Pm.compareplot throws error

Questions version agnostic
1

I was comparing two models with pm.compare and I wanted to visualize the values using pm.compare but I got an error. I’m also confused why the documentation mentions az.plot_compare?

Here’s the code:

comp_dic = {m1: trace_m1, m2: trace_m2}
df_comp_WAIC = pm.compare(comp_dic)
df_comp_WAIC
pm.compareplot(df_comp_WAIC)

Here’s the output:

---------------------------------------------------------------------------
KeyError                                  Traceback (most recent call last)
<ipython-input-142-f1b04076e5ff> in <module>
----> 1 pm.compareplot(df_comp_WAIC)

~/anaconda3/lib/python3.7/site-packages/pymc3/plots/__init__.py in compareplot(*args, **kwargs)
     81     else:
     82         args[0] = comp_df
---> 83     return az.plot_compare(*args, **kwargs)
     84 
     85 from .posteriorplot import plot_posterior_predictive_glm

~/anaconda3/lib/python3.7/site-packages/arviz/plots/compareplot.py in plot_compare(comp_df, insample_dev, plot_standard_error, plot_ic_diff, order_by_rank, figsize, textsize, plot_kwargs, ax)
    107 
    108     if order_by_rank:
--> 109         comp_df.sort_values(by="rank", inplace=True)
    110 
    111     if plot_ic_diff:

~/anaconda3/lib/python3.7/site-packages/pandas/core/frame.py in sort_values(self, by, axis, ascending, inplace, kind, na_position)
   4717 
   4718             by = by[0]
-> 4719             k = self._get_label_or_level_values(by, axis=axis)
   4720 
   4721             if isinstance(ascending, (tuple, list)):

~/anaconda3/lib/python3.7/site-packages/pandas/core/generic.py in _get_label_or_level_values(self, key, axis)
   1704             values = self.axes[axis].get_level_values(key)._values
   1705         else:
-> 1706             raise KeyError(key)
   1707 
   1708         # Check for duplicates

KeyError: 'rank'
2

Could you try upgrading to the master branch?

3

PyMC actually uses ArviZ for plots and diagnostics. I know some bugs have been solved on PyMC’s master branch but are not released yet, so I’d advise using ArviZ directly (az.) instead of PyMC (pm.) when plotting and diagnosing.

4

Can you try call compareplot with dict with traces (skip calling compare function)