augment from similar

utils.py

@@ -123,6 +123,28 @@ def get_similarities_among_diseases_uris(
     return data
 
 
+def augment_the_set_of_diseaces(engine, diseases: List[str]) -> str:
+
+    for i in range(15-len(diseases)):
+        with engine.connect() as conn:
+            with conn.begin():
+                sql = f"""
+                    SELECT TOP 1 e2.uri AS new_disease, (SUM(VECTOR_COSINE(e1.embedding, e2.embedding))/ {len(diseases)})  AS score
+                    FROM Test.EntityEmbeddings e1, Test.EntityEmbeddings e2
+                    WHERE e1.uri IN ({','.join([f"'http://identifiers.org/medgen/{disease}'" for disease in diseases])})
+                    AND e2.uri NOT IN ({','.join([f"'http://identifiers.org/medgen/{disease}'" for disease in diseases])})
+                    AND e2.label != 'nan'
+                    GROUP BY e2.label
+                    ORDER BY score DESC
+                    """
+
+                result = conn.execute(text(sql))
+                data = result.fetchall()
+
+        diseases.append(data[0][0].split('/')[-1])
+
+    return diseases
+
 def get_embedding(string: str, encoder) -> List[float]:
     # Embed the string using sentence-transformers
     vector = encoder.encode(string, show_progress_bar=False)