update req

app.py

@@ -15,7 +15,8 @@ model = AlbertModel.from_pretrained('albert-' + model_size + '-v2')
 
 model_sbert = SentenceTransformer('sentence-transformers/paraphrase-albert-base-v2')
 # for regular burt 0.98
-similarity_threshold = 0.9
+
+similarity_threshold = 0.8
 
 def get_sbert_embedding(input_text):
     embedding = model_sbert.encode(input_text)
@@ -171,6 +172,14 @@ if uploaded_file is not None:
     st.header('CAQH addresses and matches')
     st.dataframe(data_caqh, use_container_width=True)
 
+    # Calculate stats.
+    total_items = len(data_caqh)
+    item_without_matches = data_caqh['matched-addr'].value_counts().get('No Matches', 0)
+    items_with_matches = total_items - item_without_matches;
+    percent_matched = (items_with_matches/total_items)*100.0
+
+    st.write(f"From total matches {total_items}, {items_with_matches} items matched, {item_without_matches} items did not match, {percent_matched:.2f}% matched")
+
     # Create an in-memory binary stream
     output = BytesIO()
     # Save the DataFrame to the binary stream as an Excel file