pheval 0.6.2__py3-none-any.whl → 0.6.4__py3-none-any.whl

pheval/prepare/prepare_corpus.py

@@ -56,15 +56,11 @@ def prepare_corpus(
     for phenopacket_path in all_files(phenopacket_dir):
         phenopacket_util = PhenopacketUtil(phenopacket_reader(phenopacket_path))
         if not phenopacket_util.observed_phenotypic_features():
-            logger.warning(
-                f"Removed {phenopacket_path.name} from the corpus due to no observed phenotypic features."
-            )
+            logger.warning(f"Removed {phenopacket_path.name} from the corpus due to no observed phenotypic features.")
             continue
         if variant_analysis:
             if phenopacket_util.check_incomplete_variant_record():
-                logger.warning(
-                    f"Removed {phenopacket_path.name} from the corpus due to missing variant fields."
-                )
+                logger.warning(f"Removed {phenopacket_path.name} from the corpus due to missing variant fields.")
                 continue
             elif phenopacket_util.check_variant_alleles():
                 logger.warning(
@@ -73,15 +69,11 @@ def prepare_corpus(
                 )
         if gene_analysis:
             if phenopacket_util.check_incomplete_gene_record():
-                logger.warning(
-                    f"Removed {phenopacket_path.name} from the corpus due to missing gene fields."
-                )
+                logger.warning(f"Removed {phenopacket_path.name} from the corpus due to missing gene fields.")
                 continue
         if disease_analysis:
             if phenopacket_util.check_incomplete_disease_record():
-                logger.warning(
-                    f"Removed {phenopacket_path.name} from the corpus due to missing disease fields."
-                )
+                logger.warning(f"Removed {phenopacket_path.name} from the corpus due to missing disease fields.")
                 continue
         logger.info(f"{phenopacket_path.name} OK!")
         if hg19_template_vcf or hg38_template_vcf:
@@ -107,13 +99,10 @@ def prepare_corpus(
         else:
             # if not updating phenopacket gene identifiers then copy phenopacket as is to output directory
             (
-                shutil.copy(
-                    phenopacket_path, output_dir.joinpath(f"phenopackets/{phenopacket_path.name}")
-                )
+                shutil.copy(phenopacket_path, output_dir.joinpath(f"phenopackets/{phenopacket_path.name}"))
                 if phenopacket_path != output_dir.joinpath(f"phenopackets/{phenopacket_path.name}")
                 else None
             )
     logger.info(
-        f"Finished preparing corpus for {phenopacket_dir}. "
-        f"Total time: {time.perf_counter() - start_time:.2f} seconds."
+        f"Finished preparing corpus for {phenopacket_dir}. Total time: {time.perf_counter() - start_time:.2f} seconds."
     )

pheval/prepare/update_phenopacket.py

@@ -1,6 +1,5 @@
 import time
 from pathlib import Path
-from typing import Union
 
 import polars as pl
 from phenopackets import Family, Phenopacket
@@ -21,7 +20,7 @@ logger = get_logger()
 
 def update_outdated_gene_context(
     phenopacket_path: Path, gene_identifier: str, identifier_map: pl.DataFrame
-) -> Union[Phenopacket, Family]:
+) -> Phenopacket | Family:
     """
     Update the gene context of the Phenopacket.
 
@@ -66,15 +65,11 @@ def create_updated_phenopacket(
         to describe the gene identifiers.
     """
     identifier_map = create_gene_identifier_map() if identifier_map is None else identifier_map
-    updated_phenopacket = update_outdated_gene_context(
-        phenopacket_path, gene_identifier, identifier_map
-    )
+    updated_phenopacket = update_outdated_gene_context(phenopacket_path, gene_identifier, identifier_map)
     write_phenopacket(updated_phenopacket, output_dir.joinpath(phenopacket_path.name))
 
 
-def create_updated_phenopackets(
-    gene_identifier: str, phenopacket_dir: Path, output_dir: Path
-) -> None:
+def create_updated_phenopackets(gene_identifier: str, phenopacket_dir: Path, output_dir: Path) -> None:
     """
     Update the gene context within the interpretations for a directory of Phenopackets
     and writes the updated Phenopackets.
@@ -91,15 +86,11 @@ def create_updated_phenopackets(
     identifier_map = create_gene_identifier_map()
     for phenopacket_path in all_files(phenopacket_dir):
         logger.info(f"Updating gene context for: {phenopacket_path.name}")
-        updated_phenopacket = update_outdated_gene_context(
-            phenopacket_path, gene_identifier, identifier_map
-        )
+        updated_phenopacket = update_outdated_gene_context(phenopacket_path, gene_identifier, identifier_map)
         write_phenopacket(updated_phenopacket, output_dir.joinpath(phenopacket_path.name))
 
 
-def update_phenopackets(
-    gene_identifier: str, phenopacket_path: Path, phenopacket_dir: Path, output_dir: Path
-) -> None:
+def update_phenopackets(gene_identifier: str, phenopacket_path: Path, phenopacket_dir: Path, output_dir: Path) -> None:
     """
     Update the gene identifiers in either a single phenopacket or a directory of phenopackets.
 
@@ -122,8 +113,6 @@ def update_phenopackets(
         logger.info(f"Updating {phenopacket_path}.")
         create_updated_phenopacket(gene_identifier, phenopacket_path, output_dir)
     elif phenopacket_dir is not None:
-        logger.info(
-            f"Updating {len(all_files(phenopacket_dir))} phenopackets in {phenopacket_dir}."
-        )
+        logger.info(f"Updating {len(all_files(phenopacket_dir))} phenopackets in {phenopacket_dir}.")
         create_updated_phenopackets(gene_identifier, phenopacket_dir, output_dir)
     logger.info(f"Updating finished! Total time: {time.perf_counter() - start_time:.2f} seconds.")

pheval/utils/docs_gen.py

@@ -13,7 +13,7 @@ def find_methods_in_python_file(file_path):
         file_path ([type]): [description]
     """
     methods = []
-    with open(file_path, "r", encoding="utf-8") as file:
+    with open(file_path, encoding="utf-8") as file:
         text = file.read()
         parsed = ast.parse(text)
         for node in ast.walk(parsed):
@@ -73,8 +73,8 @@ def print_cli_doc(file_item):
     for method in methods:
         content = f"""
 ::: mkdocs-click
-    :package: {file_item['folder'].replace("./", '').replace('/', '.')}.{file_item['basename']}
-    :module: {file_item['folder'].replace("./", '').replace('/', '.').replace('src.', '')}.{file_item['basename']}
+    :package: {file_item["folder"].replace("./", "").replace("/", ".")}.{file_item["basename"]}
+    :module: {file_item["folder"].replace("./", "").replace("/", ".").replace("src.", "")}.{file_item["basename"]}
     :command: {method}
     :depth: 4
     :style: table

pheval/utils/file_utils.py

@@ -3,7 +3,6 @@ import re
 import unicodedata
 from os import path
 from pathlib import Path
-from typing import List
 
 import pandas as pd
 import yaml
@@ -80,7 +79,7 @@ def ensure_file_exists(*files: str):
             raise FileNotFoundError(f"File {file} not found")
 
 
-def ensure_columns_exists(cols: list, dataframes: List[pd.DataFrame], err_message: str = ""):
+def ensure_columns_exists(cols: list, dataframes: list[pd.DataFrame], err_message: str = ""):
     """Ensures the columns exist in dataframes passed as argument (e.g)
 
     "

pheval/utils/phenopacket_utils.py

@@ -3,7 +3,6 @@ import os
 from copy import copy
 from dataclasses import dataclass
 from pathlib import Path
-from typing import List, Union
 
 import polars as pl
 from google.protobuf.json_format import MessageToJson, Parse
@@ -183,7 +182,7 @@ def create_gene_identifier_map() -> pl.DataFrame:
     )
 
 
-def phenopacket_reader(file: Path) -> Union[Phenopacket, Family]:
+def phenopacket_reader(file: Path) -> Phenopacket | Family:
     """
     Read a Phenopacket file and returns its contents as a Phenopacket or Family object
 
