Update app.py

app.py

@@ -1,32 +1,51 @@
 import gradio as gr
 import pandas as pd
 import joblib
+
+# 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
+    ]
 
+    # 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 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):
-  model_input = [fixed_acidity, volatile_acidity, citric_acid, residual_sugar, chlorides, free_sulfur_dioxide, total_sulfur_dioxide, density, pH, sulphates, alcohol]
-  if 0 in model_input:
-    return_message = "Error: Invalid Input \n Please Input: \n"
-    model_input_name = ['fixed_acidity', 'volatile_acidity', 'citric_acid', 'residual_sugar', 'chlorides', 'free_sulfur_dioxide', 'total_sulfur_dioxide', 'density', 'pH', 'sulphates', 'alcohol']
+    # Create DataFrame
+    df = pd.DataFrame([model_input], columns=model_input_name)
 
-    for i in range(len(model_input)):
-      if model_input[i] == 0:
-        return_message = return_message + " " + model_input_name[i]
-    return return_message
-  else:
-    data = pd.DataFrame([[ fixed_acidity, volatile_acidity, citric_acid, residual_sugar, chlorides, free_sulfur_dioxide, total_sulfur_dioxide, density, pH, sulphates, alcohol
-]], columns=model_input_name)
-    prediction = model.predict(data)[0]
-    return_message = "Predicted Quality: " + str(prediction['prediction_label'][0]) + "\nConfidence: " + str(prediction['prediction_score'][0])
-    return return_message
+    # Predict (RandomForest returns a number like 5 or 6)
+    prediction = model.predict(df)[0]
 
+    return f"⭐ Predicted Wine Quality: {prediction}"
+
+# Gradio UI
 demo = gr.Interface(
-    fn = predict_quality,
-    inputs = ['number', 'number', 'number', 'number', 'number', 'number', 'number', 'number', 'number', 'number', 'number'],
-    outputs = [gr.Textbox(label= "Result", lines=8)], api_name = 'predict_quality',
-    title = "🍾 White Wine Quality Predictor 🍾",
-    description="🍾 This is a white wine quality predicting machine learning model based on a random forest classifier. 🍾"
-    )
-demo.launch(share=True)
+    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."
+)
+
+demo.launch()