pheval 0.5.0__py3-none-any.whl → 0.5.2__py3-none-any.whl

pheval/analyse/benchmark.py

@@ -23,27 +23,32 @@ def scan_directory(run: RunConfig, benchmark_type: BenchmarkOutputType) -> pl.La
         run (RunConfig): RunConfig object.
         benchmark_type (BenchmarkOutputTypeEnum): Benchmark output type.
     Returns:
-        pl.LazyFrame: LazyFrame object containing all the results in the directory..
+        pl.LazyFrame: LazyFrame object containing all the results in the directory.
     """
     logger = get_logger()
     logger.info(f"Analysing results in {run.results_dir.joinpath(benchmark_type.result_directory)}")
     return (
-        pl.scan_parquet(
-            run.results_dir.joinpath(benchmark_type.result_directory),
-            include_file_paths="file_path",
-        ).with_columns(
-            pl.col("rank").cast(pl.Int64),
-            pl.col("file_path").str.extract(r"([^/\\]+)$").alias("result_file"),
-            pl.col("true_positive").fill_null(False),
-        )
-    ).filter(
         (
-            pl.col("score") >= run.threshold
-            if run.score_order.lower() == "descending"
-            else pl.col("score") <= run.threshold
+            pl.scan_parquet(
+                run.results_dir.joinpath(benchmark_type.result_directory),
+                include_file_paths="file_path",
+            ).with_columns(
+                pl.col("rank").cast(pl.Int64),
+                pl.col("file_path").str.extract(r"([^/\\]+)$").alias("result_file"),
+                pl.col("true_positive").fill_null(False),
+            )
+        )
+        .filter(
+            (
+                pl.col("score") >= run.threshold
+                if run.score_order.lower() == "descending"
+                else pl.col("score") <= run.threshold
+            )
+            if run.threshold is not None
+            else True
         )
-        if run.threshold is not None
-        else True
+        .sort("rank")
+        .unique(subset=["file_path", *benchmark_type.columns], keep="first")
     )
 
 
@@ -68,14 +73,29 @@ def process_stats(
         )
         curve_results.append(compute_curves(run.run_identifier, result_scan))
         true_positive_cases.append(
-            result_scan.filter(pl.col("true_positive")).select(
+            result_scan.filter(pl.col("true_positive"))
+            .select(
                 ["result_file", *benchmark_type.columns, pl.col("rank").alias(run.run_identifier)]
             )
+            .sort(["result_file", *benchmark_type.columns])
         )
     return (
         pl.concat(stats, how="vertical").collect(),
         pl.concat(curve_results, how="vertical").collect(),
-        pl.concat(true_positive_cases, how="align_inner").collect(),
+        pl.concat(
+            [true_positive_cases[0]]
+            + [
+                df.select(
+                    [
+                        col
+                        for col in df.collect_schema().keys()
+                        if col not in ["result_file", *benchmark_type.columns]
+                    ]
+                )
+                for df in true_positive_cases[1:]
+            ],
+            how="horizontal",
+        ).collect(),
     )
 
 

pheval/post_processing/phenopacket_truth_set.py

@@ -12,6 +12,18 @@ from pheval.utils.phenopacket_utils import (
 )
 
 
+def calculate_end_pos(variant_start: int, variant_ref: str) -> int:
+    """Calculate the end position for a variant
+    Args:
+        variant_start (int): The start position of the variant
+        variant_ref (str): The reference allele of the variant
+
+    Returns:
+        int: The end position of the variant
+    """
+    return variant_start + len(variant_ref) - 1
+
+
 class PhenopacketTruthSet:
     """Class for finding the causative gene/disease/variant from a phenopacket"""
 
