Wrapping Raster to Xarray+Dask

Warp_Xarray.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "import xarray as xr\n",
    "xr.set_options(display_style='text')\n",
    "import rasterio\n",
    "from rasterio import crs, MemoryFile\n",
    "from rasterio.vrt import WarpedVRT\n",
    "from rasterio.shutil import copy as rio_copy\n",
    "import rioxarray\n",
    "from dask.distributed import LocalCluster,Client,performance_report,wait"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "distributed.comm.tcp - WARNING - Could not set timeout on TCP stream: [Errno 92] Protocol not available\n",
      "distributed.comm.tcp - WARNING - Could not set timeout on TCP stream: [Errno 92] Protocol not available\n",
      "distributed.comm.tcp - WARNING - Could not set timeout on TCP stream: [Errno 92] Protocol not available\n",
      "distributed.comm.tcp - WARNING - Could not set timeout on TCP stream: [Errno 92] Protocol not available\n",
      "distributed.comm.tcp - WARNING - Could not set timeout on TCP stream: [Errno 92] Protocol not available\n",
      "distributed.comm.tcp - WARNING - Could not set timeout on TCP stream: [Errno 92] Protocol not available\n",
      "distributed.comm.tcp - WARNING - Could not set timeout on TCP stream: [Errno 92] Protocol not available\n",
      "distributed.comm.tcp - WARNING - Could not set timeout on TCP stream: [Errno 92] Protocol not available\n",
      "distributed.comm.tcp - WARNING - Could not set timeout on TCP stream: [Errno 92] Protocol not available\n",
      "distributed.comm.tcp - WARNING - Could not set timeout on TCP stream: [Errno 92] Protocol not available\n",
      "distributed.comm.tcp - WARNING - Could not set timeout on TCP stream: [Errno 92] Protocol not available\n",
      "distributed.comm.tcp - WARNING - Could not set timeout on TCP stream: [Errno 92] Protocol not available\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<table style=\"border: 2px solid white;\">\n",
       "<tr>\n",
       "<td style=\"vertical-align: top; border: 0px solid white\">\n",
       "<h3 style=\"text-align: left;\">Client</h3>\n",
       "<ul style=\"text-align: left; list-style: none; margin: 0; padding: 0;\">\n",
       "  <li><b>Scheduler: </b>tcp://127.0.0.1:54562</li>\n",
       "  <li><b>Dashboard: </b><a href='http://127.0.0.1:8787/status' target='_blank'>http://127.0.0.1:8787/status</a></li>\n",
       "</ul>\n",
       "</td>\n",
       "<td style=\"vertical-align: top; border: 0px solid white\">\n",
       "<h3 style=\"text-align: left;\">Cluster</h3>\n",
       "<ul style=\"text-align: left; list-style:none; margin: 0; padding: 0;\">\n",
       "  <li><b>Workers: </b>6</li>\n",
       "  <li><b>Cores: </b>12</li>\n",
       "  <li><b>Memory: </b>34.10 GB</li>\n",
       "</ul>\n",
       "</td>\n",
       "</tr>\n",
       "</table>"
      ],
      "text/plain": [
       "<Client: 'tcp://127.0.0.1:54562' processes=6 threads=12, memory=34.10 GB>"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "clust = LocalCluster(n_workers=6,threads_per_worker=2,dashboard_address=':8787')\n",
    "cl = Client(clust)\n",
    "cl"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Source CRS:EPSG:32613\n",
      "Destination CRS:EPSG:4326\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<pre>&lt;xarray.Dataset&gt;\n",
       "Dimensions:      (band: 1, x: 4194, y: 3081)\n",
       "Coordinates:\n",
       "  * band         (band) int64 1\n",
       "  * y            (y) float64 43.35 43.35 43.35 43.35 ... 42.36 42.36 42.36 42.36\n",
       "  * x            (x) float64 -106.2 -106.2 -106.2 ... -104.9 -104.9 -104.9\n",
       "    spatial_ref  int64 0\n",
       "Data variables:\n",
       "    HLS_Red      (band, y, x) int16 dask.array&lt;chunksize=(1, 1500, 1500), meta=np.ndarray&gt;</pre>"
      ],
      "text/plain": [
       "<xarray.Dataset>\n",
       "Dimensions:      (band: 1, x: 4194, y: 3081)\n",
