bgc_data_processing.core.loaders.csv_loaders

CSV Loaders.

CSVLoader(provider_name, category, exclude, variables, read_params=None)

Bases: BaseLoader

Loader class to use with csv files.

Parameters:

Name	Type	Description	Default
provider_name	str	Data provider name.	required
category	str	Category provider belongs to.	required
exclude	list[str]	Filenames to exclude from loading.	required
variables	SourceVariableSet	Storer object containing all variables to consider for this data, both the one in the data file but and the one not represented in the file.	required
read_params	dict | None	Additional parameter to pass to pandas.read_csv., by default None	None

Source code in src/bgc_data_processing/core/loaders/csv_loaders.py

def __init__(
    self,
    provider_name: str,
    category: str,
    exclude: list[str],
    variables: "SourceVariableSet",
    read_params: dict | None = None,
) -> None:
    if read_params is None:
        self._read_params = {}
    else:
        self._read_params = read_params
    super().__init__(
        provider_name=provider_name,
        category=category,
        exclude=exclude,
        variables=variables,
    )

load(filepath, constraints=None)

Load a csv file from filepath.

Parameters:

Name	Type	Description	Default
filepath	Path | str	Path to the file to load.	required
constraints	Constraints | None	Constraints slicer., by default None	None

Returns:

Type	Description
DataFrame	DataFrame corresponding to the file.

Source code in src/bgc_data_processing/core/loaders/csv_loaders.py

def load(
    self,
    filepath: Path | str,
    constraints: Constraints | None = None,
) -> pd.DataFrame:
    """Load a csv file from filepath.

    Parameters
    ----------
    filepath: Path | str
        Path to the file to load.
    constraints : Constraints| None, optional
        Constraints slicer., by default None

    Returns
    -------
    pd.DataFrame
        DataFrame corresponding to the file.
    """
    if constraints is None:
        constraints = Constraints()
    df_raw = self._read(Path(filepath))
    df_form = self._format(df_raw)
    df_type = self._convert_types(df_form)
    df_corr = self._correct(df_type)
    df_sliced = constraints.apply_constraints_to_dataframe(df_corr)
    return self.remove_nan_rows(df_sliced)