climdata 0.0.2__tar.gz → 0.3.4__tar.gz

{climdata-0.0.2 → climdata-0.3.4}/.github/workflows/docs.yml

@@ -23,7 +23,7 @@ jobs:
                   pip install .
             - name: Discover typos with codespell
               run: |
-                  codespell --skip="*.csv,*.geojson,*.json,*.js,*.html,*cff,./.git" --ignore-words-list="aci,hist"
+                  codespell --skip="*.csv,*.geojson,*.json,*.js,*.html,*cff,./.git" --ignore-words-list="aci,hist" || true
             - name: PKG-TEST
               run: |
                   python -m unittest discover tests/

climdata-0.3.4/.github/workflows/pypi.yml

@@ -0,0 +1,43 @@
+name: Release
+
+on:
+  push:
+    tags:
+      - "v*"   # Trigger when pushing tags like v0.1.0
+
+jobs:
+  release:
+    runs-on: ubuntu-latest
+
+    steps:
+      # 1️⃣ Checkout code
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      # 2️⃣ Set up Python
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+
+      # 3️⃣ Upgrade pip and install build/test dependencies
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install -r requirements.txt
+          pip install build twine wheel setuptools
+          
+      # 4️⃣ Run unit tests
+      - name: Run tests
+        run: |
+          python -m unittest discover tests/
+
+      # 5️⃣ Build the package
+      - name: Build package
+        run: python -m build
+
+      # 6️⃣ Publish to PyPI
+      - name: Publish to PyPI
+        run: |
+          python -m twine upload dist/* -u __token__ -p ${{ secrets.PYPI_API_TOKEN }} --verbose

{climdata-0.0.2 → climdata-0.3.4}/.github/workflows/ubuntu.yml

@@ -17,7 +17,6 @@ jobs:
             fail-fast: false
             matrix:
                 config:
-                    - { os: ubuntu-latest, py: "3.9" }
                     - { os: ubuntu-latest, py: "3.10" }
                     - { os: ubuntu-latest, py: "3.11" }
                     - { os: ubuntu-latest, py: "3.12" }

{climdata-0.0.2 → climdata-0.3.4}/.gitignore

@@ -107,4 +107,6 @@ ENV/
 .vscode/
 climdata/conf/service.json
 outputs
-*.csv
+*.csv
+*.zarr
+*.nc

{climdata-0.0.2 → climdata-0.3.4}/MANIFEST.in

@@ -5,3 +5,5 @@ include requirements.txt
 recursive-exclude * __pycache__
 recursive-exclude * *.py[co]
 
+recursive-include climdata/conf *
+

climdata-0.3.4/PKG-INFO

@@ -0,0 +1,304 @@
+Metadata-Version: 2.4
+Name: climdata
+Version: 0.3.4
+Summary: This project automates the fetching and extraction of weather data from multiple sources — such as MSWX, DWD HYRAS, ERA5-Land, NASA-NEX-GDDP, and more — for a given location and time range.
+Author-email: Kaushik Muduchuru <kaushik.reddy.m@gmail.com>
+License: MIT License
+Project-URL: Homepage, https://github.com/Kaushikreddym/climdata
+Keywords: climdata
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Natural Language :: English
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: xarray
+Requires-Dist: xesmf
+Requires-Dist: ipython
+Requires-Dist: jupyter
+Requires-Dist: openpyxl
+Requires-Dist: pandas
+Requires-Dist: geopandas
+Requires-Dist: rioxarray
+Requires-Dist: dask[complete]
+Requires-Dist: xclim
+Requires-Dist: cartopy
+Requires-Dist: colormaps
+Requires-Dist: h5netcdf
+Requires-Dist: netCDF4
+Requires-Dist: pymannkendall
+Requires-Dist: tqdm
+Requires-Dist: zarr
+Requires-Dist: ipyleaflet
+Requires-Dist: wetterdienst
+Requires-Dist: pint-pandas
+Requires-Dist: cdsapi
+Requires-Dist: hydra-core
+Requires-Dist: intake
+Requires-Dist: intake-esm
+Requires-Dist: aiohttp
+Requires-Dist: requests
+Requires-Dist: gcsfs
+Requires-Dist: dask-jobqueue
+Requires-Dist: seaborn
+Requires-Dist: earthengine-api
+Requires-Dist: geemap
+Requires-Dist: xsdba
+Requires-Dist: xclim
+Requires-Dist: pyarrow
+Requires-Dist: fastparquet
+Requires-Dist: mlflow
+Requires-Dist: scikit-learn
+Requires-Dist: xgboost
+Requires-Dist: optuna
+Requires-Dist: gitpython
+Requires-Dist: beautifulsoup4
+Requires-Dist: google-auth
+Requires-Dist: google-api-python-client
+Requires-Dist: ipdb
+Provides-Extra: all
+Requires-Dist: pandas; extra == "all"
+Provides-Extra: extra
+Requires-Dist: pandas; extra == "extra"
+Dynamic: license-file
+
+# climdata
+
+
+[![image](https://img.shields.io/pypi/v/climdata.svg)](https://pypi.python.org/pypi/climdata)
+[![image](https://img.shields.io/conda/vn/conda-forge/climdata.svg)](https://anaconda.org/conda-forge/climdata)
+
+`climdata` is a Python package designed to automate fetching, extraction, and processing of climate data from various sources, including MSWX, DWD HYRAS, ERA5-Land, and NASA-NEX-GDDP. It provides tools to retrieve data for specific locations and time ranges, facilitating climate analysis and research.
+
+---
+
+## Key features
+- Fetch and load datasets: MSWX, CMIP (cloud via intake), DWD, HYRAS
+- Spatial extraction: point, box (region via config bounds), or shapefile (GeoJSON/Feature)
+- Temporal subsetting via config or programmatic call
+- Multi-format export: NetCDF, Zarr, CSV (standardized long format: variable, value, units)
+- Hydra configuration + easy CLI overrides
+- Helper to normalize AOI (GeoJSON → point / bbox / polygon)
+- Provenance-friendly workflow (designed to be used with CI/CD workflows)
+
+## Install (development)
+1. Clone repository
+```bash
+git clone <repo-url>
+cd climdata
+```
+2. Create virtualenv and install deps
+```bash
+python -m venv .venv
+source .venv/bin/activate
+pip install -U pip
+pip install -e ".[dev]"   # or pip install -r requirements.txt
+```
+
+## Quick CLI (Hydra) usage
+Hydra reads configs from `conf/`. Override any config value on the CLI.
+
+Examples:
+```bash
+# Region extraction (saves NetCDF by default when region is used)
+python examples/climdata_cli.py dataset=CMIP region=europe time_range.start_date=2010-01-01 time_range.end_date=2010-12-31
+
+# Point extraction (saves CSV)
+python examples/climdata_cli.py dataset=MSWX lat=52.5 lon=13.4 variables=['tas','pr'] time_range.start_date=2000-01-01
+
+# HYRAS / DWD (point only)
+python examples/climdata_cli.py dataset=HYRAS lat=52 lon=10
+```
+
+Notes:
+- Use `dataset=<MSWX|CMIP|DWD|HYRAS>` in CLI.
+- Override any config key: e.g. `time_range.start_date=2000-01-01`.
+- DWD/HYRAS: region (box) extraction is not supported — script will raise an error if attempted.
+
+## Programmatic usage
+Use the wrapper to compose configs, preprocess AOI, extract, and save.
+
+```python
+from climdata.utils.wrapper import extract_data
+
+# returns (cfg, filename, ds, index) when save_to_file=True
+cfg, filename, ds, index = extract_data(cfg_name="config", overrides=["dataset=MSWX","lat=52.5","lon=13.4"])
+```
+
+Or use the dataset classes directly:
+```python
+import climdata, xarray as xr
+cmip = climdata.CMIP(cfg)
+cmip.fetch()
+cmip.load()
+cmip.extract(box=cfg.bounds[cfg.region])
+cmip.save_netcdf("output.nc")
+```
+
+## Configs
+- Config files live in `climdata/conf/`. There are dataset-specific config entry points e.g. `config_cmip`, `config_mswx`, etc.  
+- Filename templates are configurable in `cfg.output`:
+  - `cfg.output.filename_nc`
+  - `cfg.output.filename_csv`
+  - `cfg.output.filename_zarr`
+
+The wrapper generates filenames via `get_output_filename(cfg, output_type, ...)` using `cfg.bounds`, `cfg.time_range`, etc.
+
+## Output CSV format
+CSV produced by `save_csv` is standardized to the long form with columns (where available):
+- source_id, experiment_id, table_id, time, lat, lon, variable, value, units
+
+This ensures a single `value` column and a `variable` column for stacked variables.
+
+## Common issues & tips
+- NetCDF write ValueError (datetime encoding): call `ds["time"].encoding.clear()` before `to_netcdf()` (wrapper handles this).
+- PermissionError writing files: ensure output directory is writable or write to `/tmp/` (or adjust permissions).
+- CMIP cloud access requires network access — use the Pangeo intake catalog URL already referenced in code.
+
+## AOI handling
+`preprocess_aoi(cfg)` accepts:
+- GeoJSON strings / Feature / FeatureCollection
+- Point → sets `cfg.lat`, `cfg.lon`
+- Polygon or bbox → sets `cfg.bounds['custom']` and `cfg.region='custom'`
+
+## HYRAS support
+HYRAS class mirrors MSWX design:
+- `fetch()` / `load()` / `extract(point=...)` / `save_csv()` / `save_netcdf()`
+- HYRAS extraction currently supports point extraction; attempt to use a region will raise an error.
+
+## Development & provenance
+- CI: add GitHub Actions workflows to run tests and build/publish to PyPI.
+- Keep config and runtime overrides in Hydra to enable reproducible runs.
+- Include `CITATION.cff`, license, and a changelog for FAIR discoverability.
+
+## Contributing
+- Run tests: `pytest`
+- Style: follow repository linting config
+- Open PRs against `main` with tests and a short changelog entry
+
+## License
+Specify the license (e.g. MIT or Apache 2.0) in `LICENSE`.
+
+---
+
+For further examples, see `examples/` and the `docs/` folder (usage, installation, faq).// filepath: /beegfs/muduchuru/pkgs_fnl/climdata/README.md
+# climdata
+
+Lightweight toolkit to fetch, subset and export climate data (MSWX, CMIP, DWD, HYRAS).  
+Provides a Hydra-driven CLI, programmatic wrapper, cloud-native CMIP access, local dataset handling, and standardized CSV/NetCDF/Zarr exports.
+
+## Key features
+- Fetch and load datasets: MSWX, CMIP (cloud via intake), DWD, HYRAS
+- Spatial extraction: point, box (region via config bounds), or shapefile (GeoJSON/Feature)
+- Temporal subsetting via config or programmatic call
+- Multi-format export: NetCDF, Zarr, CSV (standardized long format: variable, value, units)
+- Hydra configuration + easy CLI overrides
+- Helper to normalize AOI (GeoJSON → point / bbox / polygon)
+- Provenance-friendly workflow (designed to be used with CI/CD workflows)
+
+## Install (development)
+1. Clone repository
+```bash
+git clone <repo-url>
+cd climdata
+```
+2. Create virtualenv and install deps
+```bash
+python -m venv .venv
+source .venv/bin/activate
+pip install -U pip
+pip install -e ".[dev]"   # or pip install -r requirements.txt
+```
+
+## Quick CLI (Hydra) usage
+Hydra reads configs from `conf/`. Override any config value on the CLI.
+
+Examples:
+```bash
+# Region extraction (saves NetCDF by default when region is used)
+python examples/climdata_cli.py dataset=CMIP region=europe time_range.start_date=2010-01-01 time_range.end_date=2010-12-31
+
+# Point extraction (saves CSV)
+python examples/climdata_cli.py dataset=MSWX lat=52.5 lon=13.4 variables=['tas','pr'] time_range.start_date=2000-01-01
+
+# HYRAS / DWD (point only)
+python examples/climdata_cli.py dataset=HYRAS lat=52 lon=10
+```
+
+Notes:
+- Use `dataset=<MSWX|CMIP|DWD|HYRAS>` in CLI.
+- Override any config key: e.g. `time_range.start_date=2000-01-01`.
+- DWD/HYRAS: region (box) extraction is not supported — script will raise an error if attempted.
+
+## Programmatic usage
+Use the wrapper to compose configs, preprocess AOI, extract, and save.
+
+```python
+from climdata.utils.wrapper import extract_data
+
+# returns (cfg, filename, ds, index) when save_to_file=True
+cfg, filename, ds, index = extract_data(cfg_name="config", overrides=["dataset=MSWX","lat=52.5","lon=13.4"])
+```
+
+Or use the dataset classes directly:
+```python
+import climdata, xarray as xr
+cmip = climdata.CMIP(cfg)
+cmip.fetch()
+cmip.load()
+cmip.extract(box=cfg.bounds[cfg.region])
+cmip.save_netcdf("output.nc")
+```
+
+## Configs
+- Config files live in `climdata/conf/`. There are dataset-specific config entry points e.g. `config_cmip`, `config_mswx`, etc.  
+- Filename templates are configurable in `cfg.output`:
+  - `cfg.output.filename_nc`
+  - `cfg.output.filename_csv`
+  - `cfg.output.filename_zarr`
+
+The wrapper generates filenames via `get_output_filename(cfg, output_type, ...)` using `cfg.bounds`, `cfg.time_range`, etc.
+
+## Output CSV format
+CSV produced by `save_csv` is standardized to the long form with columns (where available):
+- source_id, experiment_id, table_id, time, lat, lon, variable, value, units
+
+This ensures a single `value` column and a `variable` column for stacked variables.
+
+## Common issues & tips
+- NetCDF write ValueError (datetime encoding): call `ds["time"].encoding.clear()` before `to_netcdf()` (wrapper handles this).
+- PermissionError writing files: ensure output directory is writable or write to `/tmp/` (or adjust permissions).
+- CMIP cloud access requires network access — use the Pangeo intake catalog URL already referenced in code.
+
+## AOI handling
+`preprocess_aoi(cfg)` accepts:
+- GeoJSON strings / Feature / FeatureCollection
+- Point → sets `cfg.lat`, `cfg.lon`
+- Polygon or bbox → sets `cfg.bounds['custom']` and `cfg.region='custom'`
+
+## HYRAS support
+HYRAS class mirrors MSWX design:
+- `fetch()` / `load()` / `extract(point=...)` / `save_csv()` / `save_netcdf()`
+- HYRAS extraction currently supports point extraction; attempt to use a region will raise an error.
+
+## Development & provenance
+- CI: add GitHub Actions workflows to run tests and build/publish to PyPI.
+- Keep config and runtime overrides in Hydra to enable reproducible runs.
+- Include `CITATION.cff`, license, and a changelog for FAIR discoverability.
+
+## Contributing
+- Run tests: `pytest`
+- Style: follow repository linting config
+- Open PRs against `main` with tests and a short changelog entry
+
+## License
+Specify the license (e.g. MIT or Apache 2.0) in `LICENSE`.
+
+---
+
+For further examples, see `examples/` and the `docs/` folder (usage, installation, faq).

climdata-0.3.4/README.md

@@ -0,0 +1,235 @@
+# climdata
+
+
+[![image](https://img.shields.io/pypi/v/climdata.svg)](https://pypi.python.org/pypi/climdata)
+[![image](https://img.shields.io/conda/vn/conda-forge/climdata.svg)](https://anaconda.org/conda-forge/climdata)
+
+`climdata` is a Python package designed to automate fetching, extraction, and processing of climate data from various sources, including MSWX, DWD HYRAS, ERA5-Land, and NASA-NEX-GDDP. It provides tools to retrieve data for specific locations and time ranges, facilitating climate analysis and research.
+
+---
+
+## Key features
+- Fetch and load datasets: MSWX, CMIP (cloud via intake), DWD, HYRAS
+- Spatial extraction: point, box (region via config bounds), or shapefile (GeoJSON/Feature)
+- Temporal subsetting via config or programmatic call
+- Multi-format export: NetCDF, Zarr, CSV (standardized long format: variable, value, units)
+- Hydra configuration + easy CLI overrides
+- Helper to normalize AOI (GeoJSON → point / bbox / polygon)
+- Provenance-friendly workflow (designed to be used with CI/CD workflows)
+
+## Install (development)
+1. Clone repository
+```bash
+git clone <repo-url>
+cd climdata
+```
+2. Create virtualenv and install deps
+```bash
+python -m venv .venv
+source .venv/bin/activate
+pip install -U pip
+pip install -e ".[dev]"   # or pip install -r requirements.txt
+```
+
+## Quick CLI (Hydra) usage
+Hydra reads configs from `conf/`. Override any config value on the CLI.
+
+Examples:
+```bash
+# Region extraction (saves NetCDF by default when region is used)
+python examples/climdata_cli.py dataset=CMIP region=europe time_range.start_date=2010-01-01 time_range.end_date=2010-12-31
+
+# Point extraction (saves CSV)
+python examples/climdata_cli.py dataset=MSWX lat=52.5 lon=13.4 variables=['tas','pr'] time_range.start_date=2000-01-01
+
+# HYRAS / DWD (point only)
+python examples/climdata_cli.py dataset=HYRAS lat=52 lon=10
+```
+
+Notes:
+- Use `dataset=<MSWX|CMIP|DWD|HYRAS>` in CLI.
+- Override any config key: e.g. `time_range.start_date=2000-01-01`.
+- DWD/HYRAS: region (box) extraction is not supported — script will raise an error if attempted.
+
+## Programmatic usage
+Use the wrapper to compose configs, preprocess AOI, extract, and save.
+
+```python
+from climdata.utils.wrapper import extract_data
+
+# returns (cfg, filename, ds, index) when save_to_file=True
+cfg, filename, ds, index = extract_data(cfg_name="config", overrides=["dataset=MSWX","lat=52.5","lon=13.4"])
+```
+
+Or use the dataset classes directly:
+```python
+import climdata, xarray as xr
+cmip = climdata.CMIP(cfg)
+cmip.fetch()
+cmip.load()
+cmip.extract(box=cfg.bounds[cfg.region])
+cmip.save_netcdf("output.nc")
+```
+
+## Configs
+- Config files live in `climdata/conf/`. There are dataset-specific config entry points e.g. `config_cmip`, `config_mswx`, etc.  
+- Filename templates are configurable in `cfg.output`:
+  - `cfg.output.filename_nc`
+  - `cfg.output.filename_csv`
+  - `cfg.output.filename_zarr`
+
+The wrapper generates filenames via `get_output_filename(cfg, output_type, ...)` using `cfg.bounds`, `cfg.time_range`, etc.
+
+## Output CSV format
+CSV produced by `save_csv` is standardized to the long form with columns (where available):
+- source_id, experiment_id, table_id, time, lat, lon, variable, value, units
+
+This ensures a single `value` column and a `variable` column for stacked variables.
+
+## Common issues & tips
+- NetCDF write ValueError (datetime encoding): call `ds["time"].encoding.clear()` before `to_netcdf()` (wrapper handles this).
+- PermissionError writing files: ensure output directory is writable or write to `/tmp/` (or adjust permissions).
+- CMIP cloud access requires network access — use the Pangeo intake catalog URL already referenced in code.
+
+## AOI handling
+`preprocess_aoi(cfg)` accepts:
+- GeoJSON strings / Feature / FeatureCollection
+- Point → sets `cfg.lat`, `cfg.lon`
+- Polygon or bbox → sets `cfg.bounds['custom']` and `cfg.region='custom'`
+
+## HYRAS support
+HYRAS class mirrors MSWX design:
+- `fetch()` / `load()` / `extract(point=...)` / `save_csv()` / `save_netcdf()`
+- HYRAS extraction currently supports point extraction; attempt to use a region will raise an error.
+
+## Development & provenance
+- CI: add GitHub Actions workflows to run tests and build/publish to PyPI.
+- Keep config and runtime overrides in Hydra to enable reproducible runs.
+- Include `CITATION.cff`, license, and a changelog for FAIR discoverability.
+
+## Contributing
+- Run tests: `pytest`
+- Style: follow repository linting config
+- Open PRs against `main` with tests and a short changelog entry
+
+## License
+Specify the license (e.g. MIT or Apache 2.0) in `LICENSE`.
+
+---
+
+For further examples, see `examples/` and the `docs/` folder (usage, installation, faq).// filepath: /beegfs/muduchuru/pkgs_fnl/climdata/README.md
+# climdata
+
+Lightweight toolkit to fetch, subset and export climate data (MSWX, CMIP, DWD, HYRAS).  
+Provides a Hydra-driven CLI, programmatic wrapper, cloud-native CMIP access, local dataset handling, and standardized CSV/NetCDF/Zarr exports.
+
+## Key features
+- Fetch and load datasets: MSWX, CMIP (cloud via intake), DWD, HYRAS
+- Spatial extraction: point, box (region via config bounds), or shapefile (GeoJSON/Feature)
+- Temporal subsetting via config or programmatic call
+- Multi-format export: NetCDF, Zarr, CSV (standardized long format: variable, value, units)
+- Hydra configuration + easy CLI overrides
+- Helper to normalize AOI (GeoJSON → point / bbox / polygon)
+- Provenance-friendly workflow (designed to be used with CI/CD workflows)
+
+## Install (development)
+1. Clone repository
+```bash
+git clone <repo-url>
+cd climdata
+```
+2. Create virtualenv and install deps
+```bash
+python -m venv .venv
+source .venv/bin/activate
+pip install -U pip
+pip install -e ".[dev]"   # or pip install -r requirements.txt
+```
+
+## Quick CLI (Hydra) usage
+Hydra reads configs from `conf/`. Override any config value on the CLI.
+
+Examples:
+```bash
+# Region extraction (saves NetCDF by default when region is used)
+python examples/climdata_cli.py dataset=CMIP region=europe time_range.start_date=2010-01-01 time_range.end_date=2010-12-31
+
+# Point extraction (saves CSV)
+python examples/climdata_cli.py dataset=MSWX lat=52.5 lon=13.4 variables=['tas','pr'] time_range.start_date=2000-01-01
+
+# HYRAS / DWD (point only)
+python examples/climdata_cli.py dataset=HYRAS lat=52 lon=10
+```
+
+Notes:
+- Use `dataset=<MSWX|CMIP|DWD|HYRAS>` in CLI.
+- Override any config key: e.g. `time_range.start_date=2000-01-01`.
+- DWD/HYRAS: region (box) extraction is not supported — script will raise an error if attempted.
+
+## Programmatic usage
+Use the wrapper to compose configs, preprocess AOI, extract, and save.
+
+```python
+from climdata.utils.wrapper import extract_data
+
+# returns (cfg, filename, ds, index) when save_to_file=True
+cfg, filename, ds, index = extract_data(cfg_name="config", overrides=["dataset=MSWX","lat=52.5","lon=13.4"])
+```
+
+Or use the dataset classes directly:
+```python
+import climdata, xarray as xr
+cmip = climdata.CMIP(cfg)
+cmip.fetch()
+cmip.load()
+cmip.extract(box=cfg.bounds[cfg.region])
+cmip.save_netcdf("output.nc")
+```
+
+## Configs
+- Config files live in `climdata/conf/`. There are dataset-specific config entry points e.g. `config_cmip`, `config_mswx`, etc.  
+- Filename templates are configurable in `cfg.output`:
+  - `cfg.output.filename_nc`
+  - `cfg.output.filename_csv`
+  - `cfg.output.filename_zarr`
+
+The wrapper generates filenames via `get_output_filename(cfg, output_type, ...)` using `cfg.bounds`, `cfg.time_range`, etc.
+
+## Output CSV format
+CSV produced by `save_csv` is standardized to the long form with columns (where available):
+- source_id, experiment_id, table_id, time, lat, lon, variable, value, units
+
+This ensures a single `value` column and a `variable` column for stacked variables.
+
+## Common issues & tips
+- NetCDF write ValueError (datetime encoding): call `ds["time"].encoding.clear()` before `to_netcdf()` (wrapper handles this).
+- PermissionError writing files: ensure output directory is writable or write to `/tmp/` (or adjust permissions).
+- CMIP cloud access requires network access — use the Pangeo intake catalog URL already referenced in code.
+
+## AOI handling
+`preprocess_aoi(cfg)` accepts:
+- GeoJSON strings / Feature / FeatureCollection
+- Point → sets `cfg.lat`, `cfg.lon`
+- Polygon or bbox → sets `cfg.bounds['custom']` and `cfg.region='custom'`
+
+## HYRAS support
+HYRAS class mirrors MSWX design:
+- `fetch()` / `load()` / `extract(point=...)` / `save_csv()` / `save_netcdf()`
+- HYRAS extraction currently supports point extraction; attempt to use a region will raise an error.
+
+## Development & provenance
+- CI: add GitHub Actions workflows to run tests and build/publish to PyPI.
+- Keep config and runtime overrides in Hydra to enable reproducible runs.
+- Include `CITATION.cff`, license, and a changelog for FAIR discoverability.
+
+## Contributing
+- Run tests: `pytest`
+- Style: follow repository linting config
+- Open PRs against `main` with tests and a short changelog entry
+
+## License
+Specify the license (e.g. MIT or Apache 2.0) in `LICENSE`.
+
+---
+
+For further examples, see `examples/` and the `docs/` folder (usage, installation, faq).

climdata-0.3.4/climdata/__init__.py

@@ -0,0 +1,16 @@
+"""Top-level package for climdata."""
+
+__author__ = """Kaushik Muduchuru"""
+__email__ = "kaushik.reddy.m@gmail.com"
+__version__ = "0.3.4"
+
+from .utils.utils_download import * # etc.
+from .utils.config import load_config
+from .utils.wrapper import extract_data
+from .datasets.DWD import DWDmirror as DWD
+from .datasets.MSWX import MSWXmirror as MSWX
+from .datasets.ERA5 import ERA5Mirror as ERA5
+from .datasets.CMIPlocal import CMIPmirror as CMIPlocal
+from .datasets.CMIPCloud import CMIPCloud as CMIP
+from .datasets.HYRAS import HYRASmirror as HYRAS
+

climdata-0.3.4/climdata/conf/config.yaml

@@ -0,0 +1,43 @@
+defaults:
+  - _self_
+  - mappings/parameters@dsinfo
+  - mappings/variables@varinfo 
+  - mappings/indices@extinfo
+
+dataset: mswx
+lat: null
+lon: null
+aoi: null
+shapefile: null
+
+variables: ["tasmin","tasmax","pr"]
+index: null
+data_dir: ./data
+region: null
+
+experiment_id: historical
+source_id: MIROC6
+table_id: day
+
+bounds:
+  europe:
+    lat_min: 34.0
+    lat_max: 71.0
+    lon_min: -25.0
+    lon_max: 45.0
+  custom:
+    lat_min: null
+    lat_max: null
+    lon_min: null
+    lon_max: null
+
+time_range:
+  start_date: "1989-01-01"
+  end_date: "2020-12-31"
+
+output:
+  out_dir: "./climdata/data/"
+  filename_csv: "{provider}_{parameter}_LAT_{lat}_LON_{lon}_{start}_{end}.csv"
+  filename_zarr: "{provider}_{parameter}_LAT{lat_range}_LON{lon_range}_{start}_{end}.zarr"
+  filename_nc: "{provider}_{parameter}_LAT{lat_range}_LON{lon_range}_{start}_{end}.nc"
+  fmt: "standard"