ngiab-data-preprocess 3.2.3__tar.gz → 3.3.0__tar.gz

{ngiab_data_preprocess-3.2.3 → ngiab_data_preprocess-3.3.0}/.gitignore

@@ -12,4 +12,5 @@ dist
 **/tiles/vpu*
 *.tar.gz
 *.dat
-uv.lock
+uv.lock
+/build

{ngiab_data_preprocess-3.2.3 → ngiab_data_preprocess-3.3.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: ngiab_data_preprocess
-Version: 3.2.3
+Version: 3.3.0
 Summary: Graphical Tools for creating Next Gen Water model input data.
 Author-email: Josh Cunningham <jcunningham8@ua.edu>
 Project-URL: Homepage, https://github.com/CIROH-UA/NGIAB_data_preprocess

{ngiab_data_preprocess-3.2.3 → ngiab_data_preprocess-3.3.0}/modules/data_processing/create_realization.py

@@ -74,7 +74,7 @@ def make_cfe_config(
             bexp=row["mode.bexp_soil_layers_stag=2"],
             dksat=row["geom_mean.dksat_soil_layers_stag=2"],
             psisat=row["geom_mean.psisat_soil_layers_stag=2"],
-            slope=row["mean.slope"],
+            slope=row["mean.slope_1km"],
             smcmax=row["mean.smcmax_soil_layers_stag=2"],
             smcwlt=row["mean.smcwlt_soil_layers_stag=2"],
             max_gw_storage=row["mean.Zmax"]/1000 if row["mean.Zmax"] is not None else "0.011[m]", # mean.Zmax is in mm!
@@ -107,10 +107,10 @@ def make_noahowp_config(
                 template.format(
                     start_datetime=start_datetime,
                     end_datetime=end_datetime,
-                    lat=divide_conf_df.loc[divide, "centroid_y"],
-                    lon=divide_conf_df.loc[divide, "centroid_x"],
-                    terrain_slope=divide_conf_df.loc[divide, "mean.slope"],
-                    azimuth=divide_conf_df.loc[divide, "circ_mean.aspect"],
+                    lat=divide_conf_df.loc[divide, "latitude"],
+                    lon=divide_conf_df.loc[divide, "longitude"],
+                    terrain_slope= divide_conf_df.loc[divide, "mean.slope_1km"],
+                    azimuth= divide_conf_df.loc[divide, "circ_mean.aspect"],
                     ISLTYP=int(divide_conf_df.loc[divide, "mode.ISLTYP"]),
                     IVGTYP=int(divide_conf_df.loc[divide, "mode.IVGTYP"]),
                 )
@@ -123,24 +123,25 @@ def get_model_attributes_modspatialite(hydrofabric: Path):
     with GeoPackage(hydrofabric) as conn:
         sql = """WITH source_crs AS (
         SELECT organization || ':' || organization_coordsys_id AS crs_string
-        FROM gpkg_spatial_ref_sys 
+        FROM gpkg_spatial_ref_sys
         WHERE srs_id = (
-            SELECT srs_id 
-            FROM gpkg_geometry_columns 
+            SELECT srs_id
+            FROM gpkg_geometry_columns
             WHERE table_name = 'divides'
         )
         )
-        SELECT 
-        d.divide_id, 
-        d.areasqkm, 
-        da."mean.slope", 
+        SELECT
+        d.divide_id,
+        d.areasqkm,
+        da."mean.slope",
+        da."mean.slope_1km",
         da."mean.elevation",
-        ST_X(Transform(MakePoint(da.centroid_x, da.centroid_y), 4326, NULL, 
+        ST_X(Transform(MakePoint(da.centroid_x, da.centroid_y), 4326, NULL,
             (SELECT crs_string FROM source_crs), 'EPSG:4326')) AS longitude,
-        ST_Y(Transform(MakePoint(da.centroid_x, da.centroid_y), 4326, NULL, 
+        ST_Y(Transform(MakePoint(da.centroid_x, da.centroid_y), 4326, NULL,
             (SELECT crs_string FROM source_crs), 'EPSG:4326')) AS latitude
-        FROM divides AS d 
-        JOIN 'divide-attributes' AS da ON d.divide_id = da.divide_id 
+        FROM divides AS d
+        JOIN 'divide-attributes' AS da ON d.divide_id = da.divide_id
         """
         divide_conf_df = pandas.read_sql_query(sql, conn)
     divide_conf_df.set_index("divide_id", inplace=True)
@@ -151,15 +152,16 @@ def get_model_attributes_pyproj(hydrofabric: Path):
     # if modspatialite is not available, use pyproj
     with sqlite3.connect(hydrofabric) as conn:
         sql = """
-        SELECT 
-        d.divide_id, 
-        d.areasqkm, 
-        da."mean.slope", 
+        SELECT
+        d.divide_id,
+        d.areasqkm,
+        da."mean.slope",
+        da."mean.slope_1km",
         da."mean.elevation",
         da.centroid_x,
         da.centroid_y
-        FROM divides AS d 
-        JOIN 'divide-attributes' AS da ON d.divide_id = da.divide_id 
+        FROM divides AS d
+        JOIN 'divide-attributes' AS da ON d.divide_id = da.divide_id
         """
         divide_conf_df = pandas.read_sql_query(sql, conn)
 
