conventions

Naming conventions for the EFTS netCDF file format.

TYPES_CONVERTIBLE_TO_TIMESTAMP module-attribute

TYPES_CONVERTIBLE_TO_TIMESTAMP = [
    str,
    datetime,
    datetime64,
    Timestamp,
]

Definition of a 'type' for type hints.

AttributesErrorLevel

Bases: Enum

Controls the behavior of variable attribute checking functions.

check_hydrologic_variables

check_hydrologic_variables(
    file_path: str,
) -> Dict[str, List[str]]

Checks if the variable names and attributes in a netCDF file comply with the STF convention.

Parameters:

• file_path (str) –

  The path to the netCDF file.

Returns:

• Dict[str, List[str]] –

  Dict[str, List[str]]: A dictionary with keys "INFO", "WARNING", "ERROR" and values as lists of strings describing compliance issues.

Source code in src/efts_io/conventions.py

def check_hydrologic_variables(file_path: str) -> Dict[str, List[str]]:
    """Checks if the variable names and attributes in a netCDF file comply with the STF convention.

    Args:
        file_path (str): The path to the netCDF file.

    Returns:
        Dict[str, List[str]]: A dictionary with keys "INFO", "WARNING", "ERROR" and values as lists of strings describing compliance issues.
    """
    try:
        dataset = None
        dataset = nc.Dataset(file_path, mode="r")
        results = {"INFO": [], "WARNING": [], "ERROR": []}

        for var in dataset.variables:
            if _is_structural_varname(var):
                continue
            if _is_known_hydro_varname(var):
                results["INFO"].append(f"Hydrologic variable '{var}' follows the recommended naming convention.")

                # Check attributes
                for msg in _check_variable_attributes(dataset.variables[var]):
                    results["WARNING"].append(msg)
            else:
                results["WARNING"].append(
                    f"Hydrologic variable '{var}' does not follow the recommended naming convention.",
                )

        return results  # noqa: TRY300

    except Exception as e:  # noqa: BLE001
        return {"ERROR": [f"Error opening or reading file '{file_path}': {e!s}"]}

    finally:
        if dataset:
            dataset.close()

check_index_found

check_index_found(
    index_id: Optional[int],
    identifier: str,
    dimension_id: str,
) -> None

Helper function to check that a value (index) was is indeed found in the dimension.

Source code in src/efts_io/conventions.py

def check_index_found(
    index_id: Optional[int],
    identifier: str,
    dimension_id: str,
) -> None:
    """Helper function to check that a value (index) was is indeed found in the dimension."""
    # return isinstance(index_id, np.int64)
    if index_id is None:
        raise ValueError(
            f"identifier '{identifier}' not found in the dimension '{dimension_id}'",
        )

check_optional_variable_attributes

check_optional_variable_attributes(
    variable: Any,
    error_threshold: AttributesErrorLevel = AttributesErrorLevel.NONE,
) -> List[str]

Checks if the attributes of the observed variable comply with the conventions.

Source code in src/efts_io/conventions.py

def check_optional_variable_attributes(
    variable: Any,
    error_threshold: AttributesErrorLevel = AttributesErrorLevel.NONE,
) -> List[str]:
    """Checks if the attributes of the observed variable comply with the conventions."""
    missing_attributes_messages = []
    required_attributes = {
        STANDARD_NAME_ATTR_KEY: str,
        LONG_NAME_ATTR_KEY: str,
        UNITS_ATTR_KEY: str,
    }
    return _check_attrs(variable, required_attributes, missing_attributes_messages, error_threshold=error_threshold)

check_stf_compliance

check_stf_compliance(
    file_path: str,
) -> Dict[str, List[str]]

Checks the compliance of a netCDF file with the STF convention.

Parameters:

• file_path (str) –

  The path to the netCDF file.

Returns:

• Dict[str, List[str]] –

  Dict[str, List[str]]: A dictionary with keys "INFO", "WARNING", "ERROR" and values as lists of strings describing compliance issues.

Source code in src/efts_io/conventions.py

def check_stf_compliance(file_path: str) -> Dict[str, List[str]]:
    """Checks the compliance of a netCDF file with the STF convention.

    Args:
        file_path (str): The path to the netCDF file.

    Returns:
        Dict[str, List[str]]: A dictionary with keys "INFO", "WARNING", "ERROR" and values as lists of strings describing compliance issues.
    """
    try:
        dataset = nc.Dataset(file_path, mode="r")
        results = {"INFO": [], "WARNING": [], "ERROR": []}

        # Check for required dimensions
        required_dims = [TIME_DIMNAME, STATION_DIMNAME, LEAD_TIME_DIMNAME, ENS_MEMBER_DIMNAME, STR_LEN_DIMNAME]
        available_dims = dataset.dimensions.keys()

        for dim in required_dims:
            if dim in available_dims:
                results["INFO"].append(f"Dimension '{dim}' is present.")
            else:
                results["ERROR"].append(f"Missing required dimension '{dim}'.")

        # Check global attributes
        required_global_attributes = [
            TITLE_ATTR_KEY,
            INSTITUTION_ATTR_KEY,
            SOURCE_ATTR_KEY,
            CATCHMENT_ATTR_KEY,
            STF_CONVENTION_VERSION_ATTR_KEY,
            STF_NC_SPEC_ATTR_KEY,
            COMMENT_ATTR_KEY,
            HISTORY_ATTR_KEY,
        ]
        available_global_attributes = dataset.ncattrs()

        for attr in required_global_attributes:
            if attr in available_global_attributes:
                results["INFO"].append(f"Global attribute '{attr}' is present.")
            else:
                results["WARNING"].append(f"Missing global attribute '{attr}'.")

        # Check mandatory variables and their attributes
        mandatory_variables = [
            TIME_DIMNAME,
            STATION_ID_VARNAME,
            STATION_NAME_VARNAME,
            ENS_MEMBER_DIMNAME,
            LEAD_TIME_DIMNAME,
            LAT_VARNAME,
            LON_VARNAME,
        ]
        variable_attributes = {
            TIME_DIMNAME: [
                STANDARD_NAME_ATTR_KEY,
                LONG_NAME_ATTR_KEY,
                UNITS_ATTR_KEY,
                TIME_STANDARD_ATTR_KEY,
                AXIS_ATTR_KEY,
            ],
            STATION_ID_VARNAME: [LONG_NAME_ATTR_KEY],
            STATION_NAME_VARNAME: [LONG_NAME_ATTR_KEY],
            ENS_MEMBER_DIMNAME: [STANDARD_NAME_ATTR_KEY, LONG_NAME_ATTR_KEY, UNITS_ATTR_KEY, AXIS_ATTR_KEY],
            LEAD_TIME_DIMNAME: [STANDARD_NAME_ATTR_KEY, LONG_NAME_ATTR_KEY, UNITS_ATTR_KEY, AXIS_ATTR_KEY],
            LAT_VARNAME: [LONG_NAME_ATTR_KEY, UNITS_ATTR_KEY, AXIS_ATTR_KEY],
            LON_VARNAME: [LONG_NAME_ATTR_KEY, UNITS_ATTR_KEY, AXIS_ATTR_KEY],
        }

        for var in mandatory_variables:
            if var in dataset.variables:
                results["INFO"].append(f"Mandatory variable '{var}' is present.")
                # Check attributes
                for attr, required_attrs in variable_attributes.items():
                    if var == attr:
                        for req_attr in required_attrs:
                            if req_attr in dataset.variables[var].ncattrs():
                                results["INFO"].append(f"Attribute '{req_attr}' for variable '{var}' is present.")
                            else:
                                results["WARNING"].append(
                                    f"Missing required attribute '{req_attr}' for variable '{var}'.",
                                )
            else:
                results["ERROR"].append(f"Missing mandatory variable '{var}'.")

        dataset.close()
        return results  # noqa: TRY300

    except Exception as e:  # noqa: BLE001
        return {"ERROR": [f"Error opening file '{file_path}': {e!s}"]}

convert_to_datetime64_utc

convert_to_datetime64_utc(
    x: ConvertibleToTimestamp,
) -> datetime64

Converts a known timestamp representation an np.datetime64.

Source code in src/efts_io/conventions.py

def convert_to_datetime64_utc(x: ConvertibleToTimestamp) -> np.datetime64:
    """Converts a known timestamp representation an np.datetime64."""
    if isinstance(x, pd.Timestamp):
        if x.tz is None:
            x = x.tz_localize("UTC")
        x = x.tz_convert("UTC")
    elif isinstance(x, datetime):
        x = pd.Timestamp(x, tz="UTC") if x.tzinfo is None else pd.Timestamp(x).tz_convert("UTC")
    elif isinstance(x, str):
        x_dt = pd.to_datetime(x)
        x = pd.Timestamp(x_dt, tz="UTC") if x_dt.tzinfo is None else pd.Timestamp(x_dt).tz_convert("UTC")
    elif isinstance(x, np.datetime64):
        x = pd.Timestamp(x).tz_localize("UTC")
    else:
        raise TypeError(f"Cannot convert {type(x)} to np.datetime64 with UTC timezone.")

    return x.to_datetime64()

exportable_to_stf2

exportable_to_stf2(data: MdDatasetsType) -> bool

Check if the dataset can be written to a netCDF file compliant with STF 2.0 specification.

