Merge pull request #55 from monarch-initiative/54-write-error-when-no…

…-results-found-for-a-omim-id-not-present-in-the-phenotypehpoa

54 write error when no results found for a omim id not present in the phenotypehpoa

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "phenotype2phenopacket"
-version = "0.6.11"
+version = "0.6.12"
 description = ""
 authors = ["Yasemin Bridges <[email protected]>"]
 readme = "README.md"

src/phenotype2phenopacket/create/create.py

@@ -11,6 +11,7 @@
 from phenotype2phenopacket.utils.utils import (
     filter_diseases,
     load_ontology,
+    read_omim_id_list,
     return_phenotype_annotation_data,
 )
 
@@ -74,7 +75,14 @@ def create_synthetic_patients(
     grouped_omim_diseases = filter_diseases(
         num_disease, omim_id, omim_id_list, phenotype_annotation_data
     )
-    for omim_disease in grouped_omim_diseases:
+    omim_ids = (
+        read_omim_id_list(omim_id_list) if omim_id_list else [None] * len(grouped_omim_diseases)
+    )
+    for omim_id, omim_disease in zip(omim_ids, grouped_omim_diseases):
+        if len(omim_disease) == 0:
+            id_message = f" for {omim_id}!" if omim_id else "!"
+            print(f"Skipping... Could not find any phenotype entries{id_message}")
+            continue
         create_synthetic_patient_phenopacket(
             human_phenotype_ontology,
             omim_disease,

src/phenotype2phenopacket/utils/phenopacket_utils.py

@@ -366,9 +366,9 @@ def worker():
             if len(self.filtered_df) == 0:
                 return frequency_df.sample(n=max_number)
             else:
-                return pl.from_dicts(self.filtered_df)
+                return pl.from_dicts(self.filtered_df, infer_schema_length=len(self.filtered_df))
         else:
-            return pl.from_dicts(self.filtered_df)
+            return pl.from_dicts(self.filtered_df, infer_schema_length=len(self.filtered_df))
 
     def get_patient_terms(self) -> pl.DataFrame:
         """
@@ -570,7 +570,7 @@ def patient_term_annotation_set(self) -> pl.DataFrame:
             patient_terms, patient_terms_sub_sample
         )
         final_patient_terms = patient_terms_filtered.to_dicts() + new_phenotype_terms
-        return pl.from_dicts(final_patient_terms)
+        return pl.from_dicts(final_patient_terms, infer_schema_length=len(final_patient_terms))
 
 
 class PhenotypeAnnotationToPhenopacketConverter: