A programming framework for agentic AI
no search when max_iter < 2
Chi Wangb03a87e73753
diff --git a/flaml/automl.py b/flaml/automl.pyindex a0315a625..08cd66519 100644--- a/flaml/automl.py+++ b/flaml/automl.py@@ -104,6 +104,7 @@ class SearchState:self.trained_estimator = Noneself.sample_size = Noneself.trial_time = 0+ self.best_n_iter = Nonedef update(self, result, time_used, save_model_history=False):if result:@@ -430,7 +431,7 @@ class AutoML:@propertydef time_to_find_best_model(self) -> float:- """time taken to find best model in seconds"""+ """Time taken to find best model in seconds"""return self.__dict__.get("_time_taken_best_iter")def predict(self, X_test):@@ -1768,6 +1769,17 @@ class AutoML:better = True # whether we find a better model in one trialif self._ensemble:self.best_model = {}+ if self._max_iter < 2 and self.estimator_list:+ # when max_iter is 1, no need to search+ self._max_iter = 0+ self._best_estimator = estimator = self.estimator_list[0]+ self._selected = state = self._search_states[estimator]+ state.best_config_sample_size = self._state.data_size+ state.best_config = (+ state.init_config+ if isinstance(state.init_config, dict)+ else state.init_config[0]+ )for self._track_iter in range(self._max_iter):if self._estimator_index is None:estimator = self._active_estimators[0]@@ -1844,9 +1856,9 @@ class AutoML:metric="val_loss",mode="min",space=search_space,- points_to_evaluate=points_to_evaluate- if len(search_state.init_config) == len(search_space)- else None,+ points_to_evaluate=[+ p for p in points_to_evaluate if len(p) == len(search_space)+ ],)search_state.search_alg = ConcurrencyLimiter(algo, max_concurrent=1)# search_state.search_alg = algodiff --git a/flaml/model.py b/flaml/model.pyindex 385bef499..740515507 100644--- a/flaml/model.py+++ b/flaml/model.py@@ -465,7 +465,7 @@ class XGBoostEstimator(SKLearnEstimator):def predict(self, X_test):import xgboost as xgb-+if not issparse(X_test):X_test = self._preprocess(X_test)dtest = xgb.DMatrix(X_test)diff --git a/test/test_automl.py b/test/test_automl.pyindex 97297c8b3..7ccbda76b 100644--- a/test/test_automl.py+++ b/test/test_automl.py@@ -31,7 +31,7 @@ class MyRegularizedGreedyForest(SKLearnEstimator):self.estimator_class = RGFClassifierelse:from rgf.sklearn import RGFRegressor-+self.estimator_class = RGFRegressor@classmethoddiff --git a/test/test_training_log.py b/test/test_training_log.pyindex 73de45d25..20c728c01 100644--- a/test/test_training_log.py+++ b/test/test_training_log.py@@ -25,23 +25,49 @@ class TestTrainingLog(unittest.TestCase):"mem_thres": 1024 * 1024,"n_jobs": 1,"model_history": True,- "train_time_limit": 0.01,+ "train_time_limit": 0.1,"verbose": 3,"ensemble": True,"keep_search_state": True,}X_train, y_train = fetch_california_housing(return_X_y=True)automl.fit(X_train=X_train, y_train=y_train, **automl_settings)- automl._state._train_with_config(automl.best_estimator, automl.best_config)-# Check if the training log file is populated.self.assertTrue(os.path.exists(filename))- with training_log_reader(filename) as reader:- count = 0- for record in reader.records():- print(record)- count += 1- self.assertGreater(count, 0)+ if automl.best_estimator:+ estimator, config = automl.best_estimator, automl.best_config+ model0 = automl.best_model_for_estimator(estimator)+ print(model0.estimator)++ automl.time_budget = None+ model, _ = automl._state._train_with_config(estimator, config)+ # model0 and model are equivalent unless model0's n_estimator is out of search space range+ assert (+ str(model0.estimator) == str(model.estimator)+ or model0["n_estimators"] < 4+ )++ # assuming estimator & config are saved and loaded as follows+ automl = AutoML()+ automl.fit(+ X_train=X_train,+ y_train=y_train,+ max_iter=0,+ task="regression",+ estimator_list=[estimator],+ n_jobs=1,+ starting_points={estimator: config},+ )+ # then the fitted model should be equivalent to model+ # print(str(model.estimator), str(automl.model.estimator))+ assert str(model.estimator) == str(automl.model.estimator)++ with training_log_reader(filename) as reader:+ count = 0+ for record in reader.records():+ print(record)+ count += 1+ self.assertGreater(count, 0)automl_settings["log_file_name"] = Noneautoml.fit(X_train=X_train, y_train=y_train, **automl_settings)