app.py

import streamlit as st
import torch
from sentence_transformers import SentenceTransformer, util
#from spellchecker import SpellChecker
import pickle
import re

# Load the pre-trained SentenceTransformer model
model = SentenceTransformer('neuml/pubmedbert-base-embeddings')

# Load stored data
with open("embeddings_1.pkl", "rb") as fIn:
    stored_data = pickle.load(fIn)
    stored_embeddings = stored_data["embeddings"]

def validate_input(input_string):
    # Regular expression pattern to match letters and numbers, or letters only
    pattern = r'^[a-zA-Z0-9]+$|^[a-zA-Z]+$'
    
    # Check if input contains at least one non-numeric character
    if re.match(pattern, input_string) or input_string.isdigit():
        return False
    else:
        return True

# Define the function for mapping code
def mapping_code(user_input):

    emb1 = model.encode(user_input.lower())
    similarities = []
    for sentence in stored_embeddings:
        similarity = util.cos_sim(sentence, emb1)
        similarities.append(similarity)

    # Filter results with similarity scores above 0.70
    result = [(code, desc, sim) for (code, desc, sim) in zip(stored_data["SBS_code"], stored_data["Description"], similarities)]

    # Sort results by similarity scores
    result.sort(key=lambda x: x[2], reverse=True)

    num_results = min(5, len(result))

    # Return top 5 entries with 'code', 'description', and 'similarity_score'
    top_5_results = []
    if num_results > 0:
        for i in range(num_results):
            code, description, similarity_score = result[i]
            top_5_results.append({"Code": code, "Description": description, "Similarity Score": similarity_score})
    else:
        top_5_results.append({"Code": "", "Description": "No match", "Similarity Score": 0.0})

    return top_5_results

# Streamlit frontend interface
import streamlit as st

def main():
    st.title("CPT Description Mapping")
    st.markdown("<font color='blue'>**💡 Please enter the input CPT description with specific available  details for best results.**</font>", unsafe_allow_html=True)

    st.markdown("<font color='blue'>**💡 Note:** Please note that the similarity scores of each code are the calculated based on language module matching and the top 5 codes descriptions results should be verified with CPT description by the user.</font>", unsafe_allow_html=True)

    # user_slider_input_number = st.sidebar.slider('Select similarity threshold', 0.0, 1.0, 0.7, 0.01, key='slider1', help='Adjust the similarity threshold')

    # Input text box for user input
    user_input = st.text_input("Enter CPT description:", placeholder="Please enter the input CPT description with specific available  details for best results.")

    # Button to trigger mapping
    if st.button("Map"):
        if not user_input.strip():  # Check if input is empty or contains only whitespace
            st.error("Input box cannot be empty.")
        elif validate_input(user_input):
            st.warning("Please input correct description containing only letters and numbers, or letters only.")
        else:
            st.write("Please wait for a moment .... ")
            # Call backend function to get mapping results
            try:
                mapping_results = mapping_code(user_input)  # user_slider_input_number
                # Display top 5 similar sentences
                st.write("Top 5 similar sentences:")
                for i, result in enumerate(mapping_results, 1):
                    st.write(f"{i}. Code: {result['Code']}, Description: {result['Description']}, Similarity Score: {float(result['Similarity Score']):.4f}")
            except ValueError as e:
                st.error(str(e))

if __name__ == "__main__":
    main()