Upload ‏‏app.py

‏‏app.py

@@ -0,0 +1,126 @@
+import streamlit as st
+import torch
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import fitz
+import os
+
+# Load Longformer model and tokenizer
+longformer_model = AutoModelForSequenceClassification.from_pretrained("Reem333/Longformer")
+longformer_tokenizer = AutoTokenizer.from_pretrained("allenai/longformer-base-4096")
+
+# Load BERT model and tokenizer
+bert_model = AutoModelForSequenceClassification.from_pretrained("Reem333/BERT")
+bert_tokenizer = AutoTokenizer.from_pretrained("google-bert/bert-base-uncased")
+
+# Function to extract text from PDF
+def extract_text_from_pdf(file_path):
+    text = ''
+    try:
+        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()
+    except Exception as e:
+        st.error(f"Error reading PDF file: {e}")
+    return text
+
+# Function to predict the class of the text using a specified model and tokenizer
+def predict_class(text, model, tokenizer):
+    try:
+        max_length = 4096 if "longformer" in str(model) else 512
+        truncated_text = text[:max_length]
+
+        inputs = tokenizer(truncated_text, return_tensors="pt", padding=True, truncation=True, max_length=max_length)
+        with torch.no_grad():
+            outputs = model(**inputs)
+            logits = outputs.logits
+            predicted_class = torch.argmax(logits, dim=1).item()
+        return predicted_class
+    except Exception as e:
+        st.error(f"Error during prediction: {e}")
+        return None
+
+# Setup for uploaded files directory
+uploaded_files_dir = "uploaded_files"
+os.makedirs(uploaded_files_dir, exist_ok=True)
+
+# Color mapping for class levels
+class_colors = {
+    0: "#d62728",  # Level 1
+    1: "#ff7f0e",  # Level 2
+    2: "#2ca02c",  # Level 3
+    3: "#1f77b4"   # Level 4
+}
+
+# Streamlit page configuration
+st.set_page_config(page_title="Paper Citation Classifier", page_icon="logo.png")
+
+# Sidebar content
+with st.sidebar:
+    st.image("logo.png", width=70)
+    st.markdown('<div style="position: absolute; left: 5px;"></div>', unsafe_allow_html=True)
+    st.markdown("# Paper Citation Classifier")
+    st.markdown("---")
+    st.markdown("## About")
+    st.markdown('''
+    This tool classifies paper citations into different levels based on their number of citations.
+    Powered by Fine-Tuned [Longformer model](https://huggingface.co/REEM-ALRASHIDI/LongFormer-Paper-Citaion-Classifier) and BERT model with custom data.
+    ''')
+    st.markdown("### Class Levels:")
+    st.markdown("- Level 1: Highly cited papers")
+    st.markdown("- Level 2: Average cited papers")
+    st.markdown("- Level 3: More cited papers")
+    st.markdown("- Level 4: Low cited papers")
+    st.markdown("---")
+    st.markdown('Tabuk University')
+
+st.title("Check Your Paper Now!")
+
+# Main content
+option = st.radio("Select input type:", ("Text", "PDF"))
+
+if option == "Text":
+    title_input = st.text_area("Enter Title:")
+    abstract_input = st.text_area("Enter Abstract:")
+    full_text_input = st.text_area("Enter Full Text:")
+    affiliations_input = st.text_area("Enter Affiliations:")
+    keywords_input = st.text_area("Enter Keywords:")
+    options = ['cs', "AI"]
+
+    selected_category = st.selectbox("Select WoS categories:", options)
+    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] {selected_category} [SEP] {affiliations_input} [SEP] {full_text_input}"
+
+    if st.button("Predict"):
+        if not any([title_input, abstract_input, keywords_input, full_text_input, affiliations_input]):
+            st.warning("Please enter paper text.")
+        else:
+            with st.spinner("Predicting..."):
+                longformer_class = predict_class(combined_text, longformer_model, longformer_tokenizer)
+                bert_class = predict_class(combined_text, bert_model, bert_tokenizer)
+                if longformer_class is not None and bert_class is not None:
+                    class_labels = ["Level 1", "Level 2", "Level 3", "Level 4"]
+
+                    st.text("Longformer Predicted Class:")
+                    for i, label in enumerate(class_labels):
+                        if i == longformer_class:
+                            st.markdown(
+                                f'<div style="background-color: {class_colors[longformer_class]}; padding: 10px; border-radius: 5px; color: white; font-weight: bold;">{label}</div>',
+                                unsafe_allow_html=True
+                            )
+                        else:
+                            st.text(label)
+
+                    st.text("BERT Predicted Class:")
+                    for i, label in enumerate(class_labels):
+                        if i == bert_class:
+                            st.markdown(
+                                f'<div style="background-color: {class_colors[bert_class]}; padding: 10px; border-radius: 5px; color: white; font-weight: bold;">{label}</div>',
+                                unsafe_allow_html=True
+                            )
+                        else:
+                            st.text(label)
+