@@ -139,13 +151,14 @@ class PhenopacketTruthSet:
         return pl.DataFrame(
             {
                 "chrom": [v.chrom for v in variants],
-                "pos": [v.pos for v in variants],
+                "start": [v.pos for v in variants],
+                "end": [calculate_end_pos(v.pos, v.ref) for v in variants],
                 "ref": [v.ref for v in variants],
                 "alt": [v.alt for v in variants],
             }
         ).with_columns(
             [
-                pl.concat_str(["chrom", "pos", "ref", "alt"], separator="-").alias("variant_id"),
+                pl.concat_str(["chrom", "start", "ref", "alt"], separator="-").alias("variant_id"),
                 pl.lit(0.0).cast(pl.Float64).alias("score"),
                 pl.lit(0).cast(pl.Int64).alias("rank"),
                 pl.lit(True).alias("true_positive"),
@@ -166,10 +179,10 @@ class PhenopacketTruthSet:
         return (
             ranked_results.with_columns(
                 [
-                    pl.struct(["chrom", "pos", "ref", "alt"])
+                    pl.struct(["chrom", "start", "end", "ref", "alt"])
                     .is_in(
                         classified_results.select(
-                            pl.struct(["chrom", "pos", "ref", "alt"])
+                            pl.struct(["chrom", "start", "end", "ref", "alt"])
                         ).to_series()
                     )
                     .alias("true_positive")
@@ -179,8 +192,10 @@ class PhenopacketTruthSet:
             .select(classified_results.columns)
             .vstack(
                 classified_results.filter(
-                    ~pl.struct(["chrom", "pos", "ref", "alt"]).is_in(
-                        ranked_results.select(pl.struct(["chrom", "pos", "ref", "alt"])).to_series()
+                    ~pl.struct(["chrom", "start", "end", "ref", "alt"]).is_in(
+                        ranked_results.select(
+                            pl.struct(["chrom", "start", "end", "ref", "alt"])
+                        ).to_series()
                     )
                 )
             )

pheval/post_processing/post_processing.py

@@ -22,18 +22,6 @@ class ResultType(Enum):
     VARIANT = "variant"
 
 
-def calculate_end_pos(variant_start: int, variant_ref: str) -> int:
-    """Calculate the end position for a variant
-    Args:
-        variant_start (int): The start position of the variant
-        variant_ref (str): The reference allele of the variant
-
-    Returns:
-        int: The end position of the variant
-    """
-    return variant_start + len(variant_ref) - 1
-
-
 class SortOrder(Enum):
     """Enumeration representing sorting orders."""
 
@@ -106,7 +94,7 @@ def _write_variant_result(ranked_results: pl.DataFrame, output_file: Path) -> No
         output_file (Path): Path to the output file.
     """
     variant_output = ranked_results.select(
-        ["rank", "score", "chromosome", "start", "end", "ref", "alt", "variant_id", "true_positive"]
+        ["rank", "score", "chrom", "start", "end", "ref", "alt", "variant_id", "true_positive"]
     )
     _write_results_file(output_file, variant_output)
 
@@ -119,9 +107,7 @@ def _write_disease_result(ranked_results: pl.DataFrame, output_file: Path) -> No
         ranked_results ([PhEvalResult]): List of ranked PhEval disease results.
         output_file (Path): Path to the output file.
     """
-    disease_output = ranked_results.select(
-        ["rank", "score", "disease_name", "disease_identifier", "true_positive"]
-    )
+    disease_output = ranked_results.select(["rank", "score", "disease_identifier", "true_positive"])
     _write_results_file(output_file, disease_output)
 
 
@@ -228,7 +214,7 @@ def generate_variant_result(
         phenopacket_dir, output_dir.joinpath("pheval_variant_results"), ResultType.VARIANT
     )
     ranked_results = _rank_results(results, sort_order).with_columns(
-        pl.concat_str(["chrom", "pos", "ref", "alt"], separator="-").alias("variant_id")
+        pl.concat_str(["chrom", "start", "ref", "alt"], separator="-").alias("variant_id")
     )
     classified_results = PhenopacketTruthSet(phenopacket_dir).merge_variant_results(
         ranked_results, output_file

pheval/post_processing/validate_result_format.py

@@ -35,18 +35,17 @@ class ResultSchema(Enum):
     )
     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:
+    def validate(self, results: pl.DataFrame) -> bool:
         """
         Validate that a DataFrame follows the expected schema.
         Args:
-            df (pl.DataFrame): The DataFrame to validate.
+            results (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.
@@ -55,18 +54,18 @@ class ResultSchema(Enum):
         """
         expected_schema = self.value
 
-        if "grouping_id" in df.columns and df["grouping_id"].null_count() > 0:
+        if "grouping_id" in results.columns and results["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 not in results.schema:
                 if col_name == "grouping_id":
                     continue
                 raise ValueError(f"Missing required column: {col_name}")
 
-            if df.schema[col_name] != expected_type:
+            if results.schema[col_name] != expected_type:
                 raise TypeError(
-                    f"Column '{col_name}' has type {df.schema[col_name]}, expected {expected_type}"
+                    f"Column '{col_name}' has type {results.schema[col_name]}, expected {expected_type}"
                 )
 
         return True
@@ -83,9 +82,9 @@ def validate_dataframe(schema: ResultSchema) -> Callable:
 
     def decorator(func: Callable) -> Callable:
         @wraps(func)
-        def wrapper(df: pl.DataFrame, *args, **kwargs):
-            schema.validate(df)
-            return func(df, *args, **kwargs)
+        def wrapper(results: pl.DataFrame, *args, **kwargs):
+            schema.validate(results)
+            return func(results, *args, **kwargs)
 
         return wrapper
 

{pheval-0.5.0.dist-info → pheval-0.5.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: pheval
-Version: 0.5.0
+Version: 0.5.2
 Summary: 
 Author: Yasemin Bridges
 Author-email: y.bridges@qmul.ac.uk
@@ -32,10 +32,10 @@ Description-Content-Type: text/markdown
 
 # PhEval - Phenotypic Inference Evaluation Framework
 
-![PyPI](https://img.shields.io/pypi/v/pheval)
+[![PyPI](https://img.shields.io/pypi/v/pheval)](https://pypi.org/project/pheval/)
 ![Build Status](https://img.shields.io/github/actions/workflow/status/monarch-initiative/pheval/pypi-publish.yml?branch=main)
 ![License](https://img.shields.io/github/license/monarch-initiative/pheval)
-![Python Version](https://img.shields.io/badge/python-3.8%2B-blue)
+![Python Version](https://img.shields.io/badge/python-3.10%2B-blue)
 ![Issues](https://img.shields.io/github/issues/monarch-initiative/pheval)
 
 ## Overview
@@ -53,7 +53,7 @@ For more information please see the full [documentation](https://monarch-initiat
 
 ## Download and Installation
 
-1. Ensure you have Python 3.8 or greater installed.
+1. Ensure you have Python 3.10 or greater installed.
 2. Install with `pip`:
 ```bash
 pip install pheval

{pheval-0.5.0.dist-info → pheval-0.5.2.dist-info}/RECORD

@@ -1,6 +1,6 @@
 pheval/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pheval/analyse/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-pheval/analyse/benchmark.py,sha256=1ysz1peGb21DhgNpEam9NgUOS5eGv7K0CI3RNjy0crQ,6275
+pheval/analyse/benchmark.py,sha256=sfjReLmodXwCT9ZyZDE6Oli0j1S5ygicJshb7n4-x4U,6916
 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
@@ -17,9 +17,9 @@ pheval/implementations/__init__.py,sha256=BMUTotjTdgy5j5xubWCIQgRXrSQ1ZIcjooer7r
 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/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/post_processing/phenopacket_truth_set.py,sha256=EvpfS0NJpcipI1muCtB0PBUghXtktln9vF5PUk57wSM,9412
+pheval/post_processing/post_processing.py,sha256=VadU-tjToEa2auvNpmbIzKuGtRvN4E89pH_GH1RiHm0,9078
+pheval/post_processing/validate_result_format.py,sha256=rRlVVIT5ZtdD_Qi0tQVqRSghCrxEDZCKImtw1ygcbtA,2927
 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
@@ -46,8 +46,8 @@ 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-0.5.0.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-0.5.2.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+pheval-0.5.2.dist-info/METADATA,sha256=do8ya_Tw3VD-md2rPf83DBmVTyytUrH7tEhQenjN-6o,6494
+pheval-0.5.2.dist-info/WHEEL,sha256=XbeZDeTWKc1w7CSIyre5aMDU_-PohRwTQceYnisIYYY,88
+pheval-0.5.2.dist-info/entry_points.txt,sha256=o9gSwDkvT4-lqKy4mlsftd1nzP9WUOXQCfnbqycURd0,81
+pheval-0.5.2.dist-info/RECORD,,