a401d620eb
- Implement FeatureExtractor class in time_domain_features.py for calculating statistical features from dataset columns. - Create build_features.py script to automate feature extraction from processed data and save results in a structured format. - Adjust build_features.py to read processed data, utilize FeatureExtractor, and save feature matrix. This update supports enhanced analysis capabilities within the thesis-project structure, allowing for more sophisticated data processing and model training stages. Closes #1
22 lines
713 B
Python
22 lines
713 B
Python
# src/features/build_features.py
|
|
import pandas as pd
|
|
from time_domain_features import FeatureExtractor
|
|
import numpy as np
|
|
|
|
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
|
|
|
|
# Save features to a file
|
|
np.savez(output_file, **features)
|
|
|
|
if __name__ == "__main__":
|
|
import sys
|
|
input_path = sys.argv[1] # 'data/processed/'
|
|
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)
|