physoce-datasets 0.1.0__tar.gz

physoce_datasets-0.1.0/.gitignore

@@ -0,0 +1,192 @@
+# ignore data files
+*.nc
+data/*
+
+# Python-generated files
+__pycache__/
+*.py[oc]
+build/
+dist/
+wheels/
+*.egg-info
+
+# Virtual environments
+.venv
+
+# Created with easyignore
+# Created by https://www.toptal.com/developers/gitignore/api/python
+# Edit at https://www.toptal.com/developers/gitignore?templates=python
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+### Python Patch ###
+# Poetry local configuration file - https://python-poetry.org/docs/configuration/#local-configuration
+poetry.toml
+
+# ruff
+.ruff_cache/
+
+# LSP config files
+pyrightconfig.json
+
+# End of https://www.toptal.com/developers/gitignore/api/python

physoce_datasets-0.1.0/PKG-INFO

@@ -0,0 +1,106 @@
+Metadata-Version: 2.4
+Name: physoce-datasets
+Version: 0.1.0
+Summary: A Python package and CLI for downloading various physical oceanographic datasets.
+Requires-Python: >=3.12
+Requires-Dist: cdsapi>=0.7.7
+Requires-Dist: cfgrib>=0.9.15.1
+Requires-Dist: click>=8.2.1
+Requires-Dist: copernicusmarine>=2.3.0
+Requires-Dist: ecmwf-datastores-client>=0.5.1
+Requires-Dist: gcsfs>=2026.3.0
+Requires-Dist: h5py>=3.16.0
+Requires-Dist: ipykernel>=7.2.0
+Requires-Dist: metpy>=1.7.1
+Requires-Dist: numpy>=2.4.4
+Requires-Dist: pycoare>=0.4.0
+Requires-Dist: python-dotenv>=1.2.2
+Requires-Dist: xarray[accel,io,parallel]>=2026.2.0
+Description-Content-Type: text/markdown
+
+# physoce-datasets
+
+A Python package and CLI for downloading various physical oceanographic datasets.
+
+## Install
+
+Clone the package and navigate to the directory:
+
+```bash
+git clone https://github.com/andrew-s28/physoce-datasets.git
+cd physoce-datasets
+```
+
+### uv
+
+`uv` is the preferred way to manage this package. Please refer to the [uv installation instructions](https://docs.astral.sh/uv/getting-started/installation/). Once uv is installed, you can initialize a virtual environment with `uv sync` or you can run any commands directly with `uv run` and `uv` will handle the `venv` creation and activation auto-magically.
+
+### pip
+
+Of course, you can also use the classic `pip`, but you have to handle creating and activating the `venv` yourself:
+
+```bash
+python -m venv .venv
+source .venv/bin/activate
+pip install -e .
+```
+
+## Credentials
+
+Upon usage, this package may prompt for credentials to various data stores. Please refer to their documentation for how to access credentials and how credentials are stored:
+
+- [Copernicus Marine Services](https://toolbox-docs.marine.copernicus.eu/en/stable/usage/login-usage.html)
+- [Copernicus Climate Data Store](https://cds.climate.copernicus.eu/how-to-api)
+
+## CLI usage
+
+Run the CLI with uv:
+
+```bash
+uv run datasets.py --help
+```
+
+Note that if you prefer the `pip` environment management, activate your environment according to the above and replace all `uv run` commands with `python`, e.g.:
+
+```bash
+python datasets.py --help
+```
+
+Available commands:
+
+- `eke`: Download altimetry-derived geostrophic velocities and compute eddy kinetic energy from Copernicus Marine Services.
+- `era5`: ERA5 workflow group with `submit` and `download` subcommands.
+
+Show command help:
+
+```bash
+uv run datasets.py eke --help
+```
+
+### Options
+
+All commands share the same base options:
+
+- `--save-dir`: Directory where the dataset file is written. If not set, defaults to the package `data/` directory.
+- `--start-date`: Start date in `YYYY-MM-DD` format. If not set, uses the earliest available date.
+- `--end-date`: End date in `YYYY-MM-DD` format. If not set, uses the latest available date
+
+Run `eke` download with defaults:
+
+```bash
+uv run datasets.py eke
+```
+
+Submit ERA5 jobs with explicit options:
+
+```bash
+uv run datasets.py era5 submit --save-dir data --start-date 2020-01-01 --end-date 2020-01-31 --max-active-requests 10
+```
+
+Download and process ERA5 files once all remote jobs are successful:
+
+```bash
+uv run datasets.py era5 download --save-dir data
+```
+
+The ERA5 workflow writes its progress to `submitted_requests.csv` inside the save directory. If the script exits or is interrupted, rerun the same command to resume from saved state.

physoce_datasets-0.1.0/README.md

@@ -0,0 +1,86 @@
+# physoce-datasets
+
+A Python package and CLI for downloading various physical oceanographic datasets.
+
+## Install
+
+Clone the package and navigate to the directory:
+
+```bash
+git clone https://github.com/andrew-s28/physoce-datasets.git
+cd physoce-datasets
+```
+
+### uv
+
+`uv` is the preferred way to manage this package. Please refer to the [uv installation instructions](https://docs.astral.sh/uv/getting-started/installation/). Once uv is installed, you can initialize a virtual environment with `uv sync` or you can run any commands directly with `uv run` and `uv` will handle the `venv` creation and activation auto-magically.
+
+### pip
+
+Of course, you can also use the classic `pip`, but you have to handle creating and activating the `venv` yourself:
+
+```bash
+python -m venv .venv
+source .venv/bin/activate
+pip install -e .
+```
+
+## Credentials
+
+Upon usage, this package may prompt for credentials to various data stores. Please refer to their documentation for how to access credentials and how credentials are stored:
+
+- [Copernicus Marine Services](https://toolbox-docs.marine.copernicus.eu/en/stable/usage/login-usage.html)
+- [Copernicus Climate Data Store](https://cds.climate.copernicus.eu/how-to-api)
+
+## CLI usage
+
+Run the CLI with uv:
+
+```bash
+uv run datasets.py --help
+```
+
+Note that if you prefer the `pip` environment management, activate your environment according to the above and replace all `uv run` commands with `python`, e.g.:
+
+```bash
+python datasets.py --help
+```
+
+Available commands:
+
+- `eke`: Download altimetry-derived geostrophic velocities and compute eddy kinetic energy from Copernicus Marine Services.
+- `era5`: ERA5 workflow group with `submit` and `download` subcommands.
+
+Show command help:
+
+```bash
+uv run datasets.py eke --help
+```
+
+### Options
+
+All commands share the same base options:
+
+- `--save-dir`: Directory where the dataset file is written. If not set, defaults to the package `data/` directory.
+- `--start-date`: Start date in `YYYY-MM-DD` format. If not set, uses the earliest available date.
+- `--end-date`: End date in `YYYY-MM-DD` format. If not set, uses the latest available date
+
+Run `eke` download with defaults:
+
+```bash
+uv run datasets.py eke
+```
+
+Submit ERA5 jobs with explicit options:
+
+```bash
+uv run datasets.py era5 submit --save-dir data --start-date 2020-01-01 --end-date 2020-01-31 --max-active-requests 10
+```
+
+Download and process ERA5 files once all remote jobs are successful:
+
+```bash
+uv run datasets.py era5 download --save-dir data
+```
+
+The ERA5 workflow writes its progress to `submitted_requests.csv` inside the save directory. If the script exits or is interrupted, rerun the same command to resume from saved state.

physoce_datasets-0.1.0/physoce_datasets/__init__.py

@@ -0,0 +1,5 @@
+"""The physoce_datasets package provides tools for downloading and processing physical oceanography datasets."""
+
+from .download import download_eke, download_era5, submit_era5
+
+__all__ = ["download_eke", "download_era5", "submit_era5"]

physoce_datasets-0.1.0/physoce_datasets/cli.py

@@ -0,0 +1,170 @@
+"""CLI commands for physoce_datasets."""
+
+from __future__ import annotations
+
+from pathlib import Path
+
+import click
+
+from .download import download_eke, download_era5, submit_era5
+
+save_dir_option = click.option(
+    "--save-dir",
+    type=click.Path(file_okay=False, dir_okay=True, path_type=Path),
+    default=None,
+    help=(
+        "Directory to save the downloaded dataset. If not specified, defaults "
+        "to a 'data' directory in the current working directory."
+    ),
+)
+save_file_option = click.option(
+    "--save-file",
+    type=str,
+    default=None,
+    help=(
+        "Filename to save the dataset. If not specified, defaults to a filename "
+        "based on the dataset name and date range (e.g., 'eke_2000-01-01_to_2020-12-31.nc')."
+    ),
+)
+start_datetime_option = click.option(
+    "--start-date",
+    type=str,
+    default=None,
+    help=(
+        "Start datetime for the dataset. Format should be YYYY-MM-DD. If not "
+        "specified, defaults to the earliest available datetime for the dataset."
+    ),
+)
+end_datetime_option = click.option(
+    "--end-date",
+    type=str,
+    default=None,
+    help=(
+        "End datetime for the dataset. Format should be YYYY-MM-DD. If not "
+        "specified, defaults to the latest available datetime for the dataset."
+    ),
+)
+update_option = click.option(
+    "--update-file",
+    type=str,
+    default=None,
+    help=(
+        "Whether to update an existing dataset with new data. If specified, should be "
+        "the path to an existing netCDF file found in the directory specified by --save-dir (default './data')."
+    ),
+)
+area_option = click.option(
+    "--area",
+    type=str,
+    default=None,
+    help=(
+        "Bounding box for the dataset in the format 'lon_min,lon_max,lat_min,lat_max'. "
+        "If not specified, defaults to global coverage."
+    ),
+)
+
+
+@click.group(invoke_without_command=True)
+@click.pass_context
+def cli(ctx: click.Context) -> None:
+    """Command-line interface for downloading datasets."""
+    if ctx.invoked_subcommand is None:
+        click.echo("No subcommand specified. Use --help for more information.")
+
+
+@cli.command(
+    "eke",
+    help="Download geostrophic velocities and compute eddy kinetic energy from Copernicus Marine Services.",
+)
+@save_dir_option
+@start_datetime_option
+@end_datetime_option
+@save_file_option
+@area_option
+def _eke(
+    save_dir: Path | None,
+    start_date: str | None,
+    end_date: str | None,
+    save_file: str | None,
+    area: str | None,
+) -> None:
+    """Download geostrophic velocities and compute eddy kinetic energy from Copernicus Marine Services.
+
+    Args:
+        save_dir (Path | None): Directory to save the downloaded dataset. If not specified,
+            defaults to a "data" directory in the current working directory.
+        start_date (str | None): Start date for the dataset. Format should be YYYY-MM-DD.
+            If not specified, defaults to the earliest available date for the dataset.
+        end_date (str | None): End date for the dataset. Format should be YYYY-MM-DD.
+            If not specified, defaults to the latest available date for the dataset.
+        save_file (str | None): Filename to save the dataset. If not specified, defaults to a filename
+            based on the dataset name and date range (e.g., "eke_2000-01-01_to_2020-12-31.nc").
+        area (str | None): Bounding box for the dataset in the format 'lon_min,lat_min,lon_max,lat_max'.
+            If not specified, defaults to global coverage.
+
+    """
+    download_eke(
+        save_dir=save_dir,
+        start_datetime=start_date,
+        end_datetime=end_date,
+        save_file=save_file,
+        area_str=area,
+    )
+
+
+@cli.group("era5", help="ERA5 workflow commands.")
+def _era5() -> None:
+    """ERA5 workflow commands group."""
+
+
+@_era5.command("submit", help="Submit ERA5 jobs until all requested months are queued.")
+@save_dir_option
+@start_datetime_option
+@end_datetime_option
+@area_option
+def _era5_submit(
+    save_dir: Path | None,
+    start_date: str | None,
+    end_date: str | None,
+    area: str | None,
+) -> None:
+    """Submit ERA5 jobs only.
+
+    Args:
+        save_dir (Path | None): Directory to save request state. If not
+            specified, defaults to a "data" directory in the current working directory.
+        start_date (str | None): Start date for the dataset. Format should be YYYY-MM-DD.
+        end_date (str | None): End date for the dataset. Format should be YYYY-MM-DD.
+        area (str | None): Bounding box for the dataset in the format 'lon_min,lat_min,lon_max,lat_max'.
+            If not specified, defaults to global coverage.
+
+    """
+    submit_era5(
+        save_dir=save_dir,
+        start_date=start_date,
+        end_date=end_date,
+        area_str=area,
+    )
+
+
+@_era5.command("download", help="Download and process ERA5 files after all remote jobs are successful.")
+@save_dir_option
+@save_file_option
+def _era5_download(save_dir: Path | None, save_file: str | None) -> None:
+    """Download ERA5 data for successful remote jobs and process locally.
+
+    Args:
+        save_dir (Path | None): Directory containing saved request state and output files.
+                If not specified, defaults to a "data" directory in the current working directory.
+        save_file (str | None): Filename to save the dataset. If not specified, defaults to a filename
+            based on the dataset name and date range.
+
+    """
+    download_era5(
+        save_dir=save_dir,
+        save_file=save_file,
+    )
+
+
+if __name__ == "__main__":
+    cli()

physoce_datasets-0.1.0/physoce_datasets/download/__init__.py

@@ -0,0 +1,10 @@
+"""Module for downloading physical oceanographic datasets.
+
+This module also processes downloaded data into xarray Datasets with
+appropriate metadata.
+"""
+
+from .eke import download_eke
+from .era5 import download_era5, submit_era5
+
+__all__ = ["download_eke", "download_era5", "submit_era5"]