Update app.py

app.py

@@ -114,533 +114,4 @@ with gr.Blocks() as demo:
         outputs=[status_output, prob_output, model_output]
     )
 
-demo.launch()import numpy as np
-import gradio as gr
-import joblib
-from tensorflow.keras.models import load_model
-
-# ============================================================
-# LOAD MODELS & SCALERS
-# ============================================================
-
-knn_model = joblib.load("knn_model.pkl")
-svm_model = joblib.load("rbf_svm_model.pkl")
-ann_model = load_model("ann_model.keras")
-
-scaler_rfe = joblib.load("scaler_rfe.pkl")
-selected_features = joblib.load("selected_features.pkl")
-
-print("Selected features used by the interface:")
-print(selected_features)
-
-
-# ============================================================
-# 1. ENCODING MAPS
-# Must be EXACTLY the same as training
-# ============================================================
-
-# IMPORTANT:
-# Training used Female = 0, Male = 1
-gender_map = {
-    "Female": 0,
-    "Male": 1
-}
-
-binary_map = {
-    "No": 0,
-    "Yes": 1
-}
-
-ordinal_map = {
-    "Low": 0,
-    "Medium": 1,
-    "High": 2
-}
-
-# Alcohol:
-# None is meaningful = no alcohol consumption
-alcohol_map = {
-    "None": 0,
-    "Low": 1,
-    "Medium": 2,
-    "High": 3
-}
-
-
-binary_features = {
-    'smoking',
-    'family_hd',
-    'diabetes',
-    'high_bp',
-    'low_hdl',
-    'high_ldl'
-}
-
-ordinal_features = {
-    'exercise',
-    'stress',
-    'sugar'
-}
-
-
-# ============================================================
-# 2. ENCODE USER INPUT
-# ============================================================
-
-def encode_input_value(feature, value):
-
-    if feature == 'gender':
-        return gender_map[value]
-
-    if feature in binary_features:
-        return binary_map[value]
-
-    if feature == 'alcohol':
-        return alcohol_map[value]
-
-    if feature in ordinal_features:
-        return ordinal_map[value]
-
-    # Numeric feature
-    return float(value)
-
-
-# ============================================================
-# 3. PREDICTION FUNCTION
-# ============================================================
-
-def predict_heart_disease(model_choice, *feature_values):
-
-    # Check input count
-    if len(feature_values) != len(selected_features):
-        return (
-            "Input Error",
-            "Input Error",
-            model_choice
-        )
-
-    # ---------------------------------------------
-    # Encode input using exact selected feature order
-    # ---------------------------------------------
-
-    encoded_inputs = []
-
-    for feature, value in zip(
-        selected_features,
-        feature_values
-    ):
-
-        encoded_value = encode_input_value(
-            feature,
-            value
-        )
-
-        encoded_inputs.append(
-            encoded_value
-        )
-
-
-    # ---------------------------------------------
-    # Convert into 2D array
-    # ---------------------------------------------
-
-    X_input = np.array(
-        [encoded_inputs],
-        dtype=float
-    )
-
-
-    # ---------------------------------------------
-    # IMPORTANT:
-    # Use SAME scaler used during model training
-    # ---------------------------------------------
-
-    X_scaled = scaler_rfe.transform(
-        X_input
-    )
-
-
-    # ---------------------------------------------
-    # DEBUG
-    # You can see whether UI inputs are really changing
-    # ---------------------------------------------
-
-    print("\n==============================")
-    print("Model:", model_choice)
-
-    print("\nSelected features:")
-    print(selected_features)
-
-    print("\nRaw UI values:")
-    print(feature_values)
-
-    print("\nEncoded values:")
-    print(encoded_inputs)
-
-    print("\nScaled values:")
-    print(X_scaled)
-
-    print("==============================")
-
-
-    # ========================================================
-    # KNN
-    # ========================================================
-
-    if model_choice == "KNN":
-
-        y_pred = knn_model.predict(
-            X_scaled
-        )[0]
-
-        y_prob = knn_model.predict_proba(
-            X_scaled
-        )[0][1]
-
-
-    # ========================================================
-    # SVM
-    # ========================================================
-
-    elif model_choice == "SVM":
-
-        y_pred = svm_model.predict(
-            X_scaled
-        )[0]
-
-        if hasattr(
-            svm_model,
-            "predict_proba"
-        ):
-
-            y_prob = svm_model.predict_proba(
-                X_scaled
-            )[0][1]
-
-        else:
-
-            score = svm_model.decision_function(
-                X_scaled
-            )[0]
-
-            # Convert decision score to approximate probability
-            y_prob = 1 / (
-                1 + np.exp(-score)
-            )
-
-
-    # ========================================================
-    # ANN
-    # ========================================================
-
-    elif model_choice == "ANN":
-
-        y_prob = float(
-            ann_model.predict(
-                X_scaled,
-                verbose=0
-            )[0][0]
-        )
-
-        y_pred = int(
-            y_prob >= 0.5
-        )
-
-
-    else:
-
-        return (
-            "Invalid model choice",
-            "Invalid model choice",
-            "Invalid model choice"
-        )
-
-
-    # ---------------------------------------------
-    # Debug prediction
-    # ---------------------------------------------