       "Coordinates:\n",
       "  * band         (band) int64 1\n",
       "  * y            (y) float64 43.35 43.35 43.35 43.35 ... 42.36 42.36 42.36 42.36\n",
       "  * x            (x) float64 -106.2 -106.2 -106.2 ... -104.9 -104.9 -104.9\n",
       "    spatial_ref  int64 0\n",
       "Data variables:\n",
       "    HLS_Red      (band, y, x) int16 dask.array<chunksize=(1, 1500, 1500), meta=np.ndarray>"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "f = 'https://hlssa.blob.core.windows.net/hls/L309/HLS.L30.T13TDH.2019165.v1.4_04.tif'\n",
    "epsg_to = 4326\n",
    "with rasterio.open(f) as src:\n",
    "    print('Source CRS:' +str(src.crs))\n",
    "    with WarpedVRT(src,resampling=1,src_crs=src.crs,crs=crs.CRS.from_epsg(epsg_to),warp_mem_limit=12000,warp_extras={'NUM_THREADS':2}) as vrt:\n",
    "        print('Destination CRS:' +str(vrt.crs))\n",
    "        ds = rioxarray.open_rasterio(vrt).chunk({'x':1500,'y':1500,'band':1}).to_dataset(name='HLS_Red')\n",
    "ds"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "distributed.comm.tcp - WARNING - Could not set timeout on TCP stream: [Errno 92] Protocol not available\n",
      "distributed.comm.tcp - WARNING - Could not set timeout on TCP stream: [Errno 92] Protocol not available\n",
      "distributed.comm.tcp - WARNING - Could not set timeout on TCP stream: [Errno 92] Protocol not available\n",
      "distributed.comm.tcp - WARNING - Could not set timeout on TCP stream: [Errno 92] Protocol not available\n",
      "distributed.comm.tcp - WARNING - Could not set timeout on TCP stream: [Errno 92] Protocol not available\n",
      "distributed.comm.tcp - WARNING - Could not set timeout on TCP stream: [Errno 92] Protocol not available\n",
      "distributed.comm.tcp - WARNING - Could not set timeout on TCP stream: [Errno 92] Protocol not available\n",
      "distributed.comm.tcp - WARNING - Could not set timeout on TCP stream: [Errno 92] Protocol not available\n",
      "distributed.comm.tcp - WARNING - Could not set timeout on TCP stream: [Errno 92] Protocol not available\n",
      "distributed.comm.tcp - WARNING - Could not set timeout on TCP stream: [Errno 92] Protocol not available\n",
      "distributed.comm.tcp - WARNING - Could not set timeout on TCP stream: [Errno 92] Protocol not available\n",
      "distributed.comm.tcp - WARNING - Could not set timeout on TCP stream: [Errno 92] Protocol not available\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<pre>&lt;xarray.Dataset&gt;\n",
       "Dimensions:      (band: 1, x: 4194, y: 3081)\n",
       "Coordinates:\n",
       "  * band         (band) int64 1\n",
       "  * y            (y) float64 43.35 43.35 43.35 43.35 ... 42.36 42.36 42.36 42.36\n",
       "  * x            (x) float64 -106.2 -106.2 -106.2 ... -104.9 -104.9 -104.9\n",
       "    spatial_ref  int64 0\n",
       "Data variables:\n",
       "    HLS_Red      (band, y, x) int16 dask.array&lt;chunksize=(1, 1500, 1500), meta=np.ndarray&gt;</pre>"
      ],
      "text/plain": [
       "<xarray.Dataset>\n",
       "Dimensions:      (band: 1, x: 4194, y: 3081)\n",
       "Coordinates:\n",
       "  * band         (band) int64 1\n",
       "  * y            (y) float64 43.35 43.35 43.35 43.35 ... 42.36 42.36 42.36 42.36\n",
       "  * x            (x) float64 -106.2 -106.2 -106.2 ... -104.9 -104.9 -104.9\n",
       "    spatial_ref  int64 0\n",
       "Data variables:\n",
       "    HLS_Red      (band, y, x) int16 dask.array<chunksize=(1, 1500, 1500), meta=np.ndarray>"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "with performance_report(filename='xr_wrap.html'):\n",
    "    ds = ds.persist()\n",
    "    wait(ds)\n",
    "ds"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python [conda env:py_geo]",
   "language": "python",
   "name": "conda-env-py_geo-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": "3.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}