{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Subset CMIP6 Datasets with xarray\n",
    "\n",
    "xarray: http://xarray.pydata.org/en/stable/index.html"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Search CMIP6 Dataset with ESGF pyclient\n",
    "\n",
    "using: https://esgf-pyclient.readthedocs.io/en/latest/index.html"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from pyesgf.search import SearchConnection\n",
    "conn = SearchConnection('https://esgf-data.dkrz.de/esg-search', distrib=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "ctx = conn.new_context(\n",
    "    project='CMIP6', \n",
    "    source_id='UKESM1-0-LL', \n",
    "    experiment_id='historical', \n",
    "    variable='tas', \n",
    "    frequency='mon', \n",
    "    variant_label='r1i1p1f2',\n",
    "    data_node='esgf-data3.ceda.ac.uk')\n",
    "ctx.hit_count"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "result = ctx.search()[0]\n",
    "result.dataset_id"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "files = result.file_context().search()\n",
    "for file in files:\n",
    "    print(file.opendap_url)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Subset single dataset with xarray\n",
    "\n",
    "Using OpenDAP: http://xarray.pydata.org/en/stable/io.html?highlight=opendap#opendap"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import xarray as xr\n",
    "ds = xr.open_dataset(files[0].opendap_url, chunks={'time': 120})\n",
    "print(ds)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "da = ds['tas']\n",
    "da = da.isel(time=slice(0, 1))\n",
    "da = da.sel(lat=slice(-50, 50), lon=slice(0, 50))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "%matplotlib inline\n",
    "da.plot()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Subset over multiple datasets\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "ds_agg = xr.open_mfdataset([files[0].opendap_url, files[1].opendap_url], chunks={'time': 120}, combine='nested', concat_dim='time')\n",
    "print(ds_agg)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "da = ds_agg['tas']\n",
    "da = da.isel(time=slice(1200, 1201))\n",
    "da = da.sel(lat=slice(-50, 50), lon=slice(0, 50))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "da.plot()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Download dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "da.to_netcdf('tas_africa_19500116.nc')"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.7.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}