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 vipandey@gmail.com designates
 209.85.214.170 as permitted sender)
DomainKey-Signature: a=rsa-sha1; c=nofws;
        d=gmail.com; s=gamma;
        h=content-type:mime-version:subject:from:in-reply-to:date
         :content-transfer-encoding:message-id:references:to:x-mailer;
        b=g6DoO0MDt7nTiB7qNUs8+67N3ZPj8U8obwhlvfUh14LL1T2YsQ9M70UMwaoQpajzFM
         AyB6udduQmwVpM9BRpMv8lmVAeOP0hOG822E0iSjdtMxA1aVfasCqv5e93ybRhSeCjtr
         YoAUBRhbst/dP6DipiTunD7OHHeSPCggwXvA8=
Content-Type: text/plain; charset=us-ascii
Mime-Version: 1.0 (Apple Message framework v1082)
Subject: Re: PFPGrowth - weird output?
From: Vipul Pandey <vipandey@gmail.com>
In-Reply-To: 
 <6C870DB6C8A84F41898F05D559707F234660F6@008-AM1MPN1-012.mgdnok.nokia.com>
Date: Sat, 5 Feb 2011 09:22:10 -0800
Content-Transfer-Encoding: quoted-printable
Message-Id: <C2E710C4-F29A-4CDF-A83F-5DFAC6A03622@gmail.com>
References: <AANLkTimiZ9JBfh3GEk+SE85aG91yhsd7pdUtSoGEs+AK@mail.gmail.com>
 <6C870DB6C8A84F41898F05D559707F234660F6@008-AM1MPN1-012.mgdnok.nokia.com>
To: user@mahout.apache.org

Hey Praveen,=20

thanks for responding.

> Frquent patterns are reported per feature which is why you are seeing =
the two patterns twice. First one is for feature 1518311 and second one =
is for feature 1476937.
That's what I thought but then different support values made me dizzy!=20=


Also, it's seems like it's not just about reporting the pattern for each =
feature but for each combination of features :=20
> 22 *1476937* 720020 *1518311*
> 30 *1518311* *1476937* 720020
> 30 720020 *1518311* *1476937*
> 34 720020 *1476937* *1518311*
> 38 *1518311* 720020 *1476937*
> 42 *1476937* *1518311* 720020
Here you can see each possible permutation of the three items =
registering different support.=20


> Are you running on multi node Hadoop cluster. If so did you read all =
the output files?
I ran locally and then on a small 4 node cluster. I'm reading the parts =
file under frequentpatterns directory.

Let me try to run it on a smaller scale and get you the output soon.

Thanks!
Vipul

On Feb 3, 2011, at 6:44 PM, <praveen.peddi@nokia.com> =
<praveen.peddi@nokia.com> wrote:

> Hi Vipul,
> Frquent patterns are reported per feature which is why you are seeing =
the two patterns twice. First one is for feature 1518311 and second one =
is for feature 1476937.
>=20
> However both should have the same exact support. I am not sure why you =
have different support for the same item set. May be if you send the =
full output from Mahout as it is we could take a look.
>=20
> Are you running on multi node Hadoop cluster. If so did you read all =
the output files?
>=20
> Praveen
> ________________________________________
> From: ext Vipul Pandey [vipandey@gmail.com]
> Sent: Thursday, February 03, 2011 8:21 PM
> To: user@mahout.apache.org
> Subject: PFPGrowth - weird output?
>=20
> Hi all!
>=20
> I'm trying to run PFPgrowth on my data and this is an output I get. =
(Please
> note that I parse the output in frequentpatterns folder and generate =
this
> output with the support followed by the itemset)
>=20
> support : Itemset
> *234     1518311    1476937  *
> 235     55843184
> 238     1238079
> 244     34541
> 247     4516454
> 252     106478
> 252     670864
> *254     1476937   1518311  *
>=20
> You can see that two items are reported twice (*1518311    1476937*) =
with
> different supports.
>=20
> And below are all the occurance of these two items together .... if =
you
> notice it has all the permutations of the three items (*1476937* =
*720020* *
> 1518311*  )
>=20
> 22 *1476937* 720020 *1518311*
> 30 *1518311* *1476937* 720020
> 30 720020 *1518311* *1476937*
> 34 720020 *1476937* *1518311*
> 38 *1518311* 720020 *1476937*
> 42 *1476937* *1518311* 720020
> 234 *1518311* *1476937*
> 254 *1476937* *1518311*
>=20
> Does this mean if I have to get the support of just the the pair  =
(*1476937*
> *1518311*  ) I will have to add all of them up !?
>=20
> Even in that case ... this total comes out to *684* and if I count the
> number of co-ocurrances of these two items in the original baskets the
> support is *766*? Why's there a difference? any idea?
>=20
>=20
> Thanks!
> Vipul