Fit Predict method

[momonga-ml]

Currently, no fit predict is supported. Behaviour is desirable and probable would need to use Parametric UMAP base or other means as workaround.

[momonga-ml]

Also see #10

[matthewmeadows81]

For the RandomizedSearchCV I get TypeError: _BaseScorer.call() missing 1 required positional argument: 'y_true' for random_search.fit(coordinates) when I place error_score="raise". Really like the code, but when I run it with GridSearchCV to see if it works it doesn't choose the optimal parameters.

[momonga-ml]

@matthewmeadows81 This is the following the "Tuning with HDBSCAN" example which initializes `validity_scorer = make_scorer(hdbscan.validity.validity_index,greater_is_better=True)?

As for the issue with GridSearchCV not choosing the optimal parameters, it could be due to a number of reasons. It could be that the scoring metric you're using is not suitable for your data or problem, or it could be that the range of parameters you're searching over does not include the optimal parameters.
`