Merge remote-tracking branch 'origin/main' into main

app.py

@@ -58,8 +58,8 @@ if uploaded_file is not None:
     data_caqh['postalcode'] = data_caqh['postalcode'].astype(str).apply(lambda x: x[:5] + '-' + x[5:] if len(x) > 5 and not '-' in x else x)
     data_caqh['full-addr'] = data_caqh['address1'].astype(str) + ', ' \
                              + np.where(data_caqh['address2'].isnull(),  '' , data_caqh['address2'].astype(str)+ ', ')  \
-                             + data_caqh['city'].astype(str) + ', '\
-                             + data_caqh['state'].astype(str) + ', ' \
+                             + data_caqh['city'].astype(str) + ' '\
+                             + data_caqh['state'].astype(str) + ' ' \
                              + data_caqh['postalcode'].astype(str)
 
     st.write(f"CAQH before duplicate removal {len(data_caqh)}")
@@ -75,8 +75,8 @@ 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['cty_nm'].astype(str).str.strip() + ', ' \
-                            + data_ndb['st_cd'].astype(str) + ', ' + data_ndb['zip_cd_zip_pls_4_cd']
+                            + data_ndb['cty_nm'].astype(str).str.strip() + '  ' \
+                            + data_ndb['st_cd'].astype(str) + ' ' + data_ndb['zip_cd_zip_pls_4_cd']
 
     # Calculate similarity For CAQH
     num_items = len(data_caqh)

references.md

@@ -0,0 +1,3 @@
+Collect various links and references to useful thing related to project.
+
+https://medium.com/streetgroup/a-street-group-address-matching-algorithm-e7e1444767cd