app.py

import streamlit as st
import pickle
import sklearn
from sklearn.preprocessing import RobustScaler, OneHotEncoder, OrdinalEncoder
from sklearn.neighbors import KNeighborsClassifier
import pandas as pd
import numpy as np




# st.markdown("""
#     <style>
#         .stApp {
#             background-image: url('https://tse3.mm.bing.net/th?id=OIP.AmAPg7MnWqITuUdPgrRaUQHaFP&pid=Api&P=0&h=180');
#             background-size: contain;
#             background-repeat: no-repeat;
#             background-position : center;
#         }
#         .stTitle {
#             color: #ffffff;
#             font-size: 36px;
#             font-weight: bold;
#             text-align: center;
#         }
#     </style>
# """, unsafe_allow_html=True)

st.title("Diabetes Prediction App")



st.header("Patient Information")
gender = st.number_input("Enter Gender:(0 = F, 1 = M)",min_value=0,max_value=1,)
age =  st.number_input("Enter Age:",min_value=20,max_value=80,step=1)
urea =  st.number_input("Enter Urea Level:",min_value=2.3,max_value=10.00,step=0.02)
cr = st.number_input("Enter Creatinine Level:",min_value=33.00,max_value=112.50,step=0.02)
HbA1c =  st.number_input("Enter HbA1c(Glycated hemoglobin) Level:",min_value=0.90,max_value=16.00,step=0.01)
chol =  st.number_input("Enter the Cholestrol Level:",min_value=0.00,max_value=10.30,step=0.01)
tg =  st.number_input("Enter TG(Triglycerides) Level:",min_value=0.80,max_value=5.10,step=0.01)
hdl =  st.number_input("Enter HDL Level:",min_value=0.70,max_value=1.90,step=0.01)
ldl =  st.number_input("Enter LDL Level:",min_value=0.75,max_value=5.60,step=0.01)
vldl =  st.number_input("Enter VLDL Level:",min_value=0.33,max_value=1.95,step=0.01)
bmi =  st.number_input("Enter BMI:",min_value=19.00,max_value=47.75,step=0.01)





with open("knn_model.pkl", "rb") as f:
    model = pickle.load(f)

with open("scaler.pkl", "rb") as f:
    scaler = pickle.load(f)

with open("features.pkl", "rb") as f:
    feature_names = pickle.load(f)

with open("accuracy.pkl", "rb") as f:
    accuracy = pickle.load(f)

if st.button("Predict Diabetes Class"):
    input_data = np.array([[gender, age, urea, cr, HbA1c, chol, tg, hdl, ldl, vldl, bmi]])
    input_scaled = scaler.transform(input_data)

    prediction = model.predict(input_scaled)[0]
    probabilities = model.predict_proba(input_scaled)[0]
    class_labels = model.classes_

    label_map = {"N": "Non-diabetes", "P": "Pre-diabetes", "Y": "Diabetes"}
    readable_prediction = label_map.get(prediction, prediction)

    st.success(f"Predicted Diabetes Class: **{readable_prediction}**")

    st.markdown("##### Prediction Confidence:")
    for label, prob in zip(class_labels, probabilities):
        st.write(f"- **{label_map.get(label, label)}**: {prob * 100:.2f}%")

    # Message based on result
    if readable_prediction == "Pre-Diabete":
        st.warning("You are in the pre-diabetic range. It's advisable to consult a healthcare professional for further evaluation.")
    elif readable_prediction == "Diabete":
        st.error("You are classified as diabetic. Please seek medical advice for appropriate management.")