def gen_data_single_document()

in src/tab_title_tuning_data.py [0:0]

• 10 lines of code
• 4 McCabe index (conditional complexity)

    def gen_data_single_document(self, dataset: pd.DataFrame, limit=0):
        for col in ['id', 'task', 'task_id', 'test_set_id']:
            if col not in dataset.columns:
                dataset[col] = dataset.index
        results = []
        test_ids = dataset["test_set_id"].unique().tolist()
        if limit > 0:
            test_ids = test_ids[:limit]
        results.extend(self.compute_training_data_for_tests(dataset, test_ids, 1))
        return pd.DataFrame(results)