ghg check

appStore/ghg.py

@@ -64,32 +64,32 @@ def app():
                 st.session_state.key1 = df
                
 
-def netzero_display():
-  if 'key1' in st.session_state:
-      df = st.session_state.key2
-      hits  = df[df['GHG Label'] == 'TARGET']
-      range_val = min(5,len(hits))
-      if range_val !=0:
-          count_df = df['GHG Label'].value_counts()
-          count_df = count_df.rename('count')
-          count_df = count_df.rename_axis('GHG Label').reset_index()
-          count_df['Label_def'] = count_df['GHG Label'].apply(lambda x: _lab_dict[x])
+# def netzero_display():
+#   if 'key1' in st.session_state:
+#       df = st.session_state.key2
+#       hits  = df[df['GHG Label'] == 'TARGET']
+#       range_val = min(5,len(hits))
+#       if range_val !=0:
+#           count_df = df['GHG Label'].value_counts()
+#           count_df = count_df.rename('count')
+#           count_df = count_df.rename_axis('GHG Label').reset_index()
+#           count_df['Label_def'] = count_df['GHG 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.plotly_chart(fig,use_container_width= True)
+#           fig = px.bar(count_df, y="Label_def", x="count", orientation='h', height =200)
+#           c1, c2 = st.columns([1,1])
+#           with c1:
+#               st.plotly_chart(fig,use_container_width= True)
               
-          hits = hits.sort_values(by=['GHG Score'], ascending=False)
-          st.write("")
-          st.markdown("###### Top few GHG Target Classified paragraph/text results ######")
-          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 {}` (Relevancy Score: {:.2f})'.format(i+1,hits.iloc[i]['page'],hits.iloc[i]['GHG Score']))
-              st.write("\t Text: \t{}".format(hits.iloc[i]['text']))
-      else:
-          st.info("🤔 No GHG target found")
+#           hits = hits.sort_values(by=['GHG Score'], ascending=False)
+#           st.write("")
+#           st.markdown("###### Top few GHG Target Classified paragraph/text results ######")
+#           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 {}` (Relevancy Score: {:.2f})'.format(i+1,hits.iloc[i]['page'],hits.iloc[i]['GHG Score']))
+#               st.write("\t Text: \t{}".format(hits.iloc[i]['text']))
+#       else:
+#           st.info("🤔 No GHG target found")
    
 

appStore/netzero.py

@@ -64,32 +64,32 @@ def app():
                 st.session_state.key1 = df
                
 
-def netzero_display():
-  if 'key1' in st.session_state:
-      df = st.session_state.key2
-      hits  = df[df['Netzero Label'] == 'NETZERO']
-      range_val = min(5,len(hits))
-      if range_val !=0:
-          count_df = df['Netzero Label'].value_counts()
-          count_df = count_df.rename('count')
-          count_df = count_df.rename_axis('Netzero Label').reset_index()
-          count_df['Label_def'] = count_df['Netzero Label'].apply(lambda x: _lab_dict[x])
+# def netzero_display():
+#   if 'key1' in st.session_state:
+#       df = st.session_state.key2
+#       hits  = df[df['Netzero Label'] == 'NETZERO']
+#       range_val = min(5,len(hits))
+#       if range_val !=0:
+#           count_df = df['Netzero Label'].value_counts()
+#           count_df = count_df.rename('count')
+#           count_df = count_df.rename_axis('Netzero Label').reset_index()
+#           count_df['Label_def'] = count_df['Netzero 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.plotly_chart(fig,use_container_width= True)
+#           fig = px.bar(count_df, y="Label_def", x="count", orientation='h', height =200)
+#           c1, c2 = st.columns([1,1])
+#           with c1:
+#               st.plotly_chart(fig,use_container_width= True)
               
-          hits = hits.sort_values(by=['Netzero Score'], ascending=False)
-          st.write("")
-          st.markdown("###### Top few NetZero Target Classified paragraph/text results ######")
-          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 {}` (Relevancy Score: {:.2f})'.format(i+1,hits.iloc[i]['page'],hits.iloc[i]['Netzero Score']))
-              st.write("\t Text: \t{}".format(hits.iloc[i]['text']))
-      else:
-          st.info("🤔 No Netzero target found")
+#           hits = hits.sort_values(by=['Netzero Score'], ascending=False)
+#           st.write("")
+#           st.markdown("###### Top few NetZero Target Classified paragraph/text results ######")
+#           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 {}` (Relevancy Score: {:.2f})'.format(i+1,hits.iloc[i]['page'],hits.iloc[i]['Netzero Score']))
+#               st.write("\t Text: \t{}".format(hits.iloc[i]['text']))
+#       else:
+#           st.info("🤔 No Netzero target found")
    
 

utils/ghg_classifier.py

@@ -76,7 +76,9 @@ def ghg_classification(haystack_doc:pd.DataFrame,
     haystack_doc['GHG Label'] = 'NA'
     haystack_doc['GHG Score'] = 'NA'
     temp = haystack_doc[haystack_doc['Target Label'] == 'TARGET']
+    temp = temp.reset_index(drop=True)
     df = haystack_doc[haystack_doc['Target Label'] == 'NEGATIVE']
+    df = df.reset_index(drop=True)
 
     if not classifier_model:
         classifier_model = st.session_state['ghg_classifier']