def generate_predictor(self, name: str, from_data: dict, datasource_id,
problem_definition_dict: dict,
join_learn_process: bool, company_id: int):
predictor_record = db.session.query(db.Predictor).filter_by(
company_id=company_id, name=name).first()
if predictor_record is not None:
raise Exception('Predictor name must be unique.')
df, problem_definition, _ = self._unpack_old_args(
from_data, problem_definition_dict)
problem_definition = ProblemDefinition.from_dict(problem_definition)
predictor_record = db.Predictor(
company_id=company_id,
name=name,
datasource_id=datasource_id,
mindsdb_version=mindsdb_version,
lightwood_version=lightwood_version,
to_predict=problem_definition.target,
learn_args=problem_definition.to_dict(),
data={'name': name})
db.session.add(predictor_record)
db.session.commit()
predictor_id = predictor_record.id
p = GenerateProcess(df, problem_definition, predictor_id)
p.start()
if join_learn_process:
p.join()
if not IS_PY36:
p.close()
db.session.refresh(predictor_record)
def learn(self, name: str, from_data: dict, to_predict: str,
datasource_id: int, kwargs: dict, company_id: int) -> None:
df, problem_definition, join_learn_process = self._unpack_old_args(
from_data, kwargs, to_predict)
p = LearnProcess(df, ProblemDefinition.from_dict(problem_definition),
name, company_id, datasource_id)
p.start()
if join_learn_process:
p.join()
if not IS_PY36:
p.close()
def learn(self,
name: str,
from_data: dict,
to_predict: str,
datasource_id: int,
kwargs: dict,
company_id: int,
delete_ds_on_fail: Optional[bool] = False) -> None:
predictor_record = db.session.query(db.Predictor).filter_by(
company_id=company_id, name=name).first()
if predictor_record is not None:
raise Exception('Predictor name must be unique.')
df, problem_definition, join_learn_process = self._unpack_old_args(
from_data, kwargs, to_predict)
problem_definition = ProblemDefinition.from_dict(problem_definition)
predictor_record = db.Predictor(
company_id=company_id,
name=name,
datasource_id=datasource_id,
mindsdb_version=mindsdb_version,
lightwood_version=lightwood_version,
to_predict=problem_definition.target,
learn_args=problem_definition.to_dict(),
data={'name': name})
db.session.add(predictor_record)
db.session.commit()
predictor_id = predictor_record.id
p = LearnProcess(df, problem_definition, predictor_id,
delete_ds_on_fail)
p.start()
if join_learn_process:
p.join()
if not IS_PY36:
p.close()
db.session.refresh(predictor_record)
data = {}
if predictor_record.update_status == 'available':
data['status'] = 'complete'
elif predictor_record.json_ai is None and predictor_record.code is None:
data['status'] = 'generating'
elif predictor_record.data is None:
data['status'] = 'editable'
elif 'training_log' in predictor_record.data:
data['status'] = 'training'
elif 'error' not in predictor_record.data:
data['status'] = 'complete'
else:
data['status'] = 'error'
def generate_predictor(self, name: str, from_data: dict, datasource_id,
problem_definition_dict: dict,
join_learn_process: bool, company_id: int):
df, problem_definition, _ = self._unpack_old_args(
from_data, problem_definition_dict)
p = GenerateProcess(df,
ProblemDefinition.from_dict(problem_definition),
name, company_id, datasource_id)
p.start()
if join_learn_process:
p.join()
if not IS_PY36:
p.close()
def run_generate(df: DataFrame, problem_definition: ProblemDefinition, name: str, company_id: int, datasource_id: int) -> int:
json_ai = lightwood.json_ai_from_problem(df, problem_definition)
code = lightwood.code_from_json_ai(json_ai)
predictor_record = db.Predictor(
company_id=company_id,
name=name,
json_ai=json_ai.to_dict(),
code=code,
datasource_id=datasource_id,
mindsdb_version=mindsdb_version,
lightwood_version=lightwood_version,
to_predict=[problem_definition.target],
learn_args=problem_definition.to_dict(),
data={'name': name}
)
db.session.add(predictor_record)
db.session.commit()
def learn(self, name: str, from_data: dict, to_predict: str, dataset_id: int, kwargs: dict,
company_id: int, delete_ds_on_fail: Optional[bool] = False) -> None:
predictor_record = db.session.query(db.Predictor).filter_by(company_id=company_id, name=name).first()
if predictor_record is not None:
raise Exception('Predictor name must be unique.')
df, problem_definition, join_learn_process, json_ai_override = self._unpack_old_args(from_data, kwargs, to_predict)
if 'url' in problem_definition:
train_url = problem_definition['url'].get('train', None)
predict_url = problem_definition['url'].get('predict', None)
com_format = problem_definition['format']
predictor_record = db.Predictor(
company_id=company_id,
name=name,
dataset_id=dataset_id,
mindsdb_version=mindsdb_version,
lightwood_version=lightwood_version,
to_predict=problem_definition['target'],
learn_args=ProblemDefinition.from_dict(problem_definition).to_dict(),
data={'name': name, 'train_url': train_url, 'predict_url': predict_url, 'format': com_format,
'status': 'complete' if train_url is None else 'training'},
is_custom=True,
# @TODO: For testing purposes, remove afterwards!
dtype_dict=json_ai_override['dtype_dict'],
)
db.session.add(predictor_record)
db.session.commit()
if train_url is not None:
p = LearnRemoteProcess(df, predictor_record.id)
p.start()
if join_learn_process:
p.join()
if not IS_PY36:
p.close()
db.session.refresh(predictor_record)
return
problem_definition = ProblemDefinition.from_dict(problem_definition)
predictor_record = db.Predictor(
company_id=company_id,
name=name,
dataset_id=dataset_id,
mindsdb_version=mindsdb_version,
lightwood_version=lightwood_version,
to_predict=problem_definition.target,
learn_args=problem_definition.to_dict(),
data={'name': name},
)
db.session.add(predictor_record)
db.session.commit()
predictor_id = predictor_record.id
p = LearnProcess(df, problem_definition, predictor_id, delete_ds_on_fail, json_ai_override)
p.start()
if join_learn_process:
p.join()
if not IS_PY36:
p.close()
db.session.refresh(predictor_record)