nwm_roundtrip.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "63feb1dd-3cce-4d10-baf3-eef39665dfb2",
   "metadata": {},
   "source": [
    "#### Encoding for streamflow from single NetCDF file from S3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "f7e649d6-f4db-452d-a1bc-11ee19cfeaba",
   "metadata": {},
   "outputs": [],
   "source": [
    "import xarray as xr\n",
    "import fsspec"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "94dbcce5-1dfe-4ce7-a7bc-2adadde2149a",
   "metadata": {},
   "outputs": [],
   "source": [
    "url = 's3://noaa-nwm-retrospective-2-1-pds/model_output/2020/202001011100.CHRTOUT_DOMAIN1.comp'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "b2e7adcc-f5bd-4472-b768-a34f1e099794",
   "metadata": {},
   "outputs": [],
   "source": [
    "fs = fsspec.filesystem('s3', anon=True)\n",
    "ds = xr.open_dataset(fs.open(url), drop_variables='reference_time', chunks={})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "e8f1a977-b166-4194-a055-e614ee837e62",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'chunksizes': (2776738,),\n",
       " 'fletcher32': False,\n",
       " 'shuffle': False,\n",
       " 'zlib': True,\n",
       " 'complevel': 2,\n",
       " 'source': '<File-like object S3FileSystem, noaa-nwm-retrospective-2-1-pds/model_output/2020/202001011100.CHRTOUT_DOMAIN1.comp>',\n",
       " 'original_shape': (2776738,),\n",
       " 'dtype': dtype('int32'),\n",
       " 'missing_value': array([-999900], dtype=int32),\n",
       " '_FillValue': array([-999900], dtype=int32),\n",
       " 'scale_factor': array([0.01], dtype=float32),\n",
       " 'add_offset': array([0.], dtype=float32),\n",
       " 'coordinates': 'latitude longitude'}"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ds.streamflow.encoding"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "87a58f92-796b-404e-958c-4b6015d9421d",
   "metadata": {},
   "outputs": [],
   "source": [
    "ds.to_netcdf('roundtrip.nc', mode='w')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "a2975878-a7d7-4ec5-a68d-09aa8804aaf1",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'zlib': True,\n",
       " 'shuffle': False,\n",
       " 'complevel': 2,\n",
       " 'fletcher32': False,\n",
       " 'contiguous': False,\n",
       " 'chunksizes': (2776738,),\n",
       " 'source': '/home/shared/users/rsignell/notebooks/NWM/roundtrip.nc',\n",
       " 'original_shape': (2776738,),\n",
       " 'dtype': dtype('int32'),\n",
       " 'missing_value': -999900,\n",
       " '_FillValue': -999900,\n",
       " 'scale_factor': 0.01,\n",
       " 'add_offset': 0.0,\n",
       " 'coordinates': 'latitude longitude'}"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "xr.open_dataset('roundtrip.nc').streamflow.encoding"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python [conda env:pangeo]",
   "language": "python",
   "name": "conda-env-pangeo-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": "3.8.10"
  },
  "widgets": {
   "application/vnd.jupyter.widget-state+json": {
    "state": {},
    "version_major": 2,
    "version_minor": 0
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}