Upload app.py

app.py

@@ -5,17 +5,16 @@ import numpy as np
 from models.neural_network.inference import load_model_and_preprocessor
 
 # Load the pre-trained model
-nn_model, nn_preprocessor = load_model_and_preprocessor('/Users/ashishpoudel/Downloads/AircraftFuelPrediction-main/saved_models/nn_model.keras',
-                                                        '/Users/ashishpoudel/Downloads/AircraftFuelPrediction-main/saved_models/nn_preprocessor.pkl')
-
-xgboost_model = joblib.load('/Users/ashishpoudel/Downloads/AircraftFuelPrediction-main/saved_models/xgboost_model.joblib')
+nn_model, nn_preprocessor = load_model_and_preprocessor('saved_models/nn_model.keras',
+                                                        'saved_models/nn_preprocessor.pkl')
+xgboost_model = joblib.load('saved_models/xgboost_model.joblib')
 
 # Load the unique aircraft data
-aircraft_data = pd.read_csv('/Users/ashishpoudel/Downloads/AircraftFuelPrediction-main/datasets/aircraft_data.csv').drop_duplicates(subset='model')
+aircraft_data = pd.read_csv('datasets/aircraft_data.csv').drop_duplicates(subset='model')
 aircraft_dict = aircraft_data.set_index('model').to_dict(orient='index')
 
 # Load the airport distances data
-airport_data = pd.read_csv('/Users/ashishpoudel/Downloads/AircraftFuelPrediction-main/datasets/airport_distances.csv')
+airport_data = pd.read_csv('datasets/airport_distances.csv')
 airport_dict = airport_data.set_index(['Origin_Airport', 'Destination_Airport']).to_dict(orient='index')
 
 
@@ -107,5 +106,3 @@ with gr.Blocks() as demo:
     submit_btn.click(predict_fuel_burn, inputs=[model_name, origin, destination, seats, distance], outputs=result)
 
 demo.launch()
-
-