chore(docstring): added assertion errors to the docstrings

src/gentropy/dataset/l2g_features/other.py

@@ -100,6 +100,9 @@ def is_protein_coding_feature_logic(
 
     Returns:
         DataFrame: Feature dataset, with 1 if the gene is protein-coding, 0 if not.
+
+    Raises:
+        AssertionError: when provided `genomic_window` is more or equal to 500kb.
     """
     assert genomic_window <= 500_000, "Genomic window must be less than 500kb."
     genes_in_window = (

src/gentropy/dataset/pairwise_ld.py

@@ -30,6 +30,9 @@ def __post_init__(self: PairwiseLD) -> None:
         """Validating the dataset upon creation.
 
         - Besides the schema, a pairwise LD table is expected have rows being a square number.
+
+        Raises:
+            AssertionError: When the number of rows in the provided dataframe to construct the LD matrix is not even after applying square root.
         """
         row_count = self.df.count()
 

src/gentropy/dataset/variant_index.py

@@ -227,10 +227,13 @@ def filter_by_variant(self: VariantIndex, df: DataFrame) -> VariantIndex:
         """Filter variant annotation dataset by a variant dataframe.
 
         Args:
-            df (DataFrame): A dataframe of variants
+            df (DataFrame): A dataframe of variants.
 
         Returns:
-            VariantIndex: A filtered variant annotation dataset
+            VariantIndex: A filtered variant annotation dataset.
+
+        Raises:
+            AssertionError: When the variant dataframe does not contain eiter `variantId` or `chromosome` column.
         """
         join_columns = ["variantId", "chromosome"]
 

src/gentropy/datasource/ensembl/vep_parser.py

@@ -325,6 +325,9 @@ def _get_most_severe_transcript(
             |{0.6, transcript3}    |
             +----------------------+
             <BLANKLINE>
+
+        Raises:
+            AssertionError: When `transcript_column_name` is not a string.
         """
         assert isinstance(
             transcript_column_name, str

src/gentropy/method/l2g/trainer.py

@@ -88,6 +88,7 @@ def fit(
 
         Raises:
             ValueError: Train data not set, nothing to fit.
+            AssertionError: When x_train_size or y_train_size are not zero.
         """
         if (
             self.x_train is not None
@@ -180,6 +181,7 @@ def log_to_wandb(
 
         Raises:
             RuntimeError: If dependencies are not available.
+            AssertionError: When x_train_size or y_train_size are not zero.
         """
         if (
             self.x_train is None

src/gentropy/method/susie_inf.py

@@ -493,6 +493,9 @@ def credible_set_qc(
 
         Returns:
             StudyLocus: Credible sets which pass filters and LD clumping.
+
+        Raises:
+            AssertionError: When running in clump mode, but no study study_index or ld_index or ld_min_r2 were provided.
         """
         cred_sets.df = (
             cred_sets.df.withColumn(

src/gentropy/variant_index.py

@@ -106,6 +106,9 @@ def __init__(
             source_formats (list[str]): Format of the input dataset.
             output_path (str): Output VCF file path.
             partition_size (int): Approximate number of variants in each output partition.
+
+        Raises:
+            AssertionError: When the length of `source_paths` does not match the lenght of `source_formats`.
         """
         assert len(source_formats) == len(
             source_paths