Submit a Dataset

In this tutorial you'll learn how to submit a dataset to a QCFractal instance (also called backend or server).

In [2]:

import os
import dotenv
import random

from tqdm.auto import tqdm

import datamol as dm
import pandas as pd

from openff.toolkit import Molecule

import qcelemental as qcel

from qcportal import PortalClient
from qcportal.record_models import PriorityEnum

from qcportal.singlepoint.dataset_models import SinglepointDatasetNewEntry
from qcportal.singlepoint.record_models import QCSpecification
from qcportal.singlepoint.record_models import SinglepointDriver

_ = dotenv.load_dotenv("../../openfractal_test_secrets.env")

import os import dotenv import random from tqdm.auto import tqdm import datamol as dm import pandas as pd from openff.toolkit import Molecule import qcelemental as qcel from qcportal import PortalClient from qcportal.record_models import PriorityEnum from qcportal.singlepoint.dataset_models import SinglepointDatasetNewEntry from qcportal.singlepoint.record_models import QCSpecification from qcportal.singlepoint.record_models import SinglepointDriver _ = dotenv.load_dotenv("../../openfractal_test_secrets.env")

Prepare the dataset¶

First we pull a random subset of datamol.data.freesolv(), create openff.Molecule objects from it and generate one conformer per molecule.

In [2]:

def get_toy_molecules(
    n_molecules: int = 10,
    progress: bool = True,
    progress_leave: bool = False,
):
    # Get some data
    data = dm.data.freesolv()
    data = data.sample(n=n_molecules)

    def _process(smiles):
        # Convert to OFF mol
        mol = Molecule.from_smiles(smiles)
        assert mol is not None

        # Generate a conformer
        mol.generate_conformers(n_conformers=1)

        return mol

    # Generate conformers
    data["mol"] = dm.parallelized(
        _process,
        data["smiles"],
        progress=progress,
        tqdm_kwargs=dict(leave=progress_leave),
    )

    data = data.reset_index(drop=True)
    return data


data = get_toy_molecules(n_molecules=10)

data

def get_toy_molecules( n_molecules: int = 10, progress: bool = True, progress_leave: bool = False, ): # Get some data data = dm.data.freesolv() data = data.sample(n=n_molecules) def _process(smiles): # Convert to OFF mol mol = Molecule.from_smiles(smiles) assert mol is not None # Generate a conformer mol.generate_conformers(n_conformers=1) return mol # Generate conformers data["mol"] = dm.parallelized( _process, data["smiles"], progress=progress, tqdm_kwargs=dict(leave=progress_leave), ) data = data.reset_index(drop=True) return data data = get_toy_molecules(n_molecules=10) data

  0%|          | 0/10 [00:00<?, ?it/s]

Out[2]:

	iupac	smiles	expt	calc	mol
0	pyridine	c1ccncc1	-4.69	-3.508	Molecule with name '' and SMILES '[H][c]1[n][c...
1	ethyl propanoate	CCC(=O)OCC	-2.68	-3.221	Molecule with name '' and SMILES '[H][C]([H])(...
2	2-methylpyridine	Cc1ccccn1	-4.63	-3.501	Molecule with name '' and SMILES '[H][c]1[n][c...
3	2,3-dichlorodibenzo-p-dioxin	c1ccc2c(c1)Oc3cc(c(cc3O2)Cl)Cl	-3.56	-3.590	Molecule with name '' and SMILES '[H][c]1[c]([...
4	1-acetoxyethyl acetate	CC(OC(=O)C)OC(=O)C	-4.97	-8.006	Molecule with name '' and SMILES '[H][C]([H])(...
5	2-methylhexane	CCCCC(C)C	2.93	2.894	Molecule with name '' and SMILES '[H][C]([H])(...
6	simazine	CCNc1nc(nc(n1)Cl)NCC	-10.22	-10.914	Molecule with name '' and SMILES '[H][N]([c]1[...
7	triethylphosphate	CCOP(=O)(OCC)OCC	-7.50	-10.251	Molecule with name '' and SMILES '[H][C]([H])(...
8	methylcyclopentane	CC1CCCC1	1.59	1.785	Molecule with name '' and SMILES '[H][C]([H])(...
9	hept-1-yne	CCCCCC#C	0.60	0.639	Molecule with name '' and SMILES '[H][C]#[C][C...

