def random_test_train_test_split(self): """Test of singletask RF ECFP regression API.""" #splittype = "random" model_params = {} tasks = ["log-solubility"] task_type = "regression" task_types = {task: task_type for task in tasks} input_file = os.path.join(self.current_dir, "example.csv") featurizer = CircularFingerprint(size=1024) loader = DataLoader(tasks=tasks, smiles_field=self.smiles_field, featurizer=featurizer, verbosity="low") dataset = loader.featurize(input_file, self.data_dir) # Splits featurized samples into train/test splitter = RandomSplitter() train_dataset, test_dataset = splitter.train_test_split( dataset, self.train_dir, self.test_dir) assert len(train_dataset) == 8 assert len(test_dataset) == 2