FACSPy.ml.supervisedGating.tune_hyperparameters

FACSPy.ml.supervisedGating.tune_hyperparameters#

supervisedGating.tune_hyperparameters(method, grid, **hyperparameter_search_kwargs)#

Method to tune hyperparameters of the classifier.

Parameters:

  • method (Literal['HalvingRandomSearchCV', 'HalvingGridSearchCV', 'RandomizedSearchCV', 'GridSearchCV']) – One of HalvingRandomSearchCV, GridSearchCV or RandomizedSearchCV. The method that is used for the gridsearch.

  • grid (dict) – The parameters to test. For further documentation, refer to the sklearn documentation.

Return type:

None

Examples

>>> adata = fp.create_dataset([...])
>>> gating = fp.ml.supervisedGating(dataset)
>>> gating.run_data_setup(
...     gated_samples = ["1", "2", "3"],
...     layer = "compensated",
...     scaling = "StandardScaler"
... )
>>> gating.setup_classifier("DecisionTreeClassifier")
>>> gating.tune_hyperparameters(
...    method = "HalvingRandomSearchCV",
...    grid = {"max_depth": [10,20,100]}
... )
>>> gating.setup_classifier("DecisionTreeClassifier")
>>> gating.train()
>>> gating.gate_dataset()
Contents