pheval 0.4.7__py3-none-any.whl → 0.5.0__py3-none-any.whl

pheval/post_processing/validate_result_format.py

@@ -0,0 +1,92 @@
+from enum import Enum
+from functools import wraps
+from typing import Callable
+
+import polars as pl
+
+
+class ResultSchema(Enum):
+    """
+    Enum for different result schema formats.
+    Attributes:
+        GENE_RESULT_SCHEMA (pl.Schema): Schema for gene-based results.
+        VARIANT_RESULT_SCHEMA (pl.Schema): Schema for variant-based results.
+        DISEASE_RESULT_SCHEMA (pl.Schema): Schema for disease-based results.
+    """
+
+    GENE_RESULT_SCHEMA = pl.Schema(
+        {
+            "gene_symbol": pl.String,
+            "gene_identifier": pl.String,
+            "score": pl.Float64,
+            "grouping_id": pl.Utf8,
+        }
+    )
+    VARIANT_RESULT_SCHEMA = pl.Schema(
+        {
+            "chrom": pl.String,
+            "start": pl.Int64,
+            "end": pl.Int64,
+            "ref": pl.String,
+            "alt": pl.String,
+            "score": pl.Float64,
+            "grouping_id": pl.Utf8,
+        }
+    )
+    DISEASE_RESULT_SCHEMA = pl.Schema(
+        {
+            "disease_name": pl.String,
+            "disease_identifier": pl.String,
+            "score": pl.Float64,
+            "grouping_id": pl.Utf8,
+        }
+    )
+
+    def validate(self, df: pl.DataFrame) -> bool:
+        """
+        Validate that a DataFrame follows the expected schema.
+        Args:
+            df (pl.DataFrame): The DataFrame to validate.
+        Raises:
+            ValueError: If a required column is missing or the grouping_id column contains a null value.
+            TypeError: If a column exists but has an incorrect data type.
+        Returns:
+            bool: True if the DataFrame is valid according to the schema.
+        """
+        expected_schema = self.value
+
+        if "grouping_id" in df.columns and df["grouping_id"].null_count() > 0:
+            raise ValueError("'grouping_id' column should not contain null values if provided.")
+
+        for col_name, expected_type in expected_schema.items():
+            if col_name not in df.schema:
+                if col_name == "grouping_id":
+                    continue
+                raise ValueError(f"Missing required column: {col_name}")
+
+            if df.schema[col_name] != expected_type:
+                raise TypeError(
+                    f"Column '{col_name}' has type {df.schema[col_name]}, expected {expected_type}"
+                )
+
+        return True
+
+
+def validate_dataframe(schema: ResultSchema) -> Callable:
+    """
+    Decorator to validate DataFrame input based on a ResultSchema.
+    Args:
+        schema (ResultSchema): The expected schema from the `ResultSchema` enum.
+    Returns:
+        Callable: A wrapped function that validates the DataFrame before execution.
+    """
+
+    def decorator(func: Callable) -> Callable:
+        @wraps(func)
+        def wrapper(df: pl.DataFrame, *args, **kwargs):
+            schema.validate(df)
+            return func(df, *args, **kwargs)
+
+        return wrapper
+
+    return decorator

pheval/prepare/update_phenopacket.py

@@ -1,7 +1,7 @@
-from collections import defaultdict
 from pathlib import Path
 from typing import Union
 
+import polars as pl
 from phenopackets import Family, Phenopacket
 
 from pheval.utils.file_utils import all_files
@@ -9,14 +9,14 @@ from pheval.utils.phenopacket_utils import (
     GeneIdentifierUpdater,
     PhenopacketRebuilder,
     PhenopacketUtil,
-    create_hgnc_dict,
+    create_gene_identifier_map,
     phenopacket_reader,
     write_phenopacket,
 )
 
 
 def update_outdated_gene_context(
-    phenopacket_path: Path, gene_identifier: str, hgnc_data: defaultdict
+    phenopacket_path: Path, gene_identifier: str, identifier_map: pl.DataFrame
 ) -> Union[Phenopacket, Family]:
     """
     Update the gene context of the Phenopacket.
@@ -24,7 +24,7 @@ def update_outdated_gene_context(
     Args:
         phenopacket_path (Path): The path to the Phenopacket file.
         gene_identifier (str): Identifier to update the gene context.
-        hgnc_data (defaultdict): The HGNC data used for updating.
+        identifier_map (pl.DataFrame): The gene identifier map used for updating.
 
