napistu 0.3.6__py3-none-any.whl → 0.3.7__py3-none-any.whl

napistu/ingestion/string.py

@@ -8,15 +8,11 @@ from napistu import sbml_dfs_core
 from napistu import sbml_dfs_utils
 from napistu import source
 from napistu import utils
+from napistu.ingestion import napistu_edgelist
 from napistu.constants import BQB
 from napistu.constants import MINI_SBO_FROM_NAME
-from napistu.ingestion import napistu_edgelist
-from napistu.ingestion.constants import SBML_SPECIES_DICT_IDENTIFIERS
-from napistu.ingestion.constants import SBML_SPECIES_DICT_NAME
-from napistu.ingestion.constants import SMBL_REACTION_DICT_IDENTIFIERS
-from napistu.ingestion.constants import SMBL_REACTION_DICT_IS_REVERSIBLE
-from napistu.ingestion.constants import SMBL_REACTION_DICT_NAME
-from napistu.ingestion.constants import SMBL_REACTION_SPEC_SBO_TERM
+from napistu.constants import ONTOLOGIES
+from napistu.constants import SBML_DFS
 from napistu.ingestion.constants import STRING_DOWNSTREAM_COMPARTMENT
 from napistu.ingestion.constants import STRING_DOWNSTREAM_NAME
 from napistu.ingestion.constants import STRING_PROTEIN_ID
@@ -137,10 +133,10 @@ def convert_string_to_sbml_dfs(
 
     # define identifier mapping from aliases to use:
     alias_to_identifier = {
-        "Ensembl_gene": ("ensembl_gene", BQB.IS_ENCODED_BY),
-        "Ensembl_transcript": ("ensembl_transcript", BQB.IS_ENCODED_BY),
-        "Ensembl_translation": ("ensembl_protein", BQB.IS),
-        "Ensembl_UniProt_AC": ("uniprot", BQB.IS),
+        "Ensembl_gene": (ONTOLOGIES.ENSEMBL_GENE, BQB.IS_ENCODED_BY),
+        "Ensembl_transcript": (ONTOLOGIES.ENSEMBL_TRANSCRIPT, BQB.IS_ENCODED_BY),
+        "Ensembl_translation": (ONTOLOGIES.ENSEMBL_PROTEIN, BQB.IS),
+        "Ensembl_UniProt_AC": (ONTOLOGIES.UNIPROT, BQB.IS),
     }
 
     # filter aliases to only keep required ones
@@ -276,17 +272,17 @@ def _build_species_df(
     species_df = (
         pd.Series(
             list(set(edgelist[source_col]).union(edgelist[target_col])),
-            name=SBML_SPECIES_DICT_NAME,
+            name=SBML_DFS.S_NAME,
         )
         .to_frame()
-        .set_index(SBML_SPECIES_DICT_NAME, drop=False)
+        .set_index(SBML_DFS.S_NAME, drop=False)
         .apply(
             _get_identifiers,
             alias_to_identifier=alias_to_identifier,
             dat_alias=aliases,
             axis=1,
         )
-        .rename(SBML_SPECIES_DICT_IDENTIFIERS)
+        .rename(SBML_DFS.S_IDENTIFIERS)
         .reset_index()
     )
     return species_df
@@ -312,8 +308,8 @@ def _build_interactor_edgelist(
         **{
             STRING_UPSTREAM_COMPARTMENT: compartment,
             STRING_DOWNSTREAM_COMPARTMENT: compartment,
-            SMBL_REACTION_SPEC_SBO_TERM: sbo_interactor,
-            SMBL_REACTION_DICT_IDENTIFIERS: lambda x: identifiers.Identifiers([]),
+            SBML_DFS.SBO_TERM: sbo_interactor,
+            SBML_DFS.R_IDENTIFIERS: lambda x: identifiers.Identifiers([]),
         }
     )
     if add_reverse_interactions:
@@ -336,10 +332,10 @@ def _build_interactor_edgelist(
         )
 
     interaction_edgelist = dat
-    interaction_edgelist[SMBL_REACTION_DICT_NAME] = _build_string_reaction_name(
+    interaction_edgelist[SBML_DFS.R_NAME] = _build_string_reaction_name(
         dat[STRING_UPSTREAM_NAME], dat[STRING_DOWNSTREAM_NAME]
     )
-    interaction_edgelist[SMBL_REACTION_DICT_IS_REVERSIBLE] = True
+    interaction_edgelist[SBML_DFS.R_ISREVERSIBLE] = True
 
     return interaction_edgelist
 

napistu/ingestion/trrust.py

@@ -8,16 +8,11 @@ from napistu import identifiers
 from napistu import sbml_dfs_core
 from napistu import source
 from napistu import utils
+from napistu.constants import BQB
+from napistu.constants import IDENTIFIERS
 from napistu.constants import MINI_SBO_FROM_NAME
 from napistu.constants import SBOTERM_NAMES
-from napistu.ingestion.constants import SBML_COMPARTMENT_DICT_IDENTIFIERS
-from napistu.ingestion.constants import SBML_COMPARTMENT_DICT_NAME
-from napistu.ingestion.constants import SBML_SPECIES_DICT_IDENTIFIERS
-from napistu.ingestion.constants import SBML_SPECIES_DICT_NAME
-from napistu.ingestion.constants import SMBL_REACTION_DICT_IDENTIFIERS
-from napistu.ingestion.constants import SMBL_REACTION_DICT_IS_REVERSIBLE
-from napistu.ingestion.constants import SMBL_REACTION_DICT_NAME
-from napistu.ingestion.constants import SMBL_REACTION_SPEC_SBO_TERM
+from napistu.constants import SBML_DFS
 from napistu.ingestion.constants import SPECIES_FULL_NAME_HUMAN
 from napistu.ingestion.constants import STRING_DOWNSTREAM_COMPARTMENT
 from napistu.ingestion.constants import STRING_DOWNSTREAM_NAME
@@ -81,16 +76,16 @@ def convert_trrust_to_sbml_dfs(
     species_df = (
         pd.DataFrame(
             {
-                SBML_SPECIES_DICT_NAME: list(
+                SBML_DFS.S_NAME: list(
                     {*edge_summaries_df["from"], *edge_summaries_df["to"]}
                 )
             }
         )
         .merge(
-            uniprot_2_symbol.rename({TRRUST_SYMBOL: SBML_SPECIES_DICT_NAME}, axis=1),
+            uniprot_2_symbol.rename({TRRUST_SYMBOL: SBML_DFS.S_NAME}, axis=1),
             how="left",
         )
-        .set_index(SBML_SPECIES_DICT_NAME)
+        .set_index(SBML_DFS.S_NAME)
     )
 
     # create Identifiers objects for all species with uniprot IDs
@@ -106,14 +101,14 @@ def convert_trrust_to_sbml_dfs(
         [
             identifiers.Identifiers(
                 [
-                    identifiers.format_uri(uri=x, biological_qualifier_type="BQB_IS")
-                    for x in species_w_ids.loc[[ind]]["url"].tolist()
+                    identifiers.format_uri(uri=x, biological_qualifier_type=BQB.IS)
+                    for x in species_w_ids.loc[[ind]][IDENTIFIERS.URL].tolist()
                 ]
             )
             for ind in species_w_ids.index.unique()
         ],
         index=species_w_ids.index.unique(),
-    ).rename(SBML_SPECIES_DICT_IDENTIFIERS)
+    ).rename(SBML_DFS.S_IDENTIFIERS)
 
     # just retain s_name and s_Identifiers
     # this just needs a source object which will be added later
@@ -124,21 +119,21 @@ def convert_trrust_to_sbml_dfs(
         .merge(
             species_w_ids_series,
             how="left",
-            left_on=SBML_SPECIES_DICT_NAME,
+            left_on=SBML_DFS.S_NAME,
             right_index=True,
         )
         .reset_index(drop=True)
     )
     # stub genes with missing IDs
-    species_df[SBML_SPECIES_DICT_IDENTIFIERS] = species_df[SBML_SPECIES_DICT_IDENTIFIERS].fillna(  # type: ignore
+    species_df[SBML_DFS.S_IDENTIFIERS] = species_df[SBML_DFS.S_IDENTIFIERS].fillna(  # type: ignore
         value=identifiers.Identifiers([])
     )
 
     # define distinct compartments
     compartments_df = pd.DataFrame(
         {
-            SBML_COMPARTMENT_DICT_NAME: TRRUST_COMPARTMENT_NUCLEOPLASM,
-            SBML_COMPARTMENT_DICT_IDENTIFIERS: identifiers.Identifiers(
+            SBML_DFS.C_NAME: TRRUST_COMPARTMENT_NUCLEOPLASM,
+            SBML_DFS.C_IDENTIFIERS: identifiers.Identifiers(
                 [
                     identifiers.format_uri(
                         uri=identifiers.create_uri_url(
@@ -159,7 +154,7 @@ def convert_trrust_to_sbml_dfs(
         upstream_compartment=TRRUST_COMPARTMENT_NUCLEOPLASM,
         downstream_compartment=TRRUST_COMPARTMENT_NUCLEOPLASM,
     )
-    gene_gene_identifier_edgelist[SMBL_REACTION_DICT_NAME] = [
+    gene_gene_identifier_edgelist[SBML_DFS.R_NAME] = [
         f"{x} {y} of {z}"
         for x, y, z in zip(
             gene_gene_identifier_edgelist[STRING_UPSTREAM_NAME],
@@ -171,15 +166,15 @@ def convert_trrust_to_sbml_dfs(
     # convert relationships to SBO terms
     interaction_edgelist = gene_gene_identifier_edgelist.replace(
         {"sign": MINI_SBO_FROM_NAME}
-    ).rename({"sign": SMBL_REACTION_SPEC_SBO_TERM}, axis=1)
+    ).rename({"sign": SBML_DFS.SBO_TERM}, axis=1)
 
     # format pubmed identifiers of interactions
-    interaction_edgelist[SMBL_REACTION_DICT_IDENTIFIERS] = [
+    interaction_edgelist[SBML_DFS.R_IDENTIFIERS] = [
         _format_pubmed_for_interactions(x) for x in interaction_edgelist["reference"]
     ]
 
     # directionality: by default, set r_isreversible to False for TRRUST data
-    interaction_edgelist[SMBL_REACTION_DICT_IS_REVERSIBLE] = False
+    interaction_edgelist[SBML_DFS.R_ISREVERSIBLE] = False
 
     # reduce to essential variables
     interaction_edgelist = interaction_edgelist[
@@ -188,10 +183,10 @@ def convert_trrust_to_sbml_dfs(
             STRING_DOWNSTREAM_NAME,
             STRING_UPSTREAM_COMPARTMENT,
             STRING_DOWNSTREAM_COMPARTMENT,
-            SMBL_REACTION_DICT_NAME,
-            SMBL_REACTION_SPEC_SBO_TERM,
-            SMBL_REACTION_DICT_IDENTIFIERS,
-            SMBL_REACTION_DICT_IS_REVERSIBLE,
+            SBML_DFS.R_NAME,
+            SBML_DFS.SBO_TERM,
+            SBML_DFS.R_IDENTIFIERS,
+            SBML_DFS.R_ISREVERSIBLE,
         ]
     ]
 
@@ -277,7 +272,7 @@ def _format_pubmed_for_interactions(pubmed_set):
         url = identifiers.create_uri_url(ontology="pubmed", identifier=p, strict=False)
         if url is not None:
             valid_url = identifiers.format_uri(
-                uri=url, biological_qualifier_type="BQB_IS_DESCRIBED_BY"
+                uri=url, biological_qualifier_type=BQB.IS_DESCRIBED_BY
             )
 
             ids.append(valid_url)

napistu/matching/species.py

@@ -33,7 +33,7 @@ def features_to_pathway_species(
         pd.Dataframe containing a "feature_identifiers_var" variable used to match entries
     species_identifiers: pd.DataFrame
         A table of molecular species identifiers produced from sbml_dfs.get_identifiers("species")
-        generally using sbml_dfs_core.export_sbml_dfs()
+        generally using sbml_dfs.export_sbml_dfs()
     ontologies: set
         A set of ontologies used to match features to pathway species
     feature_identifiers_var: str

