post processing for contract_num added

.gitignore

@@ -55,11 +55,11 @@ streamlit/DB/
 streamlit/RAW_DOCUMENTS/
 streamlit/SOURCE_DOCUMENTS/
 streamlit/contract_field_values.csv
-# streamlit/contract_fields.csv
+streamlit/contract_fields.csv
 streamlit/sample.csv
 streamlit/temp1.csv
 streamlit/temp2.csv
-# streamlit/results.csv
+streamlit/results.csv
 
 # env
 streamlit/venv

streamlit/interface_3.py

@@ -523,6 +523,11 @@ if st.session_state.user_info['mail'] in user_list:
                 answer_list = [answer if str(answer) != "one year" else "1 year" for answer in answer_list]
                 answer_list = [answer if str(answer) != "one" else "1 year" for answer in answer_list]
                 answer_list = [answer if str(answer) != "one (1) year" else "1 year" for answer in answer_list]
+                answer_list = [answer if str(answer) != "twelve" else "1 year" for answer in answer_list]
+                answer_list = [answer if str(answer) != "XI" else "11" for answer in answer_list]
+                answer_list = [answer if str(answer) != "Third" else "3" for answer in answer_list]
+                answer_list = [answer if str(answer) != "Six" else "6" for answer in answer_list]
+
                 answer_list = [answer.rstrip(".") for answer in answer_list]
             else:
                 answer_list = [answer.rstrip(".") for answer in answer_list]
@@ -564,7 +569,8 @@ if st.session_state.user_info['mail'] in user_list:
             field_values_1['Contract Name'] = document_name
             field_values_2 = pd.concat([field_values_2, field_values_1], ignore_index = True)
 
-        df = pd.merge(df, field_values_2, how ='left', on =['Contract Name', 'SF_DB_COL_NAME'])
+        df = pd.merge(df, field_values_2, how ='right', on =['Contract Name', 'SF_DB_COL_NAME'])
+        df = df.drop_duplicates(subset=['SF_DB_COL_NAME', 'Contract Name'], keep="first")
         df['Original Page Number'] = df['Original Page Number'].apply(lambda x: re.search(r'\d+', x).group(
             ) if isinstance(x, str) and  re.search(r'\d+', x) is not None else " ")
         
@@ -581,6 +587,10 @@ if st.session_state.user_info['mail'] in user_list:
         df['Actual Value Stored'] = df['Actual Value Stored'].apply(lambda x: x.strip() if isinstance(x, str) else '')
         df['New Extracted value'] = df['New Extracted value'].apply(lambda x: x.strip() if isinstance(x, str) else '')
         actual_value_list = list(df['Actual Value Stored'])
+        actual_value_list = [answer if str(answer) != "12 months" else "1 year" for answer in actual_value_list]
+        actual_value_list = [answer if str(answer) != "Fifth" else "5" for answer in actual_value_list]
+        actual_value_list = [answer if str(answer) != "Seventh" else "7" for answer in actual_value_list]
+
         answer_list = list(df['New Extracted value'])
         actual_value_list = [s.replace('-', '').replace(' ', '').replace('[', '').replace(']', '').lower() for s in actual_value_list]
         answer_list = [s.replace('-', '').replace(' ', '').replace('[', '').replace(']', '').lower() for s in answer_list]