@@ -194,7 +193,7 @@ def phenopacket_reader(file: Path) -> Union[Phenopacket, Family]:
         Union[Phenopacket, Family]: Contents of the Phenopacket file as a Phenopacket or Family object
     """
     logger.info(f"Parsing Phenopacket: {file.name}")
-    file = open(file, "r")
+    file = open(file)
     phenopacket = json.load(file)
     file.close()
     if "proband" in phenopacket:
@@ -206,7 +205,7 @@ def phenopacket_reader(file: Path) -> Union[Phenopacket, Family]:
 class PhenopacketUtil:
     """Class for retrieving data from a Phenopacket or Family object"""
 
-    def __init__(self, phenopacket_contents: Union[Phenopacket, Family]):
+    def __init__(self, phenopacket_contents: Phenopacket | Family):
         """Initialise PhenopacketUtil
 
         Args:
@@ -226,7 +225,7 @@ class PhenopacketUtil:
         else:
             return self.phenopacket_contents.subject.id
 
-    def phenotypic_features(self) -> List[PhenotypicFeature]:
+    def phenotypic_features(self) -> list[PhenotypicFeature]:
         """
         Retrieve a list of all HPO terms
 
@@ -238,7 +237,7 @@ class PhenopacketUtil:
         else:
             return self.phenopacket_contents.phenotypic_features
 
-    def observed_phenotypic_features(self) -> List[PhenotypicFeature]:
+    def observed_phenotypic_features(self) -> list[PhenotypicFeature]:
         """
         Retrieve a list of all observed HPO terms
 
@@ -253,7 +252,7 @@ class PhenopacketUtil:
             phenotypic_features.append(p)
         return phenotypic_features
 
-    def negated_phenotypic_features(self) -> List[PhenotypicFeature]:
+    def negated_phenotypic_features(self) -> list[PhenotypicFeature]:
         """
         Retrieve a list of all negated HPO terms
 
@@ -267,7 +266,7 @@ class PhenopacketUtil:
                 negated_phenotypic_features.append(p)
         return negated_phenotypic_features
 
-    def diseases(self) -> List[Disease]:
+    def diseases(self) -> list[Disease]:
         """
         Retrieve a list of Diseases associated with the proband
 
@@ -279,7 +278,7 @@ class PhenopacketUtil:
         else:
             return self.phenopacket_contents.diseases
 
-    def _diagnosis_from_interpretations(self) -> List[ProbandDisease]:
+    def _diagnosis_from_interpretations(self) -> list[ProbandDisease]:
         """
         Retrieve a list of disease diagnoses associated with the proband from the interpretations object
 
@@ -301,7 +300,7 @@ class PhenopacketUtil:
             )
         return diagnoses
 
-    def _diagnosis_from_disease(self) -> List[ProbandDisease]:
+    def _diagnosis_from_disease(self) -> list[ProbandDisease]:
         """
         Retrieve a list of disease diagnoses associated with the proband from the diseases object
 
@@ -310,12 +309,10 @@ class PhenopacketUtil:
         """
         diagnoses = []
         for disease in self.diseases():
-            diagnoses.append(
-                ProbandDisease(disease_name=disease.term.label, disease_identifier=disease.term.id)
-            )
+            diagnoses.append(ProbandDisease(disease_name=disease.term.label, disease_identifier=disease.term.id))
         return diagnoses
 
-    def diagnoses(self) -> List[ProbandDisease]:
+    def diagnoses(self) -> list[ProbandDisease]:
         """
         Retrieve a unique list of disease diagnoses associated with the proband from a Phenopacket
 
@@ -324,7 +321,7 @@ class PhenopacketUtil:
         """
         return list(set(self._diagnosis_from_interpretations() + self._diagnosis_from_disease()))
 
-    def interpretations(self) -> List[Interpretation]:
+    def interpretations(self) -> list[Interpretation]:
         """
         Retrieve a list of interpretations from a Phenopacket
 
@@ -336,7 +333,7 @@ class PhenopacketUtil:
         else:
             return self.phenopacket_contents.interpretations
 
