexer)
pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_indexer()
pandas/_libs/hashtable_class_helper.pxi in pandas._libs.hashtable.PyObjectHashTable.lookup()
TypeError: unhashable type
Output of pd.show_versions()
INSTALLED VERSIONS
commit: None
python: 2.7.14.final.0
python-bits: 64
OS: Linux
OS-release: 4.19.20-1rodete1-amd64
machine: x86_64
processor:
byteorder: little
LC_ALL: None
LANG: en_US.UTF-8
LOCALE: None.None
pandas: 0.24.2
pytest: None
pip: 19.0.3
setuptools: 36.7.1
Cython: None
numpy: 1.16.2
scipy: None
pyarrow: None
xarray: None
IPython: 5.8.0
sphinx: None
patsy: None
dateutil: 2.8.0
pytz: 2018.9
blosc: None
bottleneck: None
tables: None
numexpr: None
feather: None
matplotlib: None
openpyxl: None
xlrd: None
xlwt: None
xlsxwriter: None
lxml.etree: 4.2.5
bs4: 4.6.0
html5lib: 0.999999999
sqlalchemy: None
pymysql: None
psycopg2: None
jinja2: 2.10
s3fs: None
fastparquet: None
pandas_gbq: None
pandas_datareader: None
gcsfs: None