18938519862

Committed 30 Oct 2025 11:05AM UTC coverage: 87.977% (+4.2%) from 83.754%

Build # 18938519862

Build Type

push

github

Committed by

amarrerod

Commit Message

✅ Integrates Numpy as a primary data structure

Run Details

171 of 211 new or added lines in 19 files covered. (81.04%)

11 existing lines in 7 files now uncovered.

2122 of 2412 relevant lines covered (87.98%)

1.76 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

26.32

/digneapy/utils/save_data.py

#!/usr/bin/env python
# -*-coding:utf-8 -*-
"""
@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
"""

from collections.abc import Sequence
from typing import Literal, Optional

import pandas as pd

from digneapy.generators import GenResult


def save_results_to_files(
    filename_pattern: str,
    result: GenResult,
    only_instances: bool = True,
    only_genotypes: bool = False,
    solvers_names: Optional[Sequence[str]] = None,
    features_names: Optional[Sequence[str]] = None,
    vars_names: Optional[Sequence[str]] = None,
    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.
        only_instances (bool): Generate only the files with the resulting instances. Default True. If False, it would generate an history and arhice_metrics files.
        only_genotypes (bool): Extract only the genotype of each instance. Default False (extracts features and portfolio scores).
        solvers_names (Sequence[str]): Names of the solvers.
        features_names (Sequence[str]): Names of the features.
        vars_names (Sequence[str]): Names of the variables.
        files_format (Literal[str] = "csv" or "parquet"): Format to store the resulting instances file.
            Parquet is the most efficient for large datasets.
    """
    if files_format not in ("csv", "parquet"):
        print(f"Unrecognised file format: {files_format}. Selecting parquet.")
        files_format = "parquet"
    df = pd.DataFrame(
        [
            i.to_series(
                only_genotype=only_genotypes,
                variables_names=vars_names,
                features_names=features_names,
                score_names=solvers_names,
            )
            for i in result.instances
        ]
    )
    if not df.empty:
        df.insert(0, "target", result.target)
        if files_format == "csv":
            df.to_csv(f"{filename_pattern}_instances.csv", index=False)
        elif files_format == "parquet":
            df.to_parquet(f"{filename_pattern}_instances.parquet", index=False)

    if not only_instances:
        result.history.to_df().to_csv(f"{filename_pattern}_history.csv", index=False)
        if result.metrics is not None:
            result.metrics.to_csv(f"{filename_pattern}_archive_metrics.csv")

1	#!/usr/bin/env python
2	# --coding:utf-8 --
3	"""
4	@File : save_data.py
5	@Time : 2025/04/03 10:02:16
6	@Author : Alejandro Marrero
7	@Version : 1.0
8	@Contact : amarrerd@ull.edu.es
9	@License : (C)Copyright 2025, Alejandro Marrero
10	@Desc : None
11	"""
12
13	from collections.abc import Sequence	2✔
14	from typing import Literal, Optional	2✔
15
16	import pandas as pd	2✔
17
18	from digneapy.generators import GenResult	2✔
19
20
21	def save_results_to_files(	2✔
22	filename_pattern: str,
23	result: GenResult,
24	only_instances: bool = True,
25	only_genotypes: bool = False,
26	solvers_names: Optional[Sequence[str]] = None,
27	features_names: Optional[Sequence[str]] = None,
28	vars_names: Optional[Sequence[str]] = None,
29	files_format: Literal["csv", "parquet"] = "parquet",
30	):
31	"""Saves the results of the generation to CSV files.
32	Args:
33	filename_pattern (str): Pattern for the filenames.
34	result (GenResult): Result of the generation.
35	only_instances (bool): Generate only the files with the resulting instances. Default True. If False, it would generate an history and arhice_metrics files.
36	only_genotypes (bool): Extract only the genotype of each instance. Default False (extracts features and portfolio scores).
37	solvers_names (Sequence[str]): Names of the solvers.
38	features_names (Sequence[str]): Names of the features.
39	vars_names (Sequence[str]): Names of the variables.
40	files_format (Literal[str] = "csv" or "parquet"): Format to store the resulting instances file.
41	Parquet is the most efficient for large datasets.
42	"""
43	if files_format not in ("csv", "parquet"):	×
UNCOV 44	print(f"Unrecognised file format: {files_format}. Selecting parquet.")	×
UNCOV 45	files_format = "parquet"	×
UNCOV 46	df = pd.DataFrame(	×
47	[
48	i.to_series(
49	only_genotype=only_genotypes,
50	variables_names=vars_names,
51	features_names=features_names,
52	score_names=solvers_names,
53	)
54	for i in result.instances
55	]
56	)
57	if not df.empty:	×
58	df.insert(0, "target", result.target)	×
NEW 59	if files_format == "csv":	×
NEW 60	df.to_csv(f"{filename_pattern}_instances.csv", index=False)	×
NEW 61	elif files_format == "parquet":	×
NEW 62	df.to_parquet(f"{filename_pattern}_instances.parquet", index=False)	×
63
NEW 64	if not only_instances:	×
NEW 65	result.history.to_df().to_csv(f"{filename_pattern}_history.csv", index=False)	×
NEW 66	if result.metrics is not None:	×
NEW 67	result.metrics.to_csv(f"{filename_pattern}_archive_metrics.csv")	×

DIGNEA / DIGNEApy / 18938519862

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous