Skip to content

mtichikawa/anomaly-detection

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

25 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Real-Time Anomaly Detection System

Production-ready streaming anomaly detection with multiple ML algorithms and ensemble voting.

Features

  • Multiple Algorithms

    • Isolation Forest
    • Statistical (Z-score)
    • LSTM Autoencoder
    • Ensemble Voting
  • Real-Time Processing

    • Streaming data pipeline
    • Low latency detection
    • Configurable thresholds
  • Comprehensive Analysis

    • Performance metrics
    • Visualization dashboard
    • Statistical evaluation

Quick Start

pip install -r requirements.txt
python examples/quick_demo.py

Usage

from src.detectors.pipeline import StreamingPipeline

# Create and train
pipeline = StreamingPipeline(detector_type='ensemble')
pipeline.train(training_data)

# Detect anomalies
results = pipeline.process_stream(test_data)

# Get anomalies
for anomaly in pipeline.anomalies:
    print(f"Anomaly at {anomaly['index']}: {anomaly['value']}")

Code Structure

  • src/detectors/pipeline.py (500+ lines) - Complete detection system
  • src/visualizations.py (350+ lines) - Visualization suite
  • notebooks/complete_demo.ipynb - Full workflow
  • examples/quick_demo.py - 5-minute demo

Performance

Tested on synthetic data:

  • F1 Score: 0.81+
  • Precision: 0.85+
  • Recall: 0.78+

What I Learned

  • Streaming data processing
  • Ensemble machine learning methods
  • Production system design
  • Trade-offs: accuracy vs latency

Contact: Mike Ichikawa - projects.ichikawa@gmail.com

2026-01-05

2026-01-05

2026-01-08

2026-01-11

2026-01-14

2026-01-17

2026-01-20

2026-01-23

2026-01-26

2026-01-29

2026-02-01

2026-02-04

2026-02-07

2026-02-10

2026-02-13

2026-02-16

2026-02-17

2026-02-18

About

Real-time anomaly detection system with multiple ML algorithms (Isolation Forest, Statistical Z-score, LSTM Autoencoder) and ensemble voting for streaming data processing.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors