File size: 3,965 Bytes
0974b80 0c98cfe bce1f5b 0974b80 791c8de 0974b80 0c98cfe 0974b80 46210e1 364d7af 8a61041 8441d3c c4db698 272a9aa 0974b80 46210e1 6491141 46210e1 6491141 46210e1 bce1f5b 0974b80 c8e8d6b e2a08b5 7fca223 90da2fd 46210e1 90da2fd 0974b80 90da2fd 0c98cfe 90da2fd 0974b80 0c98cfe 0974b80 2dc6bf4 0974b80 46210e1 7107507 46210e1 2dc6bf4 46210e1 2dc6bf4 46210e1 2dc6bf4 46210e1 2dc6bf4 46210e1 2dc6bf4 46210e1 2dc6bf4 46210e1 2dc6bf4 0974b80 2dc6bf4 |
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 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 |
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"]
with open("embeddings_2.pkl", "rb") as fIn:
stored_data_cpt = pickle.load(fIn)
stored_embeddings_cpt = stored_data_cpt["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 True
else:
return False
# Define the function for mapping code
def mapping_code(user_input, mode):
if mode == "CPT_to_SBS":
stored_embeddings_cpt = stored_embeddings
stored_data_cpt = stored_data_cpt
code_column = stored_data["CPT_CODE"]
description_column = stored_data["FULL_DESCRIPTION"]
elif mode == "SBS_to_CPT":
stored_embeddings = stored_embeddings
stored_data = stored_data_sbs
code_column = stored_data["SBS_code"]
description_column = stored_data["Description"]
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(code_column, description_column, 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-SBS Code Mapping")
# Dropdown for user to choose mapping direction
mapping_mode = st.selectbox("Choose mapping direction:", ("CPT description to SBS code", "SBS description to CPT code"))
if mapping_mode == "CPT description to SBS code":
user_input_label = "Enter CPT description:"
mode = "CPT_to_SBS"
else:
user_input_label = "Enter SBS description:"
mode = "SBS_to_CPT"
# Input text box for user input
user_input = st.text_input(user_input_label, placeholder="Enter description here...")
# 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.")
else:
st.write("Please wait for a moment ...")
# Call backend function to get mapping results
try:
mapping_results = mapping_code(user_input, mode)
# Display top 5 similar sentences
st.write("Top 5 similar entries:")
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()
|