Update app.py

app.py

@@ -1,57 +1,47 @@
 import gradio as gr
 import pandas as pd
-import joblib
 
-# Load your Random Forest model
-loaded_model = joblib.load('random_forest_model.pkl')
-
-# Example: Define the training DataFrame X (replace with your actual training data)
-# This should be a DataFrame with the same structure as your training data
-X = pd.DataFrame(columns=['host_id', 'neighbourhood_group', 'neighbourhood', 'room_type',
-                          'latitude', 'longitude', 'number_of_reviews',
-                          'calculated_host_listings_count'])  # Add one-hot encoded columns as well
-
-# Function to make predictions
-def predict(host_id, neighbourhood_group, neighbourhood, room_type, latitude, longitude, number_of_reviews, calculated_host_listings_count):
-    # Prepare input data as DataFrame
-    input_data = pd.DataFrame({
+# Function to predict price
+def predict_price(host_id, neighbourhood_group, room_type, price, reviews, calculated_host_listings_count, latitude, longitude):
+    # Create a DataFrame for the input data
+    custom_data = pd.DataFrame({
         'host_id': [host_id],
-        'neighbourhood_group': [neighbourhood_group],
-        'neighbourhood': [neighbourhood],
-        'room_type': [room_type],
+        'neighbourhood_group_Brooklyn': [1 if neighbourhood_group == 'Brooklyn' else 0],
+        'neighbourhood_group_Manhattan': [1 if neighbourhood_group == 'Manhattan' else 0],
+        'neighbourhood_group_Queens': [1 if neighbourhood_group == 'Queens' else 0],
+        'neighbourhood_group_Bronx': [1 if neighbourhood_group == 'Bronx' else 0],
+        'neighbourhood_group_Staten Island': [1 if neighbourhood_group == 'Staten Island' else 0],
+        'room_type_Shared room': [1 if room_type == 'Shared room' else 0],
+        'room_type_Private room': [1 if room_type == 'Private room' else 0],
+        'room_type_Entire home/apt': [1 if room_type == 'Entire home/apt' else 0],
+        'price': [price],
+        'number_of_reviews': [reviews],
+        'calculated_host_listings_count': [calculated_host_listings_count],
         'latitude': [latitude],
-        'longitude': [longitude],
-        'number_of_reviews': [number_of_reviews],
-        'calculated_host_listings_count': [calculated_host_listings_count]
+        'longitude': [longitude]
     })
 
-    # One-hot encode the categorical features
-    input_data = pd.get_dummies(input_data, columns=['room_type', 'neighbourhood_group', 'neighbourhood'], drop_first=True)
-
-    # Ensure the input data has the same columns as the training data
-    input_data = input_data.reindex(columns=X.columns, fill_value=0)
-
-    # Make the prediction
-    predicted_price = loaded_model.predict(input_data)
+    # Make prediction
+    predicted_price = model.predict(custom_data)
     return predicted_price[0]
 
-# Create a Gradio interface
-iface = gr.Interface(
-    fn=predict,
+# Define Gradio interface
+interface = gr.Interface(
+    fn=predict_price,
     inputs=[
         gr.Number(label="Host ID"),
-        gr.Dropdown(label="Neighbourhood Group", choices=["Manhattan", "Brooklyn", "Queens", "Staten Island", "Bronx"]),
-        gr.Dropdown(label="Neighbourhood", choices=["Chelsea", "East Village", "Midtown", "SoHo", "Williamsburg"]),  # Add actual neighbourhood options
-        gr.Dropdown(label="Room Type", choices=["Entire home/apt", "Private room", "Shared room"]),
-        gr.Number(label="Latitude"),
-        gr.Number(label="Longitude"),
+        gr.Dropdown(["Brooklyn", "Manhattan", "Queens", "Bronx", "Staten Island"], label="Neighbourhood Group"),
+        gr.Dropdown(["Shared room", "Private room", "Entire home/apt"], label="Room Type"),
+        gr.Number(label="Price"),
         gr.Number(label="Number of Reviews"),
-        gr.Number(label="Calculated Host Listings Count")
+        gr.Number(label="Calculated Host Listings Count"),
+        gr.Number(label="Latitude"),
+        gr.Number(label="Longitude")
     ],
-    outputs=gr.Number(label="Predicted Price"),
+    outputs="number",
     title="Airbnb Price Prediction",
-    description="Enter the details of the Airbnb listing to predict the price."
+    description="Enter the details to predict the price of an Airbnb listing."
 )
 
 # Launch the interface
-iface.launch()
+interface.launch()