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

.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
+from time_domain_features import ExtractTimeFeatures
-import numpy as np
+import os
+import re
 
-def build_features(input_file, output_file):
+# define function, regex pattern for extracting the damage level and test number store in pairs array
-    data = pd.read_csv(input_file)
+def extract_numbers(filename):
-    # Assuming the relevant data is in the first column
+    # Find all occurrences of one or more digits in the filename
-    extractor = FeatureExtractor(data.iloc[:, 0].values)
+    numbers = re.findall(r'\d+', filename)
-    features = extractor.features
+    # 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

generate_dummy_data.py

@@ -16,8 +16,10 @@ os.makedirs(processed_path, exist_ok=True)
 # Define the number of zeros to pad
 num_damages = 5
 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}}"
@@ -25,23 +27,24 @@ for damage in range(1, num_damages + 1):  # 5 Damage levels starts from 1
     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:0{damage_pad}}_TEST{test:0{test_pad}}.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)