Initialize the PortalClient¶

The client object will allow to interact with any QCfractal instance.

In [3]:

client = PortalClient(
    address="https://openfractal-test-pgzbs3yryq-uc.a.run.app",
    username=os.environ["OPENFRACTAL_USER_1_USERNAME"],
    password=os.environ["OPENFRACTAL_USER_1_PASSWORD"],
)

client

client = PortalClient( address="https://openfractal-test-pgzbs3yryq-uc.a.run.app", username=os.environ["OPENFRACTAL_USER_1_USERNAME"], password=os.environ["OPENFRACTAL_USER_1_PASSWORD"], ) client

Out[3]:

PortalClient

• Server:   openfractal-test
• Address:   https://openfractal-test-pgzbs3yryq-uc.a.run.app/
• Username:   admin_default

You can display some general informations about this instance:

In [4]:

client.server_info

client.server_info

Out[4]:

{'name': 'openfractal-test',
 'manager_heartbeat_frequency': 10,
 'manager_heartbeat_max_missed': 5,
 'version': '0.50b12.post16+gee831184',
 'api_limits': {'get_records': 1000,
  'add_records': 500,
  'get_dataset_entries': 2000,
  'get_molecules': 1000,
  'add_molecules': 1000,
  'get_managers': 1000,
  'manager_tasks_claim': 200,
  'manager_tasks_return': 10,
  'get_server_stats': 25,
  'get_access_logs': 1000,
  'get_error_logs': 100,
  'get_internal_jobs': 1000},
 'client_version_lower_limit': '0.50b11',
 'client_version_upper_limit': '1',
 'manager_version_lower_limit': '0.50b11',
 'manager_version_upper_limit': '1',
 'motd': ''}

Create a new dataset on the server¶

In [5]:

# Generate a random suffix for your dataset
dataset_suffix = "".join(random.choices([str(i) for i in range(10)], k=10))

dataset_name = f"dataset_demo_{dataset_suffix}"

dataset_name

# Generate a random suffix for your dataset dataset_suffix = "".join(random.choices([str(i) for i in range(10)], k=10)) dataset_name = f"dataset_demo_{dataset_suffix}" dataset_name

Out[5]:

'dataset_demo_4321690179'

In [33]:

kwargs = {}
kwargs["dataset_type"] = "singlepoint"
kwargs["name"] = dataset_name
kwargs["description"] = "my great dataset!"
# the tag allows you to restrict this dataset to only specific managers
kwargs["tags"] = ["demo_tutorial"]  
kwargs["group"] = None
kwargs["provenance"] = {}
kwargs["visibility"] = True
kwargs["default_tag"] = "demo_tutorial"
kwargs["default_priority"] = PriorityEnum.normal
kwargs["metadata"] = {}
kwargs["owner_group"] = None

ds = client.add_dataset(**kwargs)

ds.dict()

kwargs = {} kwargs["dataset_type"] = "singlepoint" kwargs["name"] = dataset_name kwargs["description"] = "my great dataset!" # the tag allows you to restrict this dataset to only specific managers kwargs["tags"] = ["demo_tutorial"] kwargs["group"] = None kwargs["provenance"] = {} kwargs["visibility"] = True kwargs["default_tag"] = "demo_tutorial" kwargs["default_priority"] = PriorityEnum.normal kwargs["metadata"] = {} kwargs["owner_group"] = None ds = client.add_dataset(**kwargs) ds.dict()

Out[33]:

{'id': 5,
 'dataset_type': 'singlepoint',
 'name': 'dataset_demo_4321690179',
 'description': 'my great dataset!',
 'tagline': '',
 'tags': ['demo_tutorial'],
 'group': 'default',
 'visibility': True,
 'provenance': {},
 'default_tag': 'demo_tutorial',
 'default_priority': <PriorityEnum.normal: 1>,
 'owner_user': 'admin_default',
 'owner_group': None,
 'metadata': {},
 'extras': {},
 'entry_names_': [],
 'specifications_': {},
 'entries_': {},
 'record_map_': {},
 'contributed_values_': None,
 'auto_fetch_missing': True}

Build "entries" from the dataset¶

An entry is a single data point object that hold a 3D atomistic system (also called a molecule). You can associate custom attributes to a given molecule.

In [34]:

chunk_size = 5
progress = True
progress_leave = False


def _create_entry(i, row):
    kwargs = {}
    kwargs["name"] = f"mol_{i}"
    kwargs["molecule"] = row["mol"].to_qcschema()
    kwargs["additional_keywords"] = {}
    kwargs["attributes"] = row.drop("mol").to_dict()
    kwargs["comment"] = None
    return SinglepointDatasetNewEntry(**kwargs)


# We build and send the entry by chunk in case of large dataset
for i in tqdm(range(0, len(data), chunk_size)):
    # Get the rows
    rows = data.iloc[i : i + chunk_size]

    # Build the entries
    entries = dm.parallelized(
        _create_entry,
        rows.iterrows(),
        arg_type="args",
        total=len(rows),
        progress=progress,
        tqdm_kwargs=dict(leave=progress_leave),
    )

    # Send the entries to the server
    insert_md = ds.add_entries(entries)
    assert insert_md.success

chunk_size = 5 progress = True progress_leave = False def _create_entry(i, row): kwargs = {} kwargs["name"] = f"mol_{i}" kwargs["molecule"] = row["mol"].to_qcschema() kwargs["additional_keywords"] = {} kwargs["attributes"] = row.drop("mol").to_dict() kwargs["comment"] = None return SinglepointDatasetNewEntry(**kwargs) # We build and send the entry by chunk in case of large dataset for i in tqdm(range(0, len(data), chunk_size)): # Get the rows rows = data.iloc[i : i + chunk_size] # Build the entries entries = dm.parallelized( _create_entry, rows.iterrows(), arg_type="args", total=len(rows), progress=progress, tqdm_kwargs=dict(leave=progress_leave), ) # Send the entries to the server insert_md = ds.add_entries(entries) assert insert_md.success

  0%|          | 0/2 [00:00<?, ?it/s]

  0%|          | 0/5 [00:00<?, ?it/s]

  0%|          | 0/5 [00:00<?, ?it/s]

You can check the newly submitted entries:

In [35]:

list(ds.iterate_entries())

list(ds.iterate_entries())

Out[35]:

[SinglepointDatasetEntry(name='mol_0', molecule=Molecule(name='C5H5N', formula='C5H5N', hash='a6c6d91'), additional_keywords={}, attributes={'calc': -3.508, 'expt': -4.69, 'iupac': 'pyridine', 'smiles': 'c1ccncc1'}, comment=None, local_results=None),
 SinglepointDatasetEntry(name='mol_1', molecule=Molecule(name='C5H10O2', formula='C5H10O2', hash='7d0fe6d'), additional_keywords={}, attributes={'calc': -3.221, 'expt': -2.68, 'iupac': 'ethyl propanoate', 'smiles': 'CCC(=O)OCC'}, comment=None, local_results=None),
 SinglepointDatasetEntry(name='mol_2', molecule=Molecule(name='C6H7N', formula='C6H7N', hash='7739509'), additional_keywords={}, attributes={'calc': -3.501, 'expt': -4.63, 'iupac': '2-methylpyridine', 'smiles': 'Cc1ccccn1'}, comment=None, local_results=None),
 SinglepointDatasetEntry(name='mol_3', molecule=Molecule(name='C12Cl2H6O2', formula='C12Cl2H6O2', hash='c785c43'), additional_keywords={}, attributes={'calc': -3.59, 'expt': -3.56, 'iupac': '2,3-dichlorodibenzo-p-dioxin', 'smiles': 'c1ccc2c(c1)Oc3cc(c(cc3O2)Cl)Cl'}, comment=None, local_results=None),
 SinglepointDatasetEntry(name='mol_4', molecule=Molecule(name='C6H10O4', formula='C6H10O4', hash='7de2fa5'), additional_keywords={}, attributes={'calc': -8.006, 'expt': -4.97, 'iupac': '1-acetoxyethyl acetate', 'smiles': 'CC(OC(=O)C)OC(=O)C'}, comment=None, local_results=None),
 SinglepointDatasetEntry(name='mol_5', molecule=Molecule(name='C7H16', formula='C7H16', hash='31ac45a'), additional_keywords={}, attributes={'calc': 2.894, 'expt': 2.93, 'iupac': '2-methylhexane', 'smiles': 'CCCCC(C)C'}, comment=None, local_results=None),
 SinglepointDatasetEntry(name='mol_6', molecule=Molecule(name='C7ClH12N5', formula='C7ClH12N5', hash='ab02e52'), additional_keywords={}, attributes={'calc': -10.914, 'expt': -10.22, 'iupac': 'simazine', 'smiles': 'CCNc1nc(nc(n1)Cl)NCC'}, comment=None, local_results=None),
 SinglepointDatasetEntry(name='mol_7', molecule=Molecule(name='C6H15O4P', formula='C6H15O4P', hash='3f198c7'), additional_keywords={}, attributes={'calc': -10.251, 'expt': -7.5, 'iupac': 'triethylphosphate', 'smiles': 'CCOP(=O)(OCC)OCC'}, comment=None, local_results=None),
 SinglepointDatasetEntry(name='mol_8', molecule=Molecule(name='C6H12', formula='C6H12', hash='bc0c2a1'), additional_keywords={}, attributes={'calc': 1.785, 'expt': 1.59, 'iupac': 'methylcyclopentane', 'smiles': 'CC1CCCC1'}, comment=None, local_results=None),
 SinglepointDatasetEntry(name='mol_9', molecule=Molecule(name='C7H12', formula='C7H12', hash='f9566b0'), additional_keywords={}, attributes={'calc': 0.639, 'expt': 0.6, 'iupac': 'hept-1-yne', 'smiles': 'CCCCCC#C'}, comment=None, local_results=None)]

Create the QM specification¶

The QM specification defines a QM protocol that will be executed on a Dataset.

Here we choose a cheap level of theory: hf/sto-3g.

In [36]:

## PSI4 SCF properties
## See https://psicode.org/psi4manual/master/oeprop.html#id2
scf_properties = [
    "MBIS_CHARGES",
    "WIBERG_LOWDIN_INDICES",
    "MAYER_INDICES",
    "LOWDIN_CHARGES",
    "DIPOLE",
    "QUADRUPOLE",
]

## Build the protocols
## One of: all, none or orbitals_and_eigenvalues
protocols = {"wavefunction": "all"}

## Build the specification
kwargs = {}
kwargs["program"] = "psi4"
kwargs["driver"] = SinglepointDriver.gradient
# kwargs["method"] = "wb97m-d3bj"
# kwargs["basis"] = "def2-tzvppd"
kwargs["method"] = "hf"
kwargs["basis"] = "sto-3g"
kwargs["keywords"] = {"wcombine": False, "scf_properties": scf_properties}
kwargs["protocols"] = protocols

specification = QCSpecification(**kwargs)

specification

## PSI4 SCF properties ## See https://psicode.org/psi4manual/master/oeprop.html#id2 scf_properties = [ "MBIS_CHARGES", "WIBERG_LOWDIN_INDICES", "MAYER_INDICES", "LOWDIN_CHARGES", "DIPOLE", "QUADRUPOLE", ] ## Build the protocols ## One of: all, none or orbitals_and_eigenvalues protocols = {"wavefunction": "all"} ## Build the specification kwargs = {} kwargs["program"] = "psi4" kwargs["driver"] = SinglepointDriver.gradient # kwargs["method"] = "wb97m-d3bj" # kwargs["basis"] = "def2-tzvppd" kwargs["method"] = "hf" kwargs["basis"] = "sto-3g" kwargs["keywords"] = {"wcombine": False, "scf_properties": scf_properties} kwargs["protocols"] = protocols specification = QCSpecification(**kwargs) specification

Out[36]:

QCSpecification(program='psi4', driver=<SinglepointDriver.gradient: 'gradient'>, method='hf', basis='sto-3g', keywords={'wcombine': False, 'scf_properties': ['MBIS_CHARGES', 'WIBERG_LOWDIN_INDICES', 'MAYER_INDICES', 'LOWDIN_CHARGES', 'DIPOLE', 'QUADRUPOLE']}, protocols=AtomicResultProtocols(wavefunction=<WavefunctionProtocolEnum.all: 'all'>, stdout=True, error_correction=ErrorCorrectionProtocol(default_policy=True, policies=None), native_files=<NativeFilesProtocolEnum.none: 'none'>))

Now we associate this QM specification (protocol) to the dataset we created above to the server.

In [37]:

kwargs = {}
kwargs["name"] = "simple_qm_calculation_demo"
kwargs["specification"] = specification
kwargs["description"] = None
insert_md = ds.add_specification(**kwargs)
assert insert_md

kwargs = {} kwargs["name"] = "simple_qm_calculation_demo" kwargs["specification"] = specification kwargs["description"] = None insert_md = ds.add_specification(**kwargs) assert insert_md

In [38]:

list(ds.iterate_entries())

list(ds.iterate_entries())

Out[38]:

[SinglepointDatasetEntry(name='mol_0', molecule=Molecule(name='C5H5N', formula='C5H5N', hash='a6c6d91'), additional_keywords={}, attributes={'calc': -3.508, 'expt': -4.69, 'iupac': 'pyridine', 'smiles': 'c1ccncc1'}, comment=None, local_results=None),
 SinglepointDatasetEntry(name='mol_1', molecule=Molecule(name='C5H10O2', formula='C5H10O2', hash='7d0fe6d'), additional_keywords={}, attributes={'calc': -3.221, 'expt': -2.68, 'iupac': 'ethyl propanoate', 'smiles': 'CCC(=O)OCC'}, comment=None, local_results=None),
 SinglepointDatasetEntry(name='mol_2', molecule=Molecule(name='C6H7N', formula='C6H7N', hash='7739509'), additional_keywords={}, attributes={'calc': -3.501, 'expt': -4.63, 'iupac': '2-methylpyridine', 'smiles': 'Cc1ccccn1'}, comment=None, local_results=None),
 SinglepointDatasetEntry(name='mol_3', molecule=Molecule(name='C12Cl2H6O2', formula='C12Cl2H6O2', hash='c785c43'), additional_keywords={}, attributes={'calc': -3.59, 'expt': -3.56, 'iupac': '2,3-dichlorodibenzo-p-dioxin', 'smiles': 'c1ccc2c(c1)Oc3cc(c(cc3O2)Cl)Cl'}, comment=None, local_results=None),
 SinglepointDatasetEntry(name='mol_4', molecule=Molecule(name='C6H10O4', formula='C6H10O4', hash='7de2fa5'), additional_keywords={}, attributes={'calc': -8.006, 'expt': -4.97, 'iupac': '1-acetoxyethyl acetate', 'smiles': 'CC(OC(=O)C)OC(=O)C'}, comment=None, local_results=None),
 SinglepointDatasetEntry(name='mol_5', molecule=Molecule(name='C7H16', formula='C7H16', hash='31ac45a'), additional_keywords={}, attributes={'calc': 2.894, 'expt': 2.93, 'iupac': '2-methylhexane', 'smiles': 'CCCCC(C)C'}, comment=None, local_results=None),
 SinglepointDatasetEntry(name='mol_6', molecule=Molecule(name='C7ClH12N5', formula='C7ClH12N5', hash='ab02e52'), additional_keywords={}, attributes={'calc': -10.914, 'expt': -10.22, 'iupac': 'simazine', 'smiles': 'CCNc1nc(nc(n1)Cl)NCC'}, comment=None, local_results=None),
 SinglepointDatasetEntry(name='mol_7', molecule=Molecule(name='C6H15O4P', formula='C6H15O4P', hash='3f198c7'), additional_keywords={}, attributes={'calc': -10.251, 'expt': -7.5, 'iupac': 'triethylphosphate', 'smiles': 'CCOP(=O)(OCC)OCC'}, comment=None, local_results=None),
 SinglepointDatasetEntry(name='mol_8', molecule=Molecule(name='C6H12', formula='C6H12', hash='bc0c2a1'), additional_keywords={}, attributes={'calc': 1.785, 'expt': 1.59, 'iupac': 'methylcyclopentane', 'smiles': 'CC1CCCC1'}, comment=None, local_results=None),
 SinglepointDatasetEntry(name='mol_9', molecule=Molecule(name='C7H12', formula='C7H12', hash='f9566b0'), additional_keywords={}, attributes={'calc': 0.639, 'expt': 0.6, 'iupac': 'hept-1-yne', 'smiles': 'CCCCCC#C'}, comment=None, local_results=None)]

Submit the computation¶

Warning: once you have submitted a specification to a dataset, the compatible managers will start picking up jobs and perform the QM calculcations.

In [39]:

ds.submit()

ds.submit()

Check the submission worked.

In [63]:

print(ds.status_table())

print(ds.status_table())

             specification    complete    running
--------------------------  ----------  ---------
simple_qm_calculation_demo           4          6

Monitoring¶

Retrieve a dataset by its name.

In [41]:

ds = client.get_dataset("singlepoint", dataset_name)
ds

ds = client.get_dataset("singlepoint", dataset_name) ds

Out[41]:

SinglepointDataset(id=5, dataset_type='singlepoint', name='dataset_demo_4321690179', description='my great dataset!', tagline='', tags=['demo_tutorial'], group='default', visibility=True, provenance={}, default_tag='demo_tutorial', default_priority=<PriorityEnum.normal: 1>, owner_user='admin_default', owner_group=None, metadata={}, extras={}, entry_names_=[], specifications_={}, entries_={}, record_map_={}, contributed_values_=None, auto_fetch_missing=True)

Print a table showing the status for a dataset.

In [62]:

print(ds.status_table())

print(ds.status_table())

             specification    complete    running
--------------------------  ----------  ---------
simple_qm_calculation_demo           2          8

Read the records (some might be completed but some might still be in progress or in failing state.

In [57]:

records_list = []
for r in tqdm(client.query_records(dataset_id=ds.id)):
    # Access this object to fetch the potential errors when any
    r.error
    records_list.append(r.dict())

records = pd.DataFrame(records_list)
records = records.sort_values("id")
records = records.reset_index(drop=True)

records

records_list = [] for r in tqdm(client.query_records(dataset_id=ds.id)): # Access this object to fetch the potential errors when any r.error records_list.append(r.dict()) records = pd.DataFrame(records_list) records = records.sort_values("id") records = records.reset_index(drop=True) records

0it [00:00, ?it/s]

Out[57]:

