No subject

Mon Feb 22 19:56:25 PST 2010

Hadoop + Mahout infrastructure and documenting the setup process and<br>
the hello-world mapreduce program etc. =A0While we went through this<br>
yesterday (thanks) I feel like people will actually get to DO the<br>
things they learned later; so a written reference (new wiki page)<br>
would be great, because these questions will be asked over and over.<br>
Even better, and this is just an idea: =A0can we set up a shared AWS<br>
account so each of us doesnt have to install everything by himself? =A0I<br=
know there&#39;s the question of who pays for it, but that aside, are<br>
there technical restrictions why we could not share an account? =A0One<br>
approach would be each of us throws in $10, or perhaps theres a way to<br>
split the bills between us according to usage, or, even better we<br>
could push Noisebridge Inc to give us some allowance. =A0Getting a<br>
turnkey cloud Mahout infrastructure for Noisebridge would be H-U-G-E,<br>
even if it would not be ready in time for KDD submission. =A0Feel free<br>
to take the lead on that initiative. =A0You would go down in the history<br=
books of NB as a hero :-)<br>
Erin and Mike are already working on transforming the data, so I think<br>
we have already lots of manpower on that end.<br>
Let&#39;s tentatively plan this Sunday night to get together again. =A0Erin=
also mentioned she&#39;d like to meet again before the next Wednesday. =A0I=
can give an impromptu talk about classifiers/machine learning problem<br>
Will confirm.<br>
<div><div></div><div class=3D"h5"><br>
On Wed, May 19, 2010 at 11:38 PM, Vikram Oberoi &lt;<a href=3D"mailto:vober=
oi at">voberoi at</a>&gt; wrote:<br>
&gt; Hey folks,<br>
&gt; For those of you that came out tonight, I hope the code I walked throu=
gh and<br>
&gt; initial (albeit rough) overview of MapReduce helped. If you guys have =
&gt; questions or requests, the best way to ask would be to:<br>
&gt; a) direct an email to me over <a href=3D"mailto:ml at lists.noisebridge.n=
et">ml at</a> or...<br>
&gt; b) open an issue at the Github<br>
&gt; project:=A0<a href=3D"" target=
&gt; Both of these ways someone else might be able to answer first and ever=
&gt; will benefit from the answer, as there&#39;s a high probability that e=
&gt; will have the same questions.<br>
&gt; For next week, I&#39;m going to write a script that transforms the KDD=
&gt; in... some useful way. Your guys&#39; input on what exactly I should d=
o here is<br>
&gt; most welcome. The transformation should be involved enough that the co=
de can<br>
&gt; serve as an example for scripts you all might implement later.<br>
&gt; I&#39;ll also be taking a look at Apache Mahout (a library containing =
&gt; MapReduce implementations of numerous machine learning algorithms) and=
&gt; writing up an example of how to use it. If you have a particular algor=
&gt; that you want to apply to the dataset, check if it&#39;s in the Mahout=
&gt; and let me know.<br>
&gt; Finally, is any brainstorming/discussion about what we&#39;re doing ha=
&gt; anywhere other than the meetups? I&#39;d be happy to meet again some t=
ime before<br>
&gt; next Wednesday to hash out some ideas and run with them, as in-person<=
&gt; conversation bandwidth is *so* much higher. Alternately, we could thro=
w out<br>
&gt; ideas on the list and brainstorm over email threads. It doesn&#39;t se=
em like<br>
&gt; there&#39;s a whole lot of action on the wiki other than links to reso=
urces and<br>
&gt; TODOs. Or is there?<br>
&gt; Vikram<br>
</div></div>&gt; _______________________________________________<br>
&gt; ml mailing list<br>
&gt; <a href=3D"mailto:ml at">ml at</=
&gt; <a href=3D"" target=3D"=


More information about the ml mailing list