Update app.py

app.py

@@ -1,11 +1,10 @@
-
 import streamlit as st
 import pandas as pd
 import joblib
-import numpy as np
 
-model = joblib.load("model/xgb_model.joblib")
-scaler = joblib.load("model/scaler.joblib")
+# Load model and scaler with correct filenames
+model = joblib.load("model/tuned_xgboost_model.pkl")
+scaler = joblib.load("model/scaler.pkl")
 
 st.title("Hemoglobin Level Predictor")
 
@@ -23,25 +22,32 @@ st.markdown(
     unsafe_allow_html=True
 )
 
+# Input fields (ensure the feature names match your trained model's expected features)
 age = st.number_input("Age", min_value=0, max_value=120, value=30)
 gender = st.selectbox("Gender", options=["Male", "Female"])
-o2_saturation = st.slider("O2 Saturation (%)", min_value=50.0, max_value=100.0, value=98.0)
+o2_saturation = st.slider("Oxygen Saturation (%)", min_value=50.0, max_value=100.0, value=98.0)
 bp_systolic = st.number_input("Systolic BP", min_value=50, max_value=200, value=120)
 bp_diastolic = st.number_input("Diastolic BP", min_value=30, max_value=130, value=80)
 respiratory_rate = st.number_input("Respiratory Rate (breaths/min)", min_value=5, max_value=60, value=18)
 
-gender_num = 1 if gender == "Male" else 0
+# Map gender to expected model encoding
+gender_male = 1 if gender == "Male" else 0
+gender_female = 1 - gender_male  # if needed for one-hot features
 
+# Build input dataframe with exact feature names your model expects
 input_df = pd.DataFrame([{
     "Age": age,
-    "Gender": gender_num,
-    "O2_Saturation": o2_saturation,
+    "Gender_Encoded": gender_male,          # or "Gender_Male" if that’s the column name
+    "OxygenSaturation(%)": o2_saturation,   # exact feature name from training
     "BP_Systolic": bp_systolic,
-    "BP_Diastolic": bp_diastolic,
-    "Respiratory_Rate": respiratory_rate
+    "DBP": bp_diastolic,
+    "Respiratory_Rate": respiratory_rate,
+    # Add any other features your model needs here, with correct names!
 }])
 
 if st.button("Predict Hemoglobin Level"):
+    # Scale inputs
     input_scaled = scaler.transform(input_df)
+    # Predict using model
     prediction = model.predict(input_scaled)[0]
     st.success(f"Predicted Hemoglobin Level: {prediction:.2f} g/dL")