ngiab-data-preprocess 4.1.0__py3-none-any.whl → 4.2.0__py3-none-any.whl

data_processing/datasets.py

@@ -85,3 +85,35 @@ def load_aorc_zarr(start_year: int = None, end_year: int = None) -> xr.Dataset:
 
     validate_dataset_format(dataset)
     return dataset
+
+
+def load_swe_zarr() -> xr.Dataset:
+    """Load the swe zarr dataset from S3."""
+    s3_urls = [
+        f"s3://noaa-nwm-retrospective-3-0-pds/CONUS/zarr/ldasout.zarr"
+    ]
+    # default cache is readahead which is detrimental to performance in this case
+    fs = S3ParallelFileSystem(anon=True, default_cache_type="none")  # default_block_size
+    s3_stores = [s3fs.S3Map(url, s3=fs) for url in s3_urls]
+    # the cache option here just holds accessed data in memory to prevent s3 being queried multiple times
+    # most of the data is read once and written to disk but some of the coordinate data is read multiple times
+    dataset = xr.open_mfdataset(s3_stores, parallel=True, engine="zarr", cache=True)
+    
+    # set the crs attribute to conform with the format
+    esri_pe_string = dataset.crs.esri_pe_string
+    dataset = dataset.drop_vars(["crs"])
+    dataset.attrs["crs"] = esri_pe_string
+    # drop everything except SNEQV
+    vars_to_drop = list(dataset.data_vars)
+    vars_to_drop.remove('SNEQV')
+    dataset = dataset.drop_vars(vars_to_drop)
+    dataset.attrs["name"] = "v3_swe_zarr"
+
+    # rename the data vars to work with ngen
+    variables = {
+        "SNEQV": "swe"
+    }
+    dataset = dataset.rename_vars(variables)
+
+    validate_dataset_format(dataset)
+    return dataset

data_processing/gpkg_utils.py

@@ -69,7 +69,7 @@ def verify_indices(gpkg: str = file_paths.conus_hydrofabric) -> None:
     con.close()
 
 
-def create_empty_gpkg(gpkg: str) -> None:
+def create_empty_gpkg(gpkg: Path) -> None:
     """
     Create an empty geopackage with the necessary tables and indices.
     """
@@ -80,7 +80,7 @@ def create_empty_gpkg(gpkg: str) -> None:
         conn.executescript(sql_script)
 
 
-def add_triggers_to_gpkg(gpkg: str) -> None:
+def add_triggers_to_gpkg(gpkg: Path) -> None:
     """
     Adds geopackage triggers required to maintain spatial index integrity
     """
@@ -256,7 +256,7 @@ def insert_data(con: sqlite3.Connection, table: str, contents: List[Tuple]) -> N
     con.commit()
 
 
-def update_geopackage_metadata(gpkg: str) -> None:
+def update_geopackage_metadata(gpkg: Path) -> None:
     """
     Update the contents of the gpkg_contents table in the specified geopackage.
     """
@@ -318,10 +318,10 @@ def subset_table_by_vpu(table: str, vpu: str, hydrofabric: Path, subset_gpkg_nam
     contents = source_db.execute(sql_query).fetchall()
 
     if table == "network":
-        # Look for the network entry that has a toid not in the flowpath or nexus tables        
+        # Look for the network entry that has a toid not in the flowpath or nexus tables
         network_toids = [x[2] for x in contents]
         print(f"Network toids: {len(network_toids)}")
-        sql = "SELECT id FROM flowpaths"  
+        sql = "SELECT id FROM flowpaths"
         flowpath_ids = [x[0] for x in dest_db.execute(sql).fetchall()]
         print(f"Flowpath ids: {len(flowpath_ids)}")
         sql = "SELECT id FROM nexus"
@@ -342,8 +342,8 @@ def subset_table_by_vpu(table: str, vpu: str, hydrofabric: Path, subset_gpkg_nam
 
     dest_db.commit()
     source_db.close()
-    dest_db.close()   
-    
+    dest_db.close()
+
 
 def subset_table(table: str, ids: List[str], hydrofabric: Path, subset_gpkg_name: Path) -> None:
     """
@@ -359,7 +359,7 @@ def subset_table(table: str, ids: List[str], hydrofabric: Path, subset_gpkg_name
     source_db = sqlite3.connect(f"file:{hydrofabric}?mode=ro", uri=True)
     dest_db = sqlite3.connect(subset_gpkg_name)
 
-    table_keys = {"divides": "toid", "divide-attributes": "divide_id", "lakes": "poi_id"}
+    table_keys = {"divide-attributes": "divide_id", "lakes": "poi_id"}
 
     if table == "lakes":
         # lakes subset we get from the pois table which was already subset by water body id
@@ -377,7 +377,7 @@ def subset_table(table: str, ids: List[str], hydrofabric: Path, subset_gpkg_name
     if table in table_keys:
         key_name = table_keys[table]
     sql_query = f"SELECT * FROM '{table}' WHERE {key_name} IN ({','.join(ids)})"
-    contents = source_db.execute(sql_query).fetchall()    
+    contents = source_db.execute(sql_query).fetchall()
 
     insert_data(dest_db, table, contents)
 
@@ -429,16 +429,16 @@ def get_table_crs(gpkg: str, table: str) -> str:
 
 def get_cat_from_gage_id(gage_id: str, gpkg: Path = file_paths.conus_hydrofabric) -> str:
     """
-    Get the nexus id of associated with a gage id.
+    Get the catchment id associated with a gage id.
 
     Args:
         gage_id (str): The gage ID.
 
     Returns:
-        str: The nexus id of the watershed containing the gage ID.
+        str: The catchment id of the watershed containing the gage ID.
 
     Raises:
-        IndexError: If nexus is found for the given gage ID.
+        IndexError: If catchment is found for the given gage ID.
 
     """
     gage_id = "".join([x for x in gage_id if x.isdigit()])

data_processing/graph_utils.py

@@ -165,6 +165,10 @@ def get_upstream_cats(names: Union[str, List[str]]) -> Set[str]:
         if name in parent_ids:
             continue
         try:
+            if "cat" in name:
+                node_index = graph.vs.find(cat=name).index
+            else:
+                node_index = graph.vs.find(name=name).index
             node_index = graph.vs.find(cat=name).index
             upstream_nodes = graph.subcomponent(node_index, mode="IN")
             for node in upstream_nodes:
@@ -205,7 +209,10 @@ def get_upstream_ids(names: Union[str, List[str]], include_outlet: bool = True)
         if name in parent_ids:
             continue
         try:
-            node_index = graph.vs.find(name=name).index
+            if "cat" in name:
+                node_index = graph.vs.find(cat=name).index
+            else:
+                node_index = graph.vs.find(name=name).index
             upstream_nodes = graph.subcomponent(node_index, mode="IN")
             for node in upstream_nodes:
                 parent_ids.add(graph.vs[node]["name"])

data_processing/subset.py

@@ -31,7 +31,7 @@ subset_tables = [
 
 def create_subset_gpkg(
     ids: Union[List[str], str], hydrofabric: Path, output_gpkg_path: Path, is_vpu: bool = False
-) -> Path:
+):
     # ids is a list of nexus and wb ids, or a single vpu id
     if not isinstance(ids, list):
         ids = [ids]
@@ -65,10 +65,11 @@ def subset_vpu(vpu_id: str, output_gpkg_path: Path, hydrofabric: Path = file_pat
 def subset(
     cat_ids: List[str],
     hydrofabric: Path = file_paths.conus_hydrofabric,
-    output_gpkg_path: Path = None,
-) -> str:
-
-    upstream_ids = list(get_upstream_ids(cat_ids))
+    output_gpkg_path: Path = Path(),
+    include_outlet: bool = True,
+):
+    print(cat_ids)
+    upstream_ids = list(get_upstream_ids(cat_ids, include_outlet))
 
     if not output_gpkg_path:
         # if the name isn't provided, use the first upstream id
@@ -80,15 +81,3 @@ def subset(
     create_subset_gpkg(upstream_ids, hydrofabric, output_gpkg_path)
     logger.info(f"Subset complete for {len(upstream_ids)} features (catchments + nexuses)")
     logger.debug(f"Subset complete for {upstream_ids} catchments")
-
-
-def move_files_to_config_dir(subset_output_dir: str) -> None:
-    config_dir = subset_output_dir / "config"
-    config_dir.mkdir(parents=True, exist_ok=True)
-
-    files = [x for x in subset_output_dir.iterdir()]
-    for file in files:
-        if file.suffix in [".csv", ".json", ".geojson"]:
-            if "partitions" in file.name:
-                continue
-            os.system(f"mv {file} {config_dir}")

ngiab_data_cli/__main__.py

@@ -147,7 +147,10 @@ def main() -> None:
                 logging.info("Subsetting complete.")
             else:
                 logging.info(f"Subsetting hydrofabric")
-                subset(feature_to_subset, output_gpkg_path=paths.geopackage_path)
+                include_outlet = True
+                if args.gage:
+                    include_outlet = False
+                subset(feature_to_subset, output_gpkg_path=paths.geopackage_path, include_outlet=include_outlet)
                 logging.info("Subsetting complete.")
 
         if args.forcings:
@@ -237,7 +240,7 @@ def main() -> None:
 
         if args.vis:
             try:
-                command = f'docker run --rm -it -p 3000:3000 -v "{str(paths.subset_dir)}:/ngen/ngen/data/" joshcu/ngiab_grafana:v0.2.0'
+                command = f'docker run --rm -it -p 3000:3000 -v "{str(paths.subset_dir)}:/ngen/ngen/data/" joshcu/ngiab_grafana:v0.2.1'
                 subprocess.run(command, shell=True)
             except:
                 logging.error("Failed to launch docker container.")

{ngiab_data_preprocess-4.1.0.dist-info → ngiab_data_preprocess-4.2.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ngiab_data_preprocess
-Version: 4.1.0
+Version: 4.2.0
 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
@@ -8,11 +8,11 @@ Project-URL: Issues, https://github.com/CIROH-UA/NGIAB_data_preprocess/issues
 Classifier: Programming Language :: Python :: 3
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Operating System :: OS Independent
-Requires-Python: <3.13,>=3.10
+Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: pyogrio==0.7.2
-Requires-Dist: pyproj==3.6.1
+Requires-Dist: pyogrio>=0.7.2
+Requires-Dist: pyproj>=3.6.1
 Requires-Dist: Flask==3.0.2
 Requires-Dist: geopandas>=1.0.0
 Requires-Dist: requests==2.32.2
@@ -20,19 +20,20 @@ Requires-Dist: igraph==0.11.4
 Requires-Dist: s3fs==2024.3.1
 Requires-Dist: xarray==2024.2.0
 Requires-Dist: zarr==2.17.1
-Requires-Dist: netCDF4==1.6.5
+Requires-Dist: netCDF4>=1.6.5
 Requires-Dist: dask==2024.4.1
 Requires-Dist: dask[distributed]==2024.4.1
 Requires-Dist: black==24.3.0
 Requires-Dist: isort==5.13.2
 Requires-Dist: h5netcdf==1.3.0
 Requires-Dist: exactextract==0.2.0
-Requires-Dist: numpy==1.26.4
+Requires-Dist: numpy>=1.26.4
 Requires-Dist: tqdm==4.66.4
 Requires-Dist: rich==13.7.1
 Requires-Dist: colorama==0.4.6
 Requires-Dist: bokeh==3.5.1
 Requires-Dist: boto3
+Requires-Dist: numcodecs<0.16.0
 Provides-Extra: eval
 Requires-Dist: ngiab_eval; extra == "eval"
 Provides-Extra: plot
@@ -85,6 +86,41 @@ For automatic interactive visualisation, please run [NGIAB](https://github.com/C
 * This tool is officially supported on macOS or Ubuntu (tested on 22.04 & 24.04). To use it on Windows, please install [WSL](https://learn.microsoft.com/en-us/windows/wsl/install).
 
 ## Installation and Running
+It is highly recommended to use [Astral UV](https://docs.astral.sh/uv/) to install and run this tool. It works similarly to pip and conda, and I would also recommend you use it for other python projects as it is so useful.
+
+```bash
+# Install UV
+curl -LsSf https://astral.sh/uv/install.sh | sh
+# It can be installed via pip if that fails
+# pip install uv
+
+# Create a virtual environment in the current directory
+uv venv
+
+# Install the tool in the virtual environment 
+uv pip install ngiab_data_preprocess
+
+# To run the cli
+uv run cli --help
+
+# To run the map 
+uv run map_app
+```
+
+UV automatically detects any virtual environments in the current directory and will use them when you use `uv run`.
+
+### Running without install
+This package supports pipx and uvx which means you can run the tool without installing it. No virtual environment needed, just UV.
+```bash
+# run this from anywhere 
+uvx --from ngiab_data_preprocess cli --help
+# for the map
+uvx --from ngiab_data_preprocess map_app
+```
+
+## For legacy pip installation
+<details>
+  <summary>Click here to expand</summary>
 
 ```bash
 # If you're installing this on jupyterhub / 2i2c you HAVE TO DEACTIVATE THE CONDA ENV
@@ -102,8 +138,7 @@ pip install 'ngiab_data_preprocess'
 python -m map_app
 # CLI instructions at the bottom of the README
 ```
-
-The first time you run this command, it will download the hydrofabric from Lynker Spatial. If you already have it, place `conus_nextgen.gpkg` into `~/.ngiab/hydrofabric/v2.2/`.
+</details>
 
 ## Development Installation
 
@@ -117,24 +152,23 @@ To install and run the tool, follow these steps:
    git clone https://github.com/CIROH-UA/NGIAB_data_preprocess
    cd NGIAB_data_preprocess
    ```
-2. Create a virtual environment and activate it:
+2. Create a virtual environment:
    ```bash
-   python3 -m venv env
-   source env/bin/activate
+   uv venv
    ```
 3. Install the tool:
    ```bash
-   pip install -e .
+   uv pip install -e .
    ```
 4. Run the map app:
    ```bash
-   python -m map_app
+   uv run map_app
    ```
 </details>
 
 ## Usage
 
-Running the command `python -m map_app` will open the app in a new browser tab.
+Running the command `uv run map_app` will open the app in a new browser tab.
 
 To use the tool:
 1. Select the catchment you're interested in on the map.

{ngiab_data_preprocess-4.1.0.dist-info → ngiab_data_preprocess-4.2.0.dist-info}/RECORD

@@ -1,12 +1,12 @@
 data_processing/create_realization.py,sha256=AxUDVSORjwd6IAImZpgDr8GRHKSUQF8emQi1ikfIno4,14899
 data_processing/dataset_utils.py,sha256=4qmRmK3qMWPkiWZHXhXv3c-ISbtOwr7QhciEl2ok6Ao,7314
-data_processing/datasets.py,sha256=kAtTKj2yQINUSzI0vX-kuXMPVeQBtZVfGkfpPh6Qi_0,3528
+data_processing/datasets.py,sha256=BB_X0IvGnUrjBmj-wryn6-Nv5cd0Lje3zly3p896eU4,4822
 data_processing/file_paths.py,sha256=Cp3BxbO6sD50464ciTshjb3Z0vTvL0ZeSbOJgNdOqQ0,4698
 data_processing/forcings.py,sha256=6Q9fSXa67OrXg_r9li0K9widsclN2DQUp1-oUH2tZwo,19208
-data_processing/gpkg_utils.py,sha256=SdniJrwhta7fPchVSCliuThPENgcs0m9Elx615yttAU,20248
-data_processing/graph_utils.py,sha256=TsCSZmQ8SPm5F2YzDKv32BxdzaHlPrC6UijZxUJbZvI,7966
+data_processing/gpkg_utils.py,sha256=j-j6TkCwlkOzM5ATMHi44raYS-xrJMzk5V0XQZ_0dzQ,20220
+data_processing/graph_utils.py,sha256=I9IFkU08SkXb8pfVASTvkm7T8BYt-92CaNj7TV6wJFE,8244
 data_processing/s3fs_utils.py,sha256=WoqqwxkHpv0Qq4I5f5-gUZBCFtVQ68ehXbdOjWRKTDQ,2752
-data_processing/subset.py,sha256=WklS0CT5O4oz29fhTT46NmSOe_EFMCC93gLeg6nQ88I,2914
+data_processing/subset.py,sha256=GbvfAaSJTfEvYOAZ6K0OgFA81xG_Y5UxiGDxukxO9gE,2558
 data_sources/cfe-nowpm-realization-template.json,sha256=8an6q1drWD8wU1ocvdPab-GvZDvlQ-0di_-NommH3QI,3528
 data_sources/cfe-template.ini,sha256=6e5-usqjWtm3MWVvtm8CTeZTJJMxO1ZswkOXq0L9mnc,2033
 data_sources/em-catchment-template.yml,sha256=M08ixazEUHYI2PNavtI0xPZeSzcQ9bg2g0XzNT-8_u4,292
@@ -32,13 +32,13 @@ map_app/static/resources/light-style.json,sha256=DaE52qKpAkjiWSKY_z7LxreqA2rW4Zy
 map_app/static/resources/loading.gif,sha256=ggdkZf1AD7rSwIpSJwfiIqANgmVV1WHlxGuKxQKv7uY,72191
 map_app/static/resources/screenshot.jpg,sha256=Ia358aX-OHM9BP4B8lX05cLnguF2fHUIimno9bnFLYw,253730
 map_app/templates/index.html,sha256=ITRzQEYn15sFN4qRACjaNj5muhalOeP9n_IwcdsIlUs,6631
-ngiab_data_cli/__main__.py,sha256=X_imHhWo2RBTJzJ9bUwEcAnAtZSyjKJXB60dBxea6ck,10361
+ngiab_data_cli/__main__.py,sha256=V-g0dwa000e5Qye7PBMTtHTK7Cl7as3JS0UoAR0QrZ4,10503
 ngiab_data_cli/arguments.py,sha256=7ptImy8tLM1XvjfDr13tZszkjGVtenXo0KqllJeE3Mw,4372
 ngiab_data_cli/custom_logging.py,sha256=iS2XozaxudcxQj17qAsrCgbVK9LJAYAPmarJuVWJo1k,1280
 ngiab_data_cli/forcing_cli.py,sha256=lkcqWDk5H8IPyGv0DwLIZMQldqTUXpfwSX0C_RIuIJ8,3890
-ngiab_data_preprocess-4.1.0.dist-info/licenses/LICENSE,sha256=6dMSprwwnsRzEm02mEDbKHD9dUbL8bPIt9Vhrhb0Ulk,1081
-ngiab_data_preprocess-4.1.0.dist-info/METADATA,sha256=PiNJhT7iKzPwVbU9i1kv8A8hR1aciMEEqnKfcM3W9OI,9433
-ngiab_data_preprocess-4.1.0.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
-ngiab_data_preprocess-4.1.0.dist-info/entry_points.txt,sha256=spwlhKEJ3ZnNETQsJGeTjD7Vwy8O_zGHb9GdX8ACCtw,128
-ngiab_data_preprocess-4.1.0.dist-info/top_level.txt,sha256=CjhYAUZrdveR2fOK6rxffU09VIN2IuPD7hk4V3l3pV0,52
-ngiab_data_preprocess-4.1.0.dist-info/RECORD,,
+ngiab_data_preprocess-4.2.0.dist-info/licenses/LICENSE,sha256=6dMSprwwnsRzEm02mEDbKHD9dUbL8bPIt9Vhrhb0Ulk,1081
+ngiab_data_preprocess-4.2.0.dist-info/METADATA,sha256=Y2NVmd92S38QMwKXEkLvLKyWQ2IGy25okHV8sDy6c2c,10310
+ngiab_data_preprocess-4.2.0.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
+ngiab_data_preprocess-4.2.0.dist-info/entry_points.txt,sha256=spwlhKEJ3ZnNETQsJGeTjD7Vwy8O_zGHb9GdX8ACCtw,128
+ngiab_data_preprocess-4.2.0.dist-info/top_level.txt,sha256=CjhYAUZrdveR2fOK6rxffU09VIN2IuPD7hk4V3l3pV0,52
+ngiab_data_preprocess-4.2.0.dist-info/RECORD,,