From 7d39176e27ea97ff7dcc7576976503e9591e92f4 Mon Sep 17 00:00:00 2001
From: nuluh <dam.ar@outlook.com>
Date: Mon, 12 Aug 2024 12:37:55 +0700
Subject: [PATCH] feat: Add initial time domain feature extraction class

The code changes add a new file `time_domain_features.py` that contains a `FeatureExtractor` class. This class calculates various time domain features for a given dataset. The features include mean, max, peak, peak-to-peak, RMS, variance, standard deviation, power, crest factor, form factor, pulse indicator, margin, kurtosis, and skewness.

The class takes a file path as input and reads the data from a CSV file. It assumes the data to analyze is in the first column. The calculated features are stored in a dictionary.

The commit message suggests that the purpose of the changes is to add a new class for time domain feature extraction.
---
 code/src/features/time_domain_features.py | 42 +++++++++++++++++++++++
 1 file changed, 42 insertions(+)
 create mode 100644 code/src/features/time_domain_features.py

diff --git a/code/src/features/time_domain_features.py b/code/src/features/time_domain_features.py
new file mode 100644
index 0000000..bc61c75
--- /dev/null
+++ b/code/src/features/time_domain_features.py
@@ -0,0 +1,42 @@
+import numpy as np
+import pandas as pd
+from scipy.stats import kurtosis, skew
+
+class FeatureExtractor:
+    def __init__(self, file_path):
+        # Read data from CSV file
+        self.data = pd.read_csv(file_path)
+        # Assuming the data to analyze is in the first column
+        self.x = self.data.iloc[:, 0].values
+
+        # Calculate all features
+        self.features = {
+            'Mean': np.mean(self.x),
+            'Max': np.max(self.x),
+            'Peak (Pm)': np.max(np.abs(self.x)),
+            'Peak-to-Peak (Pk)': np.max(self.x) - np.min(self.x),
+            'RMS': np.sqrt(np.mean(self.x**2)),
+            'Variance': np.var(self.x, ddof=0),
+            'Standard Deviation': np.std(self.x, ddof=1),
+            'Power': np.mean(self.x**2),
+            'Crest Factor': np.max(np.abs(self.x)) / np.sqrt(np.mean(self.x**2)),
+            'Form Factor': np.sqrt(np.mean(self.x**2)) / np.mean(self.x),
+            'Pulse Indicator': np.max(np.abs(self.x)) / np.mean(self.x),
+            'Margin': np.max(np.abs(self.x)) / (np.mean(np.sqrt(np.abs(self.x)))),
+            'Kurtosis': kurtosis(self.x, fisher=False),
+            'Skewness': skew(self.x, bias=False)
+        }
+
+    def __repr__(self):
+        result = "Feature Extraction Results:\n"
+        for feature, value in self.features.items():
+            result += f"{feature}: {value:.4f}\n"
+        return result
+
+# 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
+# For example:
+# extractor = FeatureExtractor('path_to_your_data.csv')
+# When you call the variable in a notebook or in the interpreter, it will print the results
+# print(extractor)