mfdataset_to_zarr.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Write National Water Model (NWM) model data to Zarr"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from dask.distributed import Client, progress, LocalCluster\n",
    "import pandas as pd\n",
    "import xarray as xr\n",
    "import s3fs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<table style=\"border: 2px solid white;\">\n",
       "<tr>\n",
       "<td style=\"vertical-align: top; border: 0px solid white\">\n",
       "<h3>Client</h3>\n",
       "<ul>\n",
       "  <li><b>Scheduler: </b>tcp://127.0.0.1:38824\n",
       "  <li><b>Dashboard: </b><a href='http://127.0.0.1:42695/status' target='_blank'>http://127.0.0.1:42695/status</a>\n",
       "</ul>\n",
       "</td>\n",
       "<td style=\"vertical-align: top; border: 0px solid white\">\n",
       "<h3>Cluster</h3>\n",
       "<ul>\n",
       "  <li><b>Workers: </b>2</li>\n",
       "  <li><b>Cores: </b>2</li>\n",
       "  <li><b>Memory: </b>8.37 GB</li>\n",
       "</ul>\n",
       "</td>\n",
       "</tr>\n",
       "</table>"
      ],
      "text/plain": [
       "<Client: scheduler='tcp://127.0.0.1:38824' processes=2 cores=2>"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# depends on the machine you are using\n",
    "cluster = LocalCluster()\n",
    "client = Client(cluster)\n",
    "\n",
    "client "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "root = 'http://tds.renci.org:8080/thredds/dodsC/nwm/forcing_short_range/'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "dates = pd.date_range(start='2018-04-07T18:00', end='2018-04-08T04:00', freq='H')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "urls = ['{}{}/nwm.t{}z.short_range.forcing.f001.conus.nc'.format(root,a.strftime('%Y%m%d'),a.strftime('%H')) for a in dates]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CPU times: user 480 ms, sys: 116 ms, total: 596 ms\n",
      "Wall time: 8.58 s\n"
     ]
    }
   ],
   "source": [
    "%%time \n",
    "ds = xr.open_mfdataset(urls,concat_dim='time')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "ds = ds.drop(['ProjectionCoordinateSystem'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<xarray.Dataset>\n",
       "Dimensions:         (nv: 2, reference_time: 11, time: 11, x: 4608, y: 3840)\n",
       "Coordinates:\n",
       "  * reference_time  (reference_time) datetime64[ns] 2018-04-07T18:00:00 ...\n",
       "  * x               (x) float64 -2.304e+06 -2.303e+06 -2.302e+06 -2.301e+06 ...\n",
       "  * y               (y) float64 -1.92e+06 -1.919e+06 -1.918e+06 -1.917e+06 ...\n",
       "  * time            (time) datetime64[ns] 2018-04-07T19:00:00 ...\n",
       "Dimensions without coordinates: nv\n",
       "Data variables:\n",
       "    time_bounds     (time, nv) datetime64[ns] dask.array<shape=(11, 2), chunksize=(1, 2)>\n",
       "    T2D             (time, y, x) float64 dask.array<shape=(11, 3840, 4608), chunksize=(1, 3840, 4608)>\n",
       "    LWDOWN          (time, y, x) float64 dask.array<shape=(11, 3840, 4608), chunksize=(1, 3840, 4608)>\n",
       "    Q2D             (time, y, x) float64 dask.array<shape=(11, 3840, 4608), chunksize=(1, 3840, 4608)>\n",
       "    U2D             (time, y, x) float64 dask.array<shape=(11, 3840, 4608), chunksize=(1, 3840, 4608)>\n",
       "    V2D             (time, y, x) float64 dask.array<shape=(11, 3840, 4608), chunksize=(1, 3840, 4608)>\n",
       "    PSFC            (time, y, x) float64 dask.array<shape=(11, 3840, 4608), chunksize=(1, 3840, 4608)>\n",
       "    RAINRATE        (time, y, x) float32 dask.array<shape=(11, 3840, 4608), chunksize=(1, 3840, 4608)>\n",
       "    SWDOWN          (time, y, x) float64 dask.array<shape=(11, 3840, 4608), chunksize=(1, 3840, 4608)>\n",
       "Attributes:\n",
       "    model_initialization_time:       2018-04-07_18:00:00\n",
       "    model_output_valid_time:         2018-04-07_19:00:00\n",
       "    DODS.strlen:                     0\n",
       "    DODS_EXTRA.Unlimited_Dimension:  time"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ds"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "fs = s3fs.S3FileSystem(anon=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "f_zarr = 'rsignell/nwm/test03'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "d = s3fs.S3Map(f_zarr, s3=fs)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CPU times: user 26.3 s, sys: 5.69 s, total: 32 s\n",
      "Wall time: 12min\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<xarray.backends.zarr.ZarrStore at 0x7fdc40044e10>"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "%time ds.to_zarr(store=d, mode='w')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Test to see if we can read what we wrote"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "ds2 = xr.open_zarr(d)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<xarray.Dataset>\n",
       "Dimensions:         (nv: 2, reference_time: 11, time: 11, x: 4608, y: 3840)\n",
       "Coordinates:\n",
       "  * reference_time  (reference_time) datetime64[ns] 2018-04-07T18:00:00 ...\n",
       "  * time            (time) datetime64[ns] 2018-04-07T19:00:00 ...\n",
       "  * x               (x) float64 -2.304e+06 -2.303e+06 -2.302e+06 -2.301e+06 ...\n",
       "  * y               (y) float64 -1.92e+06 -1.919e+06 -1.918e+06 -1.917e+06 ...\n",
       "Dimensions without coordinates: nv\n",
       "Data variables:\n",
       "    LWDOWN          (time, y, x) float64 dask.array<shape=(11, 3840, 4608), chunksize=(1, 3840, 4608)>\n",
       "    PSFC            (time, y, x) float64 dask.array<shape=(11, 3840, 4608), chunksize=(1, 3840, 4608)>\n",
       "    Q2D             (time, y, x) float64 dask.array<shape=(11, 3840, 4608), chunksize=(1, 3840, 4608)>\n",
       "    RAINRATE        (time, y, x) float32 dask.array<shape=(11, 3840, 4608), chunksize=(1, 3840, 4608)>\n",
       "    SWDOWN          (time, y, x) float64 dask.array<shape=(11, 3840, 4608), chunksize=(1, 3840, 4608)>\n",
       "    T2D             (time, y, x) float64 dask.array<shape=(11, 3840, 4608), chunksize=(1, 3840, 4608)>\n",
       "    U2D             (time, y, x) float64 dask.array<shape=(11, 3840, 4608), chunksize=(1, 3840, 4608)>\n",
       "    V2D             (time, y, x) float64 dask.array<shape=(11, 3840, 4608), chunksize=(1, 3840, 4608)>\n",
       "    time_bounds     (time, nv) datetime64[ns] dask.array<shape=(11, 2), chunksize=(11, 2)>\n",
       "Attributes:\n",
       "    DODS.strlen:                     0\n",
       "    DODS_EXTRA.Unlimited_Dimension:  time\n",
       "    model_initialization_time:       2018-04-07_18:00:00\n",
       "    model_output_valid_time:         2018-04-07_19:00:00"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ds2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python [default]",
   "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": "3.6.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}