     Returns:
         Union[Phenopacket, Family]: The updated Phenopacket or Family.
@@ -37,7 +37,7 @@ def update_outdated_gene_context(
     phenopacket = phenopacket_reader(phenopacket_path)
     interpretations = PhenopacketUtil(phenopacket).interpretations()
     updated_interpretations = GeneIdentifierUpdater(
-        hgnc_data=hgnc_data, gene_identifier=gene_identifier
+        identifier_map=identifier_map, gene_identifier=gene_identifier
     ).update_genomic_interpretations_gene_identifier(interpretations, phenopacket_path)
     return PhenopacketRebuilder(phenopacket).update_interpretations(updated_interpretations)
 
@@ -57,8 +57,10 @@ def create_updated_phenopacket(
         to update to the current gene identifier in the Phenopacket. We recommend using the ENSEMBL namespace
         to describe the gene identifiers.
     """
-    hgnc_data = create_hgnc_dict()
-    updated_phenopacket = update_outdated_gene_context(phenopacket_path, gene_identifier, hgnc_data)
+    identifier_map = create_gene_identifier_map()
+    updated_phenopacket = update_outdated_gene_context(
+        phenopacket_path, gene_identifier, identifier_map
+    )
     write_phenopacket(updated_phenopacket, output_dir.joinpath(phenopacket_path.name))
 
 
@@ -78,10 +80,10 @@ def create_updated_phenopackets(
         to update to the current gene identifier in the Phenopacket. We recommend using the ENSEMBL namespace
         to describe the gene identifiers.
     """
-    hgnc_data = create_hgnc_dict()
+    identifier_map = create_gene_identifier_map()
     for phenopacket_path in all_files(phenopacket_dir):
         updated_phenopacket = update_outdated_gene_context(
-            phenopacket_path, gene_identifier, hgnc_data
+            phenopacket_path, gene_identifier, identifier_map
         )
         write_phenopacket(updated_phenopacket, output_dir.joinpath(phenopacket_path.name))
 

pheval/utils/logger.py

@@ -0,0 +1,35 @@
+import logging
+
+logging.basicConfig(
+    level=logging.INFO,
+    format="[%(asctime)s] [%(levelname)s] [%(filename)s:%(lineno)d] - %(message)s",
+    datefmt="%Y-%m-%d %H:%M:%S",
+)
+
+
+def get_logger(name="PHEVAL"):
+    return logging.getLogger(name)
+
+
+def print_ascii_banner():
+    """Prints ASCII banner only once when the script starts."""
+    if not getattr(logging, "_ascii_printed", False):
+        logging._ascii_printed = True
+        pheval_banner = """
+        Welcome to:
+        ██████╗ ██╗  ██╗███████╗██╗   ██╗ █████╗ ██╗
+        ██╔══██╗██║  ██║██╔════╝██║   ██║██╔══██╗██║
+        ██████╔╝███████║█████╗  ██║   ██║███████║██║
+        ██╔═══╝ ██╔══██║██╔══╝  ╚██╗ ██╔╝██╔══██║██║
+        ██║     ██║  ██║███████╗ ╚████╔╝ ██║  ██║███████╗
+        ╚═╝     ╚═╝  ╚═╝╚══════╝  ╚═══╝  ╚═╝  ╚═╝╚══════╝
+        A framework for the empirical evaluation of phenotype-driven prioritisation tools.
+        """
+        print(pheval_banner)
+
+
+def initialise_context(ctx):
+    ctx.ensure_object(dict)
+    if not getattr(ctx, "ascii_printed", False):
+        ctx.ascii_printed = True
+        print_ascii_banner()

pheval/utils/phenopacket_utils.py

@@ -1,13 +1,12 @@
 import json
 import logging
 import os
-from collections import defaultdict
 from copy import copy
 from dataclasses import dataclass
 from pathlib import Path
 from typing import List, Union
 
-import pandas as pd
+import polars as pl
 from google.protobuf.json_format import MessageToJson, Parse
 from phenopackets import (
     Disease,
@@ -122,79 +121,65 @@ class ProbandDisease:
     disease_identifier: str
 
 
-def read_hgnc_data() -> pd.DataFrame:
+def parse_hgnc_data() -> pl.DataFrame:
     """
-    Read HGNC data from a file and return it as a Pandas DataFrame.
+    Read HGNC data from a file and return it as a Polars DataFrame.
 
     Returns:
-        pd.DataFrame: DataFrame containing the HGNC data.
+        pl.DataFrame: DataFrame containing the HGNC data.
     """
-    return pd.read_csv(
-        os.path.dirname(__file__).replace("utils", "resources/hgnc_complete_set.txt"),
-        delimiter="\t",
-        dtype=str,
+    return (
+        pl.read_csv(
+            os.path.dirname(__file__).replace("utils", "resources/hgnc_complete_set.txt"),
+            separator="\t",
+            infer_schema=10000000000,
+            dtypes={"omim_id": pl.Utf8},
+        )
+        .select(
+            [
+                pl.col("hgnc_id").alias("hgnc_id"),
+                pl.col("symbol").alias("gene_symbol"),
+                pl.col("ensembl_gene_id").alias("ensembl_id"),
+                pl.col("entrez_id").alias("entrez_id"),
+                pl.col("refseq_accession").alias("refseq_accession"),
+                pl.col("prev_symbol").alias("previous_symbol_raw"),
+            ]
+        )
+        .with_columns(
+            pl.col("previous_symbol_raw")
+            .str.split("|")
+            .list.eval(pl.element().str.strip_chars('"'))
+            .alias("prev_symbols")
+        )
     )
 
 
-def create_hgnc_dict() -> defaultdict:
-    """
-    Create a dictionary as a reference for updating gene symbols and identifiers based on HGNC data.
-
-
-    Returns:
-        defaultdict: A dictionary containing gene symbols as keys and their associated gene information.
-
-    Notes:
-        The dictionary structure:
-        {
-            'gene_symbol': {
-                'ensembl_id': str,
-                'hgnc_id': str,
-                'entrez_id': str,
-                'refseq_accession': str,
-                'previous_symbol': [str, ...]
-            },
-            ...
-        }
-    """
-    hgnc_df = read_hgnc_data()
-    hgnc_data = defaultdict(dict)
-    for _index, row in hgnc_df.iterrows():
-        previous_names = []
-        hgnc_data[row["symbol"]]["ensembl_id"] = row["ensembl_gene_id"]
-        hgnc_data[row["symbol"]]["hgnc_id"] = row["hgnc_id"]
-        hgnc_data[row["symbol"]]["entrez_id"] = row["entrez_id"]
-        hgnc_data[row["symbol"]]["refseq_accession"] = row["refseq_accession"]
-        previous = str(row["prev_symbol"]).split("|")
-        for p in previous:
-            previous_names.append(p.strip('"'))
-        hgnc_data[row["symbol"]]["previous_symbol"] = previous_names
-
-    return hgnc_data
-
-
-def create_gene_identifier_map() -> dict:
+def create_gene_identifier_map() -> pl.DataFrame:
     """
     Create a mapping of gene identifiers to gene symbols using HGNC data.
 
     Returns:
-        dict: A mapping of gene identifiers to gene symbols.
-
-    Notes:
-        The dictionary structure:
-        {
-            'identifier': 'gene_symbol',
-            ...
-        }
+        pl.DataFrame: A mapping of gene identifiers to gene symbols.
     """
-    hgnc_df = read_hgnc_data()
-    identifier_map = {}
-    for _index, row in hgnc_df.iterrows():
-        identifier_map[row["ensembl_gene_id"]] = row["symbol"]
-        identifier_map[row["hgnc_id"]] = row["symbol"]
-        identifier_map[row["entrez_id"]] = row["symbol"]
-        identifier_map[row["refseq_accession"]] = row["symbol"]
-    return identifier_map
+    hgnc_df = parse_hgnc_data()
+    return hgnc_df.melt(
+        id_vars=["gene_symbol", "prev_symbols"],
+        value_vars=["ensembl_id", "hgnc_id", "entrez_id", "refseq_accession"],
+        variable_name="identifier_type",
+        value_name="identifier",
+    ).with_columns(
+        pl.col("identifier_type")
+        .replace(
+            {
+                "ensembl_id": "ensembl:",
+                "hgnc_id": "",
+                "entrez_id": "ncbigene:",
+                "refseq_accession": "",
+            },
+            default="",
+        )
+        .alias("prefix")
+    )
 
 
 def phenopacket_reader(file: Path) -> Union[Phenopacket, Family]:
@@ -651,17 +636,19 @@ def write_phenopacket(phenopacket: Union[Phenopacket, Family], output_file: Path
 class GeneIdentifierUpdater:
     """Class for updating gene identifiers within genomic interpretations."""
 
-    def __init__(self, gene_identifier: str, hgnc_data: dict = None, identifier_map: dict = None):
+    def __init__(
+        self,
+        gene_identifier: str,
+        identifier_map: pl.DataFrame = None,
+    ):
         """
         Initialise the GeneIdentifierUpdater.
 
         Args:
             gene_identifier (str): The gene identifier to update to.
-            hgnc_data (dict): A dictionary containing HGNC data (default: None).
-            identifier_map (dict): A dictionary mapping gene identifiers (default: None).
+            identifier_map (dict): A polars dataframe mapping gene identifiers (default: None).
         """
 
-        self.hgnc_data = hgnc_data
         self.gene_identifier = gene_identifier
         self.identifier_map = identifier_map
 
@@ -675,13 +662,20 @@ class GeneIdentifierUpdater:
         Returns:
             str: The identified gene identifier.
         """
-        if gene_symbol in self.hgnc_data.keys():
-            return self.hgnc_data[gene_symbol][self.gene_identifier]
-        else:
-            for _symbol, data in self.hgnc_data.items():
-                for prev_symbol in data["previous_symbol"]:
-                    if prev_symbol == gene_symbol:
-                        return data[self.gene_identifier]
+        matches = self.identifier_map.filter(
+            (pl.col("gene_symbol") == gene_symbol)
+            & (pl.col("identifier_type") == self.gene_identifier)
+        )
+
+        if matches.height > 0:
+            return matches["identifier"][0]
+        prev_symbol_matches = self.identifier_map.filter(
+            (pl.col("identifier_type") == self.gene_identifier)
+            & (pl.col("prev_symbols").list.contains(gene_symbol))
+        )
+        if prev_symbol_matches.height > 0:
+            return prev_symbol_matches["identifier"][0]
+        return None
 
     def obtain_gene_symbol_from_identifier(self, query_gene_identifier: str) -> str:
         """
@@ -693,7 +687,9 @@ class GeneIdentifierUpdater:
         Returns:
             str: The gene symbol corresponding to the identifier.
         """
-        return self.identifier_map[query_gene_identifier]
+        return self.identifier_map.filter(pl.col("identifier") == query_gene_identifier)[
+            "gene_symbol"
+        ][0]
 
     def _find_alternate_ids(self, gene_symbol: str) -> List[str]:
         """
@@ -705,23 +701,20 @@ class GeneIdentifierUpdater:
         Returns:
             List[str]: List of alternate IDs for the gene symbol.
         """
-        if gene_symbol in self.hgnc_data.keys():
-            return [
-                self.hgnc_data[gene_symbol]["hgnc_id"],
-                "ncbigene:" + self.hgnc_data[gene_symbol]["entrez_id"],
-                "ensembl:" + self.hgnc_data[gene_symbol]["ensembl_id"],
-                "symbol:" + gene_symbol,
+        matches = self.identifier_map.filter((pl.col("gene_symbol") == gene_symbol))
+        if matches.height > 0:
+            return [f"{row['prefix']}{row['identifier']}" for row in matches.rows(named=True)] + [
+                f"symbol:{gene_symbol}"
             ]
-        else:
-            for symbol, data in self.hgnc_data.items():
-                for prev_symbol in data["previous_symbol"]:
-                    if prev_symbol == gene_symbol:
-                        return [
-                            data["hgnc_id"],
-                            "ncbigene:" + data["entrez_id"],
-                            "ensembl:" + data["ensembl_id"],
-                            "symbol:" + symbol,
-                        ]
+        prev_symbol_matches = self.identifier_map.filter(
+            (pl.col("prev_symbols").list.contains(gene_symbol))
+        )
+        if prev_symbol_matches.height > 0:
+            return [
+                f"{row['prefix']}{row['identifier']}"
+                for row in prev_symbol_matches.rows(named=True)
+            ] + [f"symbol:{gene_symbol}"]
+        return None
 
     def update_genomic_interpretations_gene_identifier(
         self, interpretations: List[Interpretation], phenopacket_path: Path
@@ -731,6 +724,7 @@ class GeneIdentifierUpdater:
 
         Args:
             interpretations (List[Interpretation]): List of Interpretation objects.
+            phenopacket_path (Path): The Path to the Phenopacket.
 
