def __init__(
self,
ml_task,
X_train,
y_train,
sample_weight,
X_validation,
y_validation,
sample_weight_validation,
eval_metric,
cat_features_indices,
n_jobs,
random_state,
):
self.X_train = X_train
self.y_train = y_train
self.sample_weight = sample_weight
self.X_validation = X_validation
self.y_validation = y_validation
self.sample_weight_validation = sample_weight_validation
self.dtrain = lgb.Dataset(self.X_train.to_numpy() if isinstance(
self.X_train, pd.DataFrame) else self.X_train,
label=self.y_train,
weight=self.sample_weight)
self.dvalid = lgb.Dataset(
self.X_validation.to_numpy() if isinstance(
self.X_validation, pd.DataFrame) else self.X_validation,
label=self.y_validation,
weight=self.sample_weight_validation,
)
self.cat_features_indices = cat_features_indices
self.eval_metric = eval_metric
self.learning_rate = 0.025
self.rounds = 1000
self.early_stopping_rounds = 50
self.seed = random_state
self.n_jobs = n_jobs
if n_jobs == -1:
self.n_jobs = 0
self.objective = ""
self.eval_metric_name = ""
self.eval_metric_name, self.custom_eval_metric_name = lightgbm_eval_metric(
ml_task, eval_metric.name)
self.custom_eval_metric = None
if self.eval_metric.name == "r2":
self.custom_eval_metric = lightgbm_eval_metric_r2
elif self.eval_metric.name == "spearman":
self.custom_eval_metric = lightgbm_eval_metric_spearman
elif self.eval_metric.name == "pearson":
self.custom_eval_metric = lightgbm_eval_metric_pearson
elif self.eval_metric.name == "f1":
self.custom_eval_metric = lightgbm_eval_metric_f1
elif self.eval_metric.name == "average_precision":
self.custom_eval_metric = lightgbm_eval_metric_average_precision
elif self.eval_metric.name == "accuracy":
self.custom_eval_metric = lightgbm_eval_metric_accuracy
self.num_class = (len(np.unique(y_train))
if ml_task == MULTICLASS_CLASSIFICATION else None)
self.objective = lightgbm_objective(ml_task, eval_metric.name)
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