You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Missing features are current zero-imputed for training and mean-imputed for inference. Aside from their inconsistency, there are better (albeit more costly) ways to perform imputation. The current plan is to:
Exclude the AllWISE W3 and W4 magnitude errors, which are missing from >75% of the training sample
Impute a value of zero for missing mean_ztf_alert_braai
Impute the median for missing magnitude errors (mainly PS1)
Use regression (e.g. KNN imputation) to impute missing magnitudes
Use regression (potentially on a class-by-class basis) to impute missing Gaia EDR3 parallaxes
The text was updated successfully, but these errors were encountered:
This takes significantly longer than inference (~10s) for the same number of sources, but it remains important to change our imputation strategy from its current state.
Missing features are current zero-imputed for training and mean-imputed for inference. Aside from their inconsistency, there are better (albeit more costly) ways to perform imputation. The current plan is to:
mean_ztf_alert_braai
The text was updated successfully, but these errors were encountered: