Spaces:
Sleeping
Sleeping
| import streamlit as st | |
| import torch | |
| from transformers import AutoTokenizer, AutoModelForSequenceClassification | |
| import fitz | |
| import os | |
| # Load the model and tokenizer | |
| model = AutoModelForSequenceClassification.from_pretrained("REEM-ALRASHIDI/LongFormer-Paper-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: | |
| # Truncate text to maximum length of 4096 tokens | |
| max_length = 4096 | |
| 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 | |
| # Create a directory to store uploaded files | |
| uploaded_files_dir = "uploaded_files" | |
| os.makedirs(uploaded_files_dir, exist_ok=True) | |
| # Define colors for different classes | |
| class_colors = { | |
| 0: "#1f77b4", # Level 1 | |
| 1: "#ff7f0e", # Level 2 | |
| 2: "#2ca02c", # Level 3 | |
| 3: "#d62728" # Level 4 | |
| } | |
| st.title("Paper Citation Classifier") | |
| option = st.radio("Select input type:", ("Text", "PDF")) | |
| if option == "Text": | |
| # Input text boxes for abstract, full text, and affiliations | |
| abstract_input = st.text_area("Enter Abstract:") | |
| full_text_input = st.text_area("Enter Full Text:") | |
| affiliations_input = st.text_area("Enter Affiliations:") | |
| # Select categories using pills | |
| categories = st.multiselect("Select categories:", ["Category 1", "Category 2", "Category 3", "Category 4"]) | |
| # Combine selected categories with [SEP] | |
| combined_text = f"{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", "Level 2", "Level 3", "Level 4"] | |
| 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"]) | |
| if uploaded_file is not None: | |
| with st.spinner("Processing PDF..."): | |
| file_path = os.path.join(uploaded_files_dir, uploaded_file.name) | |
| with open(file_path, "wb") as f: | |
| f.write(uploaded_file.getbuffer()) | |
| st.success("File uploaded successfully.") | |
| st.text(f"File Path: {file_path}") | |
| file_text = extract_text_from_pdf(file_path) | |
| st.text("Extracted Text:") | |
| st.text(file_text) | |
| # Provide an option to predict from PDF 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) | |