2010/3/23 刘逸哲 :
> 1. for the source code changed, this quick start page is old:
> http://cwiki.apache.org/MAHOUT/tastecommandline.html
I can update this -- rather, will just point the wiki to the javadoc,
which has the up-to-date command line documentation.
> 2. The Option parser mayb
1. for the source code changed, this quick start page is old:
http://cwiki.apache.org/MAHOUT/tastecommandline.html
2. The Option parser maybe worng(note that, I could only use “-n
input/ratings.dat” to set the input data.)
hd jar mahout-examples-0.4-SNAPSHOT.job
org.apache.mahout.cf.t
: Tuesday, December 08, 2009 10:10 PM
To: mahout-user@lucene.apache.org
Subject: Re: Mahout on Hadoop
The good news is you are just about to get this running. I think it
will work now.
The bad news is I have already changed this code a little bit in the
last week. For example, the arguments have
Original Message-
> From: Sean Owen [mailto:sro...@gmail.com]
> Sent: Tuesday, December 08, 2009 2:50 PM
> To: mahout-user@lucene.apache.org
> Subject: Re: Mahout on Hadoop
>
> Harjeet I think you need to read the documentation of the code, of the
> data you're using and of
Subject: Re: Mahout on Hadoop
Harjeet I think you need to read the documentation of the code, of the
data you're using and of Hadoop. I think many of the questions you are
asking are answerable from those resources.
The userIdFile is not your ratings file. It is a file full of user IDs
to recommen
Harjeet I think you need to read the documentation of the code, of the
data you're using and of Hadoop. I think many of the questions you are
asking are answerable from those resources.
The userIdFile is not your ratings file. It is a file full of user IDs
to recommend for.
On Tue, Dec 8, 2009 at
This is not the ratings file, ua.base is the ratings file. Check the
README file in the data set.
I think you can see that because this file has 5 fields, not 3, and
has "F" -- what user or item ID would that be?
On Tue, Dec 8, 2009 at 6:24 AM, Rajpal, Harjeet Kumar
wrote:
> This is format of use
This is for me is confusing. I tried to figure out solution
but could not.:(
-Original Message-
From: Rajpal, Harjeet Kumar [mailto:harjeet.ku...@honeywell.com]
Sent: Tuesday, December 08, 2009 12:02 PM
To: mahout-user@lucene.apache.org
Subject: RE: Mahout on Hadoop
I mean if I am right
...@honeywell.com]
Sent: Tuesday, December 08, 2009 11:55 AM
To: mahout-user@lucene.apache.org
Subject: RE: Mahout on Hadoop
This is format of users.dat file from group lens data.
"1,F,1,10,48067" . format of rating file is right as userID,itemID,pref.
Bin/hadoop jar mahout-examples-0.3-SN
rg
Subject: Re: Mahout on Hadoop
Yes, use the GroupLens 100K data set.
I don't know what data file you are passing, but this does not appear
to be a valid preference file, what is this? Should be
userID,itemID,pref. You may need to transform the input.
On Mon, Dec 7, 2009 at 4:14 PM, Rajpal
1,F,1,10,48067" .
>
> If you can provide some demo data. That will be helpful.
> Best Regards,
> Harjeet Kumar
>
> -Original Message-
> From: Sean Owen [mailto:sro...@gmail.com]
> Sent: Monday, December 07, 2009 3:17 PM
> To: mahout-user@lucene.apache.org
>
uot; .
If you can provide some demo data. That will be helpful.
Best Regards,
Harjeet Kumar
-Original Message-
From: Sean Owen [mailto:sro...@gmail.com]
Sent: Monday, December 07, 2009 3:17 PM
To: mahout-user@lucene.apache.org
Subject: Re: Mahout on Hadoop
Yes, that's right, you want
> Sent: Monday, December 07, 2009 1:02 PM
> To: mahout-user@lucene.apache.org
> Subject: Re: Mahout on Hadoop
>
> Caused by: java.lang.ClassNotFoundException:
> org.uncommons.maths.random.MersenneTwisterRNG
>
> You aren't bundling the dependent class files with the .jar file used
&
...@gmail.com]
Sent: Monday, December 07, 2009 1:02 PM
To: mahout-user@lucene.apache.org
Subject: Re: Mahout on Hadoop
Caused by: java.lang.ClassNotFoundException:
org.uncommons.maths.random.MersenneTwisterRNG
You aren't bundling the dependent class files with the .jar file used
with the Hadoop job.
