Class | Description |
---|---|
AggregateAndRecommendReducer |
computes prediction values for each user
|
IDReader |
Reads user ids and item ids from files specified in usersFile, itemsFile or userItemFile options in item-based
recommender.
|
ItemFilterAsVectorAndPrefsReducer |
we use a neat little trick to explicitly filter items for some users: we inject a NaN summand into the preference
estimation for those items, which makes
AggregateAndRecommendReducer
automatically exclude them |
ItemFilterMapper |
map out all user/item pairs to filter, keyed by the itemID
|
ItemIDIndexMapper | |
ItemIDIndexReducer | |
PartialMultiplyMapper |
maps similar items and their preference values per user
|
PrefAndSimilarityColumnWritable | |
RecommenderJob |
Runs a completely distributed recommender job as a series of mapreduces.
|
SimilarityMatrixRowWrapperMapper |
maps a row of the similarity matrix to a
VectorOrPrefWritable
actually a column from that matrix has to be used but as the similarity matrix is symmetric,
we can use a row instead of having to transpose it |
ToUserVectorsReducer |
Input
|
ToVectorAndPrefReducer | |
UserVectorSplitterMapper | |
VectorAndPrefsWritable | |
VectorOrPrefWritable |
Enum | Description |
---|---|
ToUserVectorsReducer.Counters |
Copyright © 2008–2017 The Apache Software Foundation. All rights reserved.