Update utils/group_classifier.py

utils/group_classifier.py

@@ -19,7 +19,7 @@ _lab_dict = {
     6: 'Women'}
 
 @st.cache_resource
-def load_targetClassifier(config_file:str = None, classifier_name:str = None):
+def load_groupClassifier(config_file:str = None, classifier_name:str = None):
     """
     loads the document classifier using haystack, where the name/path of model
     in HF-hub as string is used to fetch the model object.Either configfile or 
@@ -51,7 +51,7 @@ def load_targetClassifier(config_file:str = None, classifier_name:str = None):
 
 
 @st.cache_data
-def target_classification(haystack_doc:pd.DataFrame,
+def group_classification(haystack_doc:pd.DataFrame,
                         threshold:float = 0.5, 
                         classifier_model:pipeline= None
                         )->Tuple[DataFrame,Series]:
@@ -74,20 +74,20 @@ def target_classification(haystack_doc:pd.DataFrame,
     x: Series object with the unique SDG covered in the document uploaded and 
     the number of times it is covered/discussed/count_of_paragraphs. 
     """
-    logging.info("Working on Target Extraction")
+    logging.info("Working on Group Extraction")
     if not classifier_model:
-        classifier_model = st.session_state['target_classifier']
+        classifier_model = st.session_state['group_classifier']
     
     results = classifier_model(list(haystack_doc.text))
     labels_= [(l[0]['label'],
                l[0]['score']) for l in results]
            
 
-    df1 = DataFrame(labels_, columns=["Target Label","Relevancy"])
+    df1 = DataFrame(labels_, columns=["Group Label","Relevancy"])
     df = pd.concat([haystack_doc,df1],axis=1)
     
     df = df.sort_values(by="Relevancy", ascending=False).reset_index(drop=True)  
     df.index += 1
-    df['Label_def'] = df['Target Label'].apply(lambda i: _lab_dict[i])
+    df['Label_def'] = df['Group Label'].apply(lambda i: _lab_dict[i])
 
     return df