Update app.py

app.py

@@ -1,51 +1,41 @@
 import gradio as gr
 import pandas as pd
 import joblib
+import os
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.model_selection import train_test_split
 
-# Load the model
-model = joblib.load('rf_model.pkl')
-
-# Feature names
-model_input_name = [
-    'fixed_acidity', 'volatile_acidity', 'citric_acid', 'residual_sugar',
-    'chlorides', 'free_sulfur_dioxide', 'total_sulfur_dioxide', 'density',
-    'pH', 'sulphates', 'alcohol'
-]
-
-def predict_quality(
-    fixed_acidity=None, volatile_acidity=None, citric_acid=None, residual_sugar=None,
-    chlorides=None, free_sulfur_dioxide=None, total_sulfur_dioxide=None, density=None,
-    pH=None, sulphates=None, alcohol=None
-):
-
-    # Collect inputs
-    model_input = [
-        fixed_acidity, volatile_acidity, citric_acid, residual_sugar, chlorides,
-        free_sulfur_dioxide, total_sulfur_dioxide, density, pH, sulphates, alcohol
-    ]
+MODEL_PATH = "rf_model.pkl"
+DATA_URL = "https://archive.ics.uci.edu/ml/machine-learning-databases/wine-quality/winequality-white.csv"
+
+# ---------------------------
+# TRAIN MODEL (only if needed)
+# ---------------------------
 
-    # Check for missing inputs (None)
-    if any(v is None for v in model_input):
-        missing = [
-            name for v, name in zip(model_input, model_input_name) if v is None
-        ]
-        return "❌ Missing Input(s):\n" + "\n".join(missing)
+def train_model():
+    print("Downloading white wine dataset...")
+    df = pd.read_csv(DATA_URL, sep=';')
 
-    # Create DataFrame
-    df = pd.DataFrame([model_input], columns=model_input_name)
+    feature_names = [
+        'fixed acidity', 'volatile acidity', 'citric acid', 'residual sugar',
+        'chlorides', 'free sulfur dioxide', 'total sulfur dioxide', 'density',
+        'pH', 'sulphates', 'alcohol'
+    ]
 
-    # Predict (RandomForest returns a number like 5 or 6)
-    prediction = model.predict(df)[0]
+    X = df[feature_names]
+    y = df['quality']
 
-    return f"⭐ Predicted Wine Quality: {prediction}"
+    X_train, X_test, y_train, y_test = train_test_split(
+        X, y, test_size=0.2, random_state=42
+    )
 
-# Gradio UI
-demo = gr.Interface(
-    fn=predict_quality,
-    inputs=[gr.Number(label=name) for name in model_input_name],
-    outputs=gr.Textbox(label="Result", lines=4),
-    title="🍾 White Wine Quality Predictor 🍾",
-    description="🍷 Predict the quality of white wine using a trained Random Forest model."
-)
+    print("Training Random Forest model...")
+    model = RandomForestClassifier(
+        n_estimators=300,
+        max_depth=12,
+        random_state=42
+    )
+    model.fit(X_train, y_train)
 
-demo.launch()
+    joblib.dump(model, MODEL_PATH)
+    print("Model sav