Merge pull request #17 from nuluh/feature/csv-padding-naming

Feature/csv padding naming

data/raw/README.md

@@ -1,8 +1,8 @@
-# Processed Data Directory
+# Raw Data Directory
 
 ## Overview
 
-This `data/processed` directory contains structured data that has been processed and formatted for analysis. Each subdirectory within `processed` represents a different level of simulated damage, and each contains multiple test files from experiments conducted under that specific damage scenario.
+This `data/raw` directory contains structured data that has been processed and formatted for analysis. Each subdirectory within `raw` represents a different level of simulated damage, and each contains multiple test files from experiments conducted under that specific damage scenario.
 
 ## Directory Structure
 
@@ -12,12 +12,12 @@ The directory is organized as follows:
 data
 └── processed
 ├── DAMAGE_1
-│ ├── D1_TEST1.csv
-│ ├── D1_TEST2.csv
+│   ├── D1_TEST1.csv
+│   ├── D1_TEST2.csv
 │ ...
-│ └── D1_TEST10.csv
+│   └── D1_TEST10.csv
 ├── DAMAGE_2
-│ ├── D2_TEST1.csv
+│   ├── D2_TEST1.csv
 │ ...
 ├── DAMAGE_3
 │ ...

generate_dummy_data.py

@@ -13,14 +13,20 @@ processed_path = os.path.join(base_path, "processed")
 os.makedirs(raw_path, exist_ok=True)
 os.makedirs(processed_path, exist_ok=True)
 
-for damage in range(1, 6):  # 5 Damage levels
-    damage_folder = f"DAMAGE_{damage}"
-    damage_path = os.path.join(processed_path, damage_folder)
+# Define the number of zeros to pad
+num_damages = 5
+num_tests = 10
+damage_pad = len(str(num_damages))
+test_pad = len(str(num_tests))
+
+for damage in range(1, num_damages + 1):  # 5 Damage levels starts from 1
+    damage_folder = f"DAMAGE_{damage:0{damage_pad}}"
+    damage_path = os.path.join(raw_path, damage_folder)
     os.makedirs(damage_path, exist_ok=True)
 
     for test in range(1, 11):  # 10 Tests per damage level
         # Filename for the CSV
-        csv_filename = f"D{damage}_TEST{test}.csv"
+        csv_filename = f"D{damage:0{damage_pad}}_TEST{test:0{test_pad}}.csv"
         csv_path = os.path.join(damage_path, csv_filename)
 
         # Generate dummy data