Log In
Or create an account -> 
Imperial Library
  • Home
  • About
  • News
  • Upload
  • Forum
  • Help
  • Login/SignUp

Index
Title Page Copyright and Credits
Machine Learning with the Elastic Stack
Dedication About Packt
Why subscribe? Packt.com
Contributors
About the authors About the reviewers Packt is searching for authors like you
Preface
Who this book is for What this book covers To get the most out of this book
Download the example code files Download the color images Conventions used
Get in touch
Reviews
Machine Learning for IT
Overcoming the historical challenges
The plethora of data The advent of automated anomaly detection
Theory of operation
Defining unusual Learning normal, unsupervised
Probability models Learning the models De-trending Scoring of unusualness
Operationalization
Jobs ML nodes Bucketization The datafeed
Supporting indices
.ml-state .ml-notifications .ml-anomalies-*
The orchestration Summary
Installing the Elastic Stack with Machine Learning
Installing the Elastic Stack
Downloading the software Installing Elasticsearch Installing Kibana Enabling Platinum features
A guided tour of Elastic ML features
Getting data for analysis ML job types in Kibana
Data Visualizer The Single metric job Multi-metric job Population job Advanced job
Controlling ML via the API
Summary
Event Change Detection
How to understand the normal rate of occurrence Exploring count functions
Summarized counts Splitting the counts Other counting functions
Non-zero count Distinct count
Counting in population analysis Detecting things that rarely occur Counting message-based logs via categorization
Types of messages that can be categorized by ML The categorization process Counting the categories Putting it all together When not to use categorization
Summary
IT Operational Analytics and Root Cause Analysis
Holistic application visibility
The importance and limitations of KPIs Beyond the KPIs
Data organization
Effective data segmentation
Custom queries for ML jobs Data enrichment on ingest
Leveraging the contextual information
Analysis splits Statistical influencers
Bringing it all together for root cause analysis
Outage background Visual correlation and shared influencers
Summary
Security Analytics with Elastic Machine Learning
Security in the field
The volume and variety of data The geometry of an attack
Threat hunting architecture
Layer-based ingestion Threat intelligence
Investigation analytics
Assessment of compromise
Summary
Alerting on ML Analysis
Results presentation The results index
Bucket results Record results Influencer results
Alerts from the Machine Learning UI in Kibana
Anatomy of the default watch from the ML UI in Kibana
Creating ML alerts manually Summary
Using Elastic ML Data in Kibana Dashboards
Visualization options in Kibana
Visualization examples Timelion Time series visual builder 
Preparing data for anomaly detection analysis
The dataset Ingesting the data Creating anomaly detection jobs
Global traffic analysis job A HTTP response code profiling of the host making requests Traffic per host analysis
Building the visualizations
Configuring the index pattern Using ML data in TSVB Creating a correlation Heat Map Using ML data in Timelion Building the dashboard
Summary
Using Elastic ML with Kibana Canvas
Introduction to Canvas
What is Canvas? The Canvas expression
Building Elastic ML Canvas slides
Preparing your data Anomalies in a Canvas data table Using the new SQL integration
Summary
Forecasting
Forecasting versus prophesying Forecasting use cases Forecasting – theory of operation Single time series forecasting
Dataset preparation Creating the ML job for forecasting
Forecast results Multiple time series forecasting Summary
ML Tips and Tricks
Job groups Influencers in split versus non-split jobs Using ML on scripted fields Using one-sided ML functions to your advantage Ignoring time periods
Ignoring an upcoming (known) window of time
Creating a calendar event Stopping and starting a datafeed to ignore the desired timeframe
Ignoring an unexpected window of time, after the fact
Clone the job and re-run historical data Revert the model snapshot
Don't over-engineer the use case ML job throughput considerations Top-down alerting by leveraging custom rules Sizing ML deployments Summary
Other Books You May Enjoy
Leave a review - let other readers know what you think
  • ← Prev
  • Back
  • Next →
  • ← Prev
  • Back
  • Next →

Chief Librarian: Las Zenow <zenow@riseup.net>
Fork the source code from gitlab
.

This is a mirror of the Tor onion service:
http://kx5thpx2olielkihfyo4jgjqfb7zx7wxr3sd4xzt26ochei4m6f7tayd.onion