Update app.py

app.py

@@ -18,7 +18,6 @@ def extract_text_from_pdf(file_path):
 
 def predict_class(text):
     try:
-
         max_length = 4096
         truncated_text = text[:max_length]
 
@@ -32,11 +31,9 @@ def predict_class(text):
         st.error(f"Error during prediction: {e}")
         return None
 
-
 uploaded_files_dir = "uploaded_files"
 os.makedirs(uploaded_files_dir, exist_ok=True)
 
-
 class_colors = {
     0: "#d62728",  # Level 1
     1: "#ff7f0e",  # Level 2
@@ -50,8 +47,6 @@ st.image("logo2.png", width=70)
 
 st.markdown('<div style="position: absolute; top: 5px; left: 5px;"></div>', unsafe_allow_html=True)
 
-# col1, col2 = st.columns([1, 3])
-
 st.title("Paper Citation Classifier")
 
 option = st.radio("Select input type:", ("Text", "PDF"))
@@ -65,25 +60,26 @@ if option == "Text":
     
     categories = pills("Select WoS category", options)
     
-    # categories = st.multiselect("Select WoS categories:", options)
-
     combined_text = f"{title_input} [SEP] {abstract_input} [SEP] {full_text_input} [SEP] {affiliations_input} [SEP] {' [SEP] '.join(categories)}"
 
     if st.button("Predict"):
-        with st.spinner("Predicting..."):
-            predicted_class = predict_class(combined_text)
-            if predicted_class is not None:
-                class_labels = ["Level 1 (Highly Cited Paper)", "Level 2 (Average Cited Paper)", "Level 3 (More Cited Paper)", "Level 4 (Low Cited Paper)"]
-
-                st.text("Predicted Class:")
-                for i, label in enumerate(class_labels):
-                    if i == predicted_class:
-                        st.markdown(
-                            f'<div style="background-color: {class_colors[predicted_class]}; padding: 10px; border-radius: 5px; color: white; font-weight: bold;">{label}</div>',
-                            unsafe_allow_html=True
-                        )
-                    else:
-                        st.text(label)
+        if not combined_text.strip():  # Check if combined_text is empty or contains only whitespace
+            st.warning("Please enter paper text.")
+        else:
+            with st.spinner("Predicting..."):
+                predicted_class = predict_class(combined_text)
+                if predicted_class is not None:
+                    class_labels = ["Level 1 (Highly Cited Paper)", "Level 2 (Average Cited Paper)", "Level 3 (More Cited Paper)", "Level 4 (Low Cited Paper)"]
+
+                    st.text("Predicted Class:")
+                    for i, label in enumerate(class_labels):
+                        if i == predicted_class:
+                            st.markdown(
+                                f'<div style="background-color: {class_colors[predicted_class]}; padding: 10px; border-radius: 5px; color: white; font-weight: bold;">{label}</div>',
+                                unsafe_allow_html=True
+                            )
+                        else:
+                            st.text(label)
 
 elif option == "PDF":
     uploaded_file = st.file_uploader("Upload a PDF file", type=["pdf"])
@@ -101,20 +97,19 @@ elif option == "PDF":
             st.text(file_text)
 
             if st.button("Predict from PDF Text"):
-                with st.spinner("Predicting..."):
-                    predicted_class = predict_class(file_text)
-                    if predicted_class is not None:
-                        class_labels = ["Level 1 (Highly Cited Paper)", "Level 2 (Average Cited Paper)", "Level 3 (More Cited Paper)", "Level 4 (Low Cited Paper)"]
-                        st.text("Predicted Class:")
-                        for i, label in enumerate(class_labels):
-                            if i == predicted_class:
-                                st.markdown(
-                                    f'<div style="background-color: {class_colors[predicted_class]}; padding: 10px; border-radius: 5px; color: white; font-weight: bold;">{label}</div>',
-                                    unsafe_allow_html=True
-                                )
-                            else:
-                                st.text(label)
-
-
-
-                                
+                if not file_text.strip():  # Check if file_text is empty or contains only whitespace
+                    st.warning("Please upload a PDF file with text content.")
+                else:
+                    with st.spinner("Predicting..."):
+                        predicted_class = predict_class(file_text)
+                        if predicted_class is not None:
+                            class_labels = ["Level 1 (Highly Cited Paper)", "Level 2 (Average Cited Paper)", "Level 3 (More Cited Paper)", "Level 4 (Low Cited Paper)"]
+                            st.text("Predicted Class:")
+                            for i, label in enumerate(class_labels):
+                                if i == predicted_class:
+                                    st.markdown(
+                                        f'<div style="background-color: {class_colors[predicted_class]}; padding: 10px; border-radius: 5px; color: white; font-weight: bold;">{label}</div>',
+                                        unsafe_allow_html=True
+                                    )
+                                else:
+                                    st.text(label)