Add back working download script

.github/workflows/ci.yml

@@ -29,7 +29,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: [3.10, 3.12]  # test oldest and latest supported versions
+        python-version: ["3.10", "3.12"]  # test oldest and latest supported versions
         runs-on: [ubuntu-latest]  # can be extended to other OSes, e.g. [ubuntu-latest, macos-latest]
 
     steps:
@@ -43,7 +43,7 @@ jobs:
           allow-prereleases: true
 
       - name: Install package
-        run: python -m pip install .[test]
+        run: python -m pip install .[dev]
 
       - name: Test package
         run: >-

.pre-commit-config.yaml

@@ -37,3 +37,8 @@ repos:
         args: []
         additional_dependencies:
           - pytest
+          - xarray
+          - pandas-stubs
+          - types-all
+          - typer
+          - dask

README.md

@@ -8,18 +8,87 @@ Tooling and infrastructure to enable cloud nowcasting.
 
 ## Installation
 
+From source (development mode):
 ```bash
-python -m pip install cloudcast
+git clone https://github.com/climetrend/cloudcast
+cd cloudcast
+python -m pip install ".[dev]"
 ```
 
-From source:
+Install pre-commit before making development changes:
+
 ```bash
-git clone https://github.com/climetrend/cloudcast
-cd cloudcast
-python -m pip install .
+pre-commit install
 ```
 
+For making changes, see the [guidance on development](https://github.com/alan-turing-institute/python-project-template?tab=readme-ov-file#setting-up-a-new-project) from the template that generated this project.
+
 ## Usage
+```bash
+ cloudcast download --help
+
+ Usage: cloudcast download [OPTIONS] START_DATE END_DATE OUTPUT_DIRECTORY
+
+ Download a selection of the available EUMETSAT data.
+ Each calendar year of data within the supplied date range will be saved to a
+ separate file in the output directory.
+ Args:     start_date: First datetime (inclusive) to download.     end_date: Last
+ datetime (inclusive) to download.     data_inner_steps: Data will be sliced into
+ data_inner_steps*5minute chunks.     output_directory: Directory to which the
+ satellite data should be saved.     lon_min: The west-most longitude (in
+ degrees) of the bounding box to download.     lon_max: The east-most longitude
+ (in degrees) of the bounding box to download.     lat_min: The south-most
+ latitude (in degrees) of the bounding box to download.     lat_max: The
+ north-most latitude (in degrees) of the bounding box to download.     get_hrv:
+ Whether to download the HRV data, else non-HRV is downloaded.
+ override_date_bounds: Whether to override the date range limits.
+ Raises:     FileNotFoundError: If the output directory doesn't exist.
+ ValueError: If there are issues with the date range or if output files already
+ exist.
+
+╭─ Arguments ────────────────────────────────────────────────────────────────────╮
+│ *    start_date            TEXT  Start date in 'YYYY-MM-DD HH:MM' format       │
+│                                  [default: None]                               │
+│                                  [required]                                    │
+│ *    end_date              TEXT  End date in 'YYYY-MM-DD HH:MM' format         │
+│                                  [default: None]                               │
+│                                  [required]                                    │
+│ *    output_directory      TEXT  Directory to save the satellite data          │
+│                                  [default: None]                               │
+│                                  [required]                                    │
+╰────────────────────────────────────────────────────────────────────────────────╯
+╭─ Options ──────────────────────────────────────────────────────────────────────╮
+│ --data-inner-steps                              INTEGER  Data will be sliced   │
+│                                                          into                  │
+│                                                          data_inner_steps*5mi… │
+│                                                          chunks                │
+│                                                          [default: 3]          │
+│ --get-hrv                --no-get-hrv                    Whether to download   │
+│                                                          HRV data              │
+│                                                          [default: no-get-hrv] │
+│ --override-date-boun…    --no-override-date…             Whether to override   │
+│                                                          date range limits     │
+│                                                          [default:             │
+│                                                          no-override-date-bou… │
+│ --lon-min                                       FLOAT    Minimum longitude     │
+│                                                          [default: -16]        │
+│ --lon-max                                       FLOAT    Maximum longitude     │
+│                                                          [default: 10]         │
+│ --lat-min                                       FLOAT    Minimum latitude      │
+│                                                          [default: 45]         │
+│ --lat-max                                       FLOAT    Maximum latitude      │
+│                                                          [default: 70]         │
+│ --help                                                   Show this message and │
+│                                                          exit.                 │
+╰────────────────────────────────────────────────────────────────────────────────╯
+
+```
+
+Example:
+
+```bash
+cloudcast download "2020-06-01 00:00" "2020-06-30 23:55" "path/to/my/dir/data.zarr"
+```
 