This method checks if the underlying xarray dataset or dataarray has the required dimensions and global attributes as specified by the STF 2.0 convention.

Returns:

• bool ( bool ) –

  True if the dataset can be written to a STF 2.0 compliant netCDF file, False otherwise.

Source code in src/efts_io/conventions.py

def exportable_to_stf2(data:MdDatasetsType) -> bool:
    """Check if the dataset can be written to a netCDF file compliant with STF 2.0 specification.

    This method checks if the underlying xarray dataset or dataarray has the required dimensions and global attributes as specified by the STF 2.0 convention.

    Returns:
        bool: True if the dataset can be written to a STF 2.0 compliant netCDF file, False otherwise.
    """
    from efts_io.conventions import has_required_stf2_dimensions, has_required_global_attributes, has_required_variables_xr, mandatory_xarray_dimensions  # noqa: I001
    required_stf2_dimensions = has_required_stf2_dimensions(data, mandatory_xarray_dimensions)
    required_attributes = has_required_global_attributes(data)
    required_variables = has_required_variables_xr(data)

    return required_stf2_dimensions and required_attributes and required_variables

get_default_dim_order

get_default_dim_order() -> List[str]

Default order of dimensions in the netCDF file.

Returns:

• List[str] –

  List[str]: dimension names: [lead_time, stations, ensemble_member, time]

Source code in src/efts_io/conventions.py

def get_default_dim_order() -> List[str]:
    """Default order of dimensions in the netCDF file.

    Returns:
        List[str]: dimension names: [lead_time, stations, ensemble_member, time]
    """
    return [
        LEAD_TIME_DIMNAME,
        STATION_DIMNAME,
        ENS_MEMBER_DIMNAME,
        TIME_DIMNAME,
    ]

has_required_global_attributes

has_required_global_attributes(d: MdDatasetsType) -> bool

has_required_global_attributes.

Source code in src/efts_io/conventions.py

def has_required_global_attributes(d: MdDatasetsType) -> bool:
    """has_required_global_attributes."""
    if _is_nc_dataset(d):
        a = d.ncattrs()
        tested = set(a)
    else:
        a = d.attrs.keys()
        tested = set(a)
    return _has_all_members(tested, mandatory_global_attributes)

has_required_stf2_dimensions

has_required_stf2_dimensions(
    d: MdDatasetsType,
    mandatory_dimensions: Optional[Iterable[str]] = None,
) -> bool

Has the dataset the required dimensions for STF conventions.

Parameters:

• d (MdDatasetsType) –

  data object to check

Returns:

• bool ( bool ) –

  Has it the minimum STF dimentions

Source code in src/efts_io/conventions.py

def has_required_stf2_dimensions(d: MdDatasetsType, mandatory_dimensions: Optional[Iterable[str]] = None) -> bool:
    """Has the dataset the required dimensions for STF conventions.

    Args:
        d (MdDatasetsType): data object to check

    Returns:
        bool: Has it the minimum STF dimentions
    """
    mandatory_dimensions = mandatory_dimensions or mandatory_netcdf_dimensions
    return _has_required_dimensions(d, mandatory_dimensions)

has_required_variables_xr

has_required_variables_xr(d: MdDatasetsType) -> bool

has_required_variables.

Source code in src/efts_io/conventions.py

def has_required_variables_xr(d: MdDatasetsType) -> bool:
    """has_required_variables."""
    a = d.variables.keys()
    tested = set(a)
    # Note: even if xarray, we do not need to check for the 'data_vars' attribute here.
    # a = d.data_vars.keys()
    # tested = set(a)
    return _has_all_members(tested, mandatory_varnames_xr)

has_required_xarray_dimensions

has_required_xarray_dimensions(d: MdDatasetsType) -> bool

Has the dataset the required dimensions for an in memory xarray representation.

Source code in src/efts_io/conventions.py

def has_required_xarray_dimensions(d: MdDatasetsType) -> bool:
    """Has the dataset the required dimensions for an in memory xarray representation."""
    return _has_required_dimensions(d, mandatory_xarray_dimensions)

has_variable

has_variable(d: MdDatasetsType, varname: str) -> bool

has_variable.

Source code in src/efts_io/conventions.py

def has_variable(d: MdDatasetsType, varname: str) -> bool:
    """has_variable."""
    a = d.variables.keys()
    tested = set(a)
    return varname in tested

Feedback