Group preprocessing by dataset.

Scripts/preprocess.sh → Scripts/preprocess_CORDEX.sh

@@ -17,10 +17,10 @@ PR_INVENTORY='/mnt/CEPH_PROJECTS/FACT_CLIMAX/CORDEX/Inventory/pr/pr_inventory_se
 # preprocess EuroCordex simulations
 
 # tasmin
-time python climax/main/preprocess.py $TARGET_GRID $SOURCE_PATH $TARGET_PATH -f $TASMIN_INVENTORY -m 'bilinear' -rm -a -o
+time python climax/main/preprocess_CORDEX.py $TARGET_GRID $SOURCE_PATH $TARGET_PATH -f $TASMIN_INVENTORY -m 'bilinear' -rm -a -o
 
 # tasmax
-time python climax/main/preprocess.py $TARGET_GRID $SOURCE_PATH $TARGET_PATH -f $TASMAX_INVENTORY -m 'bilinear' -rm -a -o
+time python climax/main/preprocess_CORDEX.py $TARGET_GRID $SOURCE_PATH $TARGET_PATH -f $TASMAX_INVENTORY -m 'bilinear' -rm -a -o
 
 # pr
-time python climax/main/preprocess.py $TARGET_GRID $SOURCE_PATH $TARGET_PATH -f $PR_INVENTORY -m 'bilinear' -rm -a -o
\ No newline at end of file
+time python climax/main/preprocess_CORDEX.py $TARGET_GRID $SOURCE_PATH $TARGET_PATH -f $PR_INVENTORY -m 'bilinear' -rm -a -o
\ No newline at end of file

climax/main/download_ERA5.py

@@ -82,6 +82,8 @@ if __name__ == '__main__':
                 product, {**CONFIG, **{'variable': var, 'year': year}}, file)
             for file, year in zip(files, years) if not file.exists())
 
+        # TODO: Move to preprocess_ERA5.py
+
         # aggregate files for different years into a single file using xarray
         # and dask
         ds = xr.open_mfdataset(files, parallel=True).compute()

climax/main/preprocess.py → climax/main/preprocess_CORDEX.py

@@ -20,7 +20,7 @@ from pysegcnn.core.logging import log_conf
 from pysegcnn.core.trainer import LogConfig
 from climax.core.utils import (get_inventory, reproject_cdo,
                                _parse_cordex_time_span)
-from climax.core.cli import preprocess_parser
+from climax.core.cli import preprocess_cordex_parser
 from climax.core.constants import EUROCORDEX_DOMAIN, CORDEX_PARAMETERS
 
 # module level logger
@@ -47,7 +47,7 @@ if __name__ == '__main__':
     dictConfig(log_conf())
 
     # define command line argument parser
-    parser = preprocess_parser()
+    parser = preprocess_cordex_parser()
 
     # parse command line arguments
     args = sys.argv[1:]

climax/main/preprocess_ERA5.py

+"""Preprocess ERA-5 data: aggregate to daily and resample to target grid."""
+
+# !/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+