def feature_selection(
model_id: str,
method: str,
split: Optional[float] = 0.7,
batch: Optional[str] = None,
task_key: Optional[str] = None,
sync: Optional[bool] = False,
model_service: ModelService = Depends(ModelService),
service: FeatureSelectionService = Depends(FeatureSelectionService),
tasks: TaskService = Depends(TaskService)):
try:
model = model_service.get_model(model_id)
mf = service.create_features_search(model,
split,
method,
task_key=task_key)
if sync:
return service.feature_selection(model, mf, sync=True)
return tasks.send(task_name='featureselection',
task_args={
'model': model.dict(),
'search_parameters': mf.dict()
},
name='feature_selection-{}-{}-{}-{}'.format(
model.symbol, model.pipeline, model.dataset,
model.target),
batch=batch)
except MessageException as e:
raise HTTPException(status_code=400, detail=e.message)
def grid_search_batch(batch: Optional[str] = None,
task_key: Optional[str] = None,
split: Optional[float] = 0.7,
query: dict = Body(...),
model_service: ModelService = Depends(ModelService),
service: GridSearchService = Depends(GridSearchService),
tasks: TaskService = Depends(TaskService)):
try:
models = model_service.query_models(query)
tests = [(model,
service.create_parameters_search(model,
split,
task_key=task_key))
for model in models]
return [
tasks.send(task_name='gridsearch',
task_args={
'model': model.dict(),
'search_parameters': search_parameters.dict()
},
name='grid_search-{}-{}-{}-{}'.format(
model.symbol, model.pipeline, model.dataset,
model.target),
batch=batch,
countdown=30) for model, search_parameters in tests
]
except MessageException as e:
raise HTTPException(status_code=400, detail=e.message)
def grid_search(model_id: str,
split: Optional[float] = 0.7,
batch: Optional[str] = None,
task_key: Optional[str] = None,
sync: Optional[bool] = False,
model_service: ModelService = Depends(ModelService),
service: GridSearchService = Depends(GridSearchService),
tasks: TaskService = Depends(TaskService)):
try:
model = model_service.get_model(model_id)
parameters = service.create_parameters_search(model,
split,
task_key=task_key)
if sync:
return service.grid_search(model, parameters, sync=True)
return tasks.send(task_name='gridsearch',
task_args={
'model': model.dict(),
'search_parameters': parameters.dict()
},
name='grid_search-{}-{}-{}-{}'.format(
model.symbol, model.pipeline, model.dataset,
model.target),
batch=batch)
except MessageException as e:
raise HTTPException(status_code=400, detail=e.message)
def merge_dataset_many(requests: List[MergeRequest] = Body(...),
tasks: TaskService = Depends(TaskService)):
_tasks = [
tasks.send(task_name='merge_datasets',
task_args=r.dict(),
name='merge_datasets-{}->{}-{}'.format(
str(r.query), r.name, r.symbol),
batch=str(r.query)) for r in requests
]
return _tasks
def build_dataset(
req: BuildRequest = Body(...),
service: DatasetBuildingService = Depends(DatasetBuildingService),
tasks: TaskService = Depends(TaskService)):
try:
service.check_builder_args(req.builder, req.args)
return tasks.send(task_name='build_dataset',
task_args=req.dict(),
name='build_dataset-{}-{}'.format(
req.symbol, req.builder))
except MessageException as e:
raise HTTPException(status_code=400, detail=e.message)
def merge_dataset(name: str,
symbol: str,
sync: Optional[bool] = False,
query: dict = Body(...),
service: DatasetService = Depends(DatasetService),
repo: DatasetRepository = Depends(DatasetRepository),
tasks: TaskService = Depends(TaskService)):
if sync:
datasets = repo.query(query)
return service.merge_datasets(datasets, name, symbol)
else:
r = MergeRequest(query=query, name=name, symbol=symbol)
return tasks.send(task_name='merge_datasets',
task_args=r.dict(),
name='merge_datasets-{}->{}-{}'.format(
str(r.query), r.name, r.symbol),
batch=str(r.query))
def test_model(model_id: str,
sync: Optional[bool] = False,
test: ModelTest = Body(...),
tasks: TaskService = Depends(TaskService),
service: ModelService = Depends(ModelService)):
try:
model = service.get_model(model_id)
if sync:
return service.test_model(model, test)
return tasks.send(task_name='testmodel',
task_args={
'model': model.dict(),
'test': test.dict()
},
name='model_test-{}-{}-{}-{}'.format(
model.symbol, model.pipeline, model.dataset,
model.target))
except MessageException as e:
raise HTTPException(status_code=400, detail=e.message)
def build_many_dataset(
requests: List[BuildRequest] = Body(...),
batch: Optional[str] = None,
service: DatasetBuildingService = Depends(DatasetBuildingService),
tasks: TaskService = Depends(TaskService)):
# Check all args are correct
for req in requests:
try:
service.check_builder_args(req.builder, req.args)
except MessageException as e:
raise HTTPException(status_code=400, detail=e.message)
# Launch tasks
_tasks = [
tasks.send(task_name='build_dataset',
task_args=r.dict(),
name='build_dataset-{}-{}'.format(req.symbol, req.builder),
batch=batch) for r in requests
]
return _tasks
def feature_selection_batch(
method: str,
batch: Optional[str] = None,
task_key: Optional[str] = None,
split: Optional[float] = 0.7,
query: dict = Body(...),
model_service: ModelService = Depends(ModelService),
service: FeatureSelectionService = Depends(FeatureSelectionService),
tasks: TaskService = Depends(TaskService)):
try:
models = model_service.query_models(query)
# This will only keep 1 copy for each (symbol, dataset, target) tuple
d_models = {
'{}-{}-{}'.format(m.symbol, m.dataset, m.target): m
for m in models
}
models = [v for k, v in d_models.items()]
def get_name_from_model(_model):
return 'feature_selection-{}-{}-{}-{}'.format(
_model.symbol, _model.pipeline, _model.dataset, _model.target)
tests = [(model,
service.create_features_search(model,
split,
method,
task_key=task_key))
for model in models]
return [
tasks.send(task_name='featureselection',
task_args={
'model': model.dict(),
'search_parameters': search_parameters.dict()
},
name=get_name_from_model(model),
batch=batch,
countdown=30)
for i, (model, search_parameters) in enumerate(tests)
]
except MessageException as e:
raise HTTPException(status_code=400, detail=e.message)