Refactor notebooks for workflow generation

This commit is contained in:
2025-06-06 17:05:10 +02:00
parent 7b3404ecd9
commit 0671f0ad7f
2 changed files with 41 additions and 516256 deletions

View File

@ -61,7 +61,11 @@
"\n",
"campaign_descriptor = load_project_yaml_files(project_path, \"campaignDescriptor.yaml\")\n",
"YEAR = campaign_descriptor['year']\n",
"STATION_ABBR = campaign_descriptor['station_abbr']"
"STATION_ABBR = campaign_descriptor['station_abbr']\n",
"\n",
"workflow_fname = f'workflow_acsm_data_{STATION_ABBR}_{YEAR}'\n",
"\n",
"print(workflow_fname)"
]
},
{
@ -95,7 +99,9 @@
"outputs": [],
"source": [
"# Uncomment and define the following variables manually to reanalize previous data collections\n",
"#CAMPAIGN_DATA_FILE = '../data/collection_PAY_2024_2025-05-26_2025-05-26.h5'\n",
"#CAMPAIGN_DATA_FILE = '../data/collection_PAY_2024_2025-06-05_2025-06-05.h5'\n",
"#CAMPAIGN_DATA_FILE = '../data/collection_JFJ_2024_2025-06-06_2025-06-06.h5'\n",
"#APPEND_DATA_DIR = '../data/collection_JFJ_2024_2025-06-06_2025-06-06'\n",
"#APPEND_DATA_DIR = '../data/collection_PAY_2024_2025-05-26_2025-05-26'\n",
"#CAMPAIGN_DATA_FILE = '../data/collection_PAY_2024_2025-05-21_2025-05-21.h5'\n",
"#APPEND_DATA_DIR = '../data/collection_PAY_2024_2025-05-21_2025-05-21'"
@ -115,7 +121,7 @@
"metadata": {},
"outputs": [],
"source": [
"update_datachain_params(CAMPAIGN_DATA_FILE, 'ACSM_TOFWARE/2024')"
"update_datachain_params(CAMPAIGN_DATA_FILE, 'ACSM_TOFWARE/2024', capture_renku_metadata=True, workflow_name=workflow_fname)"
]
},
{
@ -140,7 +146,7 @@
"path_to_data_file = CAMPAIGN_DATA_FILE\n",
"path_to_calibration_file = '../pipelines/params/calibration_factors.yaml'\n",
"\n",
"apply_calibration_factors(path_to_data_file,path_to_calibration_file)\n"
"apply_calibration_factors(path_to_data_file,path_to_calibration_file, capture_renku_metadata=True, workflow_name=workflow_fname)\n"
]
},
{
@ -166,7 +172,8 @@
"#command = ['python', 'pipelines/steps/compute_automated_flags.py', path_to_data_file, dataset_name, path_to_config_file]\n",
"#status = subprocess.run(command, capture_output=True, check=True)\n",
"#print(status.stdout.decode())\n",
"generate_flags(path_to_data_file, 'diagnostics')\n",
"path_to_data_file = CAMPAIGN_DATA_FILE\n",
"generate_flags(path_to_data_file, 'diagnostics', capture_renku_metadata=True, workflow_name=workflow_fname)\n",
"\n"
]
},
@ -177,7 +184,7 @@
"outputs": [],
"source": [
"\n",
"generate_flags(path_to_data_file, 'cpc')"
"generate_flags(path_to_data_file, 'cpc', capture_renku_metadata=True, workflow_name=workflow_fname)"
]
},
{
@ -214,7 +221,7 @@
"#command = ['python', 'pipelines/steps/compute_automated_flags.py', path_to_data_file, dataset_name, path_to_config_file]\n",
"#status = subprocess.run(command, capture_output=True, check=True)\n",
"#print(status.stdout.decode())\n",
"generate_flags(path_to_data_file, 'species')"
"generate_flags(path_to_data_file, 'species', capture_renku_metadata=True, workflow_name=workflow_fname)"
]
},
{
@ -249,7 +256,7 @@
"month = \"2-3\"\n",
"with warnings.catch_warnings():\n",
" warnings.simplefilter('ignore')\n",
" prepare_ebas_submission([PATH1, PATH2, PATH3], PATH4, month)\n"
" prepare_ebas_submission([PATH1, PATH2, PATH3], PATH4, month,capture_renku_metadata=True, workflow_name=workflow_fname)\n"
]
},
{
@ -346,7 +353,7 @@
],
"metadata": {
"kernelspec": {
"display_name": "dash_multi_chem_env",
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
@ -360,7 +367,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.9"
"version": "3.11.10"
}
},
"nbformat": 4,

File diff suppressed because one or more lines are too long