make mypy happy and add variables list

README.md

@@ -29,4 +29,4 @@ To download the following datasets, users need access to CDS via cdsapi:
 - ERA5 land
 - LAI
 
-Before submitting any request with `zampy`, please configure your `.cdsapirc` file following the instructions on https://pypi.org/project/cdsapi/.
+Before submitting any request with `zampy`, please configure your `.cdsapirc` file following the instructions on https://cds.climate.copernicus.eu/api-how-to. For the first time, it is **necessary to agree to the Terms of Use of every datasets that you intend to download**. This can only be done via web API.

demo/era5_dataset_demo.ipynb

@@ -0,0 +1,96 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Handle ERA5 dataset with Zampy\n",
+    "Demo notebook for developers."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "from zampy.datasets import ERA5\n",
+    "from zampy.datasets.dataset_protocol import TimeBounds, SpatialBounds\n",
+    "from pathlib import Path"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "work_dir = Path(\"/home/yangliu/EcoExtreML/temp\")\n",
+    "download_dir = work_dir / \"download\"\n",
+    "ingest_dir = work_dir / \"ingest\"\n",
+    "times = TimeBounds(np.datetime64(\"2010-01-01\"), np.datetime64(\"2010-01-31\"))\n",
+    "bbox_demo = SpatialBounds(54, 56, 1, 3)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "File 'era5_10m_v_component_of_wind_2010-1.nc' already exists, skipping...\n",
+      "File 'era5_surface_solar_radiation_downwards_2010-1.nc' already exists, skipping...\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "True"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "era5_dataset = ERA5()\n",
+    "era5_dataset.download(\n",
+    "    download_dir=download_dir,\n",
+    "    time_bounds=times,\n",
+    "    spatial_bounds=bbox_demo,\n",
+    "    variable_names=[\"10m_v_component_of_wind\",\n",
+    "                    \"surface_solar_radiation_downwards\",\n",
+    "                    \"mean_total_precipitation_rate\",\n",
+    "                    \"surface_pressure\",],\n",
+    ")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "ecoextreml",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.0"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

src/zampy/datasets/era5.py

@@ -1,44 +1,74 @@
 """ERA5 dataset."""
 
 from pathlib import Path
-from typing import List
 from typing import Union
 import numpy as np
-import xarray as xr
-# from zampy.datasets import converter
 from zampy.datasets import utils
-# from zampy.datasets import validation
+from zampy.datasets import validation
 from zampy.datasets.dataset_protocol import Dataset
 from zampy.datasets.dataset_protocol import SpatialBounds
 from zampy.datasets.dataset_protocol import TimeBounds
-# from zampy.datasets.dataset_protocol import Variable
-# from zampy.datasets.dataset_protocol import copy_properties_file
+from zampy.datasets.dataset_protocol import Variable
 from zampy.datasets.dataset_protocol import write_properties_file
+from zampy.reference.variables import unit_registry
+
+
+## Ignore missing class/method docstrings: they are implemented in the Dataset class.
+# ruff: noqa: D102
 
 
 class ERA5(Dataset):  # noqa: D101
     name = "era5"
     time_bounds = TimeBounds(np.datetime64("1940-01-01"), np.datetime64("2023-06-30"))
     spatial_bounds = SpatialBounds(90, 180, -90, -180)
 
+    raw_variables = (
+        Variable(name="mtpr", unit=unit_registry.precipitation),
+        Variable(name="strd", unit=unit_registry.radiation),
+        Variable(name="ssrd", unit=unit_registry.radiation),
+        Variable(name="sp", unit=unit_registry.pascal),
+        Variable(name="u10", unit=unit_registry.velocity),
+        Variable(name="v10", unit=unit_registry.velocity),
+    )
+
+    variable_names = (
+        "mean_total_precipitation_rate",
+        "surface_thermal_radiation_downwards",
+        "surface_solar_radiation_downwards",
+        "surface_pressure",
+        "10m_u_component_of_wind",
+        "10m_v_component_of_wind",
+    )
+
     license = "cc-by-4.0"
+    bib = """
+    @article{hersbach2020era5,
+        title={The ERA5 global reanalysis},
+        author={Hersbach, Hans et al.},
+        journal={Quarterly Journal of the Royal Meteorological Society},
+        volume={146},
+        number={730},
+        pages={1999--2049},
+        year={2020},
+        publisher={Wiley Online Library}
+        }
+    """
 
     def download(  # noqa: PLR0913
         self,
         download_dir: Path,
         time_bounds: TimeBounds,
         spatial_bounds: SpatialBounds,
-        variable_names: List[str],
+        variable_names: list[str],
         overwrite: bool = False,
     ) -> bool:
-        # validation.validate_download_request(
-        #     self,
-        #     download_dir,
-        #     time_bounds,
-        #     spatial_bounds,
-        #     variable_names,
-        # )
-        # call the cds_request function
+        validation.validate_download_request(
+            self,
+            download_dir,
+            time_bounds,
+            spatial_bounds,
+            variable_names,
+        )
 
         download_folder = download_dir / self.name
         download_folder.mkdir(parents=True, exist_ok=True)
@@ -66,16 +96,16 @@ def ingest(
     ) -> bool:
         return True
 
-    def load( # noqa: PLR0913
-        self,
-        ingest_dir: Path,
-        time_bounds: TimeBounds,
-        spatial_bounds: SpatialBounds,
-        resolution: float,
-        regrid_method: str,
-        variable_names: List[str],
-    ):
-        pass
+    # def load(  # noqa: PLR0913
+    #     self,
+    #     ingest_dir: Path,
+    #     time_bounds: TimeBounds,
+    #     spatial_bounds: SpatialBounds,
+    #     resolution: float,
+    #     regrid_method: str,
+    #     variable_names: List[str],
+    # ) -> None:
+    #     pass
 
     def convert(
         self,