Benchmarking different access patterns to MUR

mur-access-patterns.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "d5464971-75d2-4dfc-9af9-a773efa4f1a7",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "%pip install earthaccess[kerchunk]==0.8.2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "6ca826ed-ff77-475a-bb39-abe1e13a1d72",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "import xarray as xr\n",
    "import rasterio\n",
    "import rioxarray\n",
    "from pqdm.threads import pqdm\n",
    "import earthaccess\n",
    "import os\n",
    "from timebudget import timebudget\n",
    "from pathlib import Path\n",
    "from dask.distributed import LocalCluster\n",
    "\n",
    "\n",
    "# assumes we have a ~/.netrc created\n",
    "\n",
    "cookies = os.path.expanduser(\"~/.urs_cookies\")\n",
    "Path(cookies).touch()\n",
    "\n",
    "auth = earthaccess.login()    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "3a3169b2-6502-4eaf-b9fb-0be9363f08a2",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Granules found: 31\n"
     ]
    }
   ],
   "source": [
    "dataset=\"MUR-JPL-L4-GLOB-v4.1\",\n",
    "\n",
    "results = earthaccess.search_data(\n",
    "    short_name=dataset,\n",
    "    temporal=(\"2019-01-01\", \"2019-01-31\"),\n",
    ")\n",
    "\n",
    "data_links = [granule.data_links(access=\"external\") for granule in results]\n",
    "url_links = [f'{link[0]}' for link in data_links]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "e9110b4e-d375-441d-8934-589395d4471a",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "# kerchunking with earthaccess\n",
    "if __name__ == \"__main__\":\n",
    "    # Create a local Dask cluster for parallel metadata consolidation\n",
    "    # (but works with any Dask cluster)\n",
    "    cluster = LocalCluster()\n",
    "    client = cluster.get_client()\n",
    "    # needs a progressbar! \n",
    "    outfile = earthaccess.consolidate_metadata(\n",
    "        results,\n",
    "        outfile=f\"./direct-mur-metadata.json\",    # Writing to a local file for demo purposes\n",
    "        # outfile=f\"s3://my-bucket/{short_name}-metadata.json\",   # We could also write to a remote file\n",
    "        access=\"direct\",\n",
    "        # kerchunk_options={\"coo_map\": []}\n",
    "        kerchunk_options={\"concat_dims\": \"time\"}\n",
    "    )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "9dec9fe7-ac0e-446e-8eeb-b8b3d3ac4ad8",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "@timebudget\n",
    "def via_gdalvsi():\n",
    "  with rasterio.Env(GDAL_HTTP_COOKIEFILE=cookies, \n",
    "                    GDAL_HTTP_COOKIEJAR=cookies, \n",
    "                    GDAL_HTTP_NETRC=True):\n",
    "    ds = xr.open_mfdataset(url_links, engine = \"rasterio\", decode_times=False, parallel=True)\n",
    "    return(ds)\n",
    "\n",
    "@timebudget\n",
    "def via_earthaccess():\n",
    "    files = earthaccess.open(results)\n",
    "    # using Paralllel=True actually slows things down here, serialization overhead? bug in xarray?\n",
    "    ds = xr.open_mfdataset(files, engine=\"h5netcdf\", decode_times=False) \n",
    "    return(ds)\n",
    "\n",
    "@timebudget\n",
    "def via_earthaccess_kerchunk():\n",
    "    fs = earthaccess.get_s3fs_session(\"GES_DISC\")\n",
    "    ds = xr.open_dataset(\n",
    "        \"reference://\",\n",
    "        engine=\"zarr\",\n",
    "        chunks={},\n",
    "        decode_coords=False, # tricky, the coords are there but encoded in a way xarray can't decode for some reason. Similar to https://github.com/fsspec/kerchunk/issues/177\n",
    "        backend_kwargs={\n",
    "            \"consolidated\": False,\n",
    "            \"storage_options\": {\n",
    "                \"fo\": \"direct-mur-metadata.json\",\n",
    "                \"remote_protocol\": \"s3\",\n",
    "                \"remote_options\": fs.storage_options,\n",
    "            }\n",
    "        },\n",
    "    )\n",
    "    return(ds)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "31904fe7-3137-48ab-9fb6-5ef4025fc2fc",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/srv/conda/envs/notebook/lib/python3.10/site-packages/rioxarray/_io.py:1132: NotGeoreferencedWarning: Dataset has no geotransform, gcps, or rpcs. The identity matrix will be returned.\n",
      "  warnings.warn(str(rio_warning.message), type(rio_warning.message))  # type: ignore\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "via_gdalvsi took 54.563sec\n"
     ]
    }
   ],
   "source": [
    "# And here we go!\n",
    "ds1 = via_gdalvsi()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "eefdf990-5435-411f-a04d-ff0015502ea8",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Opening 31 granules, approx size: 11.63 GB\n",
      "using endpoint: https://archive.podaac.earthdata.nasa.gov/s3credentials\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "022baa89fcb748ad9da897e77e8ef117",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "QUEUEING TASKS | :   0%|          | 0/31 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "09902662053945048ad8afbaa5f05caf",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "PROCESSING TASKS | :   0%|          | 0/31 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "9407c01469da4e33a086a397636417d1",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "COLLECTING RESULTS | :   0%|          | 0/31 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "via_earthaccess took 12.264sec\n"
     ]
    }
   ],
   "source": [
    "ds2 = via_earthaccess()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "93835307-1c2a-4aff-ab02-2dad31f97cc6",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "via_earthaccess_kerchunk took 3.393sec\n"
     ]
    }
   ],
   "source": [
    "ds3 = via_earthaccess_kerchunk()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.10.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}