{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "87870edf-37c1-428a-a437-9c792d185a8a",
   "metadata": {},
   "source": [
    "# Notebook to understand and check what kind of daily ERA5 data is already downloaded"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "59ba9ba8-2829-4acb-98de-6ed094ea4c2e",
   "metadata": {},
   "source": [
    "currently data is available ere: https://cluster.klima.uni-bremen.de/~oggm/climate/wip/era5_daily/global/"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c49eaea7-19b8-4a40-a26c-0cea21c4ce21",
   "metadata": {},
   "source": [
    "\n",
    "goal: download data from the earliest possible until the latest possible with an easy possibility of an extension, once available\n",
    "- need daily data (best to download separately for every month)\n",
    "- + monthly data"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "053d8ec1-bf34-4a66-9f86-f5690cdb3999",
   "metadata": {},
   "source": [
    " currently using `conda env: ggm_env_2025`"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6b580b87-5613-4b88-a960-e1d9b8786d32",
   "metadata": {},
   "source": [
    "What is the difference between tmp/ERA5_Daily_t2m_2010_01.nc and ERA5_Daily_t2m_2010_01.nc ? \n",
    "- `tmp/`: raw data as downloaded from the cdsapi ECMWF server\n",
    "- `/`: minimally postprocessed data (changing some names and attributes)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "1ca22bee-33f0-4f71-b2de-2cdd2cc80d1b",
   "metadata": {},
   "outputs": [],
   "source": [
    "import xarray as xr"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "ca3c7784-ed04-4b43-82f2-3abbb5c6e627",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "❌ Missing files:\n",
      "   /home/www/oggm/climate/wip/era5_daily/global/ERA5_Daily_tp_2022_05.nc\n",
      "\n",
      "Total missing: 1\n"
     ]
    }
   ],
   "source": [
    "import os\n",
    "\n",
    "base_dir = \"/home/www/oggm/climate/wip/era5_daily/global\"\n",
    "variables = [\"t2m\", \"tp\"]\n",
    "\n",
    "year_start = 2010\n",
    "year_end = 2025\n",
    "month_end = 3  # up to March 2025\n",
    "\n",
    "missing_files = []\n",
    "\n",
    "for year in range(year_start, year_end + 1):\n",
    "    for month in range(1, 13):\n",
    "        # Stop after March 2025\n",
    "        if year == 2025 and month > month_end:\n",
    "            break\n",
    "\n",
    "        for var in variables:\n",
    "            filename = f\"ERA5_Daily_{var}_{year}_{month:02d}.nc\"\n",
    "            filepath = os.path.join(base_dir, filename)\n",
    "\n",
    "            if not os.path.exists(filepath):\n",
    "                missing_files.append(filepath)\n",
    "\n",
    "# --- Reporting ---\n",
    "if missing_files:\n",
    "    print(\"❌ Missing files:\")\n",
    "    for f in missing_files:\n",
    "        print(\"  \", f)\n",
    "    print(f\"\\nTotal missing: {len(missing_files)}\")\n",
    "else:\n",
    "    print(\"✅ All expected NetCDF files are present!\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "53674e5b-43fa-4bae-a7af-8a387daae640",
   "metadata": {},
   "source": [
    "ok, there was just one month and only tp missing (i.e., 2022_05), I rerun that manually again, and it is now in `www_lschuster/2025_10_era5_daily/tmp`"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "e0707d94-210d-4835-8316-6c853a493869",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "22d5b175-b7e8-4b3f-9f7e-e2a0afb08846",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "ename": "ValueError",
     "evalue": "did not find a match in any of xarray's currently installed IO backends ['netcdf4', 'scipy', 'rasterio']. Consider explicitly selecting one of the installed engines via the ``engine`` parameter, or installing additional IO dependencies, see:\nhttps://docs.xarray.dev/en/stable/getting-started-guide/installing.html\nhttps://docs.xarray.dev/en/stable/user-guide/io.html",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mValueError\u001b[0m                                Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[1], line 3\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mxarray\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m \u001b[38;5;21;01mxr\u001b[39;00m\n\u001b[1;32m      2\u001b[0m base_dir \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m/home/users/www_oggm/climate/wip/era5_daily/global\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m----> 3\u001b[0m \u001b[43mxr\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mopen_dataset\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43mf\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;132;43;01m{\u001b[39;49;00m\u001b[43mbase_dir\u001b[49m\u001b[38;5;132;43;01m}\u001b[39;49;00m\u001b[38;5;124;43m/download_2010_1.ipynb\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/mambaforge/envs/oggm_working_env/lib/python3.11/site-packages/xarray/backends/api.py:569\u001b[0m, in \u001b[0;36mopen_dataset\u001b[0;34m(filename_or_obj, engine, chunks, cache, decode_cf, mask_and_scale, decode_times, decode_timedelta, use_cftime, concat_characters, decode_coords, drop_variables, inline_array, chunked_array_type, from_array_kwargs, backend_kwargs, **kwargs)\u001b[0m\n\u001b[1;32m    566\u001b[0m     kwargs\u001b[38;5;241m.\u001b[39mupdate(backend_kwargs)\n\u001b[1;32m    568\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m engine \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m--> 569\u001b[0m     engine \u001b[38;5;241m=\u001b[39m \u001b[43mplugins\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mguess_engine\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfilename_or_obj\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    571\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m from_array_kwargs \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m    572\u001b[0m     from_array_kwargs \u001b[38;5;241m=\u001b[39m {}\n",
      "File \u001b[0;32m~/mambaforge/envs/oggm_working_env/lib/python3.11/site-packages/xarray/backends/plugins.py:197\u001b[0m, in \u001b[0;36mguess_engine\u001b[0;34m(store_spec)\u001b[0m\n\u001b[1;32m    189\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m    190\u001b[0m     error_msg \u001b[38;5;241m=\u001b[39m (\n\u001b[1;32m    191\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mfound the following matches with the input file in xarray\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124ms IO \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    192\u001b[0m         \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mbackends: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mcompatible_engines\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m. But their dependencies may not be installed, see:\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    193\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mhttps://docs.xarray.dev/en/stable/user-guide/io.html \u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    194\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mhttps://docs.xarray.dev/en/stable/getting-started-guide/installing.html\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    195\u001b[0m     )\n\u001b[0;32m--> 197\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(error_msg)\n",
      "\u001b[0;31mValueError\u001b[0m: did not find a match in any of xarray's currently installed IO backends ['netcdf4', 'scipy', 'rasterio']. Consider explicitly selecting one of the installed engines via the ``engine`` parameter, or installing additional IO dependencies, see:\nhttps://docs.xarray.dev/en/stable/getting-started-guide/installing.html\nhttps://docs.xarray.dev/en/stable/user-guide/io.html"
     ]
    }
   ],
   "source": [
    "import xarray as xr\n",
    "base_dir = \"/home/users/www_oggm/climate/wip/era5_daily/global\"\n",
    "_ds = xr.open_dataset(f'{base_dir}/ERA')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "74ed38ca-6281-4d2b-baf5-a8919f688f70",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python [conda env:oggm_env_2025]",
   "language": "python",
   "name": "conda-env-oggm_env_2025-py"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.14"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}