         Returns:
             List[Interpretation]: Updated list of Interpretation objects.

{pheval-0.4.7.dist-info → pheval-0.5.0.dist-info}/METADATA

@@ -1,12 +1,11 @@
 Metadata-Version: 2.3
 Name: pheval
-Version: 0.4.7
+Version: 0.5.0
 Summary: 
 Author: Yasemin Bridges
 Author-email: y.bridges@qmul.ac.uk
-Requires-Python: >=3.9,<4.0.0
+Requires-Python: >=3.10,<4.0.0
 Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
@@ -22,8 +21,9 @@ Requires-Dist: oaklib (>=0.5.6)
 Requires-Dist: pandas (>=1.5.1)
 Requires-Dist: phenopackets (>=2.0.2,<3.0.0)
 Requires-Dist: plotly (>=5.13.0,<6.0.0)
-Requires-Dist: polars (>=0.19.15,<0.20.0)
+Requires-Dist: polars (>=1.23,<2.0)
 Requires-Dist: pyaml (>=21.10.1,<22.0.0)
+Requires-Dist: pyarrow (>=19.0.1,<20.0.0)
 Requires-Dist: pyserde (>=0.9.8,<0.10.0)
 Requires-Dist: scikit-learn (>=1.4.0,<2.0.0)
 Requires-Dist: seaborn (>=0.12.2,<0.13.0)

{pheval-0.4.7.dist-info → pheval-0.5.0.dist-info}/RECORD

@@ -1,36 +1,31 @@
 pheval/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pheval/analyse/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-pheval/analyse/analysis.py,sha256=Yt2xH0WS_2NO13-wYvywzmCRCj8RinQ1MeozJQuGe3o,4009
-pheval/analyse/assess_prioritisation_base.py,sha256=znBscRTqIKxxZMHR-H6KrjFJ6Uv5P5HzwTQUWS6Eoos,3434
-pheval/analyse/benchmark_db_manager.py,sha256=IRqu5fUpLBboHpS4lx0AaAkor_W7whuvUSKiMr2-GhM,5185
-pheval/analyse/benchmark_generator.py,sha256=-LljszuKAT3oJfGQn7JHAILCGg5QXYny4nPPf273g_E,5896
-pheval/analyse/benchmarking_data.py,sha256=aRvDmwqjFGKvWDRGjMwaQxfDZscptRBwI-rcSqY-X5s,913
-pheval/analyse/binary_classification_stats.py,sha256=E35YjvGM-zFnuEt8M3pgN03vBab4MH6ih726QKvuogg,12519
-pheval/analyse/disease_prioritisation_analysis.py,sha256=t__1lhyw1PnbDBbXDxDaFgLFbdRz20D1s-8tfLQJjLs,6186
-pheval/analyse/gene_prioritisation_analysis.py,sha256=Bapg0VcHOz5vp1dI4bDba04SpX6UdDu35VGTI6sZyOk,6026
-pheval/analyse/generate_plots.py,sha256=5oxsdnAbbVgQj8ZrWTLs12rSM24EXp-IdLCjy5QB1_g,21992
-pheval/analyse/generate_summary_outputs.py,sha256=nKqwbpA-9bbL5mCySiuyV_AUDIokmCg3vD8_JAsg1ls,4157
-pheval/analyse/parse_benchmark_summary.py,sha256=vyAOIdIWF4rZjGTPFE69ajhEC9AkkN3QBVqSe_uYZsg,2946
-pheval/analyse/parse_corpus.py,sha256=pxhoKTgd-DnwAMP081UMG-NKbj89qAYBQhHve8aphfI,8698
-pheval/analyse/prioritisation_result_types.py,sha256=qJoB6O-lFYmzAMcTQeDJZQNLJ6hleoKDYATTkhvFF98,1228
-pheval/analyse/rank_stats.py,sha256=vNLVuG_NzhKDXxKmklYNPz44MczlyKUqcuHqbiuOXwI,17993
-pheval/analyse/run_data_parser.py,sha256=VQBUoOIRYRWc5uqURUvaWdaW3E3C7Su0JvLavQLHQaY,4105
-pheval/analyse/variant_prioritisation_analysis.py,sha256=HhDeczF7wmJjXt0ejAtF0qdczyMe25glqiS6uX_TFl8,6408
-pheval/cli.py,sha256=SPB8-BCIRt1fUaAalhZ5Y6JUlnJX6Cj2S52QXCovJR8,1526
+pheval/analyse/benchmark.py,sha256=1ysz1peGb21DhgNpEam9NgUOS5eGv7K0CI3RNjy0crQ,6275
+pheval/analyse/benchmark_db_manager.py,sha256=zS1TI76YuV2_YXLipHLSyh-XDR5kTxyOwhRhHRFHfjQ,764
+pheval/analyse/benchmark_output_type.py,sha256=bh-qQvV4AF7BHQyr_bdY8HTTzYZVe7KvoIoUF0D9k-g,1468
+pheval/analyse/binary_classification_curves.py,sha256=Crb45rJWc5rxDdx82sgoHRvYHE2D5pus91fgl39FyRw,5007
+pheval/analyse/binary_classification_stats.py,sha256=sOuEp6IxZ6SVp-KC6MJkZNTkZucZTNK25xApP5tU6Mk,6944
+pheval/analyse/generate_plots.py,sha256=g98DxhTw1dPRfRRYoKBmt51XfIa2KzlL_Z7weFSoBUg,14550
+pheval/analyse/generate_rank_comparisons.py,sha256=KcQJ9rm1nvvTcqLNuxAkXRXuV18vEsiP0giQ-ryHyYc,1684
+pheval/analyse/rank_stats.py,sha256=qHrqlIsZVSV2ASc5cZ6TsmKaMq3bZtCzS1ZURjL8mks,9211
+pheval/analyse/run_data_parser.py,sha256=Lr0ao_Mlp8EYLaM4XmiEjo7P7jt_rCBR2y2hb_D3c70,3366
+pheval/cli.py,sha256=rpvTTCKAvH75XkZUh0xaKv7Ftl9zIt2RncsMGIlrq9U,1556
 pheval/cli_pheval.py,sha256=fWbKUcPTZZSa1EJEtH_lNn1XE6qRApRHihqUZS5owrA,2424
-pheval/cli_pheval_utils.py,sha256=O6tWnE85QQHGNcP08OwJGANMfXJPsZtFEu-D6ATld00,16700
+pheval/cli_pheval_utils.py,sha256=sh6kx36jYfuSIWBMlrdW3g-LPftxBy-xw4b7hg8bdj4,16545
 pheval/config_parser.py,sha256=lh-Dy_FflXJUnRC3HYaEdSvPAsNZWQZlEr1hHQigrTM,1227
 pheval/implementations/__init__.py,sha256=BMUTotjTdgy5j5xubWCIQgRXrSQ1ZIcjooer7r299Zo,1228
 pheval/infra/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pheval/infra/exomiserdb.py,sha256=pM9-TfjrgurtH4OtM1Enk5oVhIxGQN3rKRlrxHuObTM,5080
 pheval/post_processing/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-pheval/post_processing/post_processing.py,sha256=MdacHoVjmwvmWBnHCSSKBboCgMW4MRGP-d_7-t1zZew,14808
+pheval/post_processing/phenopacket_truth_set.py,sha256=ue3pNeg_GZiGyuKrm6_4MsJWpW0LWtfG9wja2Cc8SLg,8873
+pheval/post_processing/post_processing.py,sha256=4xP-gjZ3VoXydU9ClPvmRtuDaSMUeJImgLugurOS5_k,9480
+pheval/post_processing/validate_result_format.py,sha256=4U6AfHt01EexwU_OnpmytQAhGVS6ZWF1S-5NVBx1oaM,2916
 pheval/prepare/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pheval/prepare/create_noisy_phenopackets.py,sha256=ydhA4mpqKTDc4hBu8YfvNW2nMubHK3dbO-cv0lA4JFQ,11504
 pheval/prepare/create_spiked_vcf.py,sha256=90A-Mi8QKhvN036vtFEVWAHgzHO37itiLYrqYlG4LiA,23953
 pheval/prepare/custom_exceptions.py,sha256=_G3_95dPtHIs1SviYBV1j7cYc-hxlhuw8hhnYdzByYY,1719
 pheval/prepare/prepare_corpus.py,sha256=YFnklpeVXeqeme9DVmd_jfsK04ytIe9cH5uXYcgK5cY,4650
-pheval/prepare/update_phenopacket.py,sha256=21fzUPbwKN6Ey5TSh9PFzjT2x86U19RAE6WmkjG8u28,4770
+pheval/prepare/update_phenopacket.py,sha256=Bjru0ptNKyzLaYElouKZe2GYRQbETTC0FMiMojrP8Lg,4850
 pheval/resources/alternate_ouputs/CADA_results.txt,sha256=Rinn2TtfwFNsx0aEWegKJOkjKnBm-Mf54gdaT3bWP0k,547
 pheval/resources/alternate_ouputs/DeepPVP_results.txt,sha256=MF9MZJYa4r4PEvFzALpi-lNGLxjENOnq_YgrgFMn-oQ,1508
 pheval/resources/alternate_ouputs/OVA_results.txt,sha256=_5XFCR4W04D-W7DObpALLsa0-693g2kiIUB_uo79aHk,9845
@@ -47,11 +42,12 @@ pheval/utils/docs_gen.py,sha256=6FGtHicBC0rZKi0tdL3Epsg8d4osE44I9f1Ga0j4JLA,3193
 pheval/utils/docs_gen.sh,sha256=LyKLKjaZuf4UJ962CWfM-XqkxtvM8O2N9wHZS5mcb9A,477
 pheval/utils/exomiser.py,sha256=m2u0PH2z9lFPaB3LVkZCmPmH5e55q1NoTzNl46zRRP8,683
 pheval/utils/file_utils.py,sha256=m21cz-qjDYqnI8ClUv3J9fKizex98a-9bSEerQ75i_c,3576
-pheval/utils/phenopacket_utils.py,sha256=6xQ8WCLdR1VhiU3nCDzaqEVKjGvDWrzvPA50_6ZAHXM,27310
+pheval/utils/logger.py,sha256=5DZl5uMltUDQorhkvg_B7_ZhFwApAmEkWneFIOKfRGQ,1566
+pheval/utils/phenopacket_utils.py,sha256=AfV_mWac6n5HCc5zjfH6CGP8T0qI0LR0VBrooaKmgdY,26978
 pheval/utils/semsim_utils.py,sha256=s7ZCR2VfPYnOh7ApX6rv66eGoVSm9QJaVYOWBEhlXpo,6151
 pheval/utils/utils.py,sha256=9V6vCT8l1g4O2-ZATYqsVyd7AYZdWGd-Ksy7_oIC3eE,2343
-pheval-0.4.7.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-pheval-0.4.7.dist-info/METADATA,sha256=JfraeowwRp8eQjKiFBBrIVUoA0fchchznGj4t8sXgFE,6469
-pheval-0.4.7.dist-info/WHEEL,sha256=XbeZDeTWKc1w7CSIyre5aMDU_-PohRwTQceYnisIYYY,88
-pheval-0.4.7.dist-info/entry_points.txt,sha256=o9gSwDkvT4-lqKy4mlsftd1nzP9WUOXQCfnbqycURd0,81
-pheval-0.4.7.dist-info/RECORD,,
+pheval-0.5.0.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+pheval-0.5.0.dist-info/METADATA,sha256=v7UNSBKUzJQAs8oBSq8XScwKnDiNXlzWZV0A70xR3M8,6456
+pheval-0.5.0.dist-info/WHEEL,sha256=XbeZDeTWKc1w7CSIyre5aMDU_-PohRwTQceYnisIYYY,88
+pheval-0.5.0.dist-info/entry_points.txt,sha256=o9gSwDkvT4-lqKy4mlsftd1nzP9WUOXQCfnbqycURd0,81
+pheval-0.5.0.dist-info/RECORD,,

