{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "0",
   "metadata": {},
   "source": [
    "# ERA5 → EOPF HEALPix Converter\n",
    "\n",
    "Converts ERA5 reanalysis surface fields (Gaussian N256/N320) to EOPF-compliant HEALPix zarr (level 7, ~50 km).\n",
    "\n",
    "**Pipeline**: download GRIB via CDS (2 MARS requests) → PSFResampler → write zarr → inject STAC → push S3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "1",
   "metadata": {},
   "outputs": [],
   "source": [
    "import logging\n",
    "from pathlib import Path\n",
    "\n",
    "from healpix_convert.converters.era5 import ERA5Converter\n",
    "\n",
    "logging.basicConfig(level=logging.INFO, format=\"%(asctime)s %(levelname)s %(message)s\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2",
   "metadata": {},
   "source": [
    "## Configuration"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "3",
   "metadata": {},
   "outputs": [],
   "source": [
    "DATE = \"2025-01-01\"\n",
    "TIME = \"00:00:00\"\n",
    "LOCAL_DIR = Path(\".\")\n",
    "OUTPUT = LOCAL_DIR / f\"S00__ADF_ECMWA_{DATE.replace('-', '')}.zarr\"\n",
    "PUSH_S3 = False  # set True to push to S3\n",
    "\n",
    "converter = ERA5Converter(\n",
    "    date=DATE,\n",
    "    time=TIME,\n",
    "    local_dir=LOCAL_DIR,\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4",
   "metadata": {},
   "source": [
    "## Step 1 — Prepare (download + PSFResampler)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "5",
   "metadata": {},
   "outputs": [],
   "source": [
    "result = converter.prepare(output_path=str(OUTPUT))\n",
    "print(f\"Chunks: {result.n_chunks} | Timesteps: {result.n_times}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6",
   "metadata": {},
   "source": [
    "## Step 2 — Convert (all spatial chunks)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "7",
   "metadata": {},
   "outputs": [],
   "source": [
    "for i in range(result.n_chunks):\n",
    "    converter.convert_group(i)\n",
    "    if (i + 1) % 20 == 0:\n",
    "        print(f\"  {i+1}/{result.n_chunks}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8",
   "metadata": {},
   "source": [
    "## Step 3 — Consolidate (STAC metadata)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "9",
   "metadata": {},
   "outputs": [],
   "source": [
    "converter.consolidate()\n",
    "print(f\"Done: {OUTPUT}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "10",
   "metadata": {},
   "source": [
    "## Validation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "11",
   "metadata": {},
   "outputs": [],
   "source": [
    "import healpy as hp\n",
    "import matplotlib.pyplot as plt\n",
    "import xarray as xr\n",
    "\n",
    "ds = xr.open_zarr(str(OUTPUT), consolidated=True)\n",
    "print(ds)\n",
    "\n",
    "var = \"t2m\"\n",
    "data = ds[var].isel(time=0).values\n",
    "hp.mollview(\n",
    "    hp.reorder(data - 273.15, n2r=True),\n",
    "    flip=\"geo\",\n",
    "    nest=False,\n",
    "    cmap=\"RdBu_r\",\n",
    "    min=-50,\n",
    "    max=50,\n",
    "    unit=\"°C\",\n",
    "    title=f\"ERA5 {var} — HEALPix level 7\",\n",
    ")\n",
    "plt.show()"
   ]
  }
 ],
 "metadata": {
  "language_info": {
   "name": "python",
   "pygments_lexer": "ipython3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}