I want to code a user based recommender :) -----Mensaje original----- De: Pat Ferrel [mailto:p...@occamsmachete.com] Enviado el: viernes, 28 de noviembre de 2014 17:51 Para: user@mahout.apache.org Asunto: Re: api and documentation
You may not need the API since several methods are supported from the command line. But once you choose a recommender we can point you to the right place. What does your data look like? From another thread ======================== Mahout has several recommenders so no need to create one from components. They all make use of the similarity of preferences between users—otherwise known as collaborative filtering. Primary Mahout Recommenders: 1) Hadoop mapreduce item-based cooccurrence recommender. Creates all recs for all users. Uses “Mahout IDs" 2) ALS-WR hadoop mapreduce, uses matrix factorization to reduce noise in the data. Sometimes better for small data sets than #1. Uses “Mahout IDs" 3) Mahout + search engine: cooccurrence type. Extremely flexible, works with multiple actions (multi-modal), works for new users that have some history, has a scalable server (from the search engine) but is more difficult to integrate than #1 or #2. Uses your own ids and reads csv files. Pick a recommender we can go from there. On Nov 28, 2014, at 4:46 AM, ARROYO MANCEBO David <david.arr...@altran.com> wrote: Hi mahouters, Where are documentation about of the API and his use? (classes, methods, data types, purposes...) I need to know all about collaboration filtering for build recommenders Thanks.
