{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# Performance of concat operator on cmip6 decadal: DWD\n", "\n", "**Rooki** calls climate data operations on the **rook** processing service." ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "import os\n", "import time\n", "os.environ['ROOK_URL'] = 'http://rook.dkrz.de/wps'\n", "\n", "from rooki import operators as ops" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Load intake catalog for cmip6 decadal" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "import intake" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "/usr/local/Caskroom/mambaforge/base/envs/rooki/lib/python3.11/site-packages/dask/dataframe/io/csv.py:542: UserWarning: Warning gzip compression does not support breaking apart files\n", "Please ensure that each individual file can fit in memory and\n", "use the keyword ``blocksize=None to remove this message``\n", "Setting ``blocksize=None``\n", " warn(\n" ] }, { "data": { "text/html": [ "
| \n", " | ds_id | \n", "path | \n", "size | \n", "mip_era | \n", "activity_id | \n", "institution_id | \n", "source_id | \n", "experiment_id | \n", "member_id | \n", "table_id | \n", "variable_id | \n", "grid_label | \n", "version | \n", "start_time | \n", "end_time | \n", "bbox | \n", "level | \n", "member_year | \n", "member_ensemble | \n", "prefix | \n", "
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | \n", "c3s-cmip6-decadal.DCPP.MPI-M.MPI-ESM1-2-HR.dcp... | \n", "DCPP/MPI-M/MPI-ESM1-2-HR/dcppA-hindcast/s2016-... | \n", "492479692 | \n", "c3s-cmip6-decadal | \n", "DCPP | \n", "MPI-M | \n", "MPI-ESM1-2-HR | \n", "dcppA-hindcast | \n", "s2016-r8i1p1f1 | \n", "day | \n", "tasmax | \n", "gn | \n", "v20210111 | \n", "2016-11-01T12:00:00 | \n", "2026-12-31T12:00:00 | \n", "0.00, -89.28, 359.06, 89.28 | \n", "2.00 | \n", "s2016 | \n", "r8i1p1f1 | \n", "c3s-cmip6-decadal | \n", "
| 1 | \n", "c3s-cmip6-decadal.DCPP.MPI-M.MPI-ESM1-2-HR.dcp... | \n", "DCPP/MPI-M/MPI-ESM1-2-HR/dcppA-hindcast/s2009-... | \n", "737204109 | \n", "c3s-cmip6-decadal | \n", "DCPP | \n", "MPI-M | \n", "MPI-ESM1-2-HR | \n", "dcppA-hindcast | \n", "s2009-r8i1p1f1 | \n", "day | \n", "pr | \n", "gn | \n", "v20210107 | \n", "2009-11-01T12:00:00 | \n", "2019-12-31T12:00:00 | \n", "0.00, -89.28, 359.06, 89.28 | \n", "NaN | \n", "s2009 | \n", "r8i1p1f1 | \n", "c3s-cmip6-decadal | \n", "
| 2 | \n", "c3s-cmip6-decadal.DCPP.MOHC.HadGEM3-GC31-MM.dc... | \n", "DCPP/MOHC/HadGEM3-GC31-MM/dcppA-hindcast/s1987... | \n", "953384 | \n", "c3s-cmip6-decadal | \n", "DCPP | \n", "MOHC | \n", "HadGEM3-GC31-MM | \n", "dcppA-hindcast | \n", "s1987-r3i1p1f2 | \n", "Amon | \n", "pr | \n", "gn | \n", "v20200417 | \n", "1987-11-16T00:00:00 | \n", "1987-12-16T00:00:00 | \n", "0.42, -89.72, 359.58, 89.72 | \n", "NaN | \n", "s1987 | \n", "r3i1p1f2 | \n", "c3s-cmip6-decadal | \n", "
| 3 | \n", "c3s-cmip6-decadal.DCPP.MOHC.HadGEM3-GC31-MM.dc... | \n", "DCPP/MOHC/HadGEM3-GC31-MM/dcppA-hindcast/s1995... | \n", "603757 | \n", "c3s-cmip6-decadal | \n", "DCPP | \n", "MOHC | \n", "HadGEM3-GC31-MM | \n", "dcppA-hindcast | \n", "s1995-r6i1p1f2 | \n", "Amon | \n", "tas | \n", "gn | \n", "v20200417 | \n", "1995-11-16T00:00:00 | \n", "1995-12-16T00:00:00 | \n", "0.42, -89.72, 359.58, 89.72 | \n", "1.50 | \n", "s1995 | \n", "r6i1p1f2 | \n", "c3s-cmip6-decadal | \n", "
| 4 | \n", "c3s-cmip6-decadal.DCPP.MOHC.HadGEM3-GC31-MM.dc... | \n", "DCPP/MOHC/HadGEM3-GC31-MM/dcppA-hindcast/s2004... | \n", "14824913 | \n", "c3s-cmip6-decadal | \n", "DCPP | \n", "MOHC | \n", "HadGEM3-GC31-MM | \n", "dcppA-hindcast | \n", "s2004-r10i1p1f2 | \n", "AERday | \n", "zg500 | \n", "gn | \n", "v20200417 | \n", "2004-11-01T12:00:00 | \n", "2004-12-30T12:00:00 | \n", "0.42, -89.72, 359.58, 89.72 | \n", "50000.00 | \n", "s2004 | \n", "r10i1p1f2 | \n", "c3s-cmip6-decadal | \n", "
<xarray.Dataset>\n",
"Dimensions: (lat: 96, bnds: 2, lon: 192, time: 12)\n",
"Coordinates:\n",
" * time (time) datetime64[ns] 2019-01-31T18:00:00 ... 2019-12-31T18:...\n",
" * lon (lon) float64 0.0 1.875 3.75 5.625 ... 352.5 354.4 356.2 358.1\n",
" * lat (lat) float64 -88.57 -86.72 -84.86 -83.0 ... 84.86 86.72 88.57\n",
" reftime datetime64[ns] ...\n",
" leadtime (time) timedelta64[ns] ...\n",
"Dimensions without coordinates: bnds\n",
"Data variables:\n",
" lat_bnds (lat, bnds) float64 ...\n",
" lon_bnds (lon, bnds) float64 ...\n",
" pr (time, lat, lon) float32 ...\n",
" realization float64 ...\n",
"Attributes: (12/47)\n",
" CDI: Climate Data Interface version 2.0.3 (https:...\n",
" cdo_openmp_thread_number: 10\n",
" NCO: netCDF Operators version 4.9.2 (Homepage = h...\n",
" institute_id: DWD\n",
" model_id: MPI-ESM-LR\n",
" modeling_realm: atmos\n",
" ... ...\n",
" license: CMIP6 model data produced by DWD is licensed...\n",
" cmor_version: 3.5.0\n",
" forcing_description: f1, CMIP6 historical forcings\n",
" physics_description: physics from the standard model configuratio...\n",
" initialization_description: hindcast initialized based on observations a...\n",
" startdate: s201811