@@ -179,6 +181,40 @@ def get_model_attributes_pyproj(hydrofabric: Path):
 
     return divide_conf_df
 
+def get_model_attributes(hydrofabric: Path):
+    try:
+        with GeoPackage(hydrofabric) as conn:
+            conf_df = pandas.read_sql_query(
+                """WITH source_crs AS (
+            SELECT organization || ':' || organization_coordsys_id AS crs_string
+            FROM gpkg_spatial_ref_sys
+            WHERE srs_id = (
+                SELECT srs_id
+                FROM gpkg_geometry_columns
+                WHERE table_name = 'divides'
+            )
+            )
+            SELECT
+            *,
+            ST_X(Transform(MakePoint(centroid_x, centroid_y), 4326, NULL,
+                (SELECT crs_string FROM source_crs), 'EPSG:4326')) AS longitude,
+            ST_Y(Transform(MakePoint(centroid_x, centroid_y), 4326, NULL,
+                (SELECT crs_string FROM source_crs), 'EPSG:4326')) AS latitude FROM 'divide-attributes';""",
+                conn,
+            )
+    except pandas.errors.DatabaseError:
+        with sqlite3.connect(hydrofabric) as conn:
+            conf_df = pandas.read_sql_query("SELECT* FROM 'divide-attributes';", conn,)
+        source_crs = get_table_crs_short(hydrofabric, "divides")
+        transformer = Transformer.from_crs(source_crs, "EPSG:4326", always_xy=True)
+        lon, lat = transformer.transform(
+            conf_df["centroid_x"].values, conf_df["centroid_y"].values
+        )
+        conf_df["longitude"] = lon
+        conf_df["latitude"] = lat
+
+        conf_df.drop(columns=["centroid_x", "centroid_y"], axis=1, inplace=True)
+    return conf_df
 
 def make_em_config(
     hydrofabric: Path,
@@ -224,8 +260,6 @@ def configure_troute(
         troute_template = file.read()
     time_step_size = 300
     nts = (end_time - start_time).total_seconds() / time_step_size
-    seconds_in_hour = 3600
-    number_of_hourly_steps = nts * time_step_size / seconds_in_hour
     filled_template = troute_template.format(
         # hard coded to 5 minutes
         time_step_size=time_step_size,
@@ -234,8 +268,7 @@ def configure_troute(
         geo_file_path=f"./config/{cat_id}_subset.gpkg",
         start_datetime=start_time.strftime("%Y-%m-%d %H:%M:%S"),
         nts=nts,
-        max_loop_size=nts,
-        stream_output_time=number_of_hourly_steps,
+        max_loop_size=nts,        
     )
 
     with open(config_dir / "troute.yaml", "w") as file:
@@ -243,7 +276,7 @@ def configure_troute(
 
 
 def make_ngen_realization_json(
-    config_dir: Path, template_path: Path, start_time: datetime, end_time: datetime 
+    config_dir: Path, template_path: Path, start_time: datetime, end_time: datetime
 ) -> None:
     with open(template_path, "r") as file:
         realization = json.load(file)
@@ -281,8 +314,8 @@ def create_realization(cat_id: str, start_time: datetime, end_time: datetime, us
 
     # get approximate groundwater levels from nwm output
     template_path = paths.template_cfe_nowpm_realization_config
-    with sqlite3.connect(paths.geopackage_path) as conn:
-        conf_df = pandas.read_sql_query("SELECT * FROM 'divide-attributes';", conn)
+    
+    conf_df = get_model_attributes(paths.geopackage_path)
 
     if use_nwm_gw:
         gw_levels = get_approximate_gw_storage(paths, start_time)
@@ -310,10 +343,10 @@ def create_partitions(paths: Path, num_partitions: int = None) -> None:
     cat_to_nex_pairs = get_cat_to_nex_flowpairs(hydrofabric=paths.geopackage_path)
     nexus = defaultdict(list)
 
-    for cat, nex in cat_to_nex_pairs:
-        nexus[nex].append(cat)
+    # for cat, nex in cat_to_nex_pairs:
+    #     nexus[nex].append(cat)
 
-    num_partitions = min(num_partitions, len(nexus))
+    num_partitions = min(num_partitions, len(cat_to_nex_pairs))
     # partition_size = ceil(len(nexus) / num_partitions)
     # num_nexus = len(nexus)
     # nexus = list(nexus.items())

{ngiab_data_preprocess-3.2.3 → ngiab_data_preprocess-3.3.0}/modules/data_processing/file_paths.py

@@ -97,12 +97,19 @@ class file_paths:
 
     @property
     def cached_nc_file(self) -> Path:
-        return self.subset_dir / "merged_data.nc"
+        return self.forcings_dir / "raw_gridded_data.nc"
+
+    def append_cli_command(self, command: list[str]) -> None:
+        current_time = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
+        command_string = " ".join(command)
+        history_file  = self.metadata_dir / "cli_commands_history.txt"
+        if not history_file.parent.exists():
+            history_file.parent.mkdir(parents=True, exist_ok=True)
+        with open(self.metadata_dir / "cli_commands_history.txt", "a") as f:
+            f.write(f"{current_time}| {command_string}\n")
 
     def setup_run_folders(self) -> None:
         folders = [
-            "restart",
-            "lakeout",
             "outputs",
             "outputs/ngen",
             "outputs/troute",

{ngiab_data_preprocess-3.2.3 → ngiab_data_preprocess-3.3.0}/modules/data_processing/forcings.py

@@ -76,6 +76,8 @@ def add_APCP_SURFACE_to_dataset(dataset: xr.Dataset) -> xr.Dataset:
     # technically should be kg/m^2/s at 1kg = 1l it equates to mm/s
     # nom says qinsur output is m/s, hopefully qinsur is converted to mm/h by ngen
     dataset["APCP_surface"] = dataset["precip_rate"] * 3600
+    dataset["APCP_surface"].attrs["units"] = "mm h^-1" # ^-1 notation copied from source data
+    dataset["APCP_surface"].attrs["source_note"] = "This is just the precip_rate variable converted to mm/h by multiplying by 3600"
     return dataset
 
 
@@ -140,6 +142,12 @@ def get_cell_weights_parallel(gdf, input_forcings, num_partitions):
         catchments = pool.starmap(get_cell_weights, args)
     return pd.concat(catchments)
 
+def get_units(dataset: xr.Dataset) -> dict:
+    units = {}
+    for var in dataset.data_vars:
+        if dataset[var].attrs["units"]:
+            units[var] = dataset[var].attrs["units"]
+    return units
 
 def compute_zonal_stats(
     gdf: gpd.GeoDataFrame, merged_data: xr.Dataset, forcings_dir: Path
@@ -152,6 +160,8 @@ def compute_zonal_stats(
 
     catchments = get_cell_weights_parallel(gdf, merged_data, num_partitions)
 
+    units = get_units(merged_data)
+
     variables = {
                 "LWDOWN": "DLWRF_surface",
                 "PSFC": "PRES_surface",
@@ -224,12 +234,12 @@ def compute_zonal_stats(
         # Merge the chunks back together
         datasets = [xr.open_dataset(forcings_dir / "temp" / f"{variable}_{i}.nc") for i in range(len(time_chunks))]
         result = xr.concat(datasets, dim="time")
-        result.to_netcdf(forcings_dir / f"{variable}.nc")
+        result.to_netcdf(forcings_dir / "temp" / f"{variable}.nc")
         # close the datasets
         result.close()
         _ = [dataset.close() for dataset in datasets]
 
-        for file in forcings_dir.glob("temp/*.nc"):
+        for file in forcings_dir.glob("temp/*_*.nc"):
             file.unlink()
         progress.remove_task(chunk_task)
     progress.update(
@@ -240,10 +250,10 @@ def compute_zonal_stats(
     logger.info(
         f"Forcing generation complete! Zonal stats computed in {time.time() - timer_start:2f} seconds"
     )
-    write_outputs(forcings_dir, variables)
+    write_outputs(forcings_dir, variables, units)
 
 
-def write_outputs(forcings_dir, variables):
+def write_outputs(forcings_dir, variables, units):
 
     # start a dask cluster if there isn't one already running
     try:
@@ -251,12 +261,15 @@ def write_outputs(forcings_dir, variables):
     except ValueError:
         cluster = LocalCluster()
         client = Client(cluster)
-
+    temp_forcings_dir = forcings_dir / "temp"
     # Combine all variables into a single dataset using dask
-    results = [xr.open_dataset(file, chunks="auto") for file in forcings_dir.glob("*.nc")]
+    results = [xr.open_dataset(file, chunks="auto") for file in temp_forcings_dir.glob("*.nc")]
     final_ds = xr.merge(results)
-
-    output_folder = forcings_dir / "by_catchment"
+    for var in final_ds.data_vars:
+        if var in units:
+            final_ds[var].attrs["units"] = units[var]
+        else:
+            logger.warning(f"Variable {var} has no units")
 
     rename_dict = {}
     for key, value in variables.items():
@@ -294,19 +307,25 @@ def write_outputs(forcings_dir, variables):
     final_ds["Time"].attrs["units"] = "s"
     final_ds["Time"].attrs["epoch_start"] = "01/01/1970 00:00:00" # not needed but suppresses the ngen warning
 
-    final_ds.to_netcdf(output_folder / "forcings.nc", engine="netcdf4")
+    final_ds.to_netcdf(forcings_dir / "forcings.nc", engine="netcdf4")
     # close the datasets
     _ = [result.close() for result in results]
     final_ds.close()
 
+    # clean up the temp files
+    for file in temp_forcings_dir.glob("*.*"):
+        file.unlink()
+    temp_forcings_dir.rmdir()
+
 
 def setup_directories(cat_id: str) -> file_paths:
     forcing_paths = file_paths(cat_id)
-    if forcing_paths.forcings_dir.exists():
-        logger.info("Forcings directory already exists, deleting")
-        shutil.rmtree(forcing_paths.forcings_dir)
-    for folder in ["by_catchment", "temp"]:
-        os.makedirs(forcing_paths.forcings_dir / folder, exist_ok=True)
+    # delete everything in the forcing folder except the cached nc file
+    for file in forcing_paths.forcings_dir.glob("*.*"):
+        if file != forcing_paths.cached_nc_file:
+            file.unlink()
+
+    os.makedirs(forcing_paths.forcings_dir / "temp", exist_ok=True)
 
     return forcing_paths
 
@@ -326,7 +345,7 @@ def create_forcings(
     if type(end_time) == datetime:
         end_time = end_time.strftime("%Y-%m-%d %H:%M")
 
-    merged_data = get_forcing_data(forcing_paths, start_time, end_time, gdf, forcing_vars)
+    merged_data = get_forcing_data(forcing_paths.cached_nc_path, start_time, end_time, gdf, forcing_vars)
     compute_zonal_stats(gdf, merged_data, forcing_paths.forcings_dir)
 
 

{ngiab_data_preprocess-3.2.3 → ngiab_data_preprocess-3.3.0}/modules/data_processing/zarr_utils.py

@@ -100,18 +100,18 @@ def compute_store(stores: xr.Dataset, cached_nc_path: Path) -> xr.Dataset:
 
 
 def get_forcing_data(
-    forcing_paths: file_paths,
+    cached_nc_path: Path,
     start_time: str,
     end_time: str,
     gdf: gpd.GeoDataFrame,
     forcing_vars: list[str] = None,
 ) -> xr.Dataset:
     merged_data = None
-    if os.path.exists(forcing_paths.cached_nc_file):
+    if os.path.exists(cached_nc_path):
         logger.info("Found cached nc file")
         # open the cached file and check that the time range is correct
         cached_data = xr.open_mfdataset(
-            forcing_paths.cached_nc_file, parallel=True, engine="h5netcdf"
+            cached_nc_path, parallel=True, engine="h5netcdf"
         )
         range_in_cache = cached_data.time[0].values <= np.datetime64(
             start_time
@@ -138,14 +138,14 @@ def get_forcing_data(
 
