Update app.py

app.py

@@ -3,26 +3,40 @@ import numpy as np
 import joblib
 from tensorflow.keras.models import load_model
 import os
+import requests
 
-# Check the current working directory and list its contents
-print("Current working directory:", os.getcwd())
-print("Contents of the directory:", os.listdir())
+# URLs of the files in your Hugging Face repository
+scaler_url = 'https://huggingface.co/spaces/saba000farahani/Env_ContaminationLevel/raw/main/scaler_X.pkl'
+rf_model_url = 'https://huggingface.co/spaces/saba000farahani/Env_ContaminationLevel/raw/main/rf_model.pkl'
+mlp_model_url = 'https://huggingface.co/spaces/saba000farahani/Env_ContaminationLevel/raw/main/mlp_model.h5'
+meta_model_url = 'https://huggingface.co/spaces/saba000farahani/Env_ContaminationLevel/raw/main/meta_model.pkl'
 
-# Paths to your saved models and scaler
+# Local paths to save the downloaded files
 scaler_path = 'scaler_X.pkl'
 rf_model_path = 'rf_model.pkl'
 mlp_model_path = 'mlp_model.h5'
 meta_model_path = 'meta_model.pkl'
 
-# Check if files exist
-print("Checking if model files exist...")
-print(f"Scaler path exists: {os.path.isfile(scaler_path)}")
-print(f"Random Forest model path exists: {os.path.isfile(rf_model_path)}")
-print(f"MLP model path exists: {os.path.isfile(mlp_model_path)}")
-print(f"Meta model path exists: {os.path.isfile(meta_model_path)}")
+# Function to download a file from a URL
+def download_file(url, local_path):
+    with requests.get(url, stream=True) as r:
+        r.raise_for_status()
+        with open(local_path, 'wb') as f:
+            for chunk in r.iter_content(chunk_size=8192):
+                f.write(chunk)
+    print(f"Downloaded {local_path}")
 
+# Download the files
+try:
+    download_file(scaler_url, scaler_path)
+    download_file(rf_model_url, rf_model_path)
+    download_file(mlp_model_url, mlp_model_path)
+    download_file(meta_model_url, meta_model_path)
+except Exception as e:
+    print(f"Error downloading files: {e}")
+
+# Load the scaler and models
 try:
-    # Load the scaler and models
     scaler_X = joblib.load(scaler_path)
     print("Scaler loaded successfully.")
     loaded_rf_model = joblib.load(rf_model_path)