Update app.py

app.py

@@ -1,31 +1,30 @@
+!pip install gradio
+from huggingface_hub import from_pretrained
 import gradio as gr
 
+# Load the model from Hugging Face Hub
+repo_id = "rmaitest/mlmodel2"  # Your model repository ID
+model = from_pretrained(repo_id)  # Loads the inference function (predict_price)
 
-# Replace with the ID of your model on Hugging Face
-model_id = "rmaitest/housepricepridiction"
 
+def predict_with_hf_model(size, bedrooms, age):
+    """Predicts house price using the model from Hugging Face Hub."""
+    # Call the loaded inference function
+    result = model.predict_price(size=size, bedrooms=bedrooms, age=age) 
+    predicted_price = result["predicted_price"]  # Extract the predicted price
 
-def predict(size, bedrooms, age):
-  """Predicts house price based on input features."""
-  # Prepare input data as a dictionary (adjust based on your model)
-  input_data = {"Size (sq ft)": size, "Number of Bedrooms": bedrooms, "Age of House (years)": age}
+    # Format the output
+    return f"Predicted Price: ${predicted_price:,.2f}"
 
-  # Send prediction request to Hugging Face Inference API
-  prediction = predictor(input_data)
-
-  # Extract predicted price
-  predicted_price = prediction[0]["predicted_price"]
-
-  # Format the output with dollar sign and two decimal places
-  return f"Predicted Price: ${predicted_price:,.2f}"
 
 # Create the Gradio interface
 iface = gr.Interface(
-    fn=predict,
-    inputs=["number", "number", "number"],  # Three numeric input fields
-    outputs="text",  # Output is the predicted price (text, not number)
+    fn=predict_with_hf_model,
+    inputs=["number", "number", "number"],
+    outputs="text",
     title="House Price Prediction",
-    description="Enter house details to predict the price using a publicly deployed model."
+    description="Enter house details to predict the price.",
 )
 
-iface.launch(share=True)
+# Launch the interface
+iface.launch()