         if range_in_cache:
             logger.info("Time range is within cached data")
-            logger.debug(f"Opened cached nc file: [{forcing_paths.cached_nc_file}]")
+            logger.debug(f"Opened cached nc file: [{cached_nc_path}]")
             merged_data = clip_dataset_to_bounds(
                 cached_data, gdf.total_bounds, start_time, end_time
             )
             logger.debug("Clipped stores")
         else:
             logger.info("Time range is incorrect")
-            os.remove(forcing_paths.cached_nc_file)
+            os.remove(cached_nc_path)
             logger.debug("Removed cached nc file")
 
     if merged_data is None:
@@ -155,7 +155,7 @@ def get_forcing_data(
         logger.debug("Got zarr stores")
         clipped_store = clip_dataset_to_bounds(lazy_store, gdf.total_bounds, start_time, end_time)
         logger.info("Clipped forcing data to bounds")
-        merged_data = compute_store(clipped_store, forcing_paths.cached_nc_file)
+        merged_data = compute_store(clipped_store, cached_nc_path)
         logger.info("Forcing data loaded and cached")
         # close the event loop
 

{ngiab_data_preprocess-3.2.3 → ngiab_data_preprocess-3.3.0}/modules/data_sources/cfe-nowpm-realization-template.json

@@ -80,7 +80,7 @@
       }
     ],
     "forcing": {
-      "path": "./forcings/by_catchment/forcings.nc",
+      "path": "./forcings/forcings.nc",
       "provider": "NetCDF",
       "enable_cache": false
     }

{ngiab_data_preprocess-3.2.3 → ngiab_data_preprocess-3.3.0}/modules/data_sources/cfe-template.ini

@@ -1,5 +1,6 @@
 forcing_file=BMI
-surface_partitioning_scheme=Schaake
+surface_water_partitioning_scheme=Schaake
+surface_runoff_scheme=GIUH
 
 # ----------------
 # State Parameters
@@ -40,13 +41,13 @@ alpha_fc=0.33
 # decimal fraction of maximum soil water storage (smcmax * depth) for the initial timestep
 soil_storage=0.05[m/m]
 # number of Nash lf reservoirs (optional, defaults to 2, ignored if storage values present)
-K_nash=0.03[]
+K_nash_subsurface=0.03[]
 # Nash Config param - primary reservoir
 K_lf=0.01[]
 # Nash Config param - secondary reservoir
-nash_storage=0.0,0.0
+nash_storage_subsurface=0.0,0.0
 # Giuh ordinates in dt time steps
-giuh_ordinates=1.00,0.00
+giuh_ordinates=0.55,0.25,0.2
 
 # ---------------------
 # Time Info
@@ -58,4 +59,4 @@ verbosity=0
 DEBUG=0
 # Parameter in the surface runoff parameterization
 # (https://mikejohnson51.github.io/hyAggregate/#Routing_Attributes)
-refkdt={refkdt}
+refkdt={refkdt}

{ngiab_data_preprocess-3.2.3 → ngiab_data_preprocess-3.3.0}/modules/data_sources/em-realization-template.json

@@ -53,7 +53,7 @@
       }
     ],
     "forcing": {
-      "path": "./forcings/by_catchment/forcings.nc",
+      "path": "./forcings/forcings.nc",
       "provider": "NetCDF",
       "enable_cache": false
     }

{ngiab_data_preprocess-3.2.3 → ngiab_data_preprocess-3.3.0}/modules/data_sources/ngen-routing-template.yaml

@@ -98,12 +98,12 @@ compute_parameters:
 output_parameters:
     #----------
     #test_output: outputs/lcr_flowveldepth.pkl
-    lite_restart:
-        #----------
-        lite_restart_output_directory: restart/
-    lakeout_output: lakeout/
+    # lite_restart:
+    #     #----------
+    #     lite_restart_output_directory: restart/
+    # lakeout_output: lakeout/
     stream_output:
         stream_output_directory: outputs/troute/
-        stream_output_time: {stream_output_time} #number of internal_frequency timesteps per output file
+        stream_output_time: -1 # -1 adds all outputs to a single file
         stream_output_type: ".nc" #please select only between netcdf '.nc' or '.csv' or '.pkl'
         stream_output_internal_frequency: 60 #[min] it should be order of 5 minutes. For instance if you want to output every hour put 60