-
-    print("\nPrediction:", y_pred)
-    print("Probability:", y_prob)
-
-
-    # ---------------------------------------------
-    # Convert prediction into readable result
-    # ---------------------------------------------
-
-    status = (
-        "Yes"
-        if int(y_pred) == 1
-        else "No"
-    )
-
-
-    # Use 4 decimal places so values such as
-    # 0.004 don't appear as simply 0.00
-    probability_text = (
-        f"{y_prob:.4f} "
-        f"({y_prob * 100:.2f}%)"
-    )
-
-
-    return (
-        status,
-        probability_text,
-        model_choice
-    )
-
-
-# ============================================================
-# 4. MODEL CHOICES
-# ============================================================
-
-model_choices = [
-    "ANN",
-    "SVM",
-    "KNN"
-]
-
-
-# ============================================================
-# 5. FEATURE LABELS
-# ============================================================
-
-feature_labels = {
-
-    'age': 'Age',
-
-    'gender': 'Gender',
-
-    'blood_pressure':
-        'Blood Pressure',
-
-    'cholesterol':
-        'Cholesterol Level',
-
-    'exercise':
-        'Exercise Habits',
-
-    'smoking':
-        'Smoking',
-
-    'family_hd':
-        'Family Heart Disease',
-
-    'diabetes':
-        'Diabetes',
-
-    'bmi':
-        'BMI',
-
-    'high_bp':
-        'High Blood Pressure',
-
-    'low_hdl':
-        'Low HDL Cholesterol',
-
-    'high_ldl':
-        'High LDL Cholesterol',
-
-    'alcohol':
-        'Alcohol Consumption',
-
-    'stress':
-        'Stress Level',
-
-    'sleep_hours':
-        'Sleep Hours',
-
-    'sugar':
-        'Sugar Consumption',
-
-    'triglyceride':
-        'Triglyceride Level',
-
-    'fasting_bs':
-        'Fasting Blood Sugar',
-
-    'crp':
-        'CRP Level',
-
-    'homocysteine':
-        'Homocysteine Level'
-}
-
-
-# ============================================================
-# 6. CREATE INPUT COMPONENT
-# ============================================================
-
-def create_feature_input(feature):
-
-    label = feature_labels.get(
-        feature,
-        feature
-    )
-
-
-    # Gender
-    if feature == 'gender':
-
-        return gr.Dropdown(
-            ["Female", "Male"],
-            label=label,
-            value="Female"
-        )
-
-
-    # Yes / No
-    if feature in binary_features:
-
-        return gr.Dropdown(
-            ["No", "Yes"],
-            label=label,
-            value="No"
-        )
-
-
-    # Alcohol
-    if feature == 'alcohol':
-
-        return gr.Dropdown(
-            [
-                "None",
-                "Low",
-                "Medium",
-                "High"
-            ],
-            label=label,
-            value="None"
-        )
-
-
-    # Ordinal
-    if feature in ordinal_features:
-
-        return gr.Dropdown(
-            [
-                "Low",
-                "Medium",
-                "High"
-            ],
-            label=label,
-            value="Medium"
-        )
-
-
-    # Numeric
-    return gr.Number(
-        label=label
-    )
-
-
-# ============================================================
-# 7. GRADIO UI
-# ============================================================
-
-with gr.Blocks() as demo:
-
-    gr.Markdown(
-        """
-        <h2 style='text-align:center'>
-        💓 Heart Disease Prediction 💓
-        </h2>
-        """
-    )
-
-
-    # --------------------------------------------------------
-    # Model selection
-    # --------------------------------------------------------
-
-    with gr.Row():
-
-        model_input = gr.Dropdown(
-            model_choices,
-            label="Choose Model",
-            value="ANN"
-        )
-
-
-    # --------------------------------------------------------
-    # Feature inputs
-    # --------------------------------------------------------
-
-    feature_inputs = []
-
-
-    for start in range(
-        0,
-        len(selected_features),
-        5
-    ):
-
-        with gr.Row():
-
-            for feature in selected_features[
-                start:start + 5
-            ]:
-
-                component = create_feature_input(
-                    feature
-                )
-
-                feature_inputs.append(
-                    component
-                )
-
-
-    # --------------------------------------------------------
-    # Prediction button
-    # --------------------------------------------------------
-
-    predict_button = gr.Button(
-        "Predict 💡",
-        variant="primary"
-    )
-
-
-    # --------------------------------------------------------
-    # Outputs
-    # --------------------------------------------------------
-
-    with gr.Row():
-
-        status_output = gr.Textbox(
-            label="Heart Disease Status"
-        )
-
-        prob_output = gr.Textbox(
-            label="Prediction Probability"
-        )
-
-        model_output = gr.Textbox(
-            label="Model Selected"
-        )
-
-
-    # --------------------------------------------------------
-    # Connect button
-    # --------------------------------------------------------
-
-    predict_button.click(
-
-        fn=predict_heart_disease,
-
-        inputs=[
-            model_input
-        ] + feature_inputs,
-
-        outputs=[
-            status_output,
-            prob_output,
-            model_output
-        ]
-    )
-
-
-# ============================================================
-# 8. LAUNCH
-# ============================================================
-
 demo.launch()