Mailing-List: contact user-help@mahout.apache.org; run by ezmlm
Precedence: bulk
Reply-To: user@mahout.apache.org
Received-SPF: pass (nike.apache.org: domain of mattmcclain1@gmail.com
 designates 209.85.223.170 as permitted sender)
MIME-Version: 1.0
In-Reply-To: <loom.20130508T123034-225@post.gmane.org>
References: <loom.20130508T123034-225@post.gmane.org>
From: Matthew McClain <mattmcclain1@gmail.com>
Date: Thu, 9 May 2013 07:52:56 -0500
Message-ID: 
 <CAKKDxBhgJQ7167Kp1ptq9cxczDYGAzWBdHfLe-BZPQxXT_y-RQ@mail.gmail.com>
Subject: Re: Which is the right approach to follow?
To: user@mahout.apache.org
Content-Type: multipart/alternative; boundary=089e013c6a20b4547304dc4888d8

--089e013c6a20b4547304dc4888d8
Content-Type: text/plain; charset=ISO-8859-1

Karan,
Without knowing why clustering didn't work, it's hard to say what a better
approach would be. Any other information you can give about the problem
you're working on would probably help, too. In particular, how did you come
up with your four categories? Typically, categories are not defined
directly in terms of the data, because the problem is to find the
relationship between the categories and data.

Matt


On Wed, May 8, 2013 at 5:44 AM, Karan <karansachan@gmail.com> wrote:

> Hi All,
>
> I have some numerical data in pairs say X & Y and I want to divide(cluster,
> may be) into four groups as LowX-LowY,LowX-HighY,HighX-LowY & HighX-HighY.
> I
> tried with clustering but unable to identify clusters(and i think is not
> the
> best way to achieve it). Can someone suggest any good(non-trivial) approach
> to proceed.
>
> Thanks,
> Karan
>
>

--089e013c6a20b4547304dc4888d8--