Update app.py

app.py

@@ -1,13 +1,26 @@
 import gradio as gr
 import numpy as np
+import pandas as pd
 import joblib
 
-# Load models, scaler, and label encoder
+# Load trained models and scaler
 model_binary = joblib.load("model_binary_cv.pkl")
 model_multiclass = joblib.load("model_multiclass_cv.pkl")
 scaler = joblib.load("scaler.pkl")
 label_enc = joblib.load("label_encoder_multiclass.pkl")
 
+# Feature names for consistency with scaler
+feature_names = [
+    'Patient Id', 'Age', 'Total cholesterol', 'HDL', 'LDL', 'VLDL',
+    'TRIGLYCERIDES', 'before glycemic control random blood sugar',
+    'before glycemic control HbA1c', 'alcohol consumption', 'family_history_diabetes',
+    'Gender_FEMALE', 'Gender_MALE', 'dietary habits_non-vegetarian',
+    'dietary habits_non-vegetarian ', 'dietary habits_vegetarian',
+    'smoking status_no', 'smoking status_yes',
+    'family_history_cardiovascular_disease_no',
+    'family_history_cardiovascular_disease_yes'
+]
+
 def predict_diabetes(
     Age,
     Total_cholesterol,
@@ -24,95 +37,86 @@ def predict_diabetes(
     smoking_status,
     family_history_cardiovascular_disease
 ):
-    # Convert binary inputs to int
+    # Convert binary inputs
     alcohol_consumption = int(alcohol_consumption)
     family_history_diabetes = int(family_history_diabetes)
 
-    # One-hot encode categorical variables
+    # One-hot encoding
     Gender_FEMALE = 1 if Gender == "Female" else 0
     Gender_MALE = 1 if Gender == "Male" else 0
 
-    dietary_non_vegetarian = 1 if dietary_habits == "Non-vegetarian" else 0
-    dietary_non_vegetarian_dup = dietary_non_vegetarian  # duplicate column in training data
-    dietary_vegetarian = 1 if dietary_habits == "Vegetarian" else 0
+    dietary_non_veg = 1 if dietary_habits == "Non-vegetarian" else 0
+    dietary_non_veg_dup = dietary_non_veg
+    dietary_veg = 1 if dietary_habits == "Vegetarian" else 0
 
     smoking_no = 1 if smoking_status == "No" else 0
     smoking_yes = 1 if smoking_status == "Yes" else 0
 
-    family_history_cvd_no = 1 if family_history_cardiovascular_disease == "No" else 0
-    family_history_cvd_yes = 1 if family_history_cardiovascular_disease == "Yes" else 0
-
-    # Prepare input array (excluding 'binary_status' and matching training order)
-    input_data = np.array([[
-        0,  # dummy Patient ID
-        Age,
-        Total_cholesterol,
-        HDL,
-        LDL,
-        VLDL,
-        TRIGLYCERIDES,
-        before_random_blood_sugar,
-        before_HbA1c,
-        alcohol_consumption,
-        family_history_diabetes,
-        Gender_FEMALE,
-        Gender_MALE,
-        dietary_non_vegetarian,
-        dietary_non_vegetarian_dup,
-        dietary_vegetarian,
-        smoking_no,
-        smoking_yes,
-        family_history_cvd_no,
-        family_history_cvd_yes
-    ]])
-
-    # Scale
-    input_scaled = scaler.transform(input_data)
-
-    # Step 1: Binary classification
+    family_cvd_no = 1 if family_history_cardiovascular_disease == "No" else 0
+    family_cvd_yes = 1 if family_history_cardiovascular_disease == "Yes" else 0
+
+    # Create input DataFrame
+    input_values = [[
+        0, Age, Total_cholesterol, HDL, LDL, VLDL, TRIGLYCERIDES,
+        before_random_blood_sugar, before_HbA1c, alcohol_consumption, family_history_diabetes,
+        Gender_FEMALE, Gender_MALE, dietary_non_veg, dietary_non_veg_dup, dietary_veg,
+        smoking_no, smoking_yes, family_cvd_no, family_cvd_yes
+    ]]
+    input_df = pd.DataFrame(input_values, columns=feature_names)
+
+    # Scale input
+    input_scaled = scaler.transform(input_df)
+
+    # Step 1: Binary prediction
     binary_pred = model_binary.predict(input_scaled)[0]
     if binary_pred == 0:
         return "✅ Prediction: No Diabetes Risk (Normal)"
 
