Update app.py

app.py

@@ -90,15 +90,22 @@ def process_entity(batch, model, device):
     spaBERT_embedding = spaBERT_embedding[:, 0, :].detach()  # [batch_size, hidden_size]
 
     #return pivot_embeddings.cpu().numpy(), input_ids.cpu().numpy()
-    return spaBERT_embedding, input_ids
+    return spaBERT_embedding, input_ids, pseudo_sentence_decoded
 
 spaBERT_embeddings = []
+pseudo_sentences = []
 for batch in (data_loader):
-    spaBERT_embedding, input_ids = process_entity(batch, spaBERT_model, device)
+    spaBERT_embedding, input_ids, pseudo_sentence = process_entity(batch, spaBERT_model, device)
     spaBERT_embeddings.append(spaBERT_embedding)
+    pseudo_sentences.append(pseudo_sentence)
 
-embedding_cache = {}
+# Print all the pseudo sentences
+print("Pseudo Sentences:")
+for idx, sentence in enumerate(pseudo_sentences):
+    print(f"{idx + 1}: {sentence}")
 
+    
+embedding_cache = {}
 
 #Get BERT Embedding for review
 def get_bert_embedding(review_text):
@@ -257,7 +264,7 @@ selected_key = user_selection.split(" (")[0]  # Remove the label part
 selected_review = example_reviews[selected_key]
 
 # Process the text when the button is clicked
-if st.button("Highlight Geo-Entities"):
+if st.button("Process Review"):
     if selected_review.strip():
         bert_embedding = get_bert_embedding(selected_review)
         spaBert_embedding = processSpatialEntities(selected_review,nlp)
@@ -270,14 +277,7 @@ if st.button("Highlight Geo-Entities"):
             st.write("Concatenated Embedding:", combined_embedding)
 
         prediction = get_prediction(combined_embedding)
-        
-        if(prediction == 0):
-            st.write("Prediction: Not Spam")
-        elif(prediction == 1):
-            st.write("Prediction: Spam")
-        else:
-            st.write("error during prediction")
-            
+                    
         # Process the text using spaCy
         doc = nlp(selected_review)
         
@@ -294,5 +294,14 @@ if st.button("Highlight Geo-Entities"):
 
         # Display the highlighted text with HTML support
         st.markdown(highlighted_text, unsafe_allow_html=True)
+
+        #Display the models prediction
+        if(prediction == 0):
+            st.write("Prediction: Not Spam")
+        elif(prediction == 1):
+            st.write("Prediction: Spam")
+        else:
+            st.write("error during prediction")
+            
     else:
         st.error("Please select a review.")