ce4a5ca7cab1ea4ae421fbcd3b28205b1e18158d,deepchem/models/tests/test_overfit.py,TestOverfitAPI,test_sklearn_regression_overfit,#TestOverfitAPI#,37

Before Change

  def test_sklearn_regression_overfit(self):
    Test that sklearn models can overfit simple regression datasets.
    tasks = ["task0"]
    task_types = {task: "regression" for task in tasks}
    n_samples = 10
    n_features = 3
    n_tasks = len(tasks)
    
    // Generate dummy dataset
    np.random.seed(123)
    ids = np.arange(n_samples)
    X = np.random.rand(n_samples, n_features)
    y = np.random.rand(n_samples, n_tasks)
    w = np.ones((n_samples, n_tasks))

    dataset = Dataset.from_numpy(self.train_dir, X, y, w, ids, tasks)

    model_params = {
      "batch_size": None,
      "data_shape": dataset.get_data_shape()
    }

    verbosity = "high"
    regression_metric = Metric(metrics.r2_score, verbosity=verbosity)
    model = SklearnModel(tasks, task_types, model_params, self.model_dir,
                         mode="regression",
                         model_instance=RandomForestRegressor())

    // Fit trained model
    model.fit(dataset)
    model.save()

After Change

    verbosity = "high"
    regression_metric = Metric(metrics.r2_score, verbosity=verbosity)
    sklearn_model = RandomForestRegressor()
    model = SklearnModel(sklearn_model, self.model_dir)

    // Fit trained model
    model.fit(dataset)
    model.save()

Instances