feat(notebook): add 'labels' column to feature extraction dataframe

Implement extraction of 'labels' from directory names and append as a new column in the dataframe during feature extraction. Adapted from the existing `build_features.py` script to enhance data usability in supervised learning models within the Jupyter notebook environment.

Closes #10

.vscode/launch.json

@@ -0,0 +1,16 @@
+{
+  // Use IntelliSense to learn about possible attributes.
+  // Hover to view descriptions of existing attributes.
+  // For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387
+  "version": "0.2.0",
+  "configurations": [
+    {
+      "name": "Python Debugger: Current File with Arguments",
+      "type": "debugpy",
+      "request": "launch",
+      "program": "${file}",
+      "console": "integratedTerminal",
+      "args": ["data/raw", "data/raw"]
+    }
+  ]
+}

code/src/features/build_features.py

@@ -1,16 +1,39 @@
 # src/features/build_features.py
 import pandas as pd
-from time_domain_features import FeatureExtractor
-import numpy as np
+from time_domain_features import ExtractTimeFeatures
+import os
+import re
 
-def build_features(input_file, output_file):
-    data = pd.read_csv(input_file)
-    # Assuming the relevant data is in the first column
-    extractor = FeatureExtractor(data.iloc[:, 0].values)
-    features = extractor.features
+# define function, regex pattern for extracting the damage level and test number store in pairs array
+def extract_numbers(filename):
+    # Find all occurrences of one or more digits in the filename
+    numbers = re.findall(r'\d+', filename)
+    # Convert the list of number strings to integers
+    numbers = [int(num) for num in numbers]
+    # Convert to a tuple and return
+    return print(tuple(numbers))
 
+def build_features(input_dir, output_dir):
+    all_features = []
+    for nth_damage in os.listdir(input_dir):
+        nth_damage_path = os.path.join(input_dir, nth_damage)
+        if os.path.isdir(nth_damage_path):
+            print(nth_damage)
+            for nth_test in os.listdir(nth_damage_path):
+                nth_test_path = os.path.join(nth_damage_path, nth_test)
+                # print(nth_test_path)
+                features = ExtractTimeFeatures(nth_test_path) # return the one csv file feature in dictionary {}
+                all_features.append(features)
+
+    # Create a DataFrame from the list of dictionaries
+    df = pd.DataFrame(all_features)
+    print(df)
+    # Save the DataFrame to a CSV file in the output directory
+    output_file_path = os.path.join(output_dir, 'combined_features.csv')
+    df.to_csv(output_file_path, index=False)
+    print(f"Features saved to {output_file_path}")
     # Save features to a file
-    np.savez(output_file, **features)
+    # np.savez(output_file, **features)
 
 if __name__ == "__main__":
     import sys
@@ -18,4 +41,4 @@ if __name__ == "__main__":
     output_path = sys.argv[2]  # 'data/features/feature_matrix.npz'
     
     # Assuming only one file for simplicity; adapt as needed
-    build_features(f"{input_path}processed_data.csv", output_path)
+    build_features(input_path, output_path)

code/src/features/time_domain_features.py

@@ -36,6 +36,13 @@ class FeatureExtractor:
             result += f"{feature}: {value:.4f}\n"
         return result
 
+def ExtractTimeFeatures(object):
+    data = pd.read_csv(object, skiprows=1) # Skip the header row separator char info
+    extractor = FeatureExtractor(data.iloc[:, 1].values) # Assuming the data is in the second column
+    features = extractor.features
+    return features
+    # Save features to a file
+    # np.savez(output_file, **features)
 # Usage
 # Assume you have a CSV file with numerical data in the first column
 # Create an instance of the class and pass the path to your CSV file