{ngiab_data_preprocess-3.2.3 → ngiab_data_preprocess-3.3.0}/modules/data_sources/noah-owp-modular-init.namelist.input

@@ -28,10 +28,10 @@
 /
 
 &model_options
-  precip_phase_option               = 2
-  snow_albedo_option                = 2 ! 1 = BATS, 2 = CLASS
-  dynamic_veg_option                = 1
-  runoff_option                     = 8
+  precip_phase_option               = 1
+  snow_albedo_option                = 1 ! 1 = BATS, 2 = CLASS
+  dynamic_veg_option                = 4
+  runoff_option                     = 3
   drainage_option                   = 8
   frozen_soil_option                = 1
   dynamic_vic_option                = 1
@@ -43,8 +43,8 @@
   soil_temp_boundary_option         = 2
   supercooled_water_option          = 1
   stomatal_resistance_option        = 1
-  evap_srfc_resistance_option       = 1
-  subsurface_option                 = 1 
+  evap_srfc_resistance_option       = 4
+  subsurface_option                 = 2 
 /
 
 &structure

{ngiab_data_preprocess-3.2.3 → ngiab_data_preprocess-3.3.0}/modules/ngiab_data_cli/__main__.py

@@ -119,7 +119,7 @@ def validate_run_directory(args, paths: file_paths):
 
 def main() -> None:
     setup_logging()
-
+    validate_all()
     try:
         args = parse_arguments()
         if args.debug:
@@ -128,7 +128,7 @@ def main() -> None:
         paths = file_paths(output_folder)
         args = set_dependent_flags(args, paths)  # --validate
         if feature_to_subset:
-            logging.info(f"Subsetting {feature_to_subset} to {paths.output_dir}")
+            logging.info(f"Processing {feature_to_subset} in {paths.output_dir}")
             if not args.vpu:
                 upstream_count = len(get_upstream_cats(feature_to_subset))
                 logging.info(f"Upstream catchments: {upstream_count}")
@@ -243,5 +243,4 @@ def main() -> None:
 
 
 if __name__ == "__main__":
-    validate_all()
     main()

ngiab_data_preprocess-3.3.0/modules/ngiab_data_cli/forcing_cli.py

@@ -0,0 +1,97 @@
+from data_sources.source_validation import validate_all
+from ngiab_data_cli.custom_logging import setup_logging
+from data_processing.forcings import compute_zonal_stats
+from data_processing.zarr_utils import get_forcing_data
+from data_processing.file_paths import file_paths
+import argparse
+import logging
+import time
+import xarray as xr
+import geopandas as gpd
+from datetime import datetime
+from pathlib import Path
+import shutil
+
+# Constants
+DATE_FORMAT = "%Y-%m-%d"  # used for datetime parsing
+DATE_FORMAT_HINT = "YYYY-MM-DD"  # printed in help message
+
+
+def parse_arguments() -> argparse.Namespace:
+    """Parse command line arguments."""
+    parser = argparse.ArgumentParser(
+        description="Subsetting hydrofabrics, forcing generation, and realization creation"
+    )
+    parser.add_argument(
+        "-i",
+        "--input_file",
+        type=Path,
+        help="path to the input hydrofabric geopackage",
+        required=True,
+    )
+    parser.add_argument(
+        "-o",
+        "--output_file",
+        type=Path,
+        help="path to the forcing output file, e.g. /path/to/forcings.nc",
+        required=True,
+    )
+    parser.add_argument(
+        "--start_date",
+        "--start",
+        type=lambda s: datetime.strptime(s, DATE_FORMAT),
+        help=f"Start date for forcings/realization (format {DATE_FORMAT_HINT})",
+        required=True,
+    )
+    parser.add_argument(
+        "--end_date",
+        "--end",
+        type=lambda s: datetime.strptime(s, DATE_FORMAT),
+        help=f"End date for forcings/realization (format {DATE_FORMAT_HINT})",
+        required=True,
+    )
+    parser.add_argument(
+        "-D",
+        "--debug",
+        action="store_true",
+        help="enable debug logging",
+    )
+
+    return parser.parse_args()
+
+def main() -> None:
+    time.sleep(0.01)
+    setup_logging()
+    validate_all()
+    args = parse_arguments()
+    projection = xr.open_dataset(file_paths.template_nc, engine="h5netcdf").crs.esri_pe_string
+    logging.debug("Got projection from grid file")
+
+    gdf = gpd.read_file(args.input_file, layer="divides").to_crs(projection)
+    logging.debug(f"gdf  bounds: {gdf.total_bounds}")
+
+    start_time = args.start_date.strftime("%Y-%m-%d %H:%M")
+    end_time = args.end_date.strftime("%Y-%m-%d %H:%M")
+
+    cached_nc_path = args.output_file.parent / (args.input_file.stem + "-raw-gridded-data.nc")
+    print(cached_nc_path)
+    merged_data = get_forcing_data(cached_nc_path, start_time, end_time, gdf)
+    forcing_working_dir = args.output_file.parent / (args.input_file.stem + "-working-dir")
+    if not forcing_working_dir.exists():
+        forcing_working_dir.mkdir(parents=True, exist_ok=True)
+
+    temp_dir = forcing_working_dir / "temp"
+    if not temp_dir.exists():
+        temp_dir.mkdir(parents=True, exist_ok=True)
+
+
+    compute_zonal_stats(gdf, merged_data, forcing_working_dir)
+
+    shutil.copy(forcing_working_dir / "forcings.nc", args.output_file)
+    logging.info(f"Created forcings file: {args.output_file}")
+    # remove the working directory
+    shutil.rmtree(forcing_working_dir)
+
+
+if __name__ == "__main__":
+    main()

