triage
triage copied to clipboard
General Purpose Risk Modeling and Prediction Toolkit for Policy and Social Good Problems
When running a new experiment and selecting a subset of the features from the already create features in the features schema, triage uses old matrices and not the new subset...
Basically is missing ...
The imputation keyword should be `zero_no_flag` instead of `zero_noflag`. This is counterintuitive
``` triage experiment experiment_config/simple_test_skeleton.yaml --project-path 'output' --validate-only /usr/local/lib/python3.6/site-packages/psycopg2/__init__.py:144: UserWarning: The psycopg2 wheel package will be renamed from release 2.8; in order to keep installing from binary please use "pip install...
Once a model group is chosen, we want to be able to generate lists of predictions going forward
ScaledLogisticRegression doesn't store the feature importances in the postgres tables.
We recently hit an error where the list of percentiles in evaluation config had a duplicate. We could of course squash duplicates in Triage, but I think this would be...
The [Running Parts of an Experiment](https://dssg.github.io/triage/experiments/running/#running-parts-of-an-experiment) section of the Triage documentation references calling `experiment.generate_imputed_features() `. However in the [base.py](https://github.com/dssg/triage/blob/master/src/triage/experiments/base.py) file, the function is renamed to `impute_missing_features`.