# logpai/loglizer

A machine learning toolkit for log-based anomaly detection [ISSRE'16]

Repository: https://github.com/logpai/loglizer
Canonical: https://ross.abutalabs.com/products/loglizer
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: log-analysis, anomaly-detection, failure-diagnosis, machine-learning, aiops
Last push: 2024-04-24T05:32:52+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3763, "days_push": 861, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1428, forks 436 (observed 2026-08-28T04:04:42.076976+00:00)

## What it is
Loglizer is a machine learning toolkit for log-based anomaly detection, implementing classic supervised and unsupervised models (LR, Decision Tree, SVM, PCA, Invariants Mining, etc.) from the ISSRE'16 research paper. It provides a pipeline covering log parsing, feature extraction, and anomaly detection for research on automated failure diagnosis.

## Use cases
- detect anomalies in system logs automatically
- train machine learning models on log data for failure prediction
- research log-based anomaly detection techniques
- diagnose system failures from runtime logs
- benchmark anomaly detection models on log datasets
- extract features from structured log sequences

## When to choose
- you are doing academic research on log anomaly detection
- you need implementations of classic log analysis models like PCA or invariant mining
- you want a reproducible pipeline from parsed logs to anomaly predictions
- you work with benchmark log datasets like HDFS or BGL

## When to avoid
- you need a production-grade, real-time log monitoring service
- you want plug-and-play integration with your existing observability stack
- you need actively developed features or commercial support
- you require deep learning based log analysis models

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, monitoring, logging, data-science
- domain: machine-learning, monitoring, data-science, developer-tools
- platform: python, cross-platform
- tags: log-analysis, anomaly-detection, aiops, failure-diagnosis, research-toolkit, jupyter-notebook, devops

## Member repositories
- logpai/loglizer (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:42.076976+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:37:19.451095+00:00, confidence not recorded.
  - readme: https://github.com/logpai/loglizer (fetched 2026-08-28T04:04:42.076976+00:00, sha 47f9d6de0335)
  - registry_pypi: https://pypi.org/pypi/loglizer/json (fetched 2026-08-29T11:48:55.870773+00:00, sha d84375ae3c69)
- Data as of 2026-08-30T08:39:29.467469+00:00.