-    def causative_variants(self) -> List[ProbandCausativeVariant]:
+    def causative_variants(self) -> list[ProbandCausativeVariant]:
         """
         Retrieve a list of causative variants listed in a Phenopacket
 
@@ -364,7 +361,7 @@ class PhenopacketUtil:
                 all_variants.append(variant_data)
         return all_variants
 
-    def files(self) -> List[File]:
+    def files(self) -> list[File]:
         """
         Retrieve a list of files associated with a phenopacket
 
@@ -394,15 +391,11 @@ class PhenopacketUtil:
             URI of the VCF file to the specified directory and returns the modified file object.
         """
         compatible_genome_assembly = ["GRCh37", "hg19", "GRCh38", "hg38"]
-        vcf_data = [file for file in self.files() if file.file_attributes["fileFormat"] == "vcf"][0]
-        if not Path(vcf_data.uri).name.endswith(".vcf") and not Path(vcf_data.uri).name.endswith(
-            ".vcf.gz"
-        ):
+        vcf_data = next(file for file in self.files() if file.file_attributes["fileFormat"] == "vcf")
+        if not Path(vcf_data.uri).name.endswith(".vcf") and not Path(vcf_data.uri).name.endswith(".vcf.gz"):
             raise IncorrectFileFormatError(Path(vcf_data.uri), ".vcf or .vcf.gz file")
         if vcf_data.file_attributes["genomeAssembly"] not in compatible_genome_assembly:
-            raise IncompatibleGenomeAssemblyError(
-                vcf_data.file_attributes["genomeAssembly"], phenopacket_path
-            )
+            raise IncompatibleGenomeAssemblyError(vcf_data.file_attributes["genomeAssembly"], phenopacket_path)
         vcf_data.uri = str(vcf_dir.joinpath(Path(vcf_data.uri).name))
         return vcf_data
 
@@ -430,7 +423,7 @@ class PhenopacketUtil:
                 gene_identifier=genomic_interpretation.gene.value_id,
             )
 
-    def diagnosed_genes(self) -> List[ProbandCausativeGene]:
+    def diagnosed_genes(self) -> list[ProbandCausativeGene]:
         """
         Retrieve the disease causing genes from a phenopacket.
         Returns:
@@ -444,7 +437,7 @@ class PhenopacketUtil:
                 genes = list({gene.gene_symbol: gene for gene in genes}.values())
         return genes
 
-    def diagnosed_variants(self) -> List[GenomicVariant]:
+    def diagnosed_variants(self) -> list[GenomicVariant]:
         """
         Retrieve a list of all known causative variants from a phenopacket.
         Returns:
@@ -455,11 +448,7 @@ class PhenopacketUtil:
         for i in pheno_interpretation:
             for g in i.diagnosis.genomic_interpretations:
                 variant = GenomicVariant(
-                    chrom=str(
-                        g.variant_interpretation.variation_descriptor.vcf_record.chrom.replace(
-                            "chr", ""
-                        )
-                    ),
+                    chrom=str(g.variant_interpretation.variation_descriptor.vcf_record.chrom.replace("chr", "")),
                     pos=int(g.variant_interpretation.variation_descriptor.vcf_record.pos),
                     ref=g.variant_interpretation.variation_descriptor.vcf_record.ref,
                     alt=g.variant_interpretation.variation_descriptor.vcf_record.alt,
@@ -480,13 +469,7 @@ class PhenopacketUtil:
         """
         variants = self.diagnosed_variants()
         for variant in variants:
-            if (
-                variant.chrom == ""
-                or variant.pos == 0
-                or variant.pos == ""
-                or variant.ref == ""
-                or variant.alt == ""
-            ):
+            if variant.chrom == "" or variant.pos in (0, "") or variant.ref == "" or variant.alt == "":
                 return True
         return False
 
@@ -537,7 +520,7 @@ class PhenopacketUtil:
 class PhenopacketRebuilder:
     """Class for rebuilding a Phenopacket"""
 
-    def __init__(self, phenopacket: Union[Phenopacket, Family]):
+    def __init__(self, phenopacket: Phenopacket | Family):
         """Initialise PhenopacketUtil
 
         Attributes:
@@ -545,9 +528,7 @@ class PhenopacketRebuilder:
         """
         self.phenopacket = phenopacket
 
-    def update_interpretations(
-        self, interpretations: [Interpretation]
-    ) -> Union[Phenopacket, Family]:
+    def update_interpretations(self, interpretations: [Interpretation]) -> Phenopacket | Family:
         """
         Add the updated interpretations to a Phenopacket or Family.
 
@@ -566,7 +547,7 @@ class PhenopacketRebuilder:
             phenopacket.interpretations.extend(interpretations)
         return phenopacket
 
-    def add_randomised_hpo(self, randomised_hpo: [PhenotypicFeature]) -> Union[Phenopacket, Family]:
+    def add_randomised_hpo(self, randomised_hpo: [PhenotypicFeature]) -> Phenopacket | Family:
         """
         Add randomised phenotypic profiles to a Phenopacket or Family.
 
@@ -585,7 +566,7 @@ class PhenopacketRebuilder:
             phenopacket.phenotypic_features.extend(randomised_hpo)
         return phenopacket
 
-    def add_spiked_vcf_path(self, spiked_vcf_file_data: File) -> Union[Phenopacket, Family]:
+    def add_spiked_vcf_path(self, spiked_vcf_file_data: File) -> Phenopacket | Family:
         """
         Add a spiked VCF path to a Phenopacket or Family.
 
@@ -597,16 +578,14 @@ class PhenopacketRebuilder:
         """
         logger.info(f"Adding spiked VCF path {spiked_vcf_file_data.uri} to phenopacket.")
         phenopacket = copy(self.phenopacket)
-        phenopacket_files = [
-            file for file in phenopacket.files if file.file_attributes["fileFormat"] != "vcf"
-        ]
+        phenopacket_files = [file for file in phenopacket.files if file.file_attributes["fileFormat"] != "vcf"]
         phenopacket_files.append(spiked_vcf_file_data)
         del phenopacket.files[:]
         phenopacket.files.extend(phenopacket_files)
         return phenopacket
 
 
-def create_json_message(phenopacket: Union[Phenopacket, Family]) -> str:
+def create_json_message(phenopacket: Phenopacket | Family) -> str:
     """
     Create a JSON message for writing to a file.
 
@@ -619,7 +598,7 @@ def create_json_message(phenopacket: Union[Phenopacket, Family]) -> str:
     return MessageToJson(phenopacket)
 
 
-def write_phenopacket(phenopacket: Union[Phenopacket, Family], output_file: Path) -> None:
+def write_phenopacket(phenopacket: Phenopacket | Family, output_file: Path) -> None:
     """
     Write a Phenopacket or Family object to a file in JSON format.
 
@@ -667,15 +646,13 @@ class GeneIdentifierUpdater:
             str: The identified gene identifier.
         """
         matches = self.identifier_map.filter(
-            (pl.col("gene_symbol") == gene_symbol)
-            & (pl.col("identifier_type") == self.gene_identifier)
+            (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))
+            (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]
@@ -692,11 +669,9 @@ class GeneIdentifierUpdater:
         Returns:
             str: The gene symbol corresponding to the identifier.
         """
-        return self.identifier_map.filter(pl.col("identifier") == query_gene_identifier)[
-            "gene_symbol"
-        ][0]
+        return self.identifier_map.filter(pl.col("identifier") == query_gene_identifier)["gene_symbol"][0]
 
-    def _find_alternate_ids(self, gene_symbol: str) -> List[str]:
+    def _find_alternate_ids(self, gene_symbol: str) -> list[str]:
         """
         Find the alternate IDs for a gene symbol.
 
@@ -706,24 +681,21 @@ class GeneIdentifierUpdater:
         Returns:
             List[str]: List of alternate IDs for the gene symbol.
         """
-        matches = self.identifier_map.filter((pl.col("gene_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}"
             ]
-        prev_symbol_matches = self.identifier_map.filter(
-            (pl.col("prev_symbols").list.contains(gene_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 [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
-    ) -> List[Interpretation]:
+        self, interpretations: list[Interpretation], phenopacket_path: Path
+    ) -> list[Interpretation]:
         """
         Update the genomic interpretations of a Phenopacket.
 
