From Mahout In Action:
You may be searching for something like “CosineMeasureSimilarity” in
Mahout. You’ve actually already found it but under
an unexpected name: PearsonCorrelationSimilarity. The cosine
measure similarity and Pearson correlation aren’t the same thing, but,
if you bother to work out the math, they actually reduce to the same
computation when the two series of input values each have a mean of 0
(“centered”).
Jeff
On 4/27/10 9:34 AM, Sebastian Schelter (JIRA) wrote:
Cosine item similarity implementation
-------------------------------------
Key: MAHOUT-387
URL: https://issues.apache.org/jira/browse/MAHOUT-387
Project: Mahout
Issue Type: New Feature
Components: Collaborative Filtering
Reporter: Sebastian Schelter
Attachments: MAHOUT-387.patch
I needed to compute the cosine similarity between two items when running
org.apache.mahout.cf.taste.hadoop.pseudo.RecommenderJob, I couldn't find an
implementation (did I overlook it maybe?) so I created my own. I want to share
it here, in case you find it useful.
