add a result summary method

[jzluo]

A summary method to present in a prettier format would be nice. I don't think it needs to be as detailed as the summary in statsmodels. This is what summary in logistf looks like:

                   coef  se(coef) lower 0.95  upper 0.95       Chisq            p method
(Intercept)  0.12025405 0.4763429 -0.8185591  1.07315122  0.06286298 8.020268e-01      2
age         -1.10598131 0.4149021 -1.9737884 -0.30742514  7.50773092 6.143472e-03      2
oc          -0.06881673 0.4344026 -0.9414363  0.78920202  0.02467044 8.751911e-01      2
vic          2.26887464 0.5384872  1.2730216  3.43543273 22.93139022 1.678877e-06      2
vicl        -2.11140817 0.5320395 -3.2608611 -1.11773495 19.10407252 1.237805e-05      2
vis         -0.78831694 0.4089620 -1.6080879  0.01518468  3.69740975 5.449701e-02      2
dia          3.09601166 1.5052197  0.7745682  8.03029352  7.89693139 4.951873e-03      2

Method: 1-Wald, 2-Profile penalized log-likelihood, 3-None

Likelihood ratio test=49.09064 on 6 df, p=7.15089e-09, n=239
Wald test = 31.96835 on 6 df, p = 1.654713e-05

Should be called like:

firth = FirthLogisticRegression()
firth.fit(X, y)
firth.summary()

Maybe an optional var_names parameter in .summary() so that the feature names can be printed in the summary as well, otherwise x0, x1, etc.

Probably the most straightforward way is to just stick everything in a Pandas dataframe and print (and perhaps return?) that. Pretty printing with tabulate can be considered, maybe with tabulate as just an optional dependency?