O
Caused by: java.lang.ClassNotFoundException:
org.uncommons.maths.random.MersenneTwisterRNG
You aren't bundling the dependent class files with the .jar file used
with the Hadoop job.
On Mon, Dec 7, 2009 at 7:01 AM, Rajpal, Harjeet Kumar
wrote:
> Hi Sean,
>
> Sorry for Delay in Reply.
> I got the
derJob.jav
a:178)
Best Regards,
Harjeet Kumar Rajpal
-Original Message-
From: Sean Owen [mailto:sro...@gmail.com]
Sent: Friday, December 04, 2009 1:38 PM
To: mahout-user@lucene.apache.org
Subject: Re: Mahout on Hadoop
Open RecommenderMapper.java. See that it contains "import
org.apach
is same.
> What can be the possible other reason?
>
> Best Regards,
> Harjeet Kumar Rajpal
>
> -Original Message-
> From: Sean Owen [mailto:sro...@gmail.com]
> Sent: Thursday, December 03, 2009 9:52 PM
> To: mahout-user@lucene.apache.org
> Subject: Re: Mahout on Had
@lucene.apache.org
Subject: Re: Mahout on Hadoop
Oh wait, no, now I see the full stack trade. Yes that looks like the
same error. Maybe you still have the old compiled code.
RecommenderMapper now implements mapred.Mapper so that should not
happen.
On Thu, Dec 3, 2009 at 4:18 PM, Rajpal, Harjeet Kumar
wrote
Oh wait, no, now I see the full stack trade. Yes that looks like the
same error. Maybe you still have the old compiled code.
RecommenderMapper now implements mapred.Mapper so that should not
happen.
On Thu, Dec 3, 2009 at 4:18 PM, Rajpal, Harjeet Kumar
wrote:
> Yes, I am using Hadoop 0.20.1 . wha
Yes, I am using Hadoop 0.20.1 . what can be reson for this error
-Original Message-
From: Sean Owen [mailto:sro...@gmail.com]
Sent: Thursday, December 03, 2009 9:37 PM
To: mahout-user@lucene.apache.org
Subject: Re: Mahout on Hadoop
That's not the same error. I don't see tha
That's not the same error. I don't see that. Are you using 0.20.1?
works for me at least.
On Thu, Dec 3, 2009 at 3:54 PM, Rajpal, Harjeet Kumar
wrote:
> Hi Sean,
> I tried that.
> But the error is same as below
>
.jav
a:178)
Thanks and Regards,
Harjeet Kumar Rajpal
-Original Message-
From: Sean Owen [mailto:sro...@gmail.com]
Sent: Thursday, December 03, 2009 9:02 PM
To: mahout-user@lucene.apache.org
Subject: Re: Mahout on Hadoop
Sounds like a server problem, but I am able to access it now.
In any
Sounds like a server problem, but I am able to access it now.
In any event, I'm just saying update the code from SVN. That's all.
On Thu, Dec 3, 2009 at 3:25 PM, Rajpal, Harjeet Kumar
wrote:
> Hi Sean,
> I am unable to access https://issues.apache.org/jira/browse/MAHOUT-143
> It shows could not
, December 03, 2009 8:17 PM
To: mahout-user@lucene.apache.org
Subject: Re: Mahout on Hadoop
You can try the code again. I updated it to use the old pre-0.20.x
APIs, and should be OK now. It works with 0.20.x though.
On Tue, Dec 1, 2009 at 7:16 AM, Sean Owen wrote:
> Yes, same error, really.
You can try the code again. I updated it to use the old pre-0.20.x
APIs, and should be OK now. It works with 0.20.x though.
On Tue, Dec 1, 2009 at 7:16 AM, Sean Owen wrote:
> Yes, same error, really. It expects an object that implements the old
> deprecated APIs, when using the new ones:
> org.ap
Yes, same error, really. It expects an object that implements the old
deprecated APIs, when using the new ones:
org.apache.hadoop.mapred.Mapper. Unless I am missing something very
big, yes, 0.20.x seems to have quite a critical problem.
These jobs are the "canaries" from the project testing out us
and regards,
Harjeet Kumar Rajpal
-Original Message-
From: Sean Owen [mailto:sro...@gmail.com]
Sent: Saturday, November 28, 2009 5:13 PM
To: mahout-user@lucene.apache.org
Subject: Re: Mahout on Hadoop
Yeah, this is an issue with Hadoop. You can see that when using the
new API, it's
Yes this code is using new 0.20.x APIs, it will not work with prior
versions (either).
On Mon, Nov 30, 2009 at 8:30 AM, Rajpal, Harjeet Kumar
wrote:
> Hi,
> I tried with Hadoop 0.19.2 also
> Error is again following
>
@lucene.apache.org
Subject: RE: Mahout on Hadoop
Hi,
Thanks for reply.
I tried mahout with Hadoop 0.18.3 now following error occurs
Command is:
hadoopad...@ie11dtxpj9k2c1s ~/hadoop-0.18.3
$ bin/hadoop jar mahout-examples-0.2-SNAPSHOT.job
org.apache.mahout.cf.taste.hadoop.RecommenderJob
regards,
Harjeet Kumar Rajpal
-Original Message-
From: Sean Owen [mailto:sro...@gmail.com]
Sent: Saturday, November 28, 2009 5:13 PM
To: mahout-user@lucene.apache.org
Subject: Re: Mahout on Hadoop
Yeah, this is an issue with Hadoop. You can see that when using the
new API, it's still lo
Not quite, it should be fine on 0.20.x. Most of the code uses the old
0.19.x APIs, but they still exist.
The problem is this bit of the code is using the newer APIs, but,
there seems to be a bug in there. It complains that the job isn't
using the old APIs, when using the new APIs.
On Sat, Nov 28,
Correct me if I'm wrong but I think you're using a newer version of
hadoop (0.20 or newer) than what mahout currently supports (0.18.3 or
0.19 I believe). The difference is in the mapred / mapreduce APIs.
Hope this helps
Sent from my iPhone
On Nov 28, 2009, at 6:16 AM, "Rajpal, Harjeet Kum
Yeah, this is an issue with Hadoop. You can see that when using the
new API, it's still looking for the old interfaces
(org.apache.hadoop.mapred.OutputFormat). I have also been waiting for
Hadoop to fix this.
On Sat, Nov 28, 2009 at 11:16 AM, Rajpal, Harjeet Kumar
wrote:
> Hi,
>
> I am a newbie
Hi,
I am a newbie to Hadoop and Mahout. I have configured Hadoop on my
machine and tried to run mahout on this.
I tried following command.
$ bin/hadoop jar mahout-core-0.2-SNAPSHOT.job
org.apache.mahout.cf.taste.hadoop.RecommenderJob org.
apache.mahout.cf.taste.impl.recommender.slopeone.Slop
;> >> fails because something in Hadoop expects 0.19 APIs. Seems like a bug
>> and
>> >> I
>> >> am waiting on a fix.
>>
>
>
>
> --
> Ted Dunning, CTO
> DeepDyve
>
>
--
View this message in context:
http://www.nabble.com/Running-mahout-on-hadoop-tp25910380p25981692.html
Sent from the Mahout User List mailing list archive at Nabble.com.
Oh, gawd how did I not put that together... SVD got me thinking of
algorithms not infrastructure. No the thing I committed today does not
resolve the problem. It's a Hadoop issue, I'm sure.
On Tue, Oct 20, 2009 at 8:06 PM, Ted Dunning wrote:
> SVN?
>
> On Tue, Oct 20, 2009 at 11:57 AM, Sean Owen
SVN?
On Tue, Oct 20, 2009 at 11:57 AM, Sean Owen wrote:
> What do you mean by svd? not sure what you are referring to.
>
> On Tue, Oct 20, 2009 at 7:47 PM, jamborta wrote:
> >
> > thanks. I saw there is a new version on svd. did you manage to solve the
> > problem?
> >
> >
> >
> > srowen wrote:
What do you mean by svd? not sure what you are referring to.
On Tue, Oct 20, 2009 at 7:47 PM, jamborta wrote:
>
> thanks. I saw there is a new version on svd. did you manage to solve the
> problem?
>
>
>
> srowen wrote:
>>
>> Yeah you see the same problem I do. If you use the Hadoop 0.20 API here
m data/data/all_data.data -f data/data/all_data.data -o /output
>
> I'm not sure about what I should put for userIdFile because userids are
> already in the dataModelFile, at least that's how your input worked
> before.
>
> thanks a lot for your help,
>
> Tamas
&
+1 for separate but integrated.
The output of the off-line computations is usable for non-Taste applications
as well and Taste should be open enough to accept other kinds of off-line
input.
On Thu, Oct 15, 2009 at 1:21 PM, Sean Owen wrote:
> I think it must be a separate implementation. Both go
I think it must be a separate implementation. Both goals are important but
can't be achieved with one implementation.
On Oct 15, 2009 11:38 AM, "Gökhan Çapan" wrote:
Ok, I also wonder what you think about the type of that implementation.
-Will it be an extesion to Taste? I mean Taste's current
Ok, I also wonder what you think about the type of that implementation.
-Will it be an extesion to Taste? I mean Taste's current implementation will
remain same, also that will be added as an extra option.
-Or do you plan to migrate Taste to that style?
I am asking because I am also working on im
Agree, and no that does not exist yet. I suppose I have temporarily paused
thinking about it until 0.20.x sorts out these issues.
On Oct 15, 2009 11:21 AM, "Gökhan Çapan" wrote:
Sorry, i've sent last post accidently.
The question was not about which version of hadoop it uses.
Let me explain,
I t
Sorry, i've sent last post accidently.
The question was not about which version of hadoop it uses.
Let me explain,
I think we all agree that item based recommendation is a 2 step process.
1-compute item-item similarities
2-create recommendations to a specific user for an item
And, 1st step can be
I mean,
On Thu, Oct 15, 2009 at 9:08 PM, Sean Owen wrote:
> Meaning using the 0.19 API? It did and I updated it but have hit the
> problem
> I mention. I am reluctant to move backwards if a fix is coming though I am
> increasingly concerned about this.
>
> On Oct 15, 2009 10:52 AM, "Gökhan Çapan
Meaning using the 0.19 API? It did and I updated it but have hit the problem
I mention. I am reluctant to move backwards if a fix is coming though I am
increasingly concerned about this.
On Oct 15, 2009 10:52 AM, "Gökhan Çapan" wrote:
I also want to ask something about topic. Does Taste have a m
gt; 10 -m data/data/all_data.data -f data/data/all_data.data -o /output
>
> I'm not sure about what I should put for userIdFile because userids are
> already in the dataModelFile, at least that's how your input worked before.
>
> thanks a lot for your help,
>
> Tamas
>
this message in context:
http://www.nabble.com/Running-mahout-on-hadoop-tp25910380p25912732.html
Sent from the Mahout User List mailing list archive at Nabble.com.
ta.data -o /output
I'm not sure about what I should put for userIdFile because userids are
already in the dataModelFile, at least that's how your input worked before.
thanks a lot for your help,
Tamas
--
View this message in context:
http://www.nabble.com/Running-mahout-on-hadoop
Yes could you be more specific at all? not sure what the issue you are
facing is.
On Thu, Oct 15, 2009 at 8:37 AM, Isabel Drost wrote:
>
> Hello jamborta,
>
> On Thu jamborta wrote:
>
>> org.apache.mahout.cf.taste.hadoop I'd be glad if someone could point
>> me towards the right direction with t
Hello jamborta,
On Thu jamborta wrote:
> org.apache.mahout.cf.taste.hadoop I'd be glad if someone could point
> me towards the right direction with this.
There just so happens to be some documentation on how to start the
taste tooling on a hadoop cluster on the wiki:
http://cwiki.apache.org/M
e.hadoop
I'd be glad if someone could point me towards the right direction with this.
thanks a lot
tamas
--
View this message in context:
http://www.nabble.com/Running-mahout-on-hadoop-tp25910380p25910380.html
Sent from the Mahout User List mailing list archive at Nabble.com.
52 matches
Mail list logo
