bgc_data_processing.core.loaders.abfile_loaders

ABfiles Loaders.

ABFileLoader(provider_name, category, exclude, variables, grid_basename)

Bases: BaseLoader

Loader class to use with ABFiles.

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
grid_basename	str	Basename of the ab grid grid file for the loader. => files are considered to be loaded over the same grid.	required

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

def __init__(
    self,
    provider_name: str,
    category: str,
    exclude: list[str],
    variables: "SourceVariableSet",
    grid_basename: str,
) -> None:
    super().__init__(
        provider_name=provider_name,
        category=category,
        exclude=exclude,
        variables=variables,
    )
    self.grid_basename = grid_basename
    self.grid_file = ABFileGrid(basename=grid_basename, action="r")
    self._index = None

level_column: str = 'LEVEL' class-attribute instance-attribute

level_key_bfile: str = 'k' class-attribute instance-attribute

field_key_bfile: str = 'field' class-attribute instance-attribute

pascal_by_seawater_meter: int = 9806 class-attribute instance-attribute

grid_basename = grid_basename instance-attribute

grid_file = ABFileGrid(basename=grid_basename, action='r') instance-attribute

convert_filepath_to_basename(filepath) staticmethod

Convert a filepath to the basename.

Parameters:

Name	Type	Description	Default
filepath	Path | str	Filepath ot convert.	required

Returns:

Type	Description
Path	Basename

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

@staticmethod
def convert_filepath_to_basename(filepath: Path | str) -> Path:
    """Convert a filepath to the basename.

    Parameters
    ----------
    filepath : Path | str
        Filepath ot convert.

    Returns
    -------
    Path
        Basename
    """
    path = Path(filepath)
    return path.parent.joinpath(path.stem)

load(filepath, constraints=None)

Load a abfiles from basename.

Parameters:

Name	Type	Description	Default
filepath	Path | str	Path to the basename of 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/abfile_loaders.py

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

    Parameters
    ----------
    filepath: Path | str
        Path to the basename of 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()
    basename = self.convert_filepath_to_basename(filepath)
    raw_data = self._read(basename=str(basename))
    # transform thickness in depth
    with_depth = self._create_depth_column(raw_data)
    # create date columns
    with_dates = self._set_date_related_columns(with_depth, Path(basename))
    # converts types
    typed = self._convert_types(with_dates)
    # apply corrections
    corrected = self._correct(typed)
    # apply constraints
    constrained = constraints.apply_constraints_to_dataframe(corrected)
    return self.remove_nan_rows(constrained)

is_file_valid(filepath)

Check whether a file is valid or not.

Parameters:

Name	Type	Description	Default
filepath	Path | str	File filepath.	required

Returns:

Type	Description
bool	True if the file can be loaded.

Raises:

Type	Description
FileNotFoundError	If the afile doesn't not exist.
FileNotFoundError	If the bfile doesn't not exist.

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

def is_file_valid(self, filepath: Path | str) -> bool:
    """Check whether a file is valid or not.

    Parameters
    ----------
    filepath : Path | str
        File filepath.

    Returns
    -------
    bool
        True if the file can be loaded.

    Raises
    ------
    FileNotFoundError
        If the afile doesn't not exist.
    FileNotFoundError
        If the bfile doesn't not exist.
    """
    path = Path(filepath)
    basepath = path.parent / path.name[:-2]
    keep_filepath = str(path) not in self.excluded_filenames
    keep_filename = path.name not in self.excluded_filenames
    keep_file = keep_filename and keep_filepath
    keep_basepath = str(basepath) not in self.excluded_filenames
    keep_basename = basepath.name not in self.excluded_filenames
    keep_base = keep_basename and keep_basepath
    afile_path = Path(f"{basepath}.a")
    bfile_path = Path(f"{basepath}.b")
    if not afile_path.is_file():
        error_msg = f"{afile_path} does not exist."
        raise FileNotFoundError(error_msg)
    if not bfile_path.is_file():
        error_msg = f"{bfile_path} does not exist."
        raise FileNotFoundError(error_msg)
    return keep_base and keep_file