Spaces:
Runtime error
Runtime error
| import streamlit as st | |
| import torch | |
| from sentence_transformers import SentenceTransformer, util | |
| from spellchecker import SpellChecker | |
| import pickle | |
| # 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"] | |
| spell = SpellChecker() | |
| # Define a function to check for misspelled words | |
| def check_misspelled_words(user_input): | |
| # Tokenize the input into words | |
| words = user_input.split() | |
| # Get a list of misspelled words excluding words containing only numbers | |
| misspelled = [word for word in words if word.isalpha() and not word.isdigit() and not spell.correction(word.lower()) == word.lower()] | |
| return misspelled | |
| # Define the function for mapping code | |
| # Define the function for mapping code | |
| def mapping_code(user_input): | |
| if len(user_input.split()) < 5: # Check if sentence has less than 5 words | |
| raise ValueError("Input sentence should be at least 5 words long.") | |
| 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) if sim > 0.70] | |
| # 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 | |
| def main(): | |
| st.title("CPT Description Mapping") | |
| st.markdown("**Note:** Similarity scores are not absolute and should be further confirmed manually for accuracy.") | |
| # Input text box for user input | |
| user_input = st.text_input("Enter CPT description:", placeholder="Please enter a full description for better search 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.") | |
| else: | |
| st.write("Please wait for a moment .... ") | |
| # Call backend function to get mapping results | |
| try: | |
| misspelled_words = check_misspelled_words(user_input) | |
| if misspelled_words: | |
| st.write("Please enter a detailed correct full description") | |
| st.write(f"Kindly check if these words are spelt correctly :{misspelled_words}") | |
| else: | |
| mapping_results = mapping_code(user_input) | |
| # 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: {result['Similarity Score']:.4f}") | |
| except ValueError as e: | |
| st.error(str(e)) | |
| if __name__ == "__main__": | |
| main() | |