Function debug_data_cli

spacy/cli/debug_data.py:71–120

Analyze, debug and validate your training and development data. Outputs useful stats, and can help you find problems like invalid entity annotations, cyclic dependencies, low data labels and more. DOCS: https://spacy.io/api/cli#debug-data

(
    # fmt: off
    ctx: typer.Context,  # This is only used to read additional arguments
    config_path: Path = Arg(
        ..., help="Path to config file", exists=True, allow_dash=True
    ),
    code_path: Optional[Path] = Opt(
        None,
        "--code-path",
        "--code",
        "-c",
        help="Path to Python file with additional code (registered functions) to be imported",
    ),
    ignore_warnings: bool = Opt(
        False,
        "--ignore-warnings",
        "-IW",
        help="Ignore warnings, only show stats and errors",
    ),
    verbose: bool = Opt(
        False, "--verbose", "-V", help="Print additional information and explanations"
    ),
    no_format: bool = Opt(
        False, "--no-format", "-NF", help="Don't pretty-print the results"
    ),
    # fmt: on
)

    hidden=True,  # hide this from main CLI help but still allow it to work with warning
)
def debug_data_cli(
    # fmt: off
    ctx: typer.Context,  # This is only used to read additional arguments
    config_path: Path = Arg(
        ..., help="Path to config file", exists=True, allow_dash=True
    ),
    code_path: Optional[Path] = Opt(
        None,
        "--code-path",
        "--code",
        "-c",
        help="Path to Python file with additional code (registered functions) to be imported",
    ),
    ignore_warnings: bool = Opt(
        False,
        "--ignore-warnings",
        "-IW",
        help="Ignore warnings, only show stats and errors",
    ),
    verbose: bool = Opt(
        False, "--verbose", "-V", help="Print additional information and explanations"
    ),
    no_format: bool = Opt(
        False, "--no-format", "-NF", help="Don't pretty-print the results"
    ),
    # fmt: on
):
    """
    Analyze, debug and validate your training and development data. Outputs
    useful stats, and can help you find problems like invalid entity annotations,
    cyclic dependencies, low data labels and more.

    DOCS: https://spacy.io/api/cli#debug-data
    """
    if ctx.command.name == "debug-data":
        msg.warn(
            "The debug-data command is now available via the 'debug data' "
            "subcommand (without the hyphen). You can run python -m spacy debug "
            "--help for an overview of the other available debugging commands."
        )
    overrides = parse_config_overrides(ctx.args)
    import_code(code_path)
    debug_data(
        config_path,
        config_overrides=overrides,
        ignore_warnings=ignore_warnings,
        verbose=verbose,
        no_format=no_format,
        silent=False,
    )


def debug_data(