code/src/ml/model_selection.py

@@ -25,9 +25,9 @@ def create_ready_data(
     """
     ready_data = []
     for file in os.listdir(stft_data_path):
-        ready_data.append(pd.read_csv(os.path.join(stft_data_path, file)))
+        ready_data.append(pd.read_csv(os.path.join(stft_data_path, file), skiprows=1))
 
-    y_data = [i for i in range(len(ready_data))]
+    y_data = [i for i in range(len(ready_data))] # TODO: Should be replaced with actual desired labels
 
     # Combine all dataframes in ready_data into a single dataframe
     if ready_data:  # Check if the list is not empty

code/src/process_stft.py

@@ -6,7 +6,7 @@ import glob
 import multiprocessing  # Added import for multiprocessing
 
 # Define the base directory where DAMAGE_X folders are located
-damage_base_path = 'D:/thesis/data/converted/raw'
+damage_base_path = 'D:/thesis/data/converted/raw_B'
 
 # Define output directories for each sensor
 output_dirs = {
@@ -105,11 +105,13 @@ def process_damage_case(damage_num):
             )
             
             # Save the aggregated STFT to CSV
-            df_aggregated.to_csv(output_file, index=False)
+            with open(output_file, 'w') as file:
+                file.write('sep=,\n')
+                df_aggregated.to_csv(output_file, index=False)
             print(f"Saved aggregated STFT for Sensor {sensor_num}, Damage {damage_num} to {output_file}")
         else:
             print(f"No STFT data aggregated for Sensor {sensor_num}, Damage {damage_num}.")
 
 if __name__ == "__main__":  # Added main guard for multiprocessing
     with multiprocessing.Pool() as pool:
-        pool.map(process_damage_case, range(1, num_damage_cases + 1))
+        pool.map(process_damage_case, range(0, num_damage_cases + 1))