fix(src): update damage base path and adjust STFT processing parameters

code/src/data_preprocessing.py

@@ -4,7 +4,7 @@ import re
 import sys
 import numpy as np
 from colorama import Fore, Style, init
-from typing import TypedDict, Dict, List
+from typing import TypedDict, Tuple, List
 from joblib import load
 from pprint import pprint
 
@@ -35,8 +35,8 @@ def complement_pairs(n, prefix, extension):
         if a != orig_a:                # skip original a
             yield (filename, [a, a + 25]) # use yield instead of return to return a generator of tuples
 
-def generate_df_tuples(prefix: str, total_dfs: int=30, extension: str="TXT", first_col_start: int=1, last_col_offset: int=25, 
+def generate_df_tuples(prefix: str, extension: str="TXT", first_col_start: int=1, last_col_offset: int=25, 
-                      group_size: int=5, special_groups: list=None, group: bool=True):
+                      group_size: int=5, special_groups: list=None, group: bool=True, undamage_file: str=None) -> List[Tuple[str, List[int]]]:
     """
     Generate a structured list of tuples containing DataFrame references and column indices.
     
@@ -78,6 +78,12 @@ def generate_df_tuples(prefix: str, total_dfs: int=30, extension: str="TXT", fir
     # Add special groups at specified positions (other than beginning)
     if special_groups:
         result.insert(0, special_groups)
+    if undamage_file:
+        for i in range (1, 6):
+            n = 5 + i
+            bottom_end = i
+            top_end = bottom_end + 25
+            result[0].append((undamage_file, [bottom_end, top_end]))
     
     
     return result
@@ -354,4 +360,4 @@ def main():
 
 
 if __name__ == "__main__":
-    main()
+    main()

code/src/process_stft.py

@@ -8,7 +8,7 @@ import multiprocessing  # Added import for multiprocessing
 from typing import Union, Tuple
 
 # 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 = {
@@ -52,7 +52,7 @@ def compute_stft(vibration_data: np.ndarray, return_param: bool = False) -> Unio
     hop_size = 512
     window = hann(window_size)
     Fs = 1024
-
+    
     frequencies, times, Zxx = stft(
                                     vibration_data, 
                                     fs=Fs, 
@@ -77,7 +77,7 @@ def process_damage_case(damage_num):
     damage_folder = os.path.join(damage_base_path, f'DAMAGE_{damage_num}')
     if damage_num == 0:
         # Number of test runs per damage case
-        num_test_runs = 120
+        num_test_runs = 125
     else:
         num_test_runs = 5
     # Check if the damage folder exists
@@ -122,12 +122,12 @@ def process_damage_case(damage_num):
             # only inlcude 21 samples vector features for first 45 num_test_runs else include 22 samples vector features
             if damage_num == 0:
                 print(f"Processing damage_num = 0, test_num = {test_num}")
-                if test_num <= 45:
+                if test_num <= 60:
-                    df_stft = df_stft.iloc[:22, :]
+                    df_stft = df_stft.iloc[:20, :]
-                    print(f"Reduced df_stft shape (21 samples): {df_stft.shape}")
+                    print(f"Reduced df_stft shape (20 samples): {df_stft.shape}")
                 else:
                     df_stft = df_stft.iloc[:21, :]
-                    print(f"Reduced df_stft shape (22 samples): {df_stft.shape}")
+                    print(f"Reduced df_stft shape (21 samples): {df_stft.shape}")
             
             # Append to the aggregated list
             aggregated_stft.append(df_stft)