Add partial credit

[eribean]

Added partial credit model to IRT models. This supports both univariate and multivariate estimation.

Univariate Signature

girth_model = GirthMCMC(model='PCM', model_args=(n_categories,))

Multivariate Signature

girth_model = GirthMCMC(model='PCM_MD', model_args=(n_categories, n_factors))

Unittests

The unittests take so long to run due to the nature of the problem. THe results of a local run are below:

----------- coverage: platform linux, python 3.8.8-final-0 -----------
Name                                               Stmts   Miss  Cover
----------------------------------------------------------------------
girth_mcmc/__init__.py                                 1      0   100%
girth_mcmc/dichotomous/__init__.py                     5      0   100%
girth_mcmc/dichotomous/multidimensional_twopl.py      44      0   100%
girth_mcmc/dichotomous/onepl_model.py                 19      0   100%
girth_mcmc/dichotomous/rasch_model.py                 16      0   100%
girth_mcmc/dichotomous/threepl_model.py               22      0   100%
girth_mcmc/dichotomous/twopl_model.py                 20      0   100%
girth_mcmc/distributions/__init__.py                   2      0   100%
girth_mcmc/distributions/partial_credit.py            15      0   100%
girth_mcmc/distributions/rayleigh.py                  20      4    80%
girth_mcmc/girth_class.py                             36      0   100%
girth_mcmc/polytomous/__init__.py                      4      0   100%
girth_mcmc/polytomous/graded_response_model.py        28      0   100%
girth_mcmc/polytomous/multidimensional_grm.py         43      0   100%
girth_mcmc/polytomous/multidimensional_pcm.py         31      0   100%
girth_mcmc/polytomous/partial_credit_model.py         20      0   100%
girth_mcmc/utils/__init__.py                           3      0   100%
girth_mcmc/utils/missing_data.py                       5      0   100%
girth_mcmc/utils/multidimensional_utils.py             9      0   100%
girth_mcmc/utils/options.py                           18      0   100%
----------------------------------------------------------------------
TOTAL                                                361      4    99%