triage
triage copied to clipboard
dssg
General Purpose Risk Modeling and Prediction Toolkit for Policy and Social Good Problems
It will be nice to have an explanation about what exactly `crosstabs` is doing, i.e. comparing two populations etc etc and why is that useful
Instead of one mish-mash example config, the example/config directory should have one example config for each of the three major types of problems. This would complement dirtyduck, allow for better...
https://github.com/dssg/triage/blob/59ffbe1f860e49eb175b4604a549c23cfb1c3fa5/src/triage/component/postmodeling/crosstabs/crosstabs.py#L164 If the feature has the same value across both positive and negative samples, the resulting rows from t-Test `ttest_T` and `ttest_p` will be dropped. We might want to keep...
@saleiro @ecsalomon and I went on a bit of a dive this morning following my exploration of the https://github.com/tdda/tdda repository . The team has talked about "premodeling" before, that could...
_From @thcrock on July 26, 2017 23:15_ Started this in https://github.com/dssg/audition/pull/21 But needs a lot more detail. We can also pair this with some docs infrastructure using mkdocs _Copied from...
If a user updates the query but not the name, we should still remake the matrices and models, even if the user doesn't set the replace flag. As is, the...
precision calculation is currently taking predictions for several as of dates, and calculating precision across all of them together, resulting in bogus results. need to look at how to do...
_From @thcrock on July 19, 2017 22:9_ From @ecsalomon: "Making a small change to a feature group (e.g., adding or removing a single feature) doesn't trigger replacing the feature table...
_From @thcrock on July 19, 2017 21:47_ There is some confusion between the categorical 'column' and aggregate 'quantity'. Merge names? _Copied from original issue: dssg/architect#6_