pheval/analyse/analysis.py

@@ -1,104 +0,0 @@
-from pheval.analyse.benchmark_generator import (
-    BenchmarkRunOutputGenerator,
-    DiseaseBenchmarkRunOutputGenerator,
-    GeneBenchmarkRunOutputGenerator,
-    VariantBenchmarkRunOutputGenerator,
-)
-from pheval.analyse.generate_summary_outputs import generate_benchmark_comparison_output
-from pheval.analyse.parse_corpus import CorpusParser
-from pheval.analyse.rank_stats import RankStatsWriter
-from pheval.analyse.run_data_parser import Config
-
-
-def _run_benchmark_comparison(
-    run_config: Config,
-    benchmark_generator: BenchmarkRunOutputGenerator,
-) -> None:
-    """
-    Run a benchmark on several result directories.
-
-    Args:
-        run_config (List[TrackInputOutputDirectories]): List of input and output directories
-            for tracking results across multiple directories.
-        benchmark_generator (BenchmarkRunOutputGenerator): Generator for benchmark run output.
-    """
-    stats_writer = RankStatsWriter(
-        run_config.benchmark_name, benchmark_generator.stats_comparison_file
-    )
-    unique_test_corpora_directories = set([result.phenopacket_dir for result in run_config.runs])
-    [
-        CorpusParser(run_config.benchmark_name, test_corpora_directory).parse_corpus(
-            benchmark_generator
-        )
-        for test_corpora_directory in unique_test_corpora_directories
-    ]
-    benchmarking_results = []
-    for run in run_config.runs:
-        benchmark_result = benchmark_generator.generate_benchmark_run_results(
-            run_config.benchmark_name, run, run.score_order, run.threshold
-        )
-        stats_writer.add_statistics_entry(
-            run.run_identifier,
-            benchmark_result.rank_stats,
-            benchmark_result.binary_classification_stats,
-        )
-        benchmarking_results.append(benchmark_result)
-    run_identifiers = [run.run_identifier for run in run_config.runs]
-    [
-        generate_benchmark_comparison_output(
-            run_config.benchmark_name,
-            benchmarking_results,
-            run_identifiers,
-            benchmark_generator,
-            f"{unique_test_corpora_directory.parents[0].name}_"
-            f"{benchmark_generator.prioritisation_type_string}",
-        )
-        for unique_test_corpora_directory in unique_test_corpora_directories
-    ]
-
-
-def benchmark_run_comparisons(
-    run_config: Config,
-) -> None:
-    """
-    Benchmark prioritisation performance for several runs.
-
-    Args:
-        run_config (Config): Run configurations.
-    """
-    gene_analysis_runs = Config(
-        benchmark_name=run_config.benchmark_name,
-        runs=[run for run in run_config.runs if run.gene_analysis],
-        plot_customisation=run_config.plot_customisation,
-    )
-    variant_analysis_runs = Config(
-        benchmark_name=run_config.benchmark_name,
-        runs=[run for run in run_config.runs if run.variant_analysis],
-        plot_customisation=run_config.plot_customisation,
-    )
-    disease_analysis_runs = Config(
-        benchmark_name=run_config.benchmark_name,
-        runs=[run for run in run_config.runs if run.disease_analysis],
-        plot_customisation=run_config.plot_customisation,
-    )
-    if gene_analysis_runs.runs:
-        _run_benchmark_comparison(
-            run_config=gene_analysis_runs,
-            benchmark_generator=GeneBenchmarkRunOutputGenerator(
-                plot_customisation=gene_analysis_runs.plot_customisation.gene_plots
-            ),
-        )
-    if variant_analysis_runs.runs:
-        _run_benchmark_comparison(
-            run_config=variant_analysis_runs,
-            benchmark_generator=VariantBenchmarkRunOutputGenerator(
-                plot_customisation=variant_analysis_runs.plot_customisation.variant_plots
-            ),
-        )
-    if disease_analysis_runs.runs:
-        _run_benchmark_comparison(
-            run_config=disease_analysis_runs,
-            benchmark_generator=DiseaseBenchmarkRunOutputGenerator(
-                plot_customisation=disease_analysis_runs.plot_customisation.disease_plots
-            ),
-        )