	id	record_type	is_service	properties	extras	status	manager_name	created_on	modified_on	owner_user	owner_group	compute_history_	task_	service_	comments_	native_files_	specification	molecule_id	molecule_	wavefunction_
0	15	singlepoint	False	{'pe energy': 0.0, 'scf dipole': [-0.000133218...	{}	RecordStatusEnum.complete	manager_hadrien_local_1-gollum-ef38f2ac-b99a-4...	2023-06-23 00:01:50.894704	2023-06-23 00:03:46.557663	admin_default	None	[{'id': 15, 'record_id': 15, 'status': 'Record...	None	None	None	None	{'program': 'psi4', 'driver': 'SinglepointDriv...	24	None	None
1	52	singlepoint	False	{'pe energy': 0.0, 'scf dipole': [0.1806203110...	{}	RecordStatusEnum.complete	manager_hadrien_local_1-gollum-ef38f2ac-b99a-4...	2023-06-23 00:01:50.894737	2023-06-23 00:06:23.031904	admin_default	None	[{'id': 52, 'record_id': 52, 'status': 'Record...	None	None	None	None	{'program': 'psi4', 'driver': 'SinglepointDriv...	37	None	None
2	269	singlepoint	False	None	None	RecordStatusEnum.running	manager_hadrien_local_1-boromir-eb6f7b1c-7db1-...	2023-06-23 13:09:57.599294	2023-06-23 13:10:14.774596	admin_default	None	[]	None	None	None	None	{'program': 'psi4', 'driver': 'SinglepointDriv...	131	None	None
3	270	singlepoint	False	None	None	RecordStatusEnum.running	manager_hadrien_local_1-boromir-eb6f7b1c-7db1-...	2023-06-23 13:09:57.599299	2023-06-23 13:10:14.774608	admin_default	None	[]	None	None	None	None	{'program': 'psi4', 'driver': 'SinglepointDriv...	127	None	None
4	271	singlepoint	False	None	None	RecordStatusEnum.running	manager_hadrien_local_1-boromir-eb6f7b1c-7db1-...	2023-06-23 13:09:57.599300	2023-06-23 13:10:14.774614	admin_default	None	[]	None	None	None	None	{'program': 'psi4', 'driver': 'SinglepointDriv...	130	None	None
5	272	singlepoint	False	None	None	RecordStatusEnum.running	manager_hadrien_local_1-boromir-eb6f7b1c-7db1-...	2023-06-23 13:09:57.599301	2023-06-23 13:10:14.774620	admin_default	None	[]	None	None	None	None	{'program': 'psi4', 'driver': 'SinglepointDriv...	133	None	None
6	273	singlepoint	False	None	None	RecordStatusEnum.running	manager_hadrien_local_1-boromir-eb6f7b1c-7db1-...	2023-06-23 13:09:57.599302	2023-06-23 13:10:14.774626	admin_default	None	[]	None	None	None	None	{'program': 'psi4', 'driver': 'SinglepointDriv...	129	None	None
7	274	singlepoint	False	None	None	RecordStatusEnum.running	manager_hadrien_local_1-boromir-eb6f7b1c-7db1-...	2023-06-23 13:09:57.599303	2023-06-23 13:10:14.774632	admin_default	None	[]	None	None	None	None	{'program': 'psi4', 'driver': 'SinglepointDriv...	126	None	None
8	275	singlepoint	False	None	None	RecordStatusEnum.running	manager_hadrien_local_1-boromir-eb6f7b1c-7db1-...	2023-06-23 13:09:57.599303	2023-06-23 13:10:14.774638	admin_default	None	[]	None	None	None	None	{'program': 'psi4', 'driver': 'SinglepointDriv...	132	None	None
9	276	singlepoint	False	None	None	RecordStatusEnum.running	manager_hadrien_local_1-boromir-eb6f7b1c-7db1-...	2023-06-23 13:09:57.599304	2023-06-23 13:10:14.774644	admin_default	None	[]	None	None	None	None	{'program': 'psi4', 'driver': 'SinglepointDriv...	128	None	None

Delete a dataset and associated records¶

Important: Before deleting the dataset you just created, you should check the other tutorials where you'll learn how to launch a manager than can perform the QM calculations submitted above!

Retrieve the ID of a given dataset.

In [6]:

client.list_datasets()

client.list_datasets()

Out[6]:

[{'id': 1, 'dataset_type': 'singlepoint', 'dataset_name': 'dataset_1'},
 {'id': 3, 'dataset_type': 'singlepoint', 'dataset_name': 'dataset_2'}]

In [4]:

dataset_id = client.get_dataset("singlepoint", "dataset_demo_4321690179").id
dataset_id

dataset_id = client.get_dataset("singlepoint", "dataset_demo_4321690179").id dataset_id

Out[4]:

5

Delete the dataset and its associated records.

Warning: this step can't be reversed.

In [5]:

client.delete_dataset(dataset_id, delete_records=True)

client.delete_dataset(dataset_id, delete_records=True)

In [ ]: