Update app.py

app.py

@@ -7,12 +7,38 @@ col1, col2= st.columns(2)
 
 with col1:
     st.title("Spamd: Turkish Spam Detector")
-    st.markdown("Message spam detection tool for Turkish language. Due the small size of the dataset, I decided to go with transformers technology Google BERT. Using the Turkish pre-trained model BERTurk, I imporved the accuracy of the tool by 18 percent compared to the previous model which used fastText.")
+    st.markdown("Message spam detection tool for Turkish language. Due the small size of the dataset, I decided to go with transformers         technology Google BERT. Using the Turkish pre-trained model BERTurk, I imporved the accuracy of the tool by 18 percent compared to the previous model which used fastText.")
 
 
+def predict(new_sentence):
+    # We need Token IDs and Attention Mask for inference on the new sentence
+    test_ids = []
+    test_attention_mask = []
 
+    # Apply the tokenizer
+    encoding = preprocessing(new_sentence, tokenizer)
 
+    # Extract IDs and Attention Mask
+    test_ids.append(encoding['input_ids'])
+    test_attention_mask.append(encoding['attention_mask'])
+    test_ids = torch.cat(test_ids, dim = 0)
+    test_attention_mask = torch.cat(test_attention_mask, dim = 0)
 
+    # Forward pass, calculate logit predictions
+    with torch.no_grad():
+      output = model(test_ids.to(device), token_type_ids = None, attention_mask = test_attention_mask.to(device))
+
+    prediction = 'Spam' if np.argmax(output.logits.cpu().numpy()).flatten().item() == 1 else 'Normal'
+    pred = 'Predicted Class: '+ prediction
+    with col2:
+        st.header(pred)
+
+with col2:
+    text = st.text_input("Enter the text you'd like to analyze for spam.")
+    if text or st.button('Analyze'):
+        predict(text)
+
+ 
 
 
 import torch
@@ -47,34 +73,8 @@ device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
 def namestr(obj, namespace):
     return [name for name in namespace if namespace[name] is obj]
 
-def predict(new_sentence):
-    # We need Token IDs and Attention Mask for inference on the new sentence
-    test_ids = []
-    test_attention_mask = []
-
-    # Apply the tokenizer
-    encoding = preprocessing(new_sentence, tokenizer)
 
-    # Extract IDs and Attention Mask
-    test_ids.append(encoding['input_ids'])
-    test_attention_mask.append(encoding['attention_mask'])
-    test_ids = torch.cat(test_ids, dim = 0)
-    test_attention_mask = torch.cat(test_attention_mask, dim = 0)
-
-    # Forward pass, calculate logit predictions
-    with torch.no_grad():
-      output = model(test_ids.to(device), token_type_ids = None, attention_mask = test_attention_mask.to(device))
-
-    prediction = 'Spam' if np.argmax(output.logits.cpu().numpy()).flatten().item() == 1 else 'Normal'
-    pred = 'Predicted Class: '+ prediction
-    with col2:
-        st.header(pred)
     
     #st.write('Input', namestr(new_sentence, globals()),': \n', new_sentence) 
    
-with col2:
-    text = st.text_input("Enter the text you'd like to analyze for spam.")
-    if text:
-        predict(text)
-    if st.button('Analyze'):
-        predict(text)
+