restructure download

appStore/target.py

@@ -34,7 +34,7 @@ _lab_dict = {
             }
 
 @st.cache_data
-def to_excel(df,hits):
+def to_excel(df):
     # df['Target Validation'] = 'No'
     # df['Netzero Validation'] = 'No'
     # df['GHG Validation'] = 'No'
@@ -44,12 +44,41 @@ def to_excel(df,hits):
     output = BytesIO()
     writer = pd.ExcelWriter(output, engine='xlsxwriter')
     df.to_excel(writer, index=False, sheet_name='rawdata')
-    if 'keep' in hits.columns:
-        hits = hits[hits.keep == True]
-        hits = hits.reset_index(drop=True)
-        hits.drop(columns = ['keep'], inplace=True)
+    if 'target_hits' in st.session_state:
+        target_hits = st.session_state['target_hits']
+        if 'keep' in target_hits.columns:
+            target_hits = target_hits[target_hits.keep == True]
+            target_hits = target_hits.reset_index(drop=True)
+            target_hits.drop(columns = ['keep'], inplace=True)
+            target_hits.to_excel(writer,index=False,sheet_name = 'Target')
+    else:
+        target_hits = df[df['Target Label'] == True]
+        target_hits.drop(columns=['Target Label','Netzero Score','GHG Score','Action Label',
+                                'Action Score','Policies_Plans Label','Indicator Label',
+                                'Policies_Plans Score','Conditional Score'],inplace=True)
+        target_hits = target_hits.sort_values(by=['Target Score'], ascending=False)
+        target_hits = target_hits.reset_index(drop=True)
+        target_hits.to_excel(writer,index=False,sheet_name = 'Target')
+
+
+    if 'action_hits' in st.session_state:
+        action_hits = st.session_state['action_hits']
+        if 'keep' in action_hits.columns:
+            action_hits = action_hits[action_hits.keep == True]
+            action_hits = action_hits.reset_index(drop=True)
+            action_hits.drop(columns = ['keep'], inplace=True)
+            action_hits.to_excel(writer,index=False,sheet_name = 'Action')  
+    else:
+        action_hits = df[df['Action Label'] == True]
+        action_hits.drop(columns=['Target Label','Target Score','Netzero Score',
+                                'Netzero Label','GHG Label',
+                                'GHG Score','Action Label','Policies_Plans Label',
+                                'Policies_Plans Score','Conditional Score'],inplace=True)
+        action_hits = action_hits.sort_values(by=['Action Score'], ascending=False)
+        action_hits = action_hits.reset_index(drop=True)
+        action_hits.to_excel(writer,index=False,sheet_name = 'Action') 
+            
     # hits = hits.drop(columns = ['Target Score','Netzero Score','GHG Score'])
-    hits.to_excel(writer,index=False,sheet_name = 'Target')
     workbook = writer.book
     # worksheet = writer.sheets['Sheet1']
     # worksheet.data_validation('L2:L{}'.format(len_df), 
@@ -152,10 +181,11 @@ def target_display():
             # filtered_df = filtered_df[filtered_df.keep == True]
             # st.write('Explore the data')
             # AgGrid(hits)
-            df_xlsx = to_excel(df,st.session_state['target_hits'])
+            
             
             with st.sidebar:
                 st.write('-------------')
+                df_xlsx = to_excel(df)
                 st.download_button(label='📥 Download Result',
                             data=df_xlsx ,
                             file_name= os.path.splitext(os.path.basename(st.session_state['filename']))[0]+'.xlsx')

utils/adapmit_classifier.py

@@ -107,4 +107,4 @@ def adapmit_classification(haystack_doc:pd.DataFrame,
     df = df.reset_index(drop =True)
     df.index += 1
 
-    return haystack_doc
+    return df