napistu/ontologies/genodexito.py

@@ -356,7 +356,7 @@ class Genodexito:
             )
             logger.debug(
                 f"{ids.shape[0] - expanded_ids.shape[0]} "
-                "ids are not included in expanded ids"
+                "ids are not included in expanded ids. These will be filled with empty Identifiers"
             )
         else:
             matched_expanded_ids = expanded_ids
@@ -364,6 +364,10 @@ class Genodexito:
         updated_ids = ids.drop(SBML_DFS.S_IDENTIFIERS, axis=1).join(
             pd.DataFrame(matched_expanded_ids)
         )
+        # fill missing attributes with empty Identifiers
+        updated_ids[SBML_DFS.S_IDENTIFIERS] = updated_ids[
+            SBML_DFS.S_IDENTIFIERS
+        ].fillna(identifiers.Identifiers([]))
 
         setattr(sbml_dfs, "species", updated_ids)
 

napistu/ontologies/renaming.py

@@ -72,6 +72,10 @@ def rename_species_ontologies(
     updated_species = sbml_dfs.species.drop(SBML_DFS.S_IDENTIFIERS, axis=1).join(
         pd.DataFrame(species_identifiers)
     )
+    # fill missing attributes with empty Identifiers
+    updated_species[SBML_DFS.S_IDENTIFIERS] = updated_species[
+        SBML_DFS.S_IDENTIFIERS
+    ].fillna(identifiers.Identifiers([]))
 
     setattr(sbml_dfs, "species", updated_species)
 

napistu/sbml_dfs_core.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+import copy
 import logging
 import re
 from typing import Any
@@ -64,6 +65,8 @@ class SBML_dfs:
         Add a new reactions data table to the model with validation.
     add_species_data(label, data)
         Add a new species data table to the model with validation.
+    copy()
+        Return a deep copy of the SBML_dfs object.
     export_sbml_dfs(model_prefix, outdir, overwrite=False, dogmatic=True)
         Export the SBML_dfs model and its tables to files in a specified directory.
     get_characteristic_species_ids(dogmatic=True)
@@ -114,7 +117,6 @@ class SBML_dfs:
     Private/Hidden Methods (alphabetical, appear after public methods)
     -----------------------------------------------------------------
     _attempt_resolve(e)
-    _check_pk_fk_correspondence()
     _find_underspecified_reactions_by_scids(sc_ids)
     _get_unused_cspecies()
     _get_unused_species()
@@ -123,9 +125,12 @@ class SBML_dfs:
     _remove_species(s_ids)
     _remove_unused_cspecies()
     _remove_unused_species()
+    _validate_identifiers()
+    _validate_pk_fk_correspondence()
     _validate_r_ids(r_ids)
     _validate_reaction_species()
     _validate_reactions_data(reactions_data_table)
+    _validate_sources()
     _validate_species_data(species_data_table)
     _validate_table(table_name)
     """
@@ -255,6 +260,17 @@ class SBML_dfs:
             )
         self.species_data[label] = data
 
+    def copy(self):
+        """
+        Return a deep copy of the SBML_dfs object.
+
+        Returns
+        -------
+        SBML_dfs
+            A deep copy of the current SBML_dfs object.
+        """
+        return copy.deepcopy(self)
+
     def export_sbml_dfs(
         self,
         model_prefix: str,
@@ -440,7 +456,7 @@ class SBML_dfs:
             If id_type is invalid or identifiers are malformed
         """
         selected_table = self.get_table(id_type, {"id"})
-        schema = self.schema
+        schema = SBML_DFS_SCHEMA.SCHEMA
 
         identifiers_dict = dict()
         for sysid in selected_table.index:
@@ -458,6 +474,7 @@ class SBML_dfs:
         if not identifiers_dict:
             # Return empty DataFrame with expected columns if nothing found
             return pd.DataFrame(columns=[schema[id_type]["pk"], "entry"])
+
         identifiers_tbl = pd.concat(identifiers_dict)
 
         identifiers_tbl.index.names = [schema[id_type]["pk"], "entry"]
@@ -1382,7 +1399,7 @@ class SBML_dfs:
             self._validate_table(table)
 
         # check whether pks and fks agree
-        self._check_pk_fk_correspondence()
+        self._validate_pk_fk_correspondence()
 
         # check optional data tables:
         for k, v in self.species_data.items():
@@ -1400,6 +1417,10 @@ class SBML_dfs:
         # validate reaction_species sbo_terms and stoi
         self._validate_reaction_species()
 
+        # validate identifiers and sources
+        self._validate_identifiers()
+        self._validate_sources()
+
     def validate_and_resolve(self):
         """
         Validate and attempt to automatically fix common issues.
@@ -1455,67 +1476,6 @@ class SBML_dfs:
             )
             raise e
 
-    def _check_pk_fk_correspondence(self):
-        """
-        Check whether primary keys and foreign keys agree for all tables in the schema.
-        Raises ValueError if any correspondence fails.
-        """
-
-        pk_df = pd.DataFrame(
-            [{"pk_table": k, "key": v["pk"]} for k, v in self.schema.items()]
-        )
-
-        fk_df = (
-            pd.DataFrame(
-                [
-                    {"fk_table": k, "fk": v["fk"]}
-                    for k, v in self.schema.items()
-                    if "fk" in v.keys()
-                ]
-            )
-            .set_index("fk_table")["fk"]
-            .apply(pd.Series)
-            .reset_index()
-            .melt(id_vars="fk_table")
-            .drop(["variable"], axis=1)
-            .rename(columns={"value": "key"})
-        )
-
-        pk_fk_correspondences = pk_df.merge(fk_df)
-
-        for i in range(0, pk_fk_correspondences.shape[0]):
-            pk_table_keys = set(
-                getattr(self, pk_fk_correspondences["pk_table"][i]).index.tolist()
-            )
-            if None in pk_table_keys:
-                raise ValueError(
-                    f"{pk_fk_correspondences['pk_table'][i]} had "
-                    "missing values in its index"
-                )
-
-            fk_table_keys = set(
-                getattr(self, pk_fk_correspondences["fk_table"][i]).loc[
-                    :, pk_fk_correspondences["key"][i]
-                ]
-            )
-            if None in fk_table_keys:
-                raise ValueError(
-                    f"{pk_fk_correspondences['fk_table'][i]} included "
-                    f"missing {pk_fk_correspondences['key'][i]} values"
-                )
-
-            # all foreign keys need to match a primary key
-            extra_fks = fk_table_keys.difference(pk_table_keys)
-            if len(extra_fks) != 0:
-                raise ValueError(
-                    f"{len(extra_fks)} distinct "
-                    f"{pk_fk_correspondences['key'][i]} values were"
-                    f" found in {pk_fk_correspondences['fk_table'][i]} "
-                    f"but missing from {pk_fk_correspondences['pk_table'][i]}."
-                    " All foreign keys must have a matching primary key.\n\n"
-                    f"Extra key are: {', '.join(extra_fks)}"
-                )
-
     def _find_underspecified_reactions_by_scids(
         self, sc_ids: Iterable[str]
     ) -> set[str]:
@@ -1640,6 +1600,88 @@ class SBML_dfs:
         s_ids = self._get_unused_species()
         self._remove_species(s_ids)
 
+    def _validate_identifiers(self):
+        """
+        Validate identifiers in the model
+
+        Iterates through all tables and checks if the identifier columns are valid.
+
+        Raises:
+            ValueError: missing identifiers in the table
+        """
+
+        SCHEMA = SBML_DFS_SCHEMA.SCHEMA
+        for table in SBML_DFS_SCHEMA.SCHEMA.keys():
+            if "id" not in SCHEMA[table].keys():
+                continue
+            id_series = self.get_table(table)[SCHEMA[table]["id"]]
+            if id_series.isna().sum() > 0:
+                missing_ids = id_series[id_series.isna()].index
+                raise ValueError(
+                    f"{table} has {len(missing_ids)} missing ids: {missing_ids}"
+                )
+
+    def _validate_pk_fk_correspondence(self):
+        """
+        Check whether primary keys and foreign keys agree for all tables in the schema.
+        Raises ValueError if any correspondence fails.
+        """
+
+        pk_df = pd.DataFrame(
+            [{"pk_table": k, "key": v["pk"]} for k, v in self.schema.items()]
+        )
+
+        fk_df = (
+            pd.DataFrame(
+                [
+                    {"fk_table": k, "fk": v["fk"]}
+                    for k, v in self.schema.items()
+                    if "fk" in v.keys()
+                ]
+            )
+            .set_index("fk_table")["fk"]
+            .apply(pd.Series)
+            .reset_index()
+            .melt(id_vars="fk_table")
+            .drop(["variable"], axis=1)
+            .rename(columns={"value": "key"})
+        )
+
+        pk_fk_correspondences = pk_df.merge(fk_df)
+
+        for i in range(0, pk_fk_correspondences.shape[0]):
+            pk_table_keys = set(
+                getattr(self, pk_fk_correspondences["pk_table"][i]).index.tolist()
+            )
+            if None in pk_table_keys:
+                raise ValueError(
+                    f"{pk_fk_correspondences['pk_table'][i]} had "
+                    "missing values in its index"
+                )
+
+            fk_table_keys = set(
+                getattr(self, pk_fk_correspondences["fk_table"][i]).loc[
+                    :, pk_fk_correspondences["key"][i]
+                ]
+            )
+            if None in fk_table_keys:
+                raise ValueError(
+                    f"{pk_fk_correspondences['fk_table'][i]} included "
+                    f"missing {pk_fk_correspondences['key'][i]} values"
+                )
+
+            # all foreign keys need to match a primary key
+            extra_fks = fk_table_keys.difference(pk_table_keys)
+            if len(extra_fks) != 0:
+                raise ValueError(
+                    f"{len(extra_fks)} distinct "
+                    f"{pk_fk_correspondences['key'][i]} values were"
+                    f" found in {pk_fk_correspondences['fk_table'][i]} "
+                    f"but missing from {pk_fk_correspondences['pk_table'][i]}."
+                    " All foreign keys must have a matching primary key.\n\n"
+                    f"Extra key are: {', '.join(extra_fks)}"
+                )
+
     def _validate_r_ids(self, r_ids: Optional[Union[str, list[str]]]) -> list[str]:
 
         if isinstance(r_ids, str):
@@ -1694,6 +1736,27 @@ class SBML_dfs:
         """
         sbml_dfs_utils._validate_matching_data(reactions_data_table, self.reactions)
 
+    def _validate_sources(self):
+        """
+        Validate sources in the model
+
+        Iterates through all tables and checks if the source columns are valid.
+
+        Raises:
+            ValueError: missing sources in the table
+        """
+
+        SCHEMA = SBML_DFS_SCHEMA.SCHEMA
+        for table in SBML_DFS_SCHEMA.SCHEMA.keys():
+            if "source" not in SCHEMA[table].keys():
+                continue
+            source_series = self.get_table(table)[SCHEMA[table]["source"]]
+            if source_series.isna().sum() > 0:
+                missing_sources = source_series[source_series.isna()].index
+                raise ValueError(
+                    f"{table} has {len(missing_sources)} missing sources: {missing_sources}"
+                )
+
     def _validate_species_data(self, species_data_table: pd.DataFrame):
         """Validates species data attribute
 

napistu/sbml_dfs_utils.py

@@ -559,6 +559,10 @@ def unnest_identifiers(id_table: pd.DataFrame, id_var: str) -> pd.DataFrame:
 
     N_invalid_ids = sum(id_table[id_var].isna())
     if N_invalid_ids != 0:
+
+        print("Rows with missing identifiers:")
+        print(id_table.loc[id_table[id_var].isna(), id_var])
+
         raise ValueError(
             f'{N_invalid_ids} entries in "id_table" were missing',
             "entries with no identifiers should still include an Identifiers object",

napistu/utils.py

@@ -810,50 +810,15 @@ def drop_extra_cols(
     return df_out.loc[:, ordered_cols]
 
 
-def _merge_and_log_overwrites(
-    left_df: pd.DataFrame, right_df: pd.DataFrame, merge_context: str, **merge_kwargs
-) -> pd.DataFrame:
+def update_pathological_names(names: pd.Series, prefix: str) -> pd.Series:
     """
-    Merge two DataFrames and log any column overwrites.
-
-    Parameters
-    ----------
-    left_df : pd.DataFrame
-        Left DataFrame for merge
-    right_df : pd.DataFrame
-        Right DataFrame for merge
-    merge_context : str
-        Description of the merge operation for logging
-    **merge_kwargs : dict
-        Additional keyword arguments passed to pd.merge
+    Update pathological names in a pandas Series.
 
-    Returns
-    -------
-    pd.DataFrame
-        Merged DataFrame with overwritten columns removed
+    Add a prefix to the names if they are all numeric.
     """
-    # Track original columns
-    original_cols = left_df.columns.tolist()
-
-    # Ensure we're using the correct suffixes
-    merge_kwargs["suffixes"] = ("_old", "")
-
-    # Perform merge
-    merged_df = pd.merge(left_df, right_df, **merge_kwargs)
-
-    # Check for and log any overwritten columns
-    new_cols = merged_df.columns.tolist()
-    overwritten_cols = [col for col in original_cols if col + "_old" in new_cols]
-    if overwritten_cols:
-        logger.warning(
-            f"The following columns were overwritten during {merge_context} merge and their original values "
-            f"have been suffixed with '_old': {', '.join(overwritten_cols)}"
-        )
-        # Drop the old columns
-        cols_to_drop = [col + "_old" for col in overwritten_cols]
-        merged_df = merged_df.drop(columns=cols_to_drop)
-
-    return merged_df
+    if names.apply(lambda x: x.isdigit()).all():
+        names = names.apply(lambda x: f"{prefix}{x}")
+    return names
 
 
 def format_identifiers_as_edgelist(
@@ -1108,3 +1073,49 @@ def _add_nameness_score(df, name_var):
 
     df.loc[:, "nameness_score"] = df[name_var].apply(score_nameness)
     return df
+
+
+def _merge_and_log_overwrites(
+    left_df: pd.DataFrame, right_df: pd.DataFrame, merge_context: str, **merge_kwargs
+) -> pd.DataFrame:
+    """
+    Merge two DataFrames and log any column overwrites.
+
+    Parameters
+    ----------
+    left_df : pd.DataFrame
+        Left DataFrame for merge
+    right_df : pd.DataFrame
+        Right DataFrame for merge
+    merge_context : str
+        Description of the merge operation for logging
+    **merge_kwargs : dict
+        Additional keyword arguments passed to pd.merge
+
+    Returns
+    -------
+    pd.DataFrame
+        Merged DataFrame with overwritten columns removed
+    """
+    # Track original columns
+    original_cols = left_df.columns.tolist()
+
+    # Ensure we're using the correct suffixes
+    merge_kwargs["suffixes"] = ("_old", "")
+
+    # Perform merge
+    merged_df = pd.merge(left_df, right_df, **merge_kwargs)
+
+    # Check for and log any overwritten columns
+    new_cols = merged_df.columns.tolist()
+    overwritten_cols = [col for col in original_cols if col + "_old" in new_cols]
+    if overwritten_cols:
+        logger.warning(
+            f"The following columns were overwritten during {merge_context} merge and their original values "
+            f"have been suffixed with '_old': {', '.join(overwritten_cols)}"
+        )
+        # Drop the old columns
+        cols_to_drop = [col + "_old" for col in overwritten_cols]
+        merged_df = merged_df.drop(columns=cols_to_drop)
+
+    return merged_df

{napistu-0.3.6.dist-info → napistu-0.3.7.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: napistu
-Version: 0.3.6
+Version: 0.3.7
 Summary: Connecting high-dimensional data to curated pathways
 Home-page: https://github.com/napistu/napistu-py
 Author: Sean Hackett