UI updates. fix column name

app.py

@@ -13,10 +13,10 @@ model = AlbertModel.from_pretrained('albert-' + model_size + '-v2')
 def get_embedding(input_text):
     encoded_input = tokenizer(input_text, return_tensors='pt')
     input_ids = encoded_input.input_ids
-    input_num_tokens = input_ids.shape[1]
+    #input_num_tokens = input_ids.shape[1]
 
-    print( "Number of input tokens: " + str(input_num_tokens))
-    print("Length of input: " + str(len(input_text)))
+    #print( "Number of input tokens: " + str(input_num_tokens))
+    #print("Length of input: " + str(len(input_text)))
 
     list_of_tokens = tokenizer.convert_ids_to_tokens(input_ids.view(-1).tolist())
 
@@ -29,6 +29,7 @@ def get_embedding(input_text):
         #sentence_embedding = output.last_hidden_state[0][0]
         return sentence_embedding.tolist()
 
+st. set_page_config(layout="wide")
 st.title('Upload the Address Dataset')
 
 st.markdown('Upload an Excel file to view the data in a table.')
@@ -36,6 +37,7 @@ st.markdown('Upload an Excel file to view the data in a table.')
 uploaded_file = st.file_uploader('Choose a file', type='xlsx')
 
 
+
 if uploaded_file is not None:
     data_caqh = pd.read_excel(uploaded_file, sheet_name='CAQH', dtype=str)
     data_ndb = pd.read_excel(uploaded_file, sheet_name='NDB', dtype=str)
@@ -56,7 +58,7 @@ if uploaded_file is not None:
                                       + data_ndb['zip_pls_4_cd'].astype(str))
 
     data_ndb['full-addr'] = data_ndb['adr_ln_1_txt'].astype(str).str.strip() + ', ' \
-                            + data_ndb['city'].astype(str) + ', ' \
+                            + data_ndb['cty_nm'].astype(str) + ', ' \
                             + data_ndb['st_cd'].astype(str) + ', ' + data_ndb['zip_cd_zip_pls_4_cd']
 
     # App
@@ -79,8 +81,14 @@ if uploaded_file is not None:
         else:
             data_caqh.at[i, 'matched-addr'] = 'No Matches'
 
-    st.dataframe(data_caqh)
-    st.dataframe(data_ndb)
+    # Drop columns not needed for display
+    data_caqh.drop(columns=['embedding'], inplace=True)
+    data_ndb.drop(columns=['embedding'], inplace=True)
+
+    st.header('CAQH addresses and matches')
+    st.dataframe(data_caqh, use_container_width=True)
+    st.header('NDB data')
+    st.dataframe(data_ndb, use_container_width=True)
 
     # calculate the embedding of each item.