     # Step 2: Multiclass prediction
-    multiclass_pred = model_multiclass.predict(input_scaled)[0]
-    status_label = label_enc.inverse_transform([multiclass_pred])[0]
+    multi_pred = model_multiclass.predict(input_scaled)[0]
+    status = label_enc.inverse_transform([multi_pred])[0]
+
+    status_display = "Prediabetes" if status == "prediabetes" else "Diabetes"
+    emoji = "⚠️🟡" if status == "prediabetes" else "🚨🔴"
 
-    return f"⚠️ At Risk: {status_label.capitalize()}"
+    return f"{emoji} At Risk: {status_display}"
 
-# Gradio interface
+# Gradio UI
 with gr.Blocks() as demo:
-    gr.Markdown("# 🩺 Diabetes Risk and Type Predictor")
+    gr.Markdown("## 🩺 Diabetes Risk and Type Predictor")
     gr.Markdown(
         """
-        Developed by Dr. Vinod Kumar Yata's research group  
+        **Developed by Dr. Vinod Kumar Yata's research group**  
         School of Allied and Healthcare Sciences, Malla Reddy University, Hyderabad, India  
-        ⚠️ **Note:** This tool predicts both diabetes **risk** and **type** (diabetes vs prediabetes).  
-        This is a research prototype. Do not use it for medical diagnosis.
+
+        ---
+        ⚠️ This AI tool is for **research purposes only**.  
+        It predicts **diabetes risk** and if at risk, whether it's **prediabetes or diabetes**.  
+        Please consult a medical professional for any diagnosis.
         """
     )
 
     with gr.Row():
         with gr.Column():
             Age = gr.Number(label="Age", value=30)
-            Total_cholesterol = gr.Number(label="Total cholesterol", value=180)
+            Total_cholesterol = gr.Number(label="Total Cholesterol", value=180)
             HDL = gr.Number(label="HDL", value=50)
             LDL = gr.Number(label="LDL", value=100)
             VLDL = gr.Number(label="VLDL", value=20)
             TRIGLYCERIDES = gr.Number(label="TRIGLYCERIDES", value=150)
-            before_random_blood_sugar = gr.Number(label="Before glycemic control random blood sugar", value=120)
-            before_HbA1c = gr.Number(label="Before glycemic control HbA1c", value=5.5)
+            before_random_blood_sugar = gr.Number(label="Random Blood Sugar (before control)", value=120)
+            before_HbA1c = gr.Number(label="HbA1c (before control)", value=5.5)
 
         with gr.Column():
-            alcohol_consumption = gr.Radio(label="Alcohol consumption", choices=["0", "1"], value="0")
-            family_history_diabetes = gr.Radio(label="Family history of diabetes", choices=["0", "1"], value="0")
+            alcohol_consumption = gr.Radio(label="Alcohol Consumption", choices=["0", "1"], value="0")
+            family_history_diabetes = gr.Radio(label="Family History of Diabetes", choices=["0", "1"], value="0")
             Gender = gr.Radio(label="Gender", choices=["Female", "Male"], value="Female")
-            dietary_habits = gr.Radio(label="Dietary habits", choices=["Vegetarian", "Non-vegetarian"], value="Vegetarian")
-            smoking_status = gr.Radio(label="Smoking status", choices=["No", "Yes"], value="No")
-            family_history_cardiovascular_disease = gr.Radio(label="Family history of cardiovascular disease", choices=["No", "Yes"], value="No")
+            dietary_habits = gr.Radio(label="Dietary Habits", choices=["Vegetarian", "Non-vegetarian"], value="Vegetarian")
+            smoking_status = gr.Radio(label="Smoking Status", choices=["No", "Yes"], value="No")
+            family_history_cardiovascular_disease = gr.Radio(label="Family History of Cardiovascular Disease", choices=["No", "Yes"], value="No")
 
-    output = gr.Textbox(label="Prediction")
-    submit_btn = gr.Button("Submit")
+    submit_btn = gr.Button("🧪 Predict")
+    output = gr.Textbox(label="Prediction Result")
 
     submit_btn.click(
         fn=predict_diabetes,