chore: Ignore .venv/ directory and update .gitignore due to error numpy error ValueError: numpy.ndarray size changed, may indicate binary incompatibility. by creating venv.

Closes #15

.gitignore

@@ -1,4 +1,4 @@
 # Ignore CSV files in the data directory and all its subdirectories
 data/**/*.csv
-
+.venv/
 *.pyc

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_TEST1.csv
-│ ├── D1_TEST2.csv
+│   ├── D1_TEST2.csv
 │ ...
-│ └── D1_TEST10.csv
+│   └── D1_TEST10.csv
 ├── DAMAGE_2
-│ ├── D2_TEST1.csv
+│   ├── D2_TEST1.csv
 │ ...
 ├── DAMAGE_3
 │ ...

generate_dummy_data.py

@@ -13,29 +13,38 @@ 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
+# Define the number of zeros to pad
-    damage_folder = f"DAMAGE_{damage}"
+num_damages = 5
-    damage_path = os.path.join(processed_path, damage_folder)
+num_tests = 10
+num_sensors = 2
+damage_pad = len(str(num_damages))
+test_pad = len(str(num_tests))
+sensor_pad = len(str(num_sensors))
+
+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
+        for sensor in range(1, 3):  # 2 Sensors per test
-        csv_filename = f"D{damage}_TEST{test}.csv"
+            # Filename for the CSV
-        csv_path = os.path.join(damage_path, csv_filename)
+            csv_filename = f"D{damage:0{damage_pad}}_TEST{test:0{test_pad}}_{sensor:0{sensor_pad}}.csv"
+            csv_path = os.path.join(damage_path, csv_filename)
             
-        # Generate dummy data
+            # Generate dummy data
-        num_rows = 10
+            num_rows = 10
-        start_time = datetime.now()
+            start_time = datetime.now()
-        timestamps = [start_time + timedelta(seconds=i*0.0078125) for i in range(num_rows)]
+            timestamps = [start_time + timedelta(seconds=i*0.0078125) for i in range(num_rows)]
-        values = np.random.randn(num_rows)  # Random float values
+            values = np.random.randn(num_rows)  # Random float values
 
-        # Create DataFrame
+            # Create DataFrame
-        df = pd.DataFrame({
+            df = pd.DataFrame({
-            "Time": timestamps,
+                "Time": timestamps,
-            "Value": values
+                "Value": values
-        })
+            })
 
-        # Save the CSV file with a custom header
+            # Save the CSV file with a custom header
-        with open(csv_path, 'w') as file:
+            with open(csv_path, 'w') as file:
-            file.write('sep=,\n')  # Writing the separator hint
+                file.write('sep=,\n')  # Writing the separator hint
-            df.to_csv(file, index=False)
+                df.to_csv(file, index=False)