Merge pull request #32 from NSAPH-Data-Processing/audiracmichelle/issue28

Audiracmichelle/issue28

Author: audiracmichelle

Dockerfile

@@ -20,4 +20,4 @@ RUN python utils/create_dir_paths.py datapaths=datapaths.yaml
 
 # snakemake --configfile conf/config.yaml --cores 4 -C shapefile_polygon_name=zcta
 ENTRYPOINT ["snakemake"]
-CMD ["--cores", "1", "-C", "shapefile_year=2015", "shapefile_polygon_name=county"]
+CMD ["--cores", "1", "-C", "shapefile_tag=2015", "shapefile_polygon_name=county"]

Snakefile

@@ -3,32 +3,33 @@ import yaml
 conda: "requirements.yaml"
 configfile: "conf/config.yaml"
 
-year=config["shapefile_year"]
+tag=config["shapefile_tag"]
 polygon_name=config["shapefile_polygon_name"]
 
 rule all:
     input:
-        f"data/output/climate_types_raster2polygon/climate_types_{polygon_name}_{year}.parquet"
+        f"data/output/climate_types_raster2polygon/climate_types_{polygon_name}_{tag}.parquet"
 
 rule download_climate_types:
     output:
         f"data/input/climate_types/{config['climate_types_file']}"
     shell:
         "python src/download_climate_types.py"
 
-rule download_shapefiles:
-    output:
-        f"data/input/shapefiles/shapefile_{polygon_name}_{year}/shapefile.shp" #ext = ["shp", "shx", "dbf", "prj", "cpg", "xml"]
-    shell:
-        f"python src/download_shapefile.py shapefile_year={year} shapefile_polygon_name={polygon_name}"
+# temporarily removing download step in snakemake
+# rule download_shapefiles:
+#     output:
+#         f"data/input/shapefiles/shapefile_{polygon_name}_{tag}/shapefile.shp" #ext = ["shp", "shx", "dbf", "prj", "cpg", "xml"]
+#     shell:
+#         f"python src/download_shapefile.py shapefile_tag={tag} shapefile_polygon_name={polygon_name}"
 
 rule aggregate_climate_types:
     input:
         f"data/input/climate_types/{config['climate_types_file']}", 
-        f"data/input/shapefiles/shapefile_{polygon_name}_{year}/shapefile.shp"
+        f"data/input/shapefiles/shapefile_{polygon_name}_{tag}/shapefile.shp"
     output:
-        f"data/output/climate_types_raster2polygon/climate_types_{polygon_name}_{year}.parquet",
-        f"data/intermediate/climate_pcts/climate_pcts_{polygon_name}_{year}.json",
-        f"data/intermediate/climate_pcts/climate_types_{polygon_name}_{year}.csv"
+        f"data/output/climate_types_raster2polygon/climate_types_{polygon_name}_{tag}.parquet",
+        f"data/intermediate/climate_pcts/climate_pcts_{polygon_name}_{tag}.json",
+        f"data/intermediate/climate_pcts/climate_types_{polygon_name}_{tag}.csv"
     shell:
-        f"python src/aggregate_climate_types.py shapefile_year={year} shapefile_polygon_name={polygon_name}"
+        f"python src/aggregate_climate_types.py shapefile_tag={tag} shapefile_polygon_name={polygon_name}"

conf/config.yaml

@@ -1,7 +1,7 @@
 defaults:
   - _self_
   - datapaths: datapaths
-  - shapefiles: shapefiles
+  - shapefiles: global_shapefiles
   - climate_keys: climate_keys
 
 # Climate types raw raster information
@@ -14,8 +14,8 @@ climate_types_file: Beck_KG_V1_present_0p0083.tif  # it's the one at highest res
   # - Beck_KG_V1_present_conf_0p5.tif
 
 # Shapefiles information
-shapefile_year: 2015 #to be matched with cfg.shapefiles
-shapefile_polygon_name: county #to be matched with cfg.shapefiles, column name of id in output file
+shapefile_tag: ADM2all #to be matched with cfg.shapefiles
+shapefile_polygon_name: MEX #to be matched with cfg.shapefiles, column name of id in output file
 
 hydra:
   run:

conf/shapefiles/global_shapefiles.yaml

@@ -0,0 +1,15 @@
+# Catalog of shapefiles
+# cfg.shapefile_tag and cfg.shapefile_polygon_name are used to match the shapefile to use
+
+CAN: 
+  ADM3all:
+    url: null
+    idvar: shapeID_3
+MEX:
+  ADM2all:
+    url: null
+    idvar: shapeID_2
+USA:
+  ADM2all:
+    url: null
+    idvar: shapeID_2

conf/shapefiles/shapefiles.yaml conf/shapefiles/us_shapefiles.yamlconf/shapefiles/shapefiles.yaml renamed to conf/shapefiles/us_shapefiles.yaml

@@ -1,5 +1,5 @@
 # Catalog of shapefiles
-# cfg.shapefile_year and cfg.shapefile_polygon_name are used to match the shapefile to use
+# cfg.shapefile_tag and cfg.shapefile_polygon_name are used to match the shapefile to use
 
 county: #County shapefiles (cartographic boudaries) https://www.census.gov/programs-surveys/geography/guidance/tiger-data-products-guide.html
   2015: