R_read_netcdf.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Goals\n",
    "This notebook explains how to open a netcdf file, read metadata, and read variables in R. \n",
    "- 'RNetCDF' library is used. More information is available at # https://github.com/mjwoods/RNetCDF\n",
    "- Man pages for RNetCDF is available at https://rdrr.io/cran/RNetCDF/man/\n",
    "\n",
    "## Prerequisite\n",
    "Make sure you have access to the directory where netCDF files exist. \n",
    "- This notebook reads netcdf files stored in /depot/ssg/geoshare/data/GLASS/INFEWS/"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[1] \"/depot/ssg/geoshare/data/GLASS/INFEWS/DOE_Flood/historical/MPI-ESM-LR.WRF.day.NAM-22i.mbcn-gridMET/daily/daily/wbm_1950.nc\"\n",
      "[1] 65536\n",
      "attr(,\"handle_ptr\")\n",
      "<pointer: 0x445ae60>\n",
      "attr(,\"class\")\n",
      "[1] \"NetCDF\"\n"
     ]
    }
   ],
   "source": [
    "library('RNetCDF')\n",
    "\n",
    "\n",
    "# set path and filename\n",
    "ncpath <- \"/depot/ssg/geoshare/data/GLASS/INFEWS/DOE_Flood/historical/MPI-ESM-LR.WRF.day.NAM-22i.mbcn-gridMET/daily/daily/\"\n",
    "ncname <- \"wbm_1950\"\n",
    "ncfname <- paste(ncpath, ncname, \".nc\", sep=\"\")\n",
    "print(ncfname)\n",
    "\n",
    "# open a netCDF file\n",
    "ncin <- open.nc(ncfname, write=FALSE)\n",
    "print(ncin)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## print.nc: Print Summary Information About a NetCDF Dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "netcdf netcdf4 {\n",
      "dimensions:\n",
      "\ttime = UNLIMITED ; // (365 currently)\n",
      "\tlat = 425 ;\n",
      "\tlon = 807 ;\n",
      "variables:\n",
      "\tNC_INT time(time) ;\n",
      "\t\tNC_CHAR time:long_name = \"Time\" ;\n",
      "\t\tNC_CHAR time:units = \"days since 1900-01-01\" ;\n",
      "\t\tNC_CHAR time:calendar = \"standard\" ;\n",
      "\t\tNC_CHAR time:resolution = \"daily\" ;\n",
      "\tNC_DOUBLE lat(lat) ;\n",
      "\t\tNC_CHAR lat:standard_name = \"latitude\" ;\n",
      "\t\tNC_CHAR lat:long_name = \"latitude\" ;\n",
      "\t\tNC_CHAR lat:units = \"degrees_north\" ;\n",
      "\tNC_DOUBLE lon(lon) ;\n",
      "\t\tNC_CHAR lon:units = \"degrees_east\" ;\n",
      "\t\tNC_CHAR lon:long_name = \"longitude\" ;\n",
      "\t\tNC_CHAR lon:standard_name = \"longitude\" ;\n",
      "\tNC_CHAR crs ;\n",
      "\t\tNC_CHAR crs:srs_ref = \"epsg:4326\" ;\n",
      "\t\tNC_CHAR crs:spatial_ref = \"GEOGCS[\"WGS 84\",DATUM[\"WGS_1984\",SPHEROID[\"WGS 84\",6378137,298.257223563,AUTHORITY[\"EPSG\",\"7030\"]],AUTHORITY[\"EPSG\",\"6326\"]],PRIMEM[\"Greenwich\",0,AUTHORITY[\"EPSG\",\"8901\"]],UNIT[\"degree\",0.0174532925199433,AUTHORITY[\"EPSG\",\"9122\"]],AXIS[\"Latitude\",NORTH],AXIS[\"Longitude\",EAST],AUTHORITY[\"EPSG\",\"4326\"]]\" ;\n",
      "\t\tNC_CHAR crs:GeoTransform = \"-127.83333333333 0.083333333333 0 57.166666666525 0 -0.083333333333\" ;\n",
      "\t\tNC_CHAR crs:srs_wkt = \"GEOGCS[\"WGS 84\",DATUM[\"WGS_1984\",SPHEROID[\"WGS 84\",6378137,298.257223563,AUTHORITY[\"EPSG\",\"7030\"]],AUTHORITY[\"EPSG\",\"6326\"]],PRIMEM[\"Greenwich\",0,AUTHORITY[\"EPSG\",\"8901\"]],UNIT[\"degree\",0.0174532925199433,AUTHORITY[\"EPSG\",\"9122\"]],AXIS[\"Latitude\",NORTH],AXIS[\"Longitude\",EAST],AUTHORITY[\"EPSG\",\"4326\"]]\" ;\n",
      "\tNC_FLOAT runoff(lon, lat, time) ;\n",
      "\t\tNC_FLOAT runoff:_FillValue = -9999 ;\n",
      "\t\tNC_CHAR runoff:grid_mapping = \"crs\" ;\n",
      "\t\tNC_CHAR runoff:long_name = \"Runoff\" ;\n",
      "\t\tNC_FLOAT runoff:missing_value = -9999 ;\n",
      "\t\tNC_CHAR runoff:reference_area = \"full grid cell area\" ;\n",
      "\t\tNC_CHAR runoff:units = \"mm/day\" ;\n",
      "\tNC_FLOAT discharge(lon, lat, time) ;\n",
      "\t\tNC_CHAR discharge:grid_mapping = \"crs\" ;\n",
      "\t\tNC_CHAR discharge:long_name = \"Discharge by LRR routing\" ;\n",
      "\t\tNC_FLOAT discharge:missing_value = -9999 ;\n",
      "\t\tNC_CHAR discharge:units = \"m3/sec\" ;\n",
      "\tNC_FLOAT baseflow(lon, lat, time) ;\n",
      "\t\tNC_CHAR baseflow:grid_mapping = \"crs\" ;\n",
      "\t\tNC_CHAR baseflow:long_name = \"Baseflow\" ;\n",
      "\t\tNC_FLOAT baseflow:missing_value = -9999 ;\n",
      "\t\tNC_CHAR baseflow:reference_area = \"full grid cell area\" ;\n",
      "\t\tNC_CHAR baseflow:units = \"mm/day\" ;\n",
      "\tNC_FLOAT airT(lon, lat, time) ;\n",
      "\t\tNC_CHAR airT:grid_mapping = \"crs\" ;\n",
      "\t\tNC_CHAR airT:long_name = \"Temperature\" ;\n",
      "\t\tNC_FLOAT airT:missing_value = -9999 ;\n",
      "\t\tNC_CHAR airT:units = \"deg C\" ;\n",
      "\tNC_FLOAT precip(lon, lat, time) ;\n",
      "\t\tNC_CHAR precip:grid_mapping = \"crs\" ;\n",
      "\t\tNC_CHAR precip:long_name = \"Precipitation\" ;\n",
      "\t\tNC_FLOAT precip:missing_value = -9999 ;\n",
      "\t\tNC_CHAR precip:units = \"mm/day\" ;\n",
      "\n",
      "// global attributes:\n",
      "\t\tNC_CHAR :Conventions = \"CF-1.6\" ;\n",
      "\t\tNC_CHAR :history = \"Created on 2021-04-18 by Danielle Grogan (Danielle.Grogan@unh.edu)\" ;\n",
      "\t\tNC_CHAR :NetCDF_version = \"NetCDF.4.21\" ;\n",
      "\t\tNC_CHAR :institution = \"Water Systems Analysis Group (WSAG), the University of New Hampshire (UNH)\" ;\n",
      "\t\tNC_CHAR :FilePath = \"/net/nfs/squam/raid/data/WBM_TrANS/DOE_Flood/historical/MPI-ESM-LR.WRF.day.NAM-22i.mbcn-gridMET/daily/wbm_1950.nc\" ;\n",
      "\t\tNC_CHAR :title = \"WBM-TrANS data\" ;\n",
      "\t\tNC_CHAR :Projection = \"epsg:4326\" ;\n",
      "\t\tNC_CHAR :WBM_VERSION = \"21.3.2\" ;\n",
      "\t\tNC_CHAR :PDL_VERSION = \"2.019\" ;\n",
      "\t\tNC_CHAR :PERL_VERSION = \"5.026001\" ;\n",
      "\t\tNC_CHAR :GDAL_VERSION = \"GDAL 3.0.0, released 2019/05/05\" ;\n",
      "\t\tNC_CHAR :WBM_RUN_ID = \"flood_MPI-ESM-LR.WRF.day.NAM-22i.mbcn-gridMET_historical\" ;\n",
      "\t\tNC_CHAR :WBM_RUN_Init = \"/net/nfs/zero/data3/WBM_TrANS/wbm_run_files/Projects/DOE_Flood/flood_MPI-ESM-LR.WRF.day.NAM-22i.mbcn-gridMET_historical.init\" ;\n",
      "\t\tNC_CHAR :WBM_Start_time = \"2021-04-17 at 10:30:32\" ;\n",
      "\t\tNC_CHAR :SYSTEM_NAME = \"yukon\" ;\n",
      "\t\tNC_CHAR :Script_dir = \"/net/home/eos/dgrogan/wbm_repos/wbm_trans/\" ;\n",
      "\t\tNC_CHAR :runIO_Comment = \"CONUS flood simulations for DOE project with Purdue\" ;\n",
      "\t\tNC_CHAR :runIO_Project = \"DOE\" ;\n",
      "\t\tNC_CHAR :runIO_MT_Code_Name = \"{MT_ID => 'flood_MPI-ESM-LR.WRF.day.NAM-22i.mbcn-gridMET_historical',Output_dir => '/net/nfs/squam/raid/data/WBM_TrANS/DOE_Flood/historical/MPI-ESM-LR.WRF.day.NAM-22i.mbcn-gridMET/',Run_End => '2005-12-31',Run_Start => '1950-01-01'}\" ;\n",
      "\t\tNC_CHAR :runIO_spinup_state_ID = \"\" ;\n",
      "\t\tNC_CHAR :runIO_Spinup_Loops = \"6\" ;\n",
      "\t\tNC_CHAR :runIO_Spinup_Start = \"1950-01-01\" ;\n",
      "\t\tNC_CHAR :runIO_Spinup_End = \"1954-12-31\" ;\n",
      "\t\tNC_CHAR :runIO_Output_vars = \"runoff discharge baseflow airT precip\" ;\n",
      "\t\tNC_CHAR :runIO_MT_Precip = \"{Primary => 'prec.hist.MPI-ESM-LR.WRF.day.NAM-22i.mbcn-gridMET_d'}\" ;\n",
      "\t\tNC_CHAR :runIO_precipFraction = \"\" ;\n",
      "\t\tNC_CHAR :runIO_MT_airT = \"{Primary => 'tmean.hist.MPI-ESM-LR.WRF.day.NAM-22i.mbcn-gridMET_d'}\" ;\n",
      "\t\tNC_CHAR :runIO_Network = \"/net/nfs/zero/data3/WBM_TrANS/data/hyd_5m_CONUS_mississippi_patched.asc\" ;\n",
      "\t\tNC_CHAR :runIO_Routing = \"LRR\" ;\n",
      "\t\tNC_CHAR :runIO_wbmParam = \"\" ;\n",
      "\t\tNC_CHAR :runIO_ConnectivityNetwork = \"\" ;\n",
      "\t\tNC_CHAR :runIO_Reservoirs = \"/net/nfs/zero/home/WBM_TrANS/data_init_files/dams/HydConDams_NAmer_v0.2c.init\" ;\n",
      "\t\tNC_CHAR :runIO_soilAWCapacity = \"NETCDF:/net/nfs/zero/home/WBM_TrANS/data/HarmSoilData/Harmonized-SoilMap_AWC-mm_6min.nc:Band1\" ;\n",
      "\t\tNC_CHAR :runIO_FieldCap = \"\" ;\n",
      "\t\tNC_CHAR :runIO_WiltingPoint = \"\" ;\n",
      "\t\tNC_CHAR :runIO_rootingDepth = \"NETCDF:/net/nfs/zero/home/WBM_TrANS/data/Global_Terrain_RootDepthWBM_LTXXXX_30min.nc:STNetwork\" ;\n",
      "\t\tNC_CHAR :runIO_PET = \"\" ;\n",
      "\t\tNC_CHAR :runIO_MT_windU = \"\" ;\n",
      "\t\tNC_CHAR :runIO_MT_windV = \"\" ;\n",
      "\t\tNC_CHAR :runIO_MT_cloudFr = \"\" ;\n",
      "\t\tNC_CHAR :runIO_MT_humidity = \"\" ;\n",
      "\t\tNC_CHAR :runIO_MT_albedo = \"\" ;\n",
      "\t\tNC_CHAR :runIO_airT_yc = \"\" ;\n",
      "\t\tNC_CHAR :runIO_openWaterEvap = \"\" ;\n",
      "\t\tNC_CHAR :runIO_Glaciers = \"\" ;\n",
      "\t\tNC_CHAR :runIO_Aquifers = \"\" ;\n",
      "\t\tNC_CHAR :runIO_Springs = \"\" ;\n",
      "\t\tNC_CHAR :runIO_snowBands = \"\" ;\n",
      "\t\tNC_CHAR :runIO_lapseDownscale = \"\" ;\n",
      "\t\tNC_CHAR :runIO_DIN = \"\" ;\n",
      "\t\tNC_CHAR :runIO_Runoff_mask = \"\" ;\n",
      "\t\tNC_CHAR :runIO_Impervious = \"/net/nfs/ipswich/raid/atlas/data/impervious/imp.asc\" ;\n",
      "\t\tNC_CHAR :runIO_openWater = \"{MaskDataset => '/net/nfs/ipswich/raid/atlas/data/UMD_landcover/zero_6min.tif',openWaterMaskValue => 0}\" ;\n",
      "\t\tNC_CHAR :runIO_canopyHt = \"\" ;\n",
      "\t\tNC_CHAR :runIO_MT_LAI = \"\" ;\n",
      "\t\tNC_CHAR :runIO_WaterDemand = \"\" ;\n",
      "\t\tNC_CHAR :runIO_landCollapse = \"average\" ;\n",
      "\t\tNC_CHAR :runIO_LandCover = \"\" ;\n",
      "\t\tNC_CHAR :runIO_Irrigation = \"{CropAreaFrac => '/net/nfs/squam/raid/data/GLEAM/GAEZ_crop_frac/GAEZ_Pasture_Total.tif',CropParFile => '/net/nfs/zero/data3/WBM_TrANS/spreadsheets/GAEZ-2010_CropParameters_Pasture.csv',ExtraCoeff => 1,IrrEfficiency => 'NETCDF:/net/nfs/zero/data3/WBM_TrANS/data/Global_Crops_IrrEfficiencyGlobalExtent_30min.nc:IrrEfficiency',Order => 1,ReturnCoeff => '0.5',SW_GW_ratio => 'NETCDF:/net/nfs/zero/data3/WBM_TrANS/data/FAO_SWGW_ratio.nc:swgwRatio',SearchDist => 100,ricePaddyDepth => 50,ricePercolation => 'NETCDF:/net/nfs/zero/data3/WBM_TrANS/data/RicePercolationRate.nc:RicePercolationRate'}\" ;\n",
      "\t\tNC_CHAR :runIO_WM_mod_precip = \"\" ;\n",
      "\t\tNC_CHAR :runIO_WM_obs_precip = \"\" ;\n",
      "\t\tNC_CHAR :runIO_WM_mod_airT = \"\" ;\n",
      "\t\tNC_CHAR :runIO_WM_obs_airT = \"\" ;\n",
      "\t\tNC_CHAR :runIO_PostProcessing = \"{Forks => 8,Polygon_Aggregation => '',Run => '',TA_multi_year_start => '',TA_multi_year_timestep => '',Temporal_Aggregation => ''}\" ;\n",
      "\t\tNC_CHAR :runIO_WaterRights = \"\" ;\n",
      "\t\tNC_CHAR :runIO_USGS = \"\" ;\n",
      "\t\tNC_CHAR :runIO_spool = \"/net/nfs/yukon/WBM_spool/hyd_5m_CONUS_mississippi_patched/\" ;\n",
      "\t\tNC_CHAR :runIO_Output_TS = \"daily\" ;\n",
      "\t\tNC_CHAR :runIO_Run_Start = \"1950-01-01\" ;\n",
      "\t\tNC_CHAR :runIO_Run_End = \"2005-12-31\" ;\n",
      "\t\tNC_CHAR :runIO_Output_dir = \"/net/nfs/squam/raid/data/WBM_TrANS/DOE_Flood/historical/MPI-ESM-LR.WRF.day.NAM-22i.mbcn-gridMET\" ;\n",
      "\t\tNC_CHAR :runIO_Input_MT = \"/net/nfs/yukon/raid0/data/RIMS/MagicTable/CGI_Names.csv\" ;\n",
      "\t\tNC_CHAR :runIO_Output_MT = \"/net/nfs/squam/raid/data/WBM_TrANS/DOE_Flood/historical/MPI-ESM-LR.WRF.day.NAM-22i.mbcn-gridMET/flood_MPI-ESM-LR.WRF.day.NAM-22i.mbcn-gridMET_historical.MT.csv\" ;\n",
      "}\n"
     ]
    }
   ],
   "source": [
    "print.nc(ncin)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<dl>\n",
       "\t<dt>$ndims</dt>\n",
       "\t\t<dd>3</dd>\n",
       "\t<dt>$nvars</dt>\n",
       "\t\t<dd>9</dd>\n",
       "\t<dt>$ngatts</dt>\n",
       "\t\t<dd>73</dd>\n",
       "\t<dt>$unlimdimid</dt>\n",
       "\t\t<dd>0</dd>\n",
       "\t<dt>$format</dt>\n",
       "\t\t<dd>'netcdf4'</dd>\n",
       "\t<dt>$libvers</dt>\n",
       "\t\t<dd>'4.5.0 of Apr 26 2020 03:53:51 $'</dd>\n",
       "</dl>\n"
      ],
      "text/latex": [
       "\\begin{description}\n",
       "\\item[\\$ndims] 3\n",
       "\\item[\\$nvars] 9\n",
       "\\item[\\$ngatts] 73\n",
       "\\item[\\$unlimdimid] 0\n",
       "\\item[\\$format] 'netcdf4'\n",
       "\\item[\\$libvers] '4.5.0 of Apr 26 2020 03:53:51 \\$'\n",
       "\\end{description}\n"
      ],
      "text/markdown": [
       "$ndims\n",
       ":   3\n",
       "$nvars\n",
       ":   9\n",
       "$ngatts\n",
       ":   73\n",
       "$unlimdimid\n",
       ":   0\n",
       "$format\n",
       ":   'netcdf4'\n",
       "$libvers\n",
       ":   '4.5.0 of Apr 26 2020 03:53:51 $'\n",
       "\n",
       "\n"
      ],
      "text/plain": [
       "$ndims\n",
       "[1] 3\n",
       "\n",
       "$nvars\n",
       "[1] 9\n",
       "\n",
       "$ngatts\n",
       "[1] 73\n",
       "\n",
       "$unlimdimid\n",
       "[1] 0\n",
       "\n",
       "$format\n",
       "[1] \"netcdf4\"\n",
       "\n",
       "$libvers\n",
       "[1] \"4.5.0 of Apr 26 2020 03:53:51 $\"\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "##  Inquire about the dataset\n",
    "file.inq.nc(ncin)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## dim.inq.nc: Inquire About a NetCDF Dimension\n",
    "\n",
    "This function returns information about a NetCDF dimension. Information about a dimension include its name, its ID, its length and a flag if it is the unlimited dimension of this NetCDF dataset, if any. The length of the unlimited dimension, if any, is the number of records written so far."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "$id\n",
      "[1] 0\n",
      "\n",
      "$name\n",
      "[1] \"time\"\n",
      "\n",
      "$length\n",
      "[1] 365\n",
      "\n",
      "$unlim\n",
      "[1] TRUE\n",
      "\n"
     ]
    }
   ],
   "source": [
    "##  Inquire about the dimensions\n",
    "print(dim.inq.nc(ncin, 0))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Create output directory if not exist\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[1] \"Dir already exists!\"\n"
     ]
    }
   ],
   "source": [
    "## Provide the dir name(i.e sub dir) that you want to create under main dir:\n",
    "main_dir <- \".\"\n",
    "sub_dir <- \"OUTPUT\"\n",
    "output_dir <- file.path(main_dir, sub_dir)\n",
    "\n",
    "if (!dir.exists(output_dir)){\n",
    "    dir.create(output_dir)\n",
    "} else {\n",
    "    print(\"Dir already exists!\")\n",
    "}\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Write to a file \n",
    "\n",
    "We can redirect the standard output to another file-like object by changing the stdout object. However, for convenience we can do this directly from within the print() function by specifying the output location with the file parameter"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[1] \"./OUTPUT/out.r.txt\"\n"
     ]
    }
   ],
   "source": [
    "filename <- 'out.r.txt'\n",
    "output_file <- paste(output_dir, filename, sep='/' )\n",
    "print(output_file)\n",
    "# write to a file\n",
    "# Save the print(nc) dump to a text file\n",
    "{\n",
    "    sink(output_file)\n",
    "    print.nc(ncin)\n",
    "    sink()\n",
    "}\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Cleanup"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "close.nc(ncin)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "R 4.0.0",
   "language": "R",
   "name": "ir-4.0.0"
  },
  "language_info": {
   "codemirror_mode": "r",
   "file_extension": ".r",
   "mimetype": "text/x-r-source",
   "name": "R",
   "pygments_lexer": "r",
   "version": "4.0.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}