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 venkat.ecosystems@gmail.com
 designates 209.85.216.170 as permitted sender)
MIME-Version: 1.0
In-Reply-To: 
 <CAJwFCa20vN4Uv0qqMkHZ4yrt+KhO9Q9J7QXjdiqMQ_RTn0-Zxg@mail.gmail.com>
References: 
 <CAG1z1RbxcqYPotm_Wji35NMwBm+1nrTS3Ef2HBgQz1h9uSDtZg@mail.gmail.com>
	<CAJwFCa20vN4Uv0qqMkHZ4yrt+KhO9Q9J7QXjdiqMQ_RTn0-Zxg@mail.gmail.com>
Date: Tue, 10 Jun 2014 15:55:38 +0530
Message-ID: 
 <CAG1z1RZagsU-cRf5EUE+Hb+zLABFurWtotGFtuzjEU09-oRFug@mail.gmail.com>
Subject: Re: Naive Bayes Algorithm
From: venkata ramana <venkat.ecosystems@gmail.com>
To: user@mahout.apache.org
Content-Type: multipart/alternative; boundary=089e0149ccdec13b5a04fb78bff9

--089e0149ccdec13b5a04fb78bff9
Content-Type: text/plain; charset=UTF-8

Hi,

I am trying to do URL categorization. I have generated NB model and
deployed in web service. my NB model  able to classify on the fly url
categorization. For evaluation I have taken 80-20 (training-testing). As of
now accuracy is 62.39%.

I would like to increase the accuracy up to 70 %. Could you help me on this.

Thanks,
Venkat


On Fri, Jun 6, 2014 at 11:17 PM, Ted Dunning <ted.dunning@gmail.com> wrote:

> All,
>
> Translation for the rest of us:  1 lakh = 100,000
> So this is 2.8 million URL's.
>
> Venkat,
>
> Can you say what you were trying to do?
>
>
>
>
> On Fri, Jun 6, 2014 at 5:20 AM, venkata ramana <
> venkat.ecosystems@gmail.com>
> wrote:
>
> > Hi Mahout,
> >
> > I have crawled the 28 lacks of url s. I were able to get 62.39 % of
> > Accuracy through Naive Bayes. I am trying feature Dictionary to tweak my
> > model.
> > Could anyone please let me know some of the techniques to tweak the NB
> > Model.
> >
> >
> >
> > Thanks,
> > Venkat
> >
>

--089e0149ccdec13b5a04fb78bff9--