Fife

Added

<u>StateModeler and ExitModeler</u>

- Outcome categories now accessible through class_values attribute

Fixed

<u>ExitModeler</u>

- If the outcome is categorical, only labels associated with an exit (i.e., that appear in the last observation of a spell) are used for training

Added

<u>Modelers</u>

- Can now specify observation weights through the argument `weight_col`. The specified column will not be used as a feature, but will be used to weight observations during training and evaluation.

Fixed

- Area under the receiver operating characteristic curve (AUROC) now computed for multiclass if no class is entirely positive. Classes with no positive values are excluded.
- ExitModeler outcome labeling
- Two hyperparameter prior distribution lower bounds now 2 ** -5 instead of 2e-5.
- LGBModelers now handle datetime categories

Changed

- Multiclass AUROC now weighted by class share (`average="weighted"` in call to [sklearn.metrics.roc_auc_score](https://scikit-learn.org/stable/modules/generated/sklearn.metrics.roc_auc_score.html)).

Added

<u>Modelers</u>

- Can now specify `allow_gaps=True` to remove the restriction that individuals be observed in every future period over the given time horizon. For example, for a time horizon of 2, the default behavior of the StateModeler is to train and evaluate only on observations where the same individual was observed in the next 2 periods. `allow_gaps=True` will instead only require that the same individual be observed 2 periods into the future, thereby allowing a gap where the individual is not observed 1 period into the future.

<u>PanelDataProcessor</u>

- Now produces "_spell" column, which reports the number of gaps in observing the given individual up to the observed time period.

Added

<u>Command-line Interface</u>

- Can now use `BY_FEATURE` to produce separate Metrics.csv files for each value of a selected feature

Fixed

- Number of classes now correctly specified for multiclass outcomes during hyperoptimization

Changed

- SHAP is now an optional dependency; install fife with `pip install fife[shap]` to ensure you can produce SHAP plots

Removed

- Dask optional dependencies except `cloudpickle` and `toolz`

Removed

- Bokeh dependency