Skip to content

Instantly share code, notes, and snippets.

@rehan243
Created July 29, 2026 19:24
Show Gist options
  • Select an option

  • Save rehan243/eb283d07d96753611881ad86fbe23cde to your computer and use it in GitHub Desktop.

Select an option

Save rehan243/eb283d07d96753611881ad86fbe23cde to your computer and use it in GitHub Desktop.
Data Drift Detector using KS-Test — Production Pattern (Python)
"""
Author: Rehan Malik | Senior AI/ML Engineer
This script implements a Data Drift Detector using the Kolmogorov-Smirnov (KS) Test.
It compares two datasets (reference and current) to identify distribution shifts
and outputs the drift results for each feature.
Usage:
- Replace or extend the demo in the `__main__` block with your datasets.
"""
from typing import List, Tuple, Dict
from scipy.stats import ks_2samp
from dataclasses import dataclass
import pandas as pd
import numpy as np
@dataclass
class DriftResult:
feature: str
p_value: float
statistic: float
drift_detected: bool
class DataDriftDetector:
def __init__(self, threshold: float = 0.05):
"""
Initialize the Data Drift Detector.
:param threshold: p-value threshold for drift detection. Defaults to 0.05.
"""
self.threshold = threshold
def detect_drift(
self, reference_data: pd.DataFrame, current_data: pd.DataFrame
) -> List[DriftResult]:
"""
Detects data drift between reference and current datasets.
:param reference_data: DataFrame containing reference data.
:param current_data: DataFrame containing current data.
:return: List of DriftResult objects for each feature.
"""
if set(reference_data.columns) != set(current_data.columns):
raise ValueError("Both datasets must have the same columns.")
results = []
for column in reference_data.columns:
ref_col = reference_data[column].dropna()
curr_col = current_data[column].dropna()
if ref_col.empty or curr_col.empty:
continue
# Perform KS-Test
stat, p_value = ks_2samp(ref_col, curr_col)
drift_detected = p_value < self.threshold
results.append(
DriftResult(
feature=column,
p_value=p_value,
statistic=stat,
drift_detected=drift_detected
)
)
return results
def summarize_results(self, results: List[DriftResult]) -> Dict[str, int]:
"""
Summarize drift detection results.
:param results: List of DriftResult objects.
:return: Summary of drift results as a dictionary.
"""
drifted_features = sum(result.drift_detected for result in results)
return {
"total_features": len(results),
"drifted_features": drifted_features,
}
if __name__ == "__main__":
# Generate sample data for demonstration
np.random.seed(42)
ref_data = pd.DataFrame({
"feature1": np.random.normal(0, 1, 1000),
"feature2": np.random.normal(5, 2, 1000),
})
curr_data = pd.DataFrame({
"feature1": np.random.normal(0, 1, 1000), # No drift
"feature2": np.random.normal(6, 2, 1000), # Drift
})
# Initialize and run detector
detector = DataDriftDetector(threshold=0.05)
drift_results = detector.detect_drift(ref_data, curr_data)
# Print detailed drift results
for result in drift_results:
print(f"Feature: {result.feature}, p-value: {result.p_value:.5f}, "
f"statistic: {result.statistic:.5f}, Drift Detected: {result.drift_detected}")
# Print summary
summary = detector.summarize_results(drift_results)
print("\nDrift Detection Summary:", summary)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment