selica Programming Guide

This document is programming guide book for selica machine learning library. It contains installation tutorial and programming about implemented algorithms.

What’s selica?

selica is an acronym for Spark MLlib Extend Library Implements Calculation Algorithms. It’s original machine learning library of Apache Spark MLlib, for my own use.

This library has following characteristics:

• still developing
• no given destination
• it’d like to support to promote users’ salary

Getting Started

• Quick Start

Algorithms

selica implements following algorithms.

• Recommender
  • item-based collaborative filtering recommendation
  • feature similarity recommendation
• Frequent Pattern Mining
• Japanese Tokenizer