Distfit

* Some code refactoring and cleaning
* Added test statistic name in the title of the figure

* Changed title text of plot with scientific notation.

* `alpha` parameter added to the `predict` function.
* Output contains `y_bool `which is `y_proba<=alpha`


from distfit import distfit
X = np.random.normal(0, 2, 1000)
y = [-8, -6, 0, 1, 2, 3, 4, 5, 6]

dist = distfit()
dist.fit_transform(X)
results = dist.predict(y, alpha=0.01)
results['y_bool']

* added doi

* Pass fig and ax to give more control to the user's for plotting.

Thank you for the contribution ksachdeva!

* New function "generate" that allows to generate samples after fitting on the data.
* Discrete output parameters aligned with output parameters of parametric models
* New output variable added: "model" which is the fitted model based on loc/scale params. The "distr" remains the unfitted model.
* Code generalized which allows that discrete and parametric runs in more same functions.
* Different scoring statistics is now also possible for discrete fitting.