You are viewing a plain text version of this content. The canonical link for it is here.
Posted to user@mahout.apache.org by Lukas Vlcek <lu...@gmail.com> on 2008/03/05 08:28:34 UTC
Collective Intelligence in Action
Hi,
did anybody have a chance to read this book - Collective intelligence in
Action (http://www.manning.com/alag/)? Based on what's inside section it
seems as it can be useful for anybody who would like to get more familiar
with Lucene/Nutch/WEKA/JDM (Java Data Mining API).
Regards,
Lukas
--
http://blog.lukas-vlcek.com/
Re: Collective Intelligence in Action; Implementing an SVM
Posted by Paul Elschot <pa...@xs4all.nl>.
Op Wednesday 05 March 2008 09:10:48 schreef Isabel Drost:
> On Wednesday 05 March 2008, Lukas Vlcek wrote:
> > Based on what's inside section it
> > seems as it can be useful for anybody who would like to get more
> > familiar with Lucene/Nutch/WEKA/JDM (Java Data Mining API).
>
> I did have a look at it but did not read it through. At least the
> section about svms is pretty good for ml users - yet it did not
> explain exactly how to implement an svm.
You don't really have to implement an svm. For text purposes
this works nicely for me for small problems:
http://people.cs.uchicago.edu/~vikass/svmlin.html
I must say though that I have not tried it yet on larger a scale.
At the moment I'm toying (basteln, DE) with a system that can
feed svmlin (running as a java process) from the termvectors
of a small lucene index (450Kb).
Svmlin works as advertised, so far this problem seems to be
too easy.
But no cross validation yet, only classifying the test data.
Schoene Gruesse,
Paul Elschot
Re: Collective Intelligence in Action
Posted by Lukas Vlcek <lu...@gmail.com>.
I downloaded java source code and it looks pretty comprehensive. However, I
was not able to find anything related to Nutch in the code (may be I just
missed this) - instead there seems to be simple implementation of own
crawler. Also nothing about Hadoop. Anyway, I think I am going to look at
this book. I am particularly interested about how JDM API is used.
Lukas
On Wed, Mar 5, 2008 at 9:10 AM, Isabel Drost <ma...@isabel-drost.de> wrote:
> On Wednesday 05 March 2008, Lukas Vlcek wrote:
> > Based on what's inside section it
> > seems as it can be useful for anybody who would like to get more
> familiar
> > with Lucene/Nutch/WEKA/JDM (Java Data Mining API).
>
> I did have a look at it but did not read it through. At least the section
> about svms is pretty good for ml users - yet it did not explain exactly
> how
> to implement an svm. I cannot say anything about the other chapters.
>
> Cheers,
> Isabel
>
> --
> Everybody wants to go to heaven, but nobody wants to die.
> |\ _,,,---,,_ Web: <http://www.isabel-drost.de>
> /,`.-'`' -. ;-;;,_
> |,4- ) )-,_..;\ ( `'-'
> '---''(_/--' `-'\_) (fL) IM: <xm...@spaceboyz.net>
>
--
http://blog.lukas-vlcek.com/
Re: Collective Intelligence in Action
Posted by Isabel Drost <ap...@isabel-drost.de>.
On Wednesday 05 March 2008, Isabel Drost wrote:
> I did have a look at it but did not read it through. At least the section
> about svms is pretty good for ml users - yet it did not explain exactly how
> to implement an svm. I cannot say anything about the other chapters.
I just noticed - the book I had seen was the book on Collective Intelligence
from O'Reilly, not the one from Manning. Sorry for the confusion :(
Isabel
--
BOFH excuse #182:endothermal recalibration
|\ _,,,---,,_ Web: <http://www.isabel-drost.de>
/,`.-'`' -. ;-;;,_
|,4- ) )-,_..;\ ( `'-'
'---''(_/--' `-'\_) (fL) IM: <xm...@spaceboyz.net>
Re: Collective Intelligence in Action
Posted by Isabel Drost <ma...@isabel-drost.de>.
