Update app.py

app.py

@@ -2,13 +2,11 @@ import gradio as gr
 import numpy as np
 import joblib
 
-# Load models and encoder
+# Load models, scaler, and label encoder
 model_binary = joblib.load("model_binary_cv.pkl")
 model_multiclass = joblib.load("model_multiclass_cv.pkl")
-label_enc = joblib.load("label_encoder_multiclass.pkl")
-
-# Define scaler
 scaler = joblib.load("scaler.pkl")
+label_enc = joblib.load("label_encoder_multiclass.pkl")
 
 def predict_diabetes(
     Age,
@@ -26,15 +24,16 @@ def predict_diabetes(
     smoking_status,
     family_history_cardiovascular_disease
 ):
-    # Convert inputs
+    # Convert binary inputs to int
     alcohol_consumption = int(alcohol_consumption)
     family_history_diabetes = int(family_history_diabetes)
 
+    # One-hot encode categorical variables
     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 = 1 if dietary_habits == "Non-vegetarian" else 0  # duplicate column
+    dietary_non_vegetarian_dup = dietary_non_vegetarian  # duplicate column in training data
     dietary_vegetarian = 1 if dietary_habits == "Vegetarian" else 0
 
     smoking_no = 1 if smoking_status == "No" else 0
@@ -43,12 +42,9 @@ def predict_diabetes(
     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
 
-    patient_id = 0  # Dummy
-    # No binary_status in input — it's what we're predicting
-
-    # Construct input feature array for binary model (drop target fields)
+    # Prepare input array (excluding 'binary_status' and matching training order)
     input_data = np.array([[
-        patient_id,
+        0,  # dummy Patient ID
         Age,
         Total_cholesterol,
         HDL,
@@ -70,29 +66,29 @@ def predict_diabetes(
         family_history_cvd_yes
     ]])
 
+    # Scale
     input_scaled = scaler.transform(input_data)
 
-    # Step 1: Binary prediction
-    risk_pred = model_binary.predict(input_scaled)[0]
-    if risk_pred == 0:
+    # Step 1: Binary classification
+    binary_pred = model_binary.predict(input_scaled)[0]
+    if binary_pred == 0:
         return "✅ Prediction: No Diabetes Risk (Normal)"
 
-    # Step 2: Multiclass prediction (only if at risk)
-    status_pred_enc = model_multiclass.predict(input_scaled)[0]
-    status_pred = label_enc.inverse_transform([status_pred_enc])[0]
+    # Step 2: Multiclass prediction
+    multiclass_pred = model_multiclass.predict(input_scaled)[0]
+    status_label = label_enc.inverse_transform([multiclass_pred])[0]
 
-    return f"⚠️ At Risk: {status_pred}"
+    return f"⚠️ At Risk: {status_label.capitalize()}"
 
-# Gradio Interface
+# Gradio interface
 with gr.Blocks() as demo:
     gr.Markdown("# 🩺 Diabetes Risk and Type Predictor")
     gr.Markdown(
         """
         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.  
-        Not a substitute for medical advice.
+        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.
         """
     )
 
@@ -115,16 +111,17 @@ with gr.Blocks() as demo:
             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")
 
-    submit_btn = gr.Button("Submit")
     output = gr.Textbox(label="Prediction")
+    submit_btn = gr.Button("Submit")
 
     submit_btn.click(
         fn=predict_diabetes,
         inputs=[
             Age, Total_cholesterol, HDL, LDL, VLDL, TRIGLYCERIDES,
             before_random_blood_sugar, before_HbA1c,
-            alcohol_consumption, family_history_diabetes, Gender,
-            dietary_habits, smoking_status, family_history_cardiovascular_disease
+            alcohol_consumption, family_history_diabetes,
+            Gender, dietary_habits, smoking_status,
+            family_history_cardiovascular_disease
         ],
         outputs=output
     )