Update app.py

app.py

@@ -1,27 +1,39 @@
-import gradio as gr
+from fastapi import FastAPI, HTTPException
+from pydantic import BaseModel
 import pandas as pd
 import xgboost as xgb
 from huggingface_hub import hf_hub_download
 
-# Load the model from the Hugging Face Hub
+# Download and load the model from the correct repo
 model_path = hf_hub_download(repo_id="caslabs/xgboost-home-price-predictor", filename="xgboost_model.json")
 model = xgb.XGBRegressor()
 model.load_model(model_path)
 
-# Define the prediction function
-def predict_price(features):
-    # Convert the JSON input to a DataFrame
-    df = pd.DataFrame([features])
-    predicted_price = model.predict(df)[0]
-    return {"predicted_price": predicted_price}
+# Initialize FastAPI app
+app = FastAPI()
 
-# Set up the Gradio interface
-iface = gr.Interface(
-    fn=predict_price,
-    inputs=gr.JSON(),  # Accept JSON input
-    outputs=gr.JSON(),  # Return JSON output
-    title="Home Price Prediction API",
-    description="Predict home price based on input features"
-)
+# Define the expected input format
+class PredictionRequest(BaseModel):
+    Site_Area_sqft: float
+    Actual_Age_Years: int
+    Total_Rooms: int
+    Bedrooms: int
+    Bathrooms: float
+    Gross_Living_Area_sqft: float
+    Design_Style_Code: int
+    Condition_Code: int
+    Energy_Efficient_Code: int
+    Garage_Carport_Code: int
 
-iface.launch()
+# Define the /predict route
+@app.post("/predict")
+async def predict(request: PredictionRequest):
+    # Convert the input data to a DataFrame
+    data = pd.DataFrame([request.dict()])
+    
+    # Make a prediction
+    try:
+        predicted_price = model.predict(data)[0]
+        return {"predicted_price": predicted_price}
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))