Categorical dtypes cause error when attempting stacked bar plot

[msure]

Code Setup w/ Fake Dataset

import numpy as np
import pandas as pd
from pandas import Series, DataFrame

# running this code in terminal/ipython
%matplotlib qt
import matplotlib.pylab
import matplotlib.pyplot as plt

geographies = ['north america', 'central/south america', 'europe', 'africa', 'asia', 'oceania']
geo_proportions = [0.35, 0.10, 0.30, 0.05, 0.15, 0.05]
task_proportions = [[0.3,0.7],[0.4,0.6],[0.3,0.7],[0.5,0.5],[0.7,0.3],[0.4,0.6]]
cats = ['unsuccessful','completed']

pieces = []
for geo, geo_prop, task_prop in zip(geographies,geo_proportions,task_proportions):
    shape = int(geo_prop * 100000)
    data = {'intl':np.repeat(geo,shape), 'task_completion':np.random.choice(cats, shape, p=task_prop)}
    frame = DataFrame(data)
    pieces.append(frame)

df = pd.concat(pieces, ignore_index=True)

Here's data frame at this point:

In [3]: df.info()
<class 'pandas.core.frame.DataFrame'>
Int64Index: 100000 entries, 0 to 99999
Data columns (total 2 columns):
intl               100000 non-null object
task_completion    100000 non-null object
dtypes: object(2)
memory usage: 2.3+ MB

Expected Output

# when running this code I expect the following chart
df.groupby(['task_completion','intl']).size().unstack(0).plot(kind='bar',stacked=True)

Error

However, my real dataset uses Categorical types:

df['intl'] = df['intl'].astype('category')
df['task_completion'] = df['task_completion'].astype('category')
df['task_completion'] = df['task_completion'].cat.set_categories(['unsuccessful','completed'], ordered=True)

Now frame is:

In [5]: df.info()
<class 'pandas.core.frame.DataFrame'>
Int64Index: 100000 entries, 0 to 99999
Data columns (total 2 columns):
intl               100000 non-null category
task_completion    100000 non-null category
dtypes: category(2)
memory usage: 976.6 KB

And I get the following error when trying to plot:

In [6]: df.groupby(['task_completion','intl']).size().unstack(0).plot(kind='bar',stacked=True)
---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-6-8d6e104892c4> in <module>()
----> 1 df.groupby(['task_completion','intl']).size().unstack(0).plot(kind='bar',stacked=True)

/Users/adrianpalacios/anaconda/lib/python3.4/site-packages/pandas/tools/plotting.py in __call__(self, x, y, kind, ax, subplots, sharex, sharey, layout, figsize, use_index, title, grid, legend, style, logx, logy, loglog, xticks, yticks, xlim, ylim, rot, fontsize, colormap, table, yerr, xerr, secondary_y, sort_columns, **kwds)
   3735                           fontsize=fontsize, colormap=colormap, table=table,
   3736                           yerr=yerr, xerr=xerr, secondary_y=secondary_y,
-> 3737                           sort_columns=sort_columns, **kwds)
   3738     __call__.__doc__ = plot_frame.__doc__
   3739

/Users/adrianpalacios/anaconda/lib/python3.4/site-packages/pandas/tools/plotting.py in plot_frame(data, x, y, kind, ax, subplots, sharex, sharey, layout, figsize, use_index, title, grid, legend, style, logx, logy, loglog, xticks, yticks, xlim, ylim, rot, fontsize, colormap, table, yerr, xerr, secondary_y, sort_columns, **kwds)
   2609                  yerr=yerr, xerr=xerr,
   2610                  secondary_y=secondary_y, sort_columns=sort_columns,
-> 2611                  **kwds)
   2612
   2613

/Users/adrianpalacios/anaconda/lib/python3.4/site-packages/pandas/tools/plotting.py in _plot(data, x, y, subplots, ax, kind, **kwds)
   2436         plot_obj = klass(data, subplots=subplots, ax=ax, kind=kind, **kwds)
   2437
-> 2438     plot_obj.generate()
   2439     plot_obj.draw()
   2440     return plot_obj.result

/Users/adrianpalacios/anaconda/lib/python3.4/site-packages/pandas/tools/plotting.py in generate(self)
   1023         self._compute_plot_data()
   1024         self._setup_subplots()
-> 1025         self._make_plot()
   1026         self._add_table()
   1027         self._make_legend()

/Users/adrianpalacios/anaconda/lib/python3.4/site-packages/pandas/tools/plotting.py in _make_plot(self)
   1959                 rect = self._plot(ax, self.ax_pos + w, y, self.bar_width,
   1960                                   start=start, label=label,
-> 1961                                   log=self.log, **kwds)
   1962                 pos_prior = pos_prior + np.where(mask, y, 0)
   1963                 neg_prior = neg_prior + np.where(mask, 0, y)

/Users/adrianpalacios/anaconda/lib/python3.4/site-packages/pandas/tools/plotting.py in _plot(cls, ax, x, y, w, start, log, **kwds)
   1913     @classmethod
   1914     def _plot(cls, ax, x, y, w, start=0, log=False, **kwds):
-> 1915         return ax.bar(x, y, w, bottom=start, log=log, **kwds)
   1916
   1917     @property

/Users/adrianpalacios/anaconda/lib/python3.4/site-packages/matplotlib/__init__.py in inner(ax, *args, **kwargs)
   1810                     warnings.warn(msg % (label_namer, func.__name__),
   1811                                   RuntimeWarning, stacklevel=2)
-> 1812             return func(ax, *args, **kwargs)
   1813         pre_doc = inner.__doc__
   1814         if pre_doc is None:

/Users/adrianpalacios/anaconda/lib/python3.4/site-packages/matplotlib/axes/_axes.py in bar(self, left, height, width, bottom, **kwargs)
   2127                 edgecolor=e,
   2128                 linewidth=lw,
-> 2129                 label='_nolegend_'
   2130                 )
   2131             r.update(kwargs)

/Users/adrianpalacios/anaconda/lib/python3.4/site-packages/matplotlib/patches.py in __init__(self, xy, width, height, angle, **kwargs)
    640
    641         self._x = float(xy[0])
--> 642         self._y = float(xy[1])
    643         self._width = float(width)
    644         self._height = float(height)

TypeError: only length-1 arrays can be converted to Python scalars

Interestingly, taking out the stacked kwarg works:

df.groupby(['task_completion','intl']).size().unstack(0).plot(kind='bar')

Output of pd.show_versions()

INSTALLED VERSIONS

commit: None
python: 3.4.4.final.0
python-bits: 64
OS: Darwin
OS-release: 15.4.0
machine: x86_64
processor: i386
byteorder: little
LC_ALL: None
LANG: en_US.UTF-8

pandas: 0.18.0
nose: 1.3.7
pip: 8.1.0
setuptools: 20.2.2
Cython: 0.22.1
numpy: 1.10.4
scipy: 0.17.0
statsmodels: 0.6.1
xarray: None
IPython: 4.1.2
sphinx: 1.3.1
patsy: 0.3.0
dateutil: 2.4.2
pytz: 2015.7
blosc: None
bottleneck: 1.0.0
tables: 3.2.0
numexpr: 2.5
matplotlib: 1.5.1
openpyxl: 1.8.5
xlrd: 0.9.3
xlwt: 1.0.0
xlsxwriter: 0.7.3
lxml: 3.4.4
bs4: 4.3.2
html5lib: None
httplib2: 0.9.1
apiclient: None
sqlalchemy: 1.0.5
pymysql: None
psycopg2: None
jinja2: 2.8
boto: 2.38.0

[jreback]

this works on master. not sure what specific issue fixed this.

@TomAugspurger @sinhrks

do we need confirming tests for this?

[msure]

Thanks for reviewing. Just so I understand...master is probably somewhat ahead of the Anaconda distribution, correct?

[jreback]

@msure yes, latest anaconda has 0.18.0 (as does conda). master is not released yet at 0.18.1 (though going to be shortly, next few days).

[sinhrks]

Yeah it works. I'll prepare tests.