@@ -745,13 +717,9 @@ class GeneIdentifierUpdater:
                     f"{g.variant_interpretation.variation_descriptor.gene_context.value_id}"
                     f" to {updated_gene_identifier}"
                 )
-                g.variant_interpretation.variation_descriptor.gene_context.value_id = (
-                    updated_gene_identifier
-                )
+                g.variant_interpretation.variation_descriptor.gene_context.value_id = updated_gene_identifier
                 del g.variant_interpretation.variation_descriptor.gene_context.alternate_ids[:]
                 g.variant_interpretation.variation_descriptor.gene_context.alternate_ids.extend(
-                    self._find_alternate_ids(
-                        g.variant_interpretation.variation_descriptor.gene_context.symbol
-                    )
+                    self._find_alternate_ids(g.variant_interpretation.variation_descriptor.gene_context.symbol)
                 )
         return updated_interpretations

pheval/utils/semsim_utils.py

@@ -8,7 +8,7 @@ import numpy
 import pandas as pd
 import plotly.express as px
 
-import pheval.utils.file_utils as file_utils
+from pheval.utils import file_utils
 
 
 def filter_non_0_score(data: pd.DataFrame, col: str) -> pd.DataFrame:
@@ -58,9 +58,7 @@ def diff_semsim(
     if absolute_diff:
         df["diff"] = df[f"{score_column}_x"] - df[f"{score_column}_y"]
         return df[["subject_id", "object_id", "diff"]]
-    df["diff"] = df.apply(
-        lambda row: get_percentage_diff(row[f"{score_column}_x"], row[f"{score_column}_y"]), axis=1
-    )
+    df["diff"] = df.apply(lambda row: get_percentage_diff(row[f"{score_column}_x"], row[f"{score_column}_y"]), axis=1)
     return df[["subject_id", "object_id", f"{score_column}_x", f"{score_column}_y", "diff"]]
 
 
@@ -91,9 +89,7 @@ def semsim_heatmap_plot(semsim_left: Path, semsim_right: Path, score_column: str
     fig.show()
 
 
-def semsim_analysis(
-    semsim_left: Path, semsim_right: Path, score_column: str, absolute_diff=True
-) -> pd.DataFrame:
+def semsim_analysis(semsim_left: Path, semsim_right: Path, score_column: str, absolute_diff=True) -> pd.DataFrame:
     """semsim_analysis
 
     Args:
@@ -147,11 +143,11 @@ def get_percentage_diff(current_number: float, previous_number: float) -> float:
     """
     try:
         if current_number == previous_number:
-            return "{:.2%}".format(0)
+            return f"{0:.2%}"
         if current_number > previous_number:
-            number = (1 - ((current_number / previous_number))) * 100
+            number = (1 - (current_number / previous_number)) * 100
         else:
             number = (100 - ((previous_number / current_number) * 100)) * -1
-        return "{:.2%}".format(number / 100)
+        return f"{number / 100:.2%}"
     except ZeroDivisionError:
         return None

pheval/utils/utils.py

@@ -4,7 +4,6 @@ import json
 import random
 from datetime import datetime
 from pathlib import Path
-from typing import List
 
 import pandas as pd
 import requests
@@ -42,7 +41,7 @@ def rand(df: pd.DataFrame, min_num: int, max_num: int, scramble_factor: float) -
 def semsim_scramble(
     input: Path,
     output: Path,
-    columns_to_be_scrambled: List[str],
+    columns_to_be_scrambled: list[str],
     scramble_factor: float = 0.5,
 ) -> pd.DataFrame:
     """
@@ -66,7 +65,7 @@ def semsim_scramble(
 
 def semsim_scramble_df(
     dataframe: pd.DataFrame,
-    columns_to_be_scrambled: List[str],
+    columns_to_be_scrambled: list[str],
     scramble_factor: float,
 ) -> pd.DataFrame:
     """scramble_semsim_df
@@ -136,6 +135,6 @@ def get_resource_timestamp(file_name: str) -> str | None:
         file_name (str): The file name.
     """
     if METADATA_PATH.exists():
-        with open(METADATA_PATH, "r") as f:
+        with open(METADATA_PATH) as f:
             return json.load(f).get(file_name)
     return None

