'Re: [Wekalist] Data correlation with WEKA'

[prev in list] [next in list] [prev in thread] [next in thread] 

List:       wekalist
Subject:    Re: [Wekalist] Data correlation with WEKA
From:       Eibe Frank <eibe.frank () waikato ! ac ! nz>
Date:       2018-05-29 9:29:48
Message-ID: f0d543b40e632d658be16dcbd005fe68 () mail ! gmail ! com
[Download RAW message or body]

[Attachment #2 (multipart/alternative)]

What kind of network are you planning to use? If you think a multi-layer
perceptron with one hidden layer is sufficient, consider using
MLPRegressor. It has a ridge parameter that you can adjust (ideally, on an
exponential scale) to combat overfitting.

If the number of hidden units is tuned properly, and the ridge parameter
set appropriately, any additional benefit from external attribute selection
is unlikely to be substantial unless you have an extreme number of
attributes. I would concentrate on optimising these parameters. You can use
MultiSearch or GridSearch to tune them.

Cheers,

Eibe

*From:* wekalist-bounces@list.waikato.ac.nz <
wekalist-bounces@list.waikato.ac.nz> *On Behalf Of *Juan Sebastian Mejia
*Sent:* Sunday, 27 May 2018 4:23 AM
*To:* Weka machine learning workbench list. <wekalist@list.waikato.ac.nz>
*Subject:* [Wekalist] Data correlation with WEKA

Hello everyone, I'm new using WEKA. I have some daily meteorological data
such as maximum temperature, minimum temperature, wind speed, relative
humidity, cloudiness, hours of solar brightness, precipitation and solar
radiation. I am going to make the prediction of solar radiation with
artificial neural networks, that is why I need to find the correlation of
the other meteorological variables with respect to the solar radiation and
thus use those most relevant variables as inputs of the prediction model,
to obtain better results.

How can I find the correlation of the data in WEKA? What methods can I use?
whether they are classifiers or clusters. Finally, how can I interpret the
results obtained by the methods used? because I have done some tests with
classifiers but unfortunately I have not been able to understand the
results obtained.

Thanks for your help.

[Attachment #5 (text/html)]

<html><head><meta http-equiv="Content-Type" content="text/html; charset=utf-8"><meta \
name="Generator" content="Microsoft Word 15 (filtered medium)"><style><!-- /* Font \
Definitions */ @font-face
	{font-family:"Cambria Math";
	panose-1:2 4 5 3 5 4 6 3 2 4;}
@font-face
	{font-family:Calibri;
	panose-1:2 15 5 2 2 2 4 3 2 4;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
	{margin:0cm;
	margin-bottom:.0001pt;
	font-size:11.0pt;
	font-family:"Calibri",sans-serif;}
a:link, span.MsoHyperlink
	{mso-style-priority:99;
	color:#0563C1;
	text-decoration:underline;}
a:visited, span.MsoHyperlinkFollowed
	{mso-style-priority:99;
	color:#954F72;
	text-decoration:underline;}
p.msonormal0, li.msonormal0, div.msonormal0
	{mso-style