Update app.py

app.py

@@ -398,7 +398,7 @@ def calculate_distance_metrics(y_true, y_pred):
 # Classical Metrics Prediction
 # ============================
 
-def classical_prediction(file, model_choice, min_mmsi, max_mmsi, models, loaded_scalers):
+def classical_prediction(file_path, model_choice, min_mmsi, max_mmsi, models, loaded_scalers):
     """
     Preprocess the input CSV and make predictions using the selected model.
     Calculate classical evaluation metrics and include inference time.
@@ -408,7 +408,7 @@ def classical_prediction(file, model_choice, min_mmsi, max_mmsi, models, loaded_
 
         # Load the uploaded CSV file and filter based on MMSI
         logging.info("Loading uploaded CSV file...")
-        df = pd.read_csv(file, delimiter=',')
+        df = pd.read_csv(file_path, delimiter=',')
         logging.info(f"Uploaded CSV file loaded with {df.shape[0]} records.")
         
         df = df[(df['mmsi'] >= min_mmsi) & (df['mmsi'] <= max_mmsi)]
@@ -557,7 +557,7 @@ def classical_prediction(file, model_choice, min_mmsi, max_mmsi, models, loaded_
 # Abnormal Behavior Detection
 # ============================
 
-def abnormal_behavior_detection(prediction_file, alpha=0.5, threshold=10.0):
+def abnormal_behavior_detection(prediction_file_path, alpha=0.5, threshold=10.0):
     """
     Detect abnormal behavior based on angular divergence and distance difference.
     Accepts a CSV file containing real and predicted positions.
@@ -567,7 +567,7 @@ def abnormal_behavior_detection(prediction_file, alpha=0.5, threshold=10.0):
 
         # Load the CSV file containing real and predicted positions
         logging.info("Loading prediction CSV file...")
-        df = pd.read_csv(prediction_file)
+        df = pd.read_csv(prediction_file_path)
         logging.info(f"Prediction CSV file loaded with {df.shape[0]} records.")
 
         # Check if necessary columns exist
@@ -691,7 +691,7 @@ def main():
     classical_tab = gr.Interface(
         fn=lambda file, model_choice, min_mmsi, max_mmsi: classical_prediction(file, model_choice, min_mmsi, max_mmsi, models, loaded_scalers),
         inputs=[
-            gr.File(label="Upload CSV File", type='file'),
+            gr.File(label="Upload CSV File", type='filepath'),
             gr.Dropdown(choices=["Auto-Select", "Teacher", "Student_North", "Student_Mid", "Student_South"], value="Auto-Select", label="Choose Model"),
             gr.Number(label="Min MMSI", value=0),
             gr.Number(label="Max MMSI", value=999999999)
@@ -709,7 +709,7 @@ def main():
     abnormal_tab = gr.Interface(
         fn=lambda prediction_file, alpha, threshold: abnormal_behavior_detection(prediction_file, alpha, threshold),
         inputs=[
-            gr.File(label="Upload Predicted Positions CSV", type='file'),
+            gr.File(label="Upload Predicted Positions CSV", type='filepath'),
             gr.Slider(minimum=0, maximum=1, step=0.1, value=0.5, label="Alpha (α)"),
             gr.Number(label="Threshold", value=10.0)
         ],