lale.search.lale_grid_search_cv module

lale.search.lale_grid_search_cv.HPValuetoGSValue(key: str, hp: SearchSpace, num_samples: Optional[int] = None) → List[Any]

lale.search.lale_grid_search_cv.SearchSpaceGridstoGSGrids(hp_grids: List[Dict[str, SearchSpacePrimitive]], num_samples: Optional[int] = None) → List[Dict[str, List[Any]]]

lale.search.lale_grid_search_cv.SearchSpaceGridtoGSGrid(hp: Dict[str, SearchSpacePrimitive], num_samples: Optional[int] = None) → Dict[str, List[Any]]

lale.search.lale_grid_search_cv.SearchSpaceNumberToGSValues(key: str, hp: SearchSpaceNumber, num_samples: Optional[int] = None) → List[Any]

Returns either a list of values intended to be sampled uniformly

lale.search.lale_grid_search_cv.get_defaults_as_param_grid(op: IndividualOp)

lale.search.lale_grid_search_cv.get_grid_search_parameter_grids(op: PlannedOperator, num_samples: Optional[int] = None, num_grids: Optional[float] = None, pgo: Optional[Dict[str, Dict[str, Dict[str, int]]]] = None, data_schema: Optional[Dict[str, Any]] = None) → List[Dict[str, List[Any]]]

Top level function: given a lale operator, returns a list of parameter grids suitable for passing to GridSearchCV. Note that you will need to wrap the lale operator for sklearn compatibility to call GridSearchCV directly. The lale GridSearchCV wrapper takes care of that for you

lale.search.lale_grid_search_cv.get_lale_gridsearchcv_op(op, params, **kwargs)

lale.search.lale_grid_search_cv.get_parameter_grids(op: PlannedOperator, num_samples: Optional[int] = None, num_grids: Optional[float] = None, pgo: Optional[Dict[str, Dict[str, Dict[str, int]]]] = None, data_schema: Optional[Dict[str, Any]] = None)

Parameters

• op (The lale PlannedOperator) –

• num_samples (integer, optional) – If set, will limit the number of samples for each distribution

• num_grids (integer or float, optional) – if set to an integer => 1, it will determine how many parameter grids will be returned (at most) if set to an float between 0 and 1, it will determine what fraction should be returned note that setting it to 1 is treated as in integer. To return all results, use None

• pgo (Optional profile guided optimization data that guides discretization) –

• data_schema (Optional schema for the input data. which is used for hyperparameter schema data constraints) –

lale.search.lale_grid_search_cv.gridsearchcv_grid_to_string(grid: Dict[str, List[Any]]) → str

lale.search.lale_grid_search_cv.gridsearchcv_grids_to_string(grids: List[Dict[str, List[Any]]]) → str