Skip to content
Snippets Groups Projects
Commit f04a2687 authored by Fabian Wachsmann's avatar Fabian Wachsmann
Browse files

Added cloud creator

parent d27c2fad
No related branches found
No related tags found
No related merge requests found
......@@ -14,13 +14,13 @@ metadata:
sources:
dkrz_cmip5_disk:
args:
esmcol_obj: https://gitlab.dkrz.de/data-infrastructure-services/intake-esm/-/raw/master/esm-collections/cloud_access/dkrz_cmip5_disk.json
esmcol_obj: https://gitlab.dkrz.de/data-infrastructure-services/intake-esm/-/raw/master/esm-collections/cloud-access/dkrz_cmip5_disk.json
description: dkrz cmip5 data on disk saved as netcdf
driver:
- intake.open_esm_datastore
dkrz_cmip5_archive:
args:
esmcol_obj: https://gitlab.dkrz.de/data-infrastructure-services/intake-esm/-/raw/master/esm-collections/cloud_access/dkrz_cmip5_archive.json
esmcol_obj: https://gitlab.dkrz.de/data-infrastructure-services/intake-esm/-/raw/master/esm-collections/cloud-access/dkrz_cmip5_archive.json
description: dkrz cmip5 data on archive saved as netcdf
driver:
- intake.open_esm_datastore
......@@ -30,7 +30,7 @@ sources:
type: list
description: description
args:
esmcol_obj: https://gitlab.dkrz.de/data-infrastructure-services/intake-esm/-/raw/master/esm-collections/cloud_access/dkrz_cmip6_disk.json
esmcol_obj: https://gitlab.dkrz.de/data-infrastructure-services/intake-esm/-/raw/master/esm-collections/cloud-access/dkrz_cmip6_disk.json
csv_kwargs:
usecols: ['activity_id', 'institution_id', 'source_id', 'experiment_id', 'member_id', 'table_id', 'variable_id','grid_label', 'dcpp_init_year', 'version', 'time_range', 'uri', 'format']
description: dkrz cmip6 data on disk saved as netcdf
......@@ -38,31 +38,31 @@ sources:
- intake.open_esm_datastore
dkrz_cmip6_cloud:
args:
esmcol_obj: https://gitlab.dkrz.de/data-infrastructure-services/intake-esm/-/raw/master/esm-collections/cloud_access/dkrz_cmip6_cloud.json
esmcol_obj: https://gitlab.dkrz.de/data-infrastructure-services/intake-esm/-/raw/master/esm-collections/cloud-access/dkrz_cmip6_cloud.json
description: dkrz cmip6 data on cloud
driver:
- intake.open_esm_datastore
dkrz_cordex_disk:
args:
esmcol_obj: https://gitlab.dkrz.de/data-infrastructure-services/intake-esm/-/raw/master/esm-collections/cloud_access/dkrz_cordex_disk.json
esmcol_obj: https://gitlab.dkrz.de/data-infrastructure-services/intake-esm/-/raw/master/esm-collections/cloud-access/dkrz_cordex_disk.json
description: dkrz cordex data on disk
driver:
- intake.open_esm_datastore
dkrz_era5_disk:
args:
esmcol_obj: https://gitlab.dkrz.de/data-infrastructure-services/intake-esm/-/raw/master/esm-collections/cloud_access/dkrz_era5_disk.json
esmcol_obj: https://gitlab.dkrz.de/data-infrastructure-services/intake-esm/-/raw/master/esm-collections/cloud-access/dkrz_era5_disk.json
description: dkrz era5 data on disk
driver:
- intake.open_esm_datastore
dkrz_mpi-ge_disk:
args:
esmcol_obj: https://gitlab.dkrz.de/data-infrastructure-services/intake-esm/-/raw/master/esm-collections/cloud_access/dkrz_mpi-ge_disk.json
esmcol_obj: https://gitlab.dkrz.de/data-infrastructure-services/intake-esm/-/raw/master/esm-collections/cloud-access/dkrz_mpi-ge_disk.json
description: dkrz mpi-ge data on disk
driver:
- intake.open_esm_datastore
dkrz_dyamond-winter_disk:
args:
esmcol_obj: https://gitlab.dkrz.de/data-infrastructure-services/intake-esm/-/raw/master/esm-collections/cloud_access/dkrz_dyamond-winter_disk.json
esmcol_obj: https://gitlab.dkrz.de/data-infrastructure-services/intake-esm/-/raw/master/esm-collections/cloud-access/dkrz_dyamond-winter_disk.json
description: dkrz dyamond-winter data on disk
driver:
- intake.open_esm_datastore
......
%% Cell type:code id:116bb321-0bbb-4e85-804a-8a75932d9e46 tags:
``` python
import glob
import pandas as pd
import json
```
%% Cell type:code id:60ccbb3d-0f0c-467e-bb43-4c025fe3ea05 tags:
``` python
cats=glob.glob("disk-access/dkrz*.json")
```
%% Cell type:code id:b98dd45c-aa97-4b36-9fce-28158467e107 tags:
``` python
for cat in cats:
targetfile=cat.split('/')[1]
target="cloud_access/"+targetfile
target="cloud-access/"+targetfile
with open(cat, "r") as f:
catjson=json.load(f)
catjson["description"]+=" which will be loaded from a source file which is in the cloud (see catalog_file)"
catjson["catalog_file"]=f"https://swift.dkrz.de/v1/dkrz_a44962e3ba914c309a7421573a6949a6/intake-esm/{catjson['id']}.csv.gz"
with open(target, "w") as f:
json.dump(catjson,f,indent=4)
```
%% Cell type:code id:2d1dfe72-e476-45a8-a1d6-2a2b8f3cbbb3 tags:
``` python
!sed 's;/pool/data/Catalogs/;https://gitlab.dkrz.de/data-infrastructure-services/intake-esm/-/raw/master/esm-collections/cloud-access/;g' disk-access/dkrz_catalog.yaml >cloud-access/dkrz_catalog.yaml
```
%% Cell type:code id:2d985cb4-ebc0-4906-9f21-fed42ffcb4a3 tags:
``` python
```
......
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment