Hi All,
My name is Dileepa Jayakody, a MSc research student from University of
Moratuwa, Sri Lanka. My research project (ReputationBox) is about
prediction the goodness of incoming emails (based on a calculated
reputation score) by analysing previous email conversations, email
correspondents and t
Hi All,
Can I implement a email reputation prediction module within my application
without hosting a Mahout server seperately?
Is there a library I can use for implementing recommendation engines?
Appreciate any suggestions.
Thanks,
Dileepa
On Thu, Mar 20, 2014 at 4:29 PM, Dileepa Jayakody wr
Hi Frank, we are using a very similar system in production.
Hashing text like data to a 5 dimensional vector with two probes, and
then applying tf-idf weighting.
For IDF we dont keep a separate weight dictionary but just count the
distinct training examples ("documents") that have a non null v
On Thu, Mar 20, 2014 at 12:39 PM, Johannes Schulte <
johannes.schu...@gmail.com> wrote:
> For representing the cluster we have a separate job that assigns users
> ("documents") to clusters and shows the most discriminating words for the
> cluster via the LogLikelihood class. The results are then v
Hello,
I am using mahout 0.9 and hadoop 1.2.1. I've just run cub on a bunch of
documents, and I can output the top N words per topic using vector dump.
What I don't understand is how to get the actual topics as strings. When
I do something like this:
./bin/mahout vectordump -i doc-topics/pa
Filed a ticket here: https://issues.apache.org/jira/browse/MAHOUT-1470
On Thu, Mar 6, 2014 at 4:36 PM, Cosinus WebDev wrote:
> Hi,
>
> Thank you for the answer, now I can rest a second :)
>
> Hope this will be fixed soon. If you file a JIRA please send me the link so
> I can watch the result.
>
Hi everybody,
I'd like to do some market basket analysis to suggest cross-sells, but many
of the products are very low sales volume items, so in the past the results
weren't that useful.
Do you think it would make sense to do market basket analysis at more
aggregate levels, for example by brand,
Exception in thread "main" java.lang.Error: Unresolved compilation
problems:
DataModel cannot be resolved to a type
FileDataModel cannot be resolved to a type
UserSimilarity cannot be resolved to a type
PearsonCorrelationSimilarity cannot be resolved to a type
UserNeighborhood cannot be resolved to
I can tell you my experience is that it's absolutely informative to take a look
at running the recommendation stuff on things other than items (brands,
categories, sub-categories, etc.). If you're in a multi-brand environment it
can give you a great view into brand pen by customer groups pretty
Yes that can help, depending on what you're doing. Want to talk more about it?
> On Mar 20, 2014, at 5:14 PM, Si Chen wrote:
>
> Hi everybody,
>
> I'd like to do some market basket analysis to suggest cross-sells, but many
> of the products are very low sales volume items, so in the past the r
This looks like your class path is not set up correctly.
You can try running with -verbose:class as a command line option and see if
the Mahout classes are even being loaded.
On Thu, Mar 20, 2014 at 5:30 PM, Masoud Nikravesh wrote:
> Exception in thread "main" java.lang.Error: Unresolved compi
I have done the equivalent thing with music (moving up from track to album
to artist) with very good results.
On Thu, Mar 20, 2014 at 5:58 PM, Martin, Nick wrote:
> I can tell you my experience is that it's absolutely informative to take a
> look at running the recommendation stuff on things o
12 matches
Mail list logo