search

USGS-R / regional-hydrologic-forcings-ml

Repo for machine learning models for regional prediction of hydrologic forcing functions. Includes probabilistic seasonal high flow regions for CONUS, and prediction of high flow metrics for selected regions.
Creative Commons Zero v1.0 Universal
0 stars 4 forks source link

Remove features with NAs for CONUS reaches #187

Closed jds485 closed 1 year ago

jds485 commented 1 year ago

We should further explore the attributes available for CONUS reaches and make decisions about applicability of prediction for those reaches. For example, there are NAs for some attributes:

colnames(p1_feature_vars_conus)[unique(which(is.na(p1_feature_vars_conus), arr.ind = TRUE)[,2])] [1] "CAT_STREAMRIVER" "CAT_ARTIFICIAL" "CAT_CANALDITCH" "CAT_CONNECTOR" "CAT_PIPELINE" "ACC_STREAMRIVER" [7] "ACC_ARTIFICIAL" "ACC_CANALDITCH" "ACC_CONNECTOR" "ACC_PIPELINE" "TOT_STREAMRIVER" "TOT_ARTIFICIAL" [13] "TOT_CANALDITCH" "TOT_CONNECTOR" "TOT_PIPELINE" "CAT_STRM_DENS" "ACC_STRM_DENS" "TOT_STRM_DENS"

jds485 commented 1 year ago

I think we'd have to make a downstream target with these selected attributes to avoid triggering a full pipeline rebuild.