add adaptation mitigation

appStore/target.py

@@ -257,7 +257,7 @@ def filter_dataframe(df: pd.DataFrame) -> pd.DataFrame:
                     df = df[df[column].str.contains(user_text_input)]
         df['keep'] = True
         df = df[['keep','text','Target Score','Netzero Label','GHG Label',
-            'Conditional Label','Sector Label']]
+            'Conditional Label','Sector Label','Adapt-Mitig Label','page']]
         df = st.data_editor(
                   df,
                   column_config={

utils/adapmit_classifier.py

@@ -63,11 +63,20 @@ def adapmit_classification(haystack_doc:pd.DataFrame,
     """
     logging.info("Working on Adaptation-Mitigation Identification")
     haystack_doc['Adapt-Mitig Label'] = 'NA'
+    haystack_doc['cond_check'] = haystack_doc.apply(lambda x: True if (
+                (x['Target Label'] == 'TARGET') | (x['Action Label'] == 'Action') |
+                (x['Policies_Plans Label'] == 'Policies and Plans')) else
+                False, axis=1)
+    # we apply Netzero to only paragraphs which are classified as 'Target' related
+    df1 = haystack_doc[haystack_doc['cond_check'] == True]
+    df1 = temp.reset_index(drop=True)
+    df = haystack_doc[haystack_doc['cond_check'] == False]
+    df = df.reset_index(drop=True)
 
     if not classifier_model:
         classifier_model = st.session_state['adapmit_classifier']
     
-    predictions = classifier_model(list(haystack_doc.text))
+    predictions = classifier_model(list(df1.text))
      # converting the predictions to desired format
     list_ = []
     for i in range(len(predictions)):
@@ -92,6 +101,10 @@ def adapmit_classification(haystack_doc:pd.DataFrame,
     truth_df['Adapt-Mitig Label'] = truth_df.apply(lambda x: 
                                   list(x['Adapt-Mitig Label'] -{None}),axis=1)
     # adding Adaptation-Mitigation label                              
-    haystack_doc['Adapt-Mitig Label'] = list(truth_df['Adapt-Mitig Label'])
+    df1['Adapt-Mitig Label'] = list(truth_df['Adapt-Mitig Label'])
+    df = pd.concat([df,df1])
+    df = df.drop(columns = ['cond_check'])
+    df = df.reset_index(drop =True)
+    df.index += 1
 
     return haystack_doc