policy download

appStore/policyaction.py

@@ -293,6 +293,39 @@ def filter_dataframe(df: pd.DataFrame) -> pd.DataFrame:
         st.session_state['action_hits'] = df
         
     return
+def policy_display():
+    if  'key1' in st.session_state:
+        df = st.session_state.key1   
+        st.caption(""" **{}** is splitted into **{}** paragraphs/text chunks."""\
+                      .format(os.path.basename(st.session_state['filename']),
+                             len(df)))         
+        hits  = df[df['Policies_Plans Label'] == 'Policy and Plans']
+        range_val = min(5,len(hits))
+        if range_val !=0:
+            count_action = len(hits)
+            hits.drop(columns=['Target Label','Target Score','Netzero Score',
+                                'Netzero Label','GHG Label',
+                                'GHG Score','Action Label','Policies_Plans Label',
+                                'Action Score','Conditional Score'],inplace=True)
+            hits = hits.sort_values(by=['Action Score'], ascending=False)
+            hits = hits.reset_index(drop=True)
+
+            st.write('----------------')
+
+
+            st.caption("Filter table to select rows to keep for Policies and Plans category")
+            filter_dataframe(hits)
+            # filtered_df = filtered_df[filtered_df.keep == True]
+            # st.write('Explore the data')
+            # AgGrid(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')
             #count_netzero = sum(hits['Netzero Label'] == 'NETZERO')
             #count_ghg = sum(hits['GHG Label'] == 'GHG')
             #count_economy = sum([True if 'Economy-wide' in x else False 
@@ -363,82 +396,82 @@ def filter_dataframe(df: pd.DataFrame) -> pd.DataFrame:
         #     st.info("🤔 No Actions found")
 
 
-def policy_display():
-    if  'key1' in st.session_state:
-        df = st.session_state.key1
+# def policy_display():
+#     if  'key1' in st.session_state:
+#         df = st.session_state.key1
                 
         
-        df['Policy_check']  = df['Policy-Action Label'].apply(lambda x: True if 'Policies & Plans' in x else False)
-        hits  = df[df['Policy_check'] == True]
-        # hits['GHG Label'] = hits['GHG Label'].apply(lambda i: _lab_dict[i])
-        range_val = min(5,len(hits))
-        if range_val !=0:
-            count_policy = len(hits)
-            #count_netzero = sum(hits['Netzero Label'] == 'NETZERO')
-            #count_ghg = sum(hits['GHG Label'] == 'GHG')
-            #count_economy = sum([True if 'Economy-wide' in x else False 
-            #                  for x in hits['Sector Label']])
+#         df['Policy_check']  = df['Policy-Action Label'].apply(lambda x: True if 'Policies & Plans' in x else False)
+#         hits  = df[df['Policy_check'] == True]
+#         # hits['GHG Label'] = hits['GHG Label'].apply(lambda i: _lab_dict[i])
+#         range_val = min(5,len(hits))
+#         if range_val !=0:
+#             count_policy = len(hits)
+#             #count_netzero = sum(hits['Netzero Label'] == 'NETZERO')
+#             #count_ghg = sum(hits['GHG Label'] == 'GHG')
+#             #count_economy = sum([True if 'Economy-wide' in x else False 
+#             #                  for x in hits['Sector Label']])
             
-            # count_df = df['Target Label'].value_counts()
-            # count_df = count_df.rename('count')
-            # count_df = count_df.rename_axis('Target Label').reset_index()
-            # count_df['Label_def'] = count_df['Target Label'].apply(lambda x: _lab_dict[x])
-
-            # fig = px.bar(count_df, y="Label_def", x="count", orientation='h', height=200)
-        #    c1, c2 = st.columns([1,1])
-        #    with c1:
-        #        st.write('**Target Paragraphs**: `{}`'.format(count_target))
-        #        st.write('**NetZero Related Paragraphs**: `{}`'.format(count_netzero))
-#
- #               # st.plotly_chart(fig,use_container_width= True)
-  #          
-            # count_netzero = sum(hits['Netzero Label'] == 'NETZERO')
-            # count_ghg = sum(hits['GHG Label'] == 'LABEL_2')
-            # count_economy = sum([True if 'Economy-wide' in x else False 
-            #                   for x in hits['Sector Label']])
-     #       with c2:
-      #          st.write('**GHG Related Paragraphs**: `{}`'.format(count_ghg))
-       #         st.write('**Economy-wide Related Paragraphs**: `{}`'.format(count_economy))
-        #    st.write('-------------------')    
-    #        hits = hits.sort_values(by=['Relevancy'], ascending=False)
-     #       netzerohit = hits[hits['Netzero Label'] == 'NETZERO']
-      #      if not netzerohit.empty:
-       #         netzerohit = netzerohit.sort_values(by = ['Netzero Score'], ascending = False)
-        #        # st.write('-------------------')
-                # st.markdown("###### Netzero paragraph ######")
-      #          st.write('**Netzero paragraph** `page {}`: {}'.format(netzerohit.iloc[0]['page'],
-      #                          netzerohit.iloc[0]['text'].replace("\n", " ")))                        
-       #         st.write("")
-        #    else:
-         #       st.info("🤔 No Netzero paragraph found")
-
-            # st.write("**Result {}** `page {}` (Relevancy Score: {:.2f})'".format(i+1,hits.iloc[i]['page'],hits.iloc[i]['Relevancy'])")
-           # st.write('-------------------')
-            st.write("")
-            st.markdown("###### Top few Policy/Plans Classified paragraph/text results from list of {} classified paragraphs ######".format(count_policy))
-            st.markdown("""<hr style="height:10px;border:none;color:#097969;background-color:#097969;" /> """, unsafe_allow_html=True)
-            range_val = min(5,len(hits))
-            for i in range(range_val):
-                # the page number reflects the page that contains the main paragraph 
-                # according to split limit, the overlapping part can be on a separate page
-                st.write('**Result {}** : `page {}`, `Sector: {}`,\
-                            `Indicators: {}`, `Adapt-Mitig :{}`'\
-                    .format(i+1,
-                            hits.iloc[i]['page'], hits.iloc[i]['Sector Label'],
-                            hits.iloc[i]['Indicator Label'],hits.iloc[i]['Adapt-Mitig Label']))                        
-                st.write("\t Text: \t{}".format(hits.iloc[i]['text'].replace("\n", " ")))
-            hits = hits.reset_index(drop =True)
-            st.write('----------------')
-            st.write('Explore the data')
-            st.write(hits)
-            df.drop(columns = ['Policy_check'],inplace=True)
-            df_xlsx = to_excel(df)
+#             # count_df = df['Target Label'].value_counts()
+#             # count_df = count_df.rename('count')
+#             # count_df = count_df.rename_axis('Target Label').reset_index()
+#             # count_df['Label_def'] = count_df['Target Label'].apply(lambda x: _lab_dict[x])
+
+#             # fig = px.bar(count_df, y="Label_def", x="count", orientation='h', height=200)
+#         #    c1, c2 = st.columns([1,1])
+#         #    with c1:
+#         #        st.write('**Target Paragraphs**: `{}`'.format(count_target))
+#         #        st.write('**NetZero Related Paragraphs**: `{}`'.format(count_netzero))
+# #
+#  #               # st.plotly_chart(fig,use_container_width= True)
+#   #          
+#             # count_netzero = sum(hits['Netzero Label'] == 'NETZERO')
+#             # count_ghg = sum(hits['GHG Label'] == 'LABEL_2')
+#             # count_economy = sum([True if 'Economy-wide' in x else False 
+#             #                   for x in hits['Sector Label']])
+#      #       with c2:
+#       #          st.write('**GHG Related Paragraphs**: `{}`'.format(count_ghg))
+#        #         st.write('**Economy-wide Related Paragraphs**: `{}`'.format(count_economy))
+#         #    st.write('-------------------')    
+#     #        hits = hits.sort_values(by=['Relevancy'], ascending=False)
+#      #       netzerohit = hits[hits['Netzero Label'] == 'NETZERO']
+#       #      if not netzerohit.empty:
+#        #         netzerohit = netzerohit.sort_values(by = ['Netzero Score'], ascending = False)
+#         #        # st.write('-------------------')
+#                 # st.markdown("###### Netzero paragraph ######")
+#       #          st.write('**Netzero paragraph** `page {}`: {}'.format(netzerohit.iloc[0]['page'],
+#       #                          netzerohit.iloc[0]['text'].replace("\n", " ")))                        
+#        #         st.write("")
+#         #    else:
+#          #       st.info("🤔 No Netzero paragraph found")
+
+#             # st.write("**Result {}** `page {}` (Relevancy Score: {:.2f})'".format(i+1,hits.iloc[i]['page'],hits.iloc[i]['Relevancy'])")
+#            # st.write('-------------------')
+#             st.write("")
+#             st.markdown("###### Top few Policy/Plans Classified paragraph/text results from list of {} classified paragraphs ######".format(count_policy))
+#             st.markdown("""<hr style="height:10px;border:none;color:#097969;background-color:#097969;" /> """, unsafe_allow_html=True)
+#             range_val = min(5,len(hits))
+#             for i in range(range_val):
+#                 # the page number reflects the page that contains the main paragraph 
+#                 # according to split limit, the overlapping part can be on a separate page
+#                 st.write('**Result {}** : `page {}`, `Sector: {}`,\
+#                             `Indicators: {}`, `Adapt-Mitig :{}`'\
+#                     .format(i+1,
+#                             hits.iloc[i]['page'], hits.iloc[i]['Sector Label'],
+#                             hits.iloc[i]['Indicator Label'],hits.iloc[i]['Adapt-Mitig Label']))                        
+#                 st.write("\t Text: \t{}".format(hits.iloc[i]['text'].replace("\n", " ")))
+#             hits = hits.reset_index(drop =True)
+#             st.write('----------------')
+#             st.write('Explore the data')
+#             st.write(hits)
+#             df.drop(columns = ['Policy_check'],inplace=True)
+#             df_xlsx = to_excel(df)
             
-            with st.sidebar:
-                st.write('-------------')
-                st.download_button(label='📥 Download Result',
-                            data=df_xlsx ,
-                            file_name= os.path.splitext(st.session_state['filename'])[0]+'.xlsx')
-
-        else:
-            st.info("🤔 No Policy/Plans found")
+#             with st.sidebar:
+#                 st.write('-------------')
+#                 st.download_button(label='📥 Download Result',
+#                             data=df_xlsx ,
+#                             file_name= os.path.splitext(st.session_state['filename'])[0]+'.xlsx')
+
+#         else:
+#             st.info("🤔 No Policy/Plans found")