@File : save_data.py @Time : 2025/04/03 10:02:16 @Author : Alejandro Marrero @Version : 1.0 @Contact : amarrerd@ull.edu.es @License : (C)Copyright 2025, Alejandro Marrero @Desc : None

save_results_to_files(base_dir, filename_pattern, result, variables_names=None, descriptor_names=None, lazily=False, only_instances=False, files_format='parquet')

Saves the results of the generation to CSV files. Args: filename_pattern (str): Pattern for the filenames. result (GenResult): Result of the generation. variables_names (Sequence[str]): Names of the variables. lazily (bool, optional): Whether the instances inside the result object should be collected as a LazyFrame or a DataFrame. Defaults ot False. only_instances (bool): Generate only the files with the resulting instances. Default True. If False, it would generate an history and arhice_metrics files. files_format (Literal[str] = "csv", "parquet"): Format to store the resulting instances file. Parquet is the most efficient for large datasets.

Source code in digneapy/utils/save_data.py 
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
def save_results_to_files(
    base_dir: Path,
    filename_pattern: str,
    result: GenerationResult,
    variables_names: Optional[Sequence[str]] = None,
    descriptor_names: Optional[Sequence[str]] = None,
    lazily: bool = False,
    only_instances: bool = False,
    files_format: Literal["csv", "parquet"] = "parquet",
):
    """Saves the results of the generation to CSV files.
    Args:
        filename_pattern (str): Pattern for the filenames.
        result (GenResult): Result of the generation.
        variables_names (Sequence[str]): Names of the variables.
        lazily (bool, optional): Whether the instances inside the result object
            should be collected as a LazyFrame or a DataFrame. Defaults ot False.
        only_instances (bool): Generate only the files with the resulting instances.
            Default True. If False, it would generate an history and arhice_metrics files.
        files_format (Literal[str] = "csv", "parquet"): Format to store the resulting instances file. Parquet is the most efficient for large datasets.
    """
    if files_format not in ("csv", "parquet"):
        warnings.warn(
            f"Unrecognised file format: {files_format}. Selecting parquet as fallback.",
            category=RuntimeWarning,
            stacklevel=2,
        )
        files_format = "parquet"
    _saving_fn = __saving_methods[files_format]
    if len(result.instances) != 0:
        frames = pl.concat(
            [
                instance.to_df(
                    variables_names=variables_names,
                    descriptor_names=descriptor_names,
                    portfolio_names=result.solvers,
                    lazy=lazily,
                )
                for instance in result.instances
            ],
            how="vertical_relaxed",
        )
        _saving_fn(
            frames=frames,
            base_dir=base_dir,
            filename_pattern=filename_pattern,
            lazily=lazily,
        )

        if not only_instances:
            result.history.to_df().write_csv(
                base_dir / f"{filename_pattern}_history.csv"
            )
            if result.metrics is not None:
                result.metrics.write_csv(
                    base_dir / f"{filename_pattern}_archive_metrics.csv"
                )
    else:
        warnings.warn(
            "Archive in Generation result is empty. Nothing to do in save_results_to_files.",
            category=RuntimeWarning,
            stacklevel=2,
        )