GitXplorerGitXplorer
f

LCBM

public
0 stars
2 forks
0 issues

Commits

List of commits on branch master.
Unverified
4bb02ea0c4bc00d3bba6ebc2ed732ed7e901924e

ffabiopetroni committed 9 years ago
Unverified
5b1e6a5588d41d257987284a3d161bcb7e2da96e

ffabiopetroni committed 9 years ago
Unverified
77f8d9a6195fbe0e1957499e4d68ba702a5fd615

ffabiopetroni committed 9 years ago
Unverified
9457506276fa1772a0f638758b542331244e0e0b

ffabiopetroni committed 9 years ago
Unverified
6e87596745784f1e964f0eb9e3206a5919c3545a

ffabiopetroni committed 9 years ago
Unverified
4806ef8b2aa642d0209bd3bc56928674b3cfc457

ffabiopetroni committed 9 years ago

README

The README file for this repository.

LCBM

a fast and lightweight collaborative filtering algorithm for binary ratings.

If you use LCBM please cite the following paper:

  • F. Petroni, L. Querzoni, R. Beraldi, M. Paolucci: "LCBM: Statistics-Based Parallel Collaborative Filtering." In: Proceedings of the 17th International Conference on Business Information Systems (BIS), 2014.

###Hadoop MapReduce:

To run the project on hadoop type the following:

bin/hadoop jar /home/hduser/LCBM_mapreduce.jar train test [options]

Parameters:

  • train: the name of the file with the train data
  • test: the name of the file with the test data.

Options:

  • -k int -> specifies the multiplicative factor for the SE. Default 2.
  • -split_token char -> specifies the character that splits the dataset.
  • -output1 string -> specifies the name of the first output directory in the hdfs.
  • -output2 sting -> specifies the name of the second output directory in the hdfs.

Example

bin/hadoop jar /home/hduser/LCBM_mapreduce.jar ml100k/trace1.base ml100k/trace1.test