On Wednesday 05 March 2008, Lukas Vlcek wrote:
> Based on what's inside section it
> seems as it can be useful for anybody who would like to get more familiar
> with Lucene/Nutch/WEKA/JDM (Java Data Mining API).
I did have a look at it but did not read it through. At least the section
about svms is pretty good for ml users - yet it did not explain exactly how
to implement an svm. I cannot say anything about the other chapters.
Cheers,
Isabel
--
Everybody wants to go to heaven, but nobody wants to die.
|\ _,,,---,,_ Web: <http://www.isabel-drost.de>
/,`.-'`' -. ;-;;,_
|,4- ) )-,_..;\ ( `'-'
'---''(_/--' `-'\_) (fL) IM: <xm...@spaceboyz.net>
Re: Collective Intelligence in Action
Posted by Grant Ingersoll <gs...@apache.org>.
I have the Segaran book which is quite good and comes w/ actual code
examples. I am somewhat aware of the later book, but haven't bought
it. I am definitely interested in books that take the more practical
approach to these problems (i.e. talk about real solutions in
pseudocode or actual code versus a bunch of math formulas)
-Grant
On Mar 5, 2008, at 7:03 AM, Lukas Vlcek wrote:
> Karl,
>
> Are you talking about Programming Collective
> Intelligence<http://www.amazon.com/Programming-Collective-Intelligence-Building-Applications/dp/0596529325/
> >by
> Toby
> Segaran <http://kiwitobes.com/> or Collective Intelligence in
> Action<http://www.manning.com/alag/>by Satman Alag?
> I was asking about the second book by Satman Alag.
>
> Lukas
>
>
> On Wed, Mar 5, 2008 at 12:32 PM, Karl Wettin <ka...@gmail.com>
> wrote:
>
>> Lukas Vlcek skrev:
>>> Hi,
>>>
>>> did anybody have a chance to read this book - Collective
>>> intelligence in
>>> Action (http://www.manning.com/alag/)? Based on what's inside
>>> section it
>>> seems as it can be useful for anybody who would like to get more
>> familiar
>>> with Lucene/Nutch/WEKA/JDM (Java Data Mining API).
>>
>> I have a copy of "Programming collective intelligence". It's great.
>> All
>> math and algorithms are described with python rather than greek
>> letters.
>>
>> http://www.oreilly.com/catalog/9780596529321/
>>
>>
>>
>> karl
>>
>
>
>
> --
> http://blog.lukas-vlcek.com/
Re: Collective Intelligence in Action
Posted by Lukas Vlcek <lu...@gmail.com>.
Karl,
Are you talking about Programming Collective
Intelligence<http://www.amazon.com/Programming-Collective-Intelligence-Building-Applications/dp/0596529325/>by
Toby
Segaran <http://kiwitobes.com/> or Collective Intelligence in
Action<http://www.manning.com/alag/>by Satman Alag?
I was asking about the second book by Satman Alag.
Lukas
On Wed, Mar 5, 2008 at 12:32 PM, Karl Wettin <ka...@gmail.com> wrote:
> Lukas Vlcek skrev:
> > Hi,
> >
> > did anybody have a chance to read this book - Collective intelligence in
> > Action (http://www.manning.com/alag/)? Based on what's inside section it
> > seems as it can be useful for anybody who would like to get more
> familiar
> > with Lucene/Nutch/WEKA/JDM (Java Data Mining API).
>
> I have a copy of "Programming collective intelligence". It's great. All
> math and algorithms are described with python rather than greek letters.
>
> http://www.oreilly.com/catalog/9780596529321/
>
>
>
> karl
>
--
http://blog.lukas-vlcek.com/
Re: Collective Intelligence in Action
Posted by Lukas Vlcek <lu...@gmail.com>.
I think the source code for the "Java" (not the "Python") book looks
interesting: http://www.manning-source.com/books/alag/CIiA-src.zip
I am not able to speak for the content of the book.
Lukas
On Wed, Mar 5, 2008 at 2:42 PM, Goel, Ankur <An...@corp.aol.com> wrote:
> I did get a chance to glance at both the books -
> http://www.manning.com/alag/ and
> http://www.oreilly.com/catalog/9780596529321/.
>
> The topic list of later looks really comprehensive and the topic
> previews leave the reader asking for more.
> The only drawback as already mentioned is that the code is in Python so
> reader who doesn't know Python will face
> a little difficuly in understanding the code examples.
>
> After reading the topic list of the first book and the free chapter
> available online, I don't think the rest of the
> content would be as comprehensive at discussing each techinque as the
> second book.
>
> So I would definitely like to read the second one -
> http://www.oreilly.com/catalog/9780596529321/
>
> Does anyone have an e-copy of
> http://www.oreilly.com/catalog/9780596529321/ which can be shared ?
>
>
> -----Original Message-----
> From: Lukas Vlcek [mailto:lukas.vlcek@gmail.com]
> Sent: Wednesday, March 05, 2008 6:24 PM
> To: mahout-user@lucene.apache.org
> Subject: Re: Collective Intelligence in Action
>
> I know Toby's book (have it as well :-) but all the code is in Python.
> The later book seems to be truly Java oriented and uses JDM in some
> examples (and WEKA). All the source code can be downloaded now from the
> web page.
> This could be interesting for Mahout developers to see how to use JDM
> since we might think of it in the future.
>
> On Wed, Mar 5, 2008 at 1:36 PM, Dawid Weiss
> <da...@cs.put.poznan.pl>
> wrote:
>
> >
> > I also have Toby's book (the one Karl mentions). It is great. I'm
> > thinking such a book would be actually a nice deliverable from Mahout
> > at some point -- examples of Mahout use for solving some real-life
> > problems :)
> >
> > D.
> >
> > Karl Wettin wrote:
> > > Lukas Vlcek skrev:
> > >> Hi,
> > >>
> > >> did anybody have a chance to read this book - Collective
> > >> intelligence
> > in
> > >> Action (http://www.manning.com/alag/)? Based on what's inside
> > >> section
> > it
> > >> seems as it can be useful for anybody who would like to get more
> > familiar
> > >> with Lucene/Nutch/WEKA/JDM (Java Data Mining API).
> > >
> > > I have a copy of "Programming collective intelligence". It's great.
> > > All math and algorithms are described with python rather than greek
> letters.
> > >
> > > http://www.oreilly.com/catalog/9780596529321/
> > >
> > >
> > >
> > > karl
> >
>
>
>
> --
> http://blog.lukas-vlcek.com/
>
--
http://blog.lukas-vlcek.com/
RE: Collective Intelligence in Action
Posted by "Goel, Ankur" <An...@corp.aol.com>.
I did get a chance to glance at both the books -
http://www.manning.com/alag/ and
http://www.oreilly.com/catalog/9780596529321/.
The topic list of later looks really comprehensive and the topic
previews leave the reader asking for more.
The only drawback as already mentioned is that the code is in Python so
reader who doesn't know Python will face
a little difficuly in understanding the code examples.
After reading the topic list of the first book and the free chapter
available online, I don't think the rest of the
content would be as comprehensive at discussing each techinque as the
second book.
So I would definitely like to read the second one -
http://www.oreilly.com/catalog/9780596529321/
Does anyone have an e-copy of
http://www.oreilly.com/catalog/9780596529321/ which can be shared ?
-----Original Message-----
From: Lukas Vlcek [mailto:lukas.vlcek@gmail.com]
Sent: Wednesday, March 05, 2008 6:24 PM
To: mahout-user@lucene.apache.org
Subject: Re: Collective Intelligence in Action
I know Toby's book (have it as well :-) but all the code is in Python.
The later book seems to be truly Java oriented and uses JDM in some
examples (and WEKA). All the source code can be downloaded now from the
web page.
This could be interesting for Mahout developers to see how to use JDM
since we might think of it in the future.
On Wed, Mar 5, 2008 at 1:36 PM, Dawid Weiss
<da...@cs.put.poznan.pl>
wrote:
>
> I also have Toby's book (the one Karl mentions). It is great. I'm
> thinking such a book would be actually a nice deliverable from Mahout
> at some point -- examples of Mahout use for solving some real-life
> problems :)
>
> D.
>
> Karl Wettin wrote:
> > Lukas Vlcek skrev:
> >> Hi,
> >>
> >> did anybody have a chance to read this book - Collective
> >> intelligence
> in
> >> Action (http://www.manning.com/alag/)? Based on what's inside
> >> section
> it
> >> seems as it can be useful for anybody who would like to get more
> familiar
> >> with Lucene/Nutch/WEKA/JDM (Java Data Mining API).
> >
> > I have a copy of "Programming collective intelligence". It's great.
> > All math and algorithms are described with python rather than greek
letters.
> >
> > http://www.oreilly.com/catalog/9780596529321/
> >
> >
> >
> > karl
>
--
http://blog.lukas-vlcek.com/
Re: Collective Intelligence in Action
Posted by Lukas Vlcek <lu...@gmail.com>.
I know Toby's book (have it as well :-) but all the code is in Python. The
later book seems to be truly Java oriented and uses JDM in some examples
(and WEKA). All the source code can be downloaded now from the web page.
This could be interesting for Mahout developers to see how to use JDM since
we might think of it in the future.
On Wed, Mar 5, 2008 at 1:36 PM, Dawid Weiss <da...@cs.put.poznan.pl>
wrote:
>
> I also have Toby's book (the one Karl mentions). It is great. I'm thinking
> such
> a book would be actually a nice deliverable from Mahout at some point --
> examples of Mahout use for solving some real-life problems :)
>
> D.
>
> Karl Wettin wrote:
> > Lukas Vlcek skrev:
> >> Hi,
> >>
> >> did anybody have a chance to read this book - Collective intelligence
> in
> >> Action (http://www.manning.com/alag/)? Based on what's inside section
> it
> >> seems as it can be useful for anybody who would like to get more
> familiar
> >> with Lucene/Nutch/WEKA/JDM (Java Data Mining API).
> >
> > I have a copy of "Programming collective intelligence". It's great. All
> > math and algorithms are described with python rather than greek letters.
> >
> > http://www.oreilly.com/catalog/9780596529321/
> >
> >
> >
> > karl
>
--
http://blog.lukas-vlcek.com/
Re: Collective Intelligence in Action
Posted by Dawid Weiss <da...@cs.put.poznan.pl>.
I also have Toby's book (the one Karl mentions). It is great. I'm thinking such
a book would be actually a nice deliverable from Mahout at some point --
examples of Mahout use for solving some real-life problems :)
D.
Karl Wettin wrote:
> Lukas Vlcek skrev:
>> Hi,
>>
>> did anybody have a chance to read this book - Collective intelligence in
>> Action (http://www.manning.com/alag/)? Based on what's inside section it
>> seems as it can be useful for anybody who would like to get more familiar
>> with Lucene/Nutch/WEKA/JDM (Java Data Mining API).
>
> I have a copy of "Programming collective intelligence". It's great. All
> math and algorithms are described with python rather than greek letters.
>
> http://www.oreilly.com/catalog/9780596529321/
>
>
>
> karl
Re: Collective Intelligence in Action
Posted by Karl Wettin <ka...@gmail.com>.
Lukas Vlcek skrev:
> Hi,
>
> did anybody have a chance to read this book - Collective intelligence in
> Action (http://www.manning.com/alag/)? Based on what's inside section it
> seems as it can be useful for anybody who would like to get more familiar
> with Lucene/Nutch/WEKA/JDM (Java Data Mining API).
I have a copy of "Programming collective intelligence". It's great. All
math and algorithms are described with python rather than greek letters.
http://www.oreilly.com/catalog/9780596529321/
karl