feat(data-processing): Implement CSV data transformation for SVM analysis

Introduce a Python script for transforming QUGS 2D grid structure data into a simplified 1D beam format suitable for SVM-based damage detection. The script efficiently slices original CSV files into smaller, manageable sets, correlating specific damage scenarios with their corresponding sensor data. This change addresses the challenge of retaining critical damage localization information during the data conversion process, ensuring high-quality, relevant data for 1D analysis.

Closes #20

data/QUGS/convert.py

@@ -0,0 +1,63 @@
+import pandas as pd
+import os
+import sys
+from colorama import Fore, Style, init
+
+def create_damage_files(base_path, output_base):
+    # Initialize colorama
+    init(autoreset=True)
+    
+    # Generate column labels based on expected duplication in input files
+    columns = ['Real'] + [f'Real.{i}' for i in range(1, 30)]  # Explicitly setting column names
+
+    sensor_end_map = {1: 'Real.25', 2: 'Real.26', 3: 'Real.27', 4: 'Real.28', 5: 'Real.29'}
+
+    # Define the damage scenarios and the corresponding original file indices
+    damage_scenarios = {
+        1: range(6, 11),  # Damage 1 files from zzzAD6.csv to zzzAD10.csv
+        2: range(11, 16), # Damage 2 files from zzzAD11.csv to zzzAD15.csv
+        3: range(16, 21), # Damage 3 files from zzzAD16.csv to zzzAD20.csv
+        4: range(21, 26)  # Damage 4 files from zzzAD21.csv to zzzAD25.csv
+    }
+
+    for damage, files in damage_scenarios.items():
+        for i, file_index in enumerate(files, start=1):
+            # Load original data file
+            file_path = os.path.join(base_path, f'zzzAD{file_index}.TXT')
+            df = pd.read_csv(file_path, sep='\t', skiprows=10)  # Read with explicit column names
+
+            top_sensor = columns[damage-1]
+            print(top_sensor, type(top_sensor))
+            output_file_1 = os.path.join(output_base, f'DAMAGE_{damage}', f'D{damage}_TEST{i}_01.csv')
+            print(f"Creating {output_file_1} from taking zzzAD{file_index}.TXT")
+            print("Taking datetime column on index 0...")
+            print(f"Taking `{top_sensor}`...")
+            df[['Time', top_sensor]].to_csv(output_file_1, index=False)
+            print(Fore.GREEN + "Done")
+
+            bottom_sensor = sensor_end_map[damage]
+            output_file_2 = os.path.join(output_base, f'DAMAGE_{damage}', f'D{damage}_TEST{i}_02.csv')
+            print(f"Creating {output_file_2} from taking zzzAD{file_index}.TXT")
+            print("Taking datetime column on index 0...")
+            print(f"Taking `{bottom_sensor}`...")
+            df[['Time', bottom_sensor]].to_csv(output_file_2, index=False)
+            print(Fore.GREEN + "Done")
+            print("---")
+
+def main():
+    if len(sys.argv) < 2:
+        print("Usage: python convert.py <path_to_csv_files>")
+        sys.exit(1)
+
+    base_path = sys.argv[1]
+    output_base = "output_data"  # Define output directory
+
+    # Create output folders if they don't exist
+    for i in range(1, 5):
+        os.makedirs(os.path.join(output_base, f'DAMAGE_{i}'), exist_ok=True)
+
+    create_damage_files(base_path, output_base)
+    print(Fore.YELLOW + Style.BRIGHT + "All files have been created successfully.")
+
+if __name__ == "__main__":
+    main()