{pheval-0.6.2.dist-info → pheval-0.6.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: pheval
-Version: 0.6.2
+Version: 0.6.4
 Summary: 
 Author: Yasemin Bridges
 Author-email: y.bridges@qmul.ac.uk

pheval-0.6.4.dist-info/RECORD

@@ -0,0 +1,57 @@
+pheval/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+pheval/analyse/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+pheval/analyse/benchmark.py,sha256=Ktjovg3uEuaBi02AIiGX4OaZ73yAruwcsohhfBrDY44,6874
+pheval/analyse/benchmark_db_manager.py,sha256=zS1TI76YuV2_YXLipHLSyh-XDR5kTxyOwhRhHRFHfjQ,764
+pheval/analyse/benchmark_output_type.py,sha256=AG4HtEfscbDqESMBQ_M5Brnj8AmfrFxU6q7Gi2FOebw,1493
+pheval/analyse/binary_classification_curves.py,sha256=b5YseLqv519DT7rsOweMRx7ElxYv9LcukXtLeAxflQE,4953
+pheval/analyse/binary_classification_stats.py,sha256=oWkaj-A2-2MaUIsJjlehwLApx-wGLx-TQ49v9O4lMAs,6910
+pheval/analyse/generate_plots.py,sha256=fyUMOgmbqYeYMPW843VR-CVArt3R75HgGbyq1i2XO7A,14489
+pheval/analyse/generate_rank_comparisons.py,sha256=BmksHkvJhpR0Rcrnc-r2_OF5L3ROHB8o3HuDSXjgeK4,1660
+pheval/analyse/rank_stats.py,sha256=io8UWTEUZfZQSnxXBjk2Z_1u6WWoxX0kSfEvxtpC-Kg,8241
+pheval/analyse/run_data_parser.py,sha256=da8-J9sSwyOUow80A2ETKdVP7GUX-zuEiiBix-M18Mo,3601
+pheval/cli.py,sha256=1kPhBYFSKjvPv9YcpknDj3Y7DZl5CA41ucqDRR7fAjk,1599
+pheval/cli_pheval.py,sha256=N8xp3r8avYqLswPhakxtTQyemVdgHAvnpAIj_FmoN5k,3510
+pheval/cli_pheval_utils.py,sha256=fLbskjHQSTN29qFXmjvsXYn7dE8-3OZuJUqlEQB-wyI,16481
+pheval/config_parser.py,sha256=6wK8x9hXHg-kTDkkqfKshYvIdn91SGhucTYUul3fjNs,1353
+pheval/implementations/__init__.py,sha256=BUTnw9urZOApRFVy6NYsq8TCLphHWsr3vhxvsx2RZ3E,1318
+pheval/implementations/pheval_class_resolver.py,sha256=YNNk3PoQbSvbKmbihlt_bsHNxRM95O-VrtUIbQnfBcw,1567
+pheval/infra/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+pheval/infra/exomiserdb.py,sha256=0NXkqYT59Ueu2F5o7u4iCWJCAqTIL4KxShQuePFmpLo,5015
+pheval/post_processing/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+pheval/post_processing/mondo_mapping.py,sha256=Vetk0acOtR__FXnx9wy2pcDDWFz1mQkc88alKUn0muI,937
+pheval/post_processing/phenopacket_truth_set.py,sha256=rK_iIZm7OwdDEj_7SV7jMEROPHPe06baXLlHVO8wrSE,9889
+pheval/post_processing/post_processing.py,sha256=mQWBpGmWd3ZPwZtDutekn_osJdGQFj4fPf6ibb7o8xA,10040
+pheval/post_processing/validate_result_format.py,sha256=jg3HjvMwGI8rsLtOM0gpcVlGB3weGZiZek5JwFzw1zE,2862
+pheval/prepare/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+pheval/prepare/create_noisy_phenopackets.py,sha256=U-tYex4kbXT9OEkGnMl4p4pt4LRuqBKwKTgVBvhA7xU,12142
+pheval/prepare/create_spiked_vcf.py,sha256=Po7WSQZAHaBObLa7SU50djUJ_XwAlUfTBeE9C0-7GA8,24299
+pheval/prepare/custom_exceptions.py,sha256=8Bwi5SmDgWuvzLWPI7foUl2m5C6QdirlxPeeeC594AU,1637
+pheval/prepare/prepare_corpus.py,sha256=726Ez5xLyvsibfEN3NqC1CFN0BgRl4Uswj4CaNTHS4o,5264
+pheval/prepare/update_phenopacket.py,sha256=IeLKtp2i60LmBbGOh387ccq5J7Mk8y0hx4K55J7Mnbs,5550
+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
+pheval/resources/alternate_ouputs/Phen2Gene_results.json,sha256=xxKsuiHKW9qQOz2baFlLW9RYphA4kxjoTsg1weZkTY8,14148
+pheval/resources/alternate_ouputs/Phenolyzer_results.txt,sha256=TltiEzYm2PY79u6EdZR3f4ZqadNDCUN_d4f0TFF-t5A,594
+pheval/resources/alternate_ouputs/lirical_results.tsv,sha256=0juf5HY6ttg-w7aWgYJUmSP5zmoaooEQDY8xhOcerLk,431068
+pheval/resources/alternate_ouputs/svanna_results.tsv,sha256=OpTamPhJwh12wkdAxoIGb0wWs_T7TcqNWgqkQzgOek4,714
+pheval/resources/hgnc_complete_set.txt,sha256=9-aNcyGZzarD1DnO_780NK0r-ppwbyu9e4-cQDmtUC8,16593567
+pheval/resources/metadata.json,sha256=aabSMPCwE-KR6cAxBCMRZmDD1fGD7qCeSvPLduvO3gA,112
+pheval/resources/mondo.sssom.tsv,sha256=Egu8UqHPL6TbSRQKlRgQ7kNq5S4e1VElR5JWHWgc7F0,12700455
+pheval/run_metadata.py,sha256=isEs63c-O6LZ6TBmk9wmAOmzjNE3Nf_k9V9uiYu0x8s,1122
+pheval/runners/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+pheval/runners/runner.py,sha256=zkS6yvbnC6UBCtV2VR3FEfr5naWRDdNcQFN1CoH1ha8,4902
+pheval/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+pheval/utils/docs_gen.py,sha256=8roEavgcVlEgOg54zTn9-xUOTu3qsQF-JfKSj3-mKMg,3188
+pheval/utils/docs_gen.sh,sha256=LyKLKjaZuf4UJ962CWfM-XqkxtvM8O2N9wHZS5mcb9A,477
+pheval/utils/exomiser.py,sha256=m2u0PH2z9lFPaB3LVkZCmPmH5e55q1NoTzNl46zRRP8,683
+pheval/utils/file_utils.py,sha256=FY4B17NVS7tXeTso0OZYgde-H9KJdUbQbWYT6fMdnCM,3552
+pheval/utils/logger.py,sha256=5DZl5uMltUDQorhkvg_B7_ZhFwApAmEkWneFIOKfRGQ,1566
+pheval/utils/phenopacket_utils.py,sha256=qt816uYkJKAe2MATFoulqEr78zg0-Z2Z_FxfEO9iSFE,26740
+pheval/utils/semsim_utils.py,sha256=tSDin3PwCdtMjtMXubIXTiGaCEFNz7iF4IngrjNHprI,6104
+pheval/utils/utils.py,sha256=T9zzqMlzY2hrcYn9ObatYgOHtKWTpWbW5nU0tTTcYxI,4489
+pheval-0.6.4.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+pheval-0.6.4.dist-info/METADATA,sha256=QNcXx4I83wCz7jEkPn1sbKC8phoFxYuil5Gzlb6JSIQ,6494
+pheval-0.6.4.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
+pheval-0.6.4.dist-info/entry_points.txt,sha256=o9gSwDkvT4-lqKy4mlsftd1nzP9WUOXQCfnbqycURd0,81
+pheval-0.6.4.dist-info/RECORD,,