Skip to content

Run data parser

Config

Bases: BaseModel

Store configurations for a runs. Attributes: runs (List[RunConfig]): The list of run configurations.

Source code in src/pheval/analyse/run_data_parser.py 
87
88
89
90
91
92
93
94
95
96
class Config(BaseModel):
    """
    Store configurations for a runs.
    Attributes:
        runs (List[RunConfig]): The list of run configurations.
    """

    benchmark_name: str
    runs: list[RunConfig]
    plot_customisation: PlotCustomisation

PlotCustomisation

Bases: BaseModel

Store customisations for all plots. Attributes: gene_plots (SinglePlotCustomisation): Customisation for all gene benchmarking plots. disease_plots (SinglePlotCustomisation): Customisation for all disease benchmarking plots. variant_plots (SinglePlotCustomisation): Customisation for all variant benchmarking plots.

Source code in src/pheval/analyse/run_data_parser.py 
73
74
75
76
77
78
79
80
81
82
83
84
class PlotCustomisation(BaseModel):
    """
    Store customisations for all plots.
    Attributes:
        gene_plots (SinglePlotCustomisation): Customisation for all gene benchmarking plots.
        disease_plots (SinglePlotCustomisation): Customisation for all disease benchmarking plots.
        variant_plots (SinglePlotCustomisation): Customisation for all variant benchmarking plots.
    """

    gene_plots: SinglePlotCustomisation
    disease_plots: SinglePlotCustomisation
    variant_plots: SinglePlotCustomisation

RunConfig

Bases: BaseModel

Store configurations for a run.

Attributes:

Name Type Description
run_identifier str

The run identifier.
phenopacket_dir str

The path to the phenopacket directory used for generating the results.
results_dir str

The path to the result directory.
gene_analysis bool

Whether to benchmark gene analysis results.
variant_analysis bool

Whether to benchmark variant analysis results.
disease_analysis bool

Whether to benchmark disease analysis results.
threshold Optional[float]

The threshold to consider for benchmarking.
score_order Optional[str]

The order of scores to consider for benchmarking, either ascending or descending.
Source code in src/pheval/analyse/run_data_parser.py 
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
class RunConfig(BaseModel):
    """
    Store configurations for a run.

    Attributes:
        run_identifier (str): The run identifier.
        phenopacket_dir (str): The path to the phenopacket directory used for generating the results.
        results_dir (str): The path to the result directory.
        gene_analysis (bool): Whether to benchmark gene analysis results.
        variant_analysis (bool): Whether to benchmark variant analysis results.
        disease_analysis (bool): Whether to benchmark disease analysis results.
        threshold (Optional[float]): The threshold to consider for benchmarking.
        score_order (Optional[str]): The order of scores to consider for benchmarking, either ascending or descending.
    """

    run_identifier: str
    phenopacket_dir: Path
    results_dir: Path
    gene_analysis: bool
    variant_analysis: bool
    disease_analysis: bool
    threshold: float | None
    score_order: str | None

    @field_validator("threshold", mode="before")
    @classmethod
    def set_threshold(cls, threshold):
        return threshold or None

    @field_validator("score_order", mode="before")
    @classmethod
    def set_score_order(cls, score_order):
        return score_order or "descending"

    @field_validator("results_dir", mode="after")
    @classmethod
    def check_results_dir_exists(cls, results_dir: Path):
        if not results_dir.exists():
            raise FileNotFoundError(f"The specified results directory does not exist: {results_dir}")
        return results_dir

SinglePlotCustomisation

Bases: BaseModel

Store customisations for plots.

Attributes:

Name Type Description
plot_type str

The plot type.
rank_plot_title str

The title for the rank summary plot.
roc_curve_title str

The title for the roc curve plot.
precision_recall_title str

The title for the precision-recall plot.
Source code in src/pheval/analyse/run_data_parser.py 
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
class SinglePlotCustomisation(BaseModel):
    """
    Store customisations for plots.

    Attributes:
        plot_type (str): The plot type.
        rank_plot_title (str): The title for the rank summary plot.
        roc_curve_title (str): The title for the roc curve plot.
        precision_recall_title (str): The title for the precision-recall plot.
    """

    plot_type: str | None = "bar_cumulative"
    rank_plot_title: str | None
    roc_curve_title: str | None
    precision_recall_title: str | None

    @field_validator("plot_type", mode="before")
    @classmethod
    def set_plot_type(cls, plot_type):
        return plot_type or "bar_cumulative"

parse_run_config(run_config)

Parse a run configuration yaml file. Args: run_config (Path): The path to the run data yaml configuration. Returns: Config: The parsed run configurations.

Source code in src/pheval/analyse/run_data_parser.py 
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
def parse_run_config(run_config: Path) -> Config:
    """
    Parse a run configuration yaml file.
    Args:
        run_config (Path): The path to the run data yaml configuration.
    Returns:
        Config: The parsed run configurations.
    """
    logger = get_logger()
    logger.info(f"Loading benchmark configuration from {run_config}")
    with open(run_config) as f:
        config_data = yaml.safe_load(f)
    f.close()
    config = Config(**config_data)
    return config