{ "cells": [ { "cell_type": "markdown", "id": "experimental-reality", "metadata": {}, "source": [ "# Build a catalog for CMIP6 CMorized output" ] }, { "cell_type": "markdown", "id": "imperial-radio", "metadata": {}, "source": [ "## Import packages" ] }, { "cell_type": "code", "execution_count": 1, "id": "solid-connection", "metadata": {}, "outputs": [], "source": [ "from ecgtools import Builder\n", "from ecgtools.parsers import parse_cmip6" ] }, { "cell_type": "markdown", "id": "resistant-indicator", "metadata": {}, "source": [ "## Instantiate a `Builder` object" ] }, { "cell_type": "code", "execution_count": 2, "id": "isolated-glossary", "metadata": {}, "outputs": [], "source": [ "b = Builder([\"/glade/collections/cmip/CMIP6/CFMIP/\"], depth=3, njobs=-1)" ] }, { "cell_type": "markdown", "id": "decreased-object", "metadata": {}, "source": [ "## Build catalog and inspect built catalog\n", "Here we use the CMIP6 parser!" ] }, { "cell_type": "code", "execution_count": 3, "id": "fundamental-supervisor", "metadata": { "tags": [] }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "[Parallel(n_jobs=-1)]: Using backend LokyBackend with 36 concurrent workers.\n", "[Parallel(n_jobs=-1)]: Done 3 out of 24 | elapsed: 1.2s remaining: 8.2s\n", "[Parallel(n_jobs=-1)]: Done 8 out of 24 | elapsed: 1.2s remaining: 2.5s\n", "[Parallel(n_jobs=-1)]: Done 13 out of 24 | elapsed: 1.3s remaining: 1.1s\n", "[Parallel(n_jobs=-1)]: Done 18 out of 24 | elapsed: 1.5s remaining: 0.5s\n", "[Parallel(n_jobs=-1)]: Done 24 out of 24 | elapsed: 2.3s finished\n", "[Parallel(n_jobs=-1)]: Using backend LokyBackend with 36 concurrent workers.\n", "[Parallel(n_jobs=-1)]: Done 90 tasks | elapsed: 1.6s\n", "[Parallel(n_jobs=-1)]: Done 216 tasks | elapsed: 2.1s\n", "[Parallel(n_jobs=-1)]: Done 504 tasks | elapsed: 3.1s\n", "[Parallel(n_jobs=-1)]: Done 1296 tasks | elapsed: 6.4s\n", "[Parallel(n_jobs=-1)]: Done 2232 tasks | elapsed: 10.4s\n", "[Parallel(n_jobs=-1)]: Done 3312 tasks | elapsed: 14.5s\n", "[Parallel(n_jobs=-1)]: Done 4536 tasks | elapsed: 19.2s\n", "[Parallel(n_jobs=-1)]: Done 5904 tasks | elapsed: 24.4s\n", "[Parallel(n_jobs=-1)]: Done 7416 tasks | elapsed: 30.5s\n", "[Parallel(n_jobs=-1)]: Done 9072 tasks | elapsed: 36.6s\n", "[Parallel(n_jobs=-1)]: Done 10872 tasks | elapsed: 42.5s\n", "[Parallel(n_jobs=-1)]: Done 12816 tasks | elapsed: 49.2s\n", "[Parallel(n_jobs=-1)]: Done 14904 tasks | elapsed: 56.7s\n", "[Parallel(n_jobs=-1)]: Done 17136 tasks | elapsed: 1.1min\n", "[Parallel(n_jobs=-1)]: Done 17912 out of 17912 | elapsed: 1.1min finished\n", "/glade/work/mgrover/git_repos/ecgtools/ecgtools/builder.py:180: UserWarning: Unable to parse 8 assets/files. A list of these assets can be found in `.invalid_assets` attribute.\n", " parsing_func, parsing_func_kwargs\n" ] }, { "data": { "text/plain": [ "Builder(root_path=PosixPath('/glade/collections/cmip/CMIP6/CFMIP'), extension='.nc', depth=3, exclude_patterns=None, njobs=-1)" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "b.build(parse_cmip6)" ] }, { "cell_type": "code", "execution_count": 4, "id": "eleven-touch", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
| \n", " | activity_id | \n", "branch_method | \n", "branch_time_in_child | \n", "branch_time_in_parent | \n", "experiment | \n", "experiment_id | \n", "frequency | \n", "grid | \n", "grid_label | \n", "institution_id | \n", "... | \n", "standard_name | \n", "long_name | \n", "units | \n", "vertical_levels | \n", "init_year | \n", "start_time | \n", "end_time | \n", "time_range | \n", "path | \n", "version | \n", "
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | \n", "CFMIP | \n", "no parent | \n", "0.0 | \n", "0.0 | \n", "An AGCM experiment with monthly-varying SSTs a... | \n", "piSST-4xCO2 | \n", "mon | \n", "native 0.9x1.25 finite volume grid (192x288 la... | \n", "gn | \n", "NCAR | \n", "... | \n", "relative_humidity | \n", "Relative Humidity | \n", "% | \n", "32.0 | \n", "NaN | \n", "0001-01-15 12:00:00 | \n", "0030-12-15 12:00:00 | \n", "0001-01-15 12:00:00-0030-12-15 12:00:00 | \n", "/glade/collections/cmip/CMIP6/CFMIP/NCAR/CESM2... | \n", "v0 | \n", "
| 1 | \n", "CFMIP | \n", "no parent | \n", "0.0 | \n", "0.0 | \n", "An AGCM experiment with monthly-varying SSTs a... | \n", "piSST-4xCO2 | \n", "mon | \n", "native 0.9x1.25 finite volume grid (192x288 la... | \n", "gn | \n", "NCAR | \n", "... | \n", "relative_humidity | \n", "Relative Humidity | \n", "% | \n", "32.0 | \n", "NaN | \n", "0001-01-15 12:00:00 | \n", "0030-12-15 12:00:00 | \n", "0001-01-15 12:00:00-0030-12-15 12:00:00 | \n", "/glade/collections/cmip/CMIP6/CFMIP/NCAR/CESM2... | \n", "v20200209 | \n", "
| 2 | \n", "CFMIP | \n", "no parent | \n", "0.0 | \n", "0.0 | \n", "An AGCM experiment with monthly-varying SSTs a... | \n", "piSST-4xCO2 | \n", "mon | \n", "native 0.9x1.25 finite volume grid (192x288 la... | \n", "gn | \n", "NCAR | \n", "... | \n", "tendency_of_air_temperature_due_to_advection | \n", "Tendency of Air Temperature Due to Advection | \n", "K s-1 | \n", "32.0 | \n", "NaN | \n", "0001-01-15 12:00:00 | \n", "0030-12-15 12:00:00 | \n", "0001-01-15 12:00:00-0030-12-15 12:00:00 | \n", "/glade/collections/cmip/CMIP6/CFMIP/NCAR/CESM2... | \n", "v0 | \n", "
| 3 | \n", "CFMIP | \n", "no parent | \n", "0.0 | \n", "0.0 | \n", "An AGCM experiment with monthly-varying SSTs a... | \n", "piSST-4xCO2 | \n", "mon | \n", "native 0.9x1.25 finite volume grid (192x288 la... | \n", "gn | \n", "NCAR | \n", "... | \n", "tendency_of_air_temperature_due_to_advection | \n", "Tendency of Air Temperature Due to Advection | \n", "K s-1 | \n", "32.0 | \n", "NaN | \n", "0001-01-15 12:00:00 | \n", "0030-12-15 12:00:00 | \n", "0001-01-15 12:00:00-0030-12-15 12:00:00 | \n", "/glade/collections/cmip/CMIP6/CFMIP/NCAR/CESM2... | \n", "v20200209 | \n", "
| 4 | \n", "CFMIP | \n", "no parent | \n", "0.0 | \n", "0.0 | \n", "An AGCM experiment with monthly-varying SSTs a... | \n", "piSST-4xCO2 | \n", "mon | \n", "native 0.9x1.25 finite volume grid (192x288 la... | \n", "gn | \n", "NCAR | \n", "... | \n", "cloud_area_fraction | \n", "CALIPSO Total Cloud Cover Percentage | \n", "% | \n", "1.0 | \n", "NaN | \n", "0001-01-15 12:00:00 | \n", "0030-12-15 12:00:00 | \n", "0001-01-15 12:00:00-0030-12-15 12:00:00 | \n", "/glade/collections/cmip/CMIP6/CFMIP/NCAR/CESM2... | \n", "v0 | \n", "
5 rows × 36 columns
\n", "| \n", " | INVALID_ASSET | \n", "TRACEBACK | \n", "
|---|---|---|
| 6372 | \n", "/glade/collections/cmip/CMIP6/CFMIP/NCAR/CESM2... | \n", "Traceback (most recent call last):\\n File \"/g... | \n", "
| 6373 | \n", "/glade/collections/cmip/CMIP6/CFMIP/NCAR/CESM2... | \n", "Traceback (most recent call last):\\n File \"/g... | \n", "
| 6374 | \n", "/glade/collections/cmip/CMIP6/CFMIP/NCAR/CESM2... | \n", "Traceback (most recent call last):\\n File \"/g... | \n", "
| 6583 | \n", "/glade/collections/cmip/CMIP6/CFMIP/NCAR/CESM2... | \n", "Traceback (most recent call last):\\n File \"/g... | \n", "
| 14578 | \n", "/glade/collections/cmip/CMIP6/CFMIP/NCAR/CESM2... | \n", "Traceback (most recent call last):\\n File \"/g... | \n", "
| 14579 | \n", "/glade/collections/cmip/CMIP6/CFMIP/NCAR/CESM2... | \n", "Traceback (most recent call last):\\n File \"/g... | \n", "
| 14580 | \n", "/glade/collections/cmip/CMIP6/CFMIP/NCAR/CESM2... | \n", "Traceback (most recent call last):\\n File \"/g... | \n", "
| 14789 | \n", "/glade/collections/cmip/CMIP6/CFMIP/NCAR/CESM2... | \n", "Traceback (most recent call last):\\n File \"/g... | \n", "