def deserialize_random_forest_regressor(model_dict):
model = RandomForestRegressor(**model_dict['params'])
estimators = [
deserialize_decision_tree_regressor(decision_tree)
for decision_tree in model_dict['estimators_']
]
model.estimators_ = np.array(estimators)
model.n_features_ = model_dict['n_features_']
model.n_outputs_ = model_dict['n_outputs_']
model.max_depth = model_dict['max_depth']
model.min_samples_split = model_dict['min_samples_split']
model.min_samples_leaf = model_dict['min_samples_leaf']
model.min_weight_fraction_leaf = model_dict['min_weight_fraction_leaf']
model.max_features = model_dict['max_features']
model.max_leaf_nodes = model_dict['max_leaf_nodes']
model.min_impurity_decrease = model_dict['min_impurity_decrease']
model.min_impurity_split = model_dict['min_impurity_split']
if 'oob_score_' in model_dict:
model.oob_score_ = model_dict['oob_score_']
if 'oob_prediction_' in model_dict:
model.oob_prediction_ = np.array(model_dict['oob_prediction_'])
return model
def _fit_random_forest(X_train, y_train,
obj_func_name = "mse",
sample_weight = None,
model_params = None,
log_target_reg = False):
if model_params is None:
model_params = {}
# checking if obj_func is correct
_check_obj_func_name(obj_func_name, "random_forest")
if "criterion" in model_params.keys():
assert obj_func_name == model_params["criterion"], "use the obj_func_name argument instead of setting criterion in model_params"
model_params["criterion"] = obj_func_name
model = RandomForestRegressor(**model_params)
if log_target_reg:
model = _log_target_regressor(model)
model.fit(X = X_train, y = y_train, sample_weight = sample_weight)
if log_target_reg:
if hasattr(model.regressor_, "oob_prediction_"):
oob_pred = model.regressor_.oob_prediction_
# must convert back to original units
oob_pred = model.inverse_func(oob_pred)
else:
oob_pred = None
model.oob_prediction_ = oob_pred
model.feature_importances_ = model.regressor_.feature_importances_
return model
