Class DefaultDataParser

python/dgl/data/csv_dataset_base.py:367–386

Default data parser for CSVDataset. It 1. ignores any columns which does not have a header. 2. tries to convert to list of numeric values(generated by np.array().tolist()) if cell data is a str separated by ','. 3. read data and infer data type directly, otherwise.

class DefaultDataParser:
    """Default data parser for CSVDataset. It
    1. ignores any columns which does not have a header.
    2. tries to convert to list of numeric values(generated by
        np.array().tolist()) if cell data is a str separated by ','.
    3. read data and infer data type directly, otherwise.
    """

    def __call__(self, df: pd.DataFrame):
        data = {}
        for header in df:
            if "Unnamed" in header:
                dgl_warning("Unnamed column is found. Ignored...")
                continue
            dt = df[header].to_numpy().squeeze()
            if len(dt) > 0 and isinstance(dt[0], str):
                # probably consists of list of numeric values
                dt = np.array([ast.literal_eval(row) for row in dt])
            data[header] = dt
        return data