Hey all. We had also the same problem described by Nishkam almost in the
same big data setting. We fixed the fetch failure by increasing the timeout
for acks in the driver:
set("spark.core.connection.ack.wait.timeout", "600") // 10 minutes timeout
for acks between nodes
Cheers, Christoph
2014-09
Hey Deb,
NDCG is the "Normalized Discounted Cumulative Gain" [1]. Another popular
measure is "Expected Reciprocal Rank" (ERR) [2]; it is based on a
probabilistic user model, where the user scans the presented list of search
results or recommendations and chooses the first that is sufficiently
rele
I totally agree, and we discovered also some drawbacks with the
classification models implementation that are based on GLMs:
- There is no distinction between predicting scores, classes, and
calibrated scores (probabilities). For these models it is common to have
access to all of them and the pred
