File size: 2,778 Bytes
8b91654
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
31fe8a6
 
 
 
8b91654
 
3655658
 
 
 
 
 
 
8b91654
 
3655658
8b91654
 
 
 
 
 
3655658
 
 
 
 
31fe8a6
3655658
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
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:
        inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True)
        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)

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:")

    # Concatenate inputs with [SEP]
    combined_text = f"{abstract_input} [SEP] {full_text_input} [SEP] {affiliations_input}"

    if st.button("Predict"):
        predicted_class = predict_class(combined_text)
        if predicted_class is not None:
            class_labels = ["Level 1", "Level 2", "Level 3", "Level 4"]
            st.text(f"Predicted Class: {class_labels[predicted_class]}")

elif option == "PDF":
    uploaded_file = st.file_uploader("Upload a PDF file", type=["pdf"])

    if uploaded_file is not None:
        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"):
            predicted_class = predict_class(file_text)
            if predicted_class is not None:
                class_labels = ["Level 1", "Level 2", "Level 3", "Level 4"]
                st.text(f"Predicted Class: {class_labels[predicted_class]}")