diff --git a/data/QUGS/convert.py b/data/QUGS/convert.py index d1a686e..2982a03 100644 --- a/data/QUGS/convert.py +++ b/data/QUGS/convert.py @@ -73,26 +73,6 @@ class DataProcessor: else: self.data = self._load_all_data() - def _extract_column_names(self, file_path: str) -> List[str]: - """ - Extracts column names from the header of the given file. - Assumes the 6th line contains column names. - - :param file_path: Path to the data file. - :return: List of column names. - """ - with open(file_path, "r") as f: - header_lines = [next(f) for _ in range(12)] - - # Extract column names from the 6th line - channel_line = header_lines[10].strip() - tokens = re.findall(r'"([^"]+)"', channel_line) - if not channel_line.startswith('"'): - first_token = channel_line.split()[0] - tokens = [first_token] + tokens - - return tokens # Prepend 'Time' column if applicable - def _load_dataframe(self, file_path: str) -> OriginalSingleDamageScenario: """ Loads a single data file into a pandas DataFrame. @@ -100,11 +80,7 @@ class DataProcessor: :param file_path: Path to the data file. :return: DataFrame containing the numerical data. """ - col_names = self._extract_column_names(file_path) - df = pd.read_csv( - file_path, delim_whitespace=True, skiprows=11, header=None, memory_map=True - ) - df.columns = col_names + df = pd.read_csv(file_path, delim_whitespace=True, skiprows=10, header=0, memory_map=True) return df def _load_all_data(self) -> GroupDataset: