Update app.py

app.py

@@ -7,14 +7,6 @@ import os
 model = AutoModelForSequenceClassification.from_pretrained("Reem333/Citaion-Classifier")
 tokenizer = AutoTokenizer.from_pretrained("allenai/longformer-base-4096")
 
-def extract_text_from_pdf(file_path):
-    text = ''
-    with fitz.open(file_path) as pdf_document:
-        for page_number in range(pdf_document.page_count):
-            page = pdf_document.load_page(page_number)
-            text += page.get_text()
-    return text
-
 def predict_class(text):
     try:
         max_length = 4096
@@ -59,7 +51,7 @@ with st.sidebar:
     st.markdown("- Level 3: More cited papers")
     st.markdown("- Level 4: Low cited papers")
     st.markdown("---")
-    st.markdown('Tabuk University')
+    #st.markdown('Tabuk University')
 
 st.title("Check Your Paper Now!")
 
@@ -73,12 +65,12 @@ if option == "Text":
     keywords_input = st.text_area("Enter Keywords:")
     options=["Nursing", "Physics", "Maths", "Chemical", "Nuclear", "Engineering" ,"Other"]
     
-    selected_category = st.selectbox("Select WoS categories:", options)
+    selected_category = st.selectbox("Select WoS categories:", options, index= None)
     if selected_category == "Other":
         custom_category = st.text_input("Enter custom category:")
         selected_category = custom_category if custom_category else "Other"
 
-    combined_text = f"{title_input} [SEP] {keywords_input} [SEP] {abstract_input} [SEP] {full_text_input} [SEP] {affiliations_input} [SEP] {' [SEP] '.join(selected_category)}"
+    combined_text = f"{title_input} [SEP] {keywords_input} [SEP] {abstract_input} [SEP] {selected_category} [SEP] {affiliations_input} [SEP] {' [SEP] '.join(full_text_input)}"
 
     if st.button("Predict"):
         if not any([title_input, abstract_input,keywords_input, full_text_input, affiliations_input]):
@@ -130,4 +122,4 @@ elif option == "PDF":
                                         unsafe_allow_html=True
                                     )
                                 else:
-                                    st.text(label)
+                                    st.text(label)