def setUpClass(cls):
np.random.seed(None)
df = pd.read_csv(
"tests/data/adult_missing_values_missing_target_500rows.csv")
cls.data = {"train": {"X": df[df.columns[:-1]], "y": df["income"]}}
available_models = list(
ModelsRegistry.registry[BINARY_CLASSIFICATION].keys())
model_type = np.random.permutation(available_models)[0]
model_info = ModelsRegistry.registry[BINARY_CLASSIFICATION][model_type]
model_params = RandomParameters.get(model_info["params"])
required_preprocessing = model_info["required_preprocessing"]
model_additional = model_info["additional"]
preprocessing_params = PreprocessingTuner.get(required_preprocessing,
cls.data,
BINARY_CLASSIFICATION)
cls.train_params = {
"additional": model_additional,
"preprocessing": preprocessing_params,
"validation": {
"validation_type": "split",
"train_ratio": 0.8,
# "validation_type": "kfold",
# "k_folds": 5,
"shuffle": True,
},
"learner": {
"model_type": model_info["class"].algorithm_short_name,
**model_params,
},
}
def _get_model_params(self, model_type, X, y, models_cnt):
model_info = AlgorithmsRegistry.registry[self._ml_task][model_type]
model_params = RandomParameters.get(model_info["params"],
models_cnt + self._seed)
required_preprocessing = model_info["required_preprocessing"]
model_additional = model_info["additional"]
preprocessing_params = PreprocessingTuner.get(
required_preprocessing, {"train": {
"X": X,
"y": y
}}, self._ml_task)
model_params = {
"additional": model_additional,
"preprocessing": preprocessing_params,
"validation": self._validation,
"learner": {
"model_type": model_info["class"].algorithm_short_name,
"ml_task": self._ml_task,
**model_params,
},
}
num_class = (len(np.unique(y[~pd.isnull(y)]))
if self._ml_task == MULTICLASS_CLASSIFICATION else None)
if num_class is not None:
model_params["learner"]["num_class"] = num_class
model_params["ml_task"] = self._ml_task
return model_params
def _get_model_params(self, model_type, X, y):
model_info = ModelsRegistry.registry[BINARY_CLASSIFICATION][model_type]
model_params = RandomParameters.get(model_info["params"])
required_preprocessing = model_info["required_preprocessing"]
model_additional = model_info["additional"]
preprocessing_params = PreprocessingTuner.get(
required_preprocessing, {"train": {"X": X, "y": y}}, BINARY_CLASSIFICATION
)
return {
"additional": model_additional,
"preprocessing": preprocessing_params,
"validation": self._validation,
"learner": {
"model_type": model_info["class"].algorithm_short_name,
**model_params,
},
}
def _get_model_params(self, model_type, seed, params_type="random"):
model_info = AlgorithmsRegistry.registry[self._ml_task][model_type]
model_params = None
if params_type == "default":
model_params = model_info["default_params"]
model_params["seed"] = seed
else:
model_params = RandomParameters.get(model_info["params"],
seed + self._seed)
if model_params is None:
return None
required_preprocessing = model_info["required_preprocessing"]
model_additional = model_info["additional"]
preprocessing_params = PreprocessingTuner.get(required_preprocessing,
self._data_info,
self._ml_task)
model_params = {
"additional": model_additional,
"preprocessing": preprocessing_params,
"validation_strategy": self._validation_strategy,
"learner": {
"model_type": model_info["class"].algorithm_short_name,
"ml_task": self._ml_task,
"n_jobs": self._n_jobs,
**model_params,
},
}
if self._data_info.get("num_class") is not None:
model_params["learner"]["num_class"] = self._data_info.get(
"num_class")
model_params["ml_task"] = self._ml_task
model_params["explain_level"] = self._explain_level
return model_params
def _get_model_params(self, model_type, seed, params_type="random"):
model_info = AlgorithmsRegistry.registry[self._ml_task][model_type]
model_params = None
if params_type == "default":
model_params = model_info["default_params"]
model_params["seed"] = seed
else:
model_params = RandomParameters.get(model_info["params"], seed + self._seed)
if model_params is None:
return None
# set eval metric
if model_info["class"].algorithm_short_name == "Xgboost":
model_params["eval_metric"] = xgboost_eval_metric(
self._ml_task, self._eval_metric
)
if model_info["class"].algorithm_short_name == "LightGBM":
metric, custom_metric = lightgbm_eval_metric(
self._ml_task, self._eval_metric
)
model_params["metric"] = metric
model_params["custom_eval_metric_name"] = custom_metric
if model_info["class"].algorithm_short_name == "CatBoost":
model_params["eval_metric"] = catboost_eval_metric(
self._ml_task, self._eval_metric
)
elif model_info["class"].algorithm_short_name in [
"Random Forest",
"Extra Trees",
]:
model_params["eval_metric_name"] = self._eval_metric
model_params["ml_task"] = self._ml_task
required_preprocessing = model_info["required_preprocessing"]
model_additional = model_info["additional"]
preprocessing_params = PreprocessingTuner.get(
required_preprocessing, self._data_info, self._ml_task
)
model_params = {
"additional": model_additional,
"preprocessing": preprocessing_params,
"validation_strategy": self._validation_strategy,
"learner": {
"model_type": model_info["class"].algorithm_short_name,
"ml_task": self._ml_task,
"n_jobs": self._n_jobs,
**model_params,
},
"automl_random_state": self._seed,
}
if self._data_info.get("num_class") is not None:
model_params["learner"]["num_class"] = self._data_info.get("num_class")
model_params["ml_task"] = self._ml_task
model_params["explain_level"] = self._explain_level
return model_params