Mailing-List: contact user-help@predictionio.incubator.apache.org; run by ezmlm
Precedence: bulk
Reply-To: user@predictionio.incubator.apache.org
MIME-Version: 1.0
In-Reply-To: <CA+69RXbrzUAG8rZatmBGS1y0Vq_+eNA6K075RiF7SqXBWYq5Pw@mail.gmail.com>
References: <CAFawqDP=U3dJuSJmhE2=Ly1NgO8T7x6b2O=nDrU0MN9HeEcFog@mail.gmail.com>
 <CA+69RXbrzUAG8rZatmBGS1y0Vq_+eNA6K075RiF7SqXBWYq5Pw@mail.gmail.com>
From: Mahesh Hegde <mahesh.hegde@tracxn.com>
Date: Mon, 31 Jul 2017 14:03:42 +0530
Message-ID: <CAFawqDNUQ05+ewJ-KfAPCo0_-eK2-OtnPPps2b+oy3BeE-kkRQ@mail.gmail.com>
Subject: Re: how to Clear trained data in predictionIO 0.11.0
To: user@predictionio.incubator.apache.org
Content-Type: multipart/alternative; boundary="001a113e54c0702064055598e3b8"
archived-at: Mon, 31 Jul 2017 08:33:54 -0000

--001a113e54c0702064055598e3b8
Content-Type: text/plain; charset="UTF-8"

I retrained with new data after deleting the old event data with pio app
data-delete my_app_name , even then my query is return old label "spam" for
predicted result, which is from email spam example.

Also I tried to change the models directory used by localfs , but it looks
like its refrering to old model file and gave
error models/pio_modelAV2XQxw-3F2NATbCwlg3 file doesnt exist.

-Mahesh

On Mon, Jul 31, 2017 at 1:19 PM, Vaghawan Ojha <vaghawan781@gmail.com>
wrote:

> I think, when you retrain the model, the trained model will automatically
> change.
>
> Thanks
>
>
> On Mon, Jul 31, 2017 at 1:33 PM, Mahesh Hegde <mahesh.hegde@tracxn.com>
> wrote:
>
>> pio app delete-data deletes only event data,
>>
>> I wanted to know , how to clean the trained data.
>> I am using elasticsearch (metadata) , hbase (eventdata) and localfs(model
>> data) stack
>>
>> -Mahesh
>>
>> This email is subject to Tracxn's Email Policy
>> <https://tracxn.com/emailpolicy>
>
>
>

-- 
This email is subject to Tracxn's Email Policy 
<https://tracxn.com/emailpolicy>

--001a113e54c0702064055598e3b8
Content-Type: text/html; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

<div dir=3D"ltr">I retrained with new data after deleting the old event dat=
a with pio app data-delete my_app_name , even then my query is return old l=
abel &quot;spam&quot; for predicted result, which is from email spam exampl=
e.<div><br></div><div>Also I tried to change the models directory used by l=
ocalfs , but it looks like its refrering to old model file and gave error=
=C2=A0models/pio_modelAV2XQxw-3F2NATbCwlg3 file doesnt exist.</div><div><br=
></div><div>-Mahesh</div></div><div class=3D"gmail_extra"><br><div class=3D=
"gmail_quote">On Mon, Jul 31, 2017 at 1:19 PM, Vaghawan Ojha <span dir=3D"l=
tr">&lt;<a href=3D"mailto:vaghawan781@gmail.com" target=3D"_blank">vaghawan=
781@gmail.com</a>&gt;</span> wrote:<br><blockquote class=3D"gmail_quote" st=
yle=3D"margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div =
dir=3D"ltr">I think, when you retrain the model, the trained model will aut=
omatically change.=C2=A0<div><br></div><div>Thanks</div><div><br></div><img=
 src=3D"http://t.sidekickopen69.com/e1t/o/5/f18dQhb0S7ks8dDMPbW2n0x6l2B9gXr=
N7sKj6v5dpCFVdnscn3M2z18W63Bb_s3LvrVvW3ZBnHX1k1H6H0?si=3D5110286667350016&a=
mp;pi=3Dfd62acef-f407-4638-8e86-213b5d2d4fe7" style=3D"display:none!importa=
nt" height=3D"1" width=3D"1"></div><div class=3D"gmail_extra"><br><div clas=
s=3D"gmail_quote"><div><div class=3D"h5">On Mon, Jul 31, 2017 at 1:33 PM, M=
ahesh Hegde <span dir=3D"ltr">&lt;<a href=3D"mailto:mahesh.hegde@tracxn.com=
" target=3D"_blank">mahesh.hegde@tracxn.com</a>&gt;</span> wrote:<br></div>=
</div><blockquote class=3D"gmail_quote" style=3D"margin:0 0 0 .8ex;border-l=
eft:1px #ccc solid;padding-left:1ex"><div><div class=3D"h5"><div dir=3D"ltr=
">pio app delete-data deletes only event data,<div><br></div><div>I wanted =
to know , how to clean the trained data.</div><div>I am using elasticsearch=
 (metadata) , hbase (eventdata) and localfs(model data) stack</div><div><br=
></div><div>-Mahesh</div></div>

<br>
</div></div><font color=3D"#808080" size=3D"1">This email is subject to Tra=
cxn&#39;s <a href=3D"https://tracxn.com/emailpolicy" target=3D"_blank">Emai=
l Policy</a></font></blockquote></div><br></div>
</blockquote></div><br></div>

<br>
<font color=3D"#808080" size=3D"1">This email is subject to Tracxn&#39;s <a=
 href=3D"https://tracxn.com/emailpolicy" target=3D"_blank">Email Policy</a>=
</font>
--001a113e54c0702064055598e3b8--