def test_slice_features_original_unchanged(self): df = pd.DataFrame([[1, 2, 3], [4, 5, 6], [7, 8, 9]], columns=["weight", "height", "age"]) labels = ["m", "f", "m"] dataset = DataSet(df, labels=labels) sliced = dataset.slice_features(["weight", "height"]) # Modify sliced data sliced.set_column("weight", [0, 0, 0]) sliced.labels[0] = "x" # Check that it was indeed changed assert_that(sliced.get_column("weight"), contains(0, 0, 0)) assert_that(sliced.get_labels(), contains("x", "f", "m")) # Verify it was not changed in the original dataset assert_that(dataset.get_column("weight"), contains(1, 4, 7)) assert_that(dataset.get_labels(), contains(*labels))
def test_get_column(self): dataset = DataSet([[1, 2, 3], [4, 5, 6], [7, 8, 9]]) column1 = dataset.get_column(1) assert_that(column1.values, contains(2, 5, 8))
def test_get_column_set_value(self): dataset = DataSet([[1, 2, 3], [4, 5, 6], [7, 8, 9]]) dataset.get_column(1)[:] = 1 assert_that(dataset.get_column(1), contains(1, 1, 1))