 
 ## Contributing

notebooks/plotting.ipynb

@@ -0,0 +1,59 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import ocf_blosc2  # noqa: F401\n",
+    "import xarray as xr\n",
+    "\n",
+    "ds_sat = xr.open_zarr(\"path/to/new/satellite/directory/2020_nonhrv.zarr\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ds_sat.sel(time=\"2020-06-01 12:00\", variable=\"VIS008\").data.plot()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "timestamp = '2020-01-06T09:00:00.000000000'\n",
+    "\n",
+    "# Calculate the number of variables (columns)\n",
+    "num_vars = len(ds_sat.variable)\n",
+    "\n",
+    "\n",
+    "col_wrap = 3\n",
+    "num_rows = (num_vars + 3) // col_wrap  # Using 4 as col_wrap, adjust if different\n",
+    "\n",
+    "# Calculate the figure size based on the image resolution of 614x372\n",
+    "fig_width = 6.14 * col_wrap\n",
+    "fig_height = 3.72 * num_rows\n",
+    "\n",
+    "ds_sat.sel(time=timestamp).data.plot(\n",
+    "    col=\"variable\",\n",
+    "    col_wrap=col_wrap,\n",
+    "    figsize=(fig_width, fig_height),\n",
+    "    robust=True,\n",
+    ");"
+   ]
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

notebooks/requirements.txt

@@ -0,0 +1,2 @@
+ipykernel
+matplotlib

pyproject.toml

@@ -1,18 +1,7 @@
 [build-system]
 requires = ["setuptools>=61"]
 build-backend = "setuptools.build_meta"
-license = "MIT"
-description = "Tooling and infrastructure to enable cloud nowcasting."
-readme = "README.md"
 
-classifiers = [
-  "Development Status :: 1 - Planning",
-  "Intended Audience :: Science/Research",
-  "Intended Audience :: Developers",
-  "Operating System :: OS Independent",
-  "Topic :: Scientific/Engineering",
-"Typing :: Typed",
-]
 
 [project]
 name = "cloudcast"
@@ -32,22 +21,34 @@ classifiers = [
   "Programming Language :: Python",
   "Programming Language :: Python :: 3",
   "Programming Language :: Python :: 3 :: Only",
-  "Programming Language :: Python :: 3.9",
   "Programming Language :: Python :: 3.10",
   "Programming Language :: Python :: 3.11",
   "Programming Language :: Python :: 3.12",
   "Topic :: Scientific/Engineering",
   "Typing :: Typed",
 ]
-dependencies = []
-
+dependencies = [
+    "gcsfs",
+    "zarr",
+    "xarray",
+    "dask",
+    "pyresample",
+    "pyproj",
+    "ocf-blosc2",
+    "ocf-datapipes",
+    "typer"
+]
 [project.optional-dependencies]
 dev = [
   "pytest >=6",
   "pytest-cov >=3",
   "pre-commit",
+
 ]
 
+[project.scripts]
+cloudcast = "cloudcast.cli:app"
+
 [project.urls]
 Homepage = "https://github.com/climetrend/cloudcast"
 "Bug Tracker" = "https://github.com/climetrend/cloudcast/issues"
@@ -75,7 +76,7 @@ port.exclude_lines = [
 ]
 
 [tool.mypy]
-files = ["src", "tests"]
+files = ["src"]
 python_version = "3.10"
 show_error_codes = true
 warn_unreachable = true
@@ -90,10 +91,24 @@ module = "cloudcast.*"
 disallow_untyped_defs = true
 disallow_incomplete_defs = true
 
+[[tool.mypy.overrides]]
+module = [
+    "ocf_blosc2",
+    "ocf_datapipes.utils.geospatial"
+]
+ignore_missing_imports = true
+
+[[tool.mypy.overrides]]
+module = [
+    "cloudcast.download",
+    "cloudcast.cli",
+]
+disallow_untyped_calls = false
+
 [tool.ruff]
 src = ["src"]
 exclude = []
-line-length = 88  # how long you want lines to be
+line-length = 100 # how long you want lines to be
 
 [tool.ruff.format]
 docstring-code-format = true  # code snippets in docstrings will be formatted
@@ -129,3 +144,5 @@ unfixable = [
   "F841",   # Would remove unused variables
 ]
 flake8-unused-arguments.ignore-variadic-names = true  # allow unused *args/**kwargsisort.required-imports = ["from __future__ import annotations"]
+[tool.ruff.lint.per-file-ignores]
+"src/cloudcast/download.py" = ["E402"]

src/cloudcast/__init__.py

@@ -6,5 +6,7 @@
 
 from importlib.metadata import version
 
-__all__ = ("__version__",)
+from cloudcast import cli, download
+
+__all__ = ("__version__", "download", "cli")
 __version__ = version(__name__)

src/cloudcast/__main__.py

@@ -0,0 +1,3 @@
+from cloudcast.cli import app
+
+app()

src/cloudcast/cli.py

@@ -0,0 +1,8 @@
+import typer
+
+from cloudcast.download import download_satellite_data
+
+# typer app code
+app = typer.Typer()
+app.command("download")(download_satellite_data)
+app.command("validate")(lambda x: x)  # placeholder