{ngiab_data_preprocess-3.2.3 → ngiab_data_preprocess-3.3.0}/modules/ngiab_data_preprocess.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: ngiab_data_preprocess
-Version: 3.2.3
+Version: 3.3.0
 Summary: Graphical Tools for creating Next Gen Water model input data.
 Author-email: Josh Cunningham <jcunningham8@ua.edu>
 Project-URL: Homepage, https://github.com/CIROH-UA/NGIAB_data_preprocess

{ngiab_data_preprocess-3.2.3 → ngiab_data_preprocess-3.3.0}/modules/ngiab_data_preprocess.egg-info/SOURCES.txt

@@ -40,6 +40,7 @@ modules/map_app/templates/index.html
 modules/ngiab_data_cli/__main__.py
 modules/ngiab_data_cli/arguments.py
 modules/ngiab_data_cli/custom_logging.py
+modules/ngiab_data_cli/forcing_cli.py
 modules/ngiab_data_preprocess.egg-info/PKG-INFO
 modules/ngiab_data_preprocess.egg-info/SOURCES.txt
 modules/ngiab_data_preprocess.egg-info/dependency_links.txt

{ngiab_data_preprocess-3.2.3 → ngiab_data_preprocess-3.3.0}/modules/ngiab_data_preprocess.egg-info/entry_points.txt

@@ -1,3 +1,4 @@
 [console_scripts]
 cli = ngiab_data_cli.__main__:main
+forcings = ngiab_data_cli.forcing_cli:main
 map_app = map_app.__main__:main

{ngiab_data_preprocess-3.2.3 → ngiab_data_preprocess-3.3.0}/pyproject.toml

@@ -12,7 +12,7 @@ exclude = ["tests*"]
 
 [project]
 name = "ngiab_data_preprocess"
-version = "v3.2.3"
+version = "v3.3.0"
 authors = [{ name = "Josh Cunningham", email = "jcunningham8@ua.edu" }]
 description = "Graphical Tools for creating Next Gen Water model input data."
 readme = "README.md"
@@ -43,7 +43,7 @@ dependencies = [
     "tqdm==4.66.4",
     "rich==13.7.1",
     "colorama==0.4.6",
-    "bokeh==3.5.1"
+    "bokeh==3.5.1",
 ]
 
 [project.optional-dependencies]
@@ -57,6 +57,7 @@ Issues = "https://github.com/CIROH-UA/NGIAB_data_preprocess/issues"
 [project.scripts]
 cli = "ngiab_data_cli.__main__:main"
 map_app = "map_app.__main__:main"
+forcings = "ngiab_data_cli.forcing_cli:main"
 
 [build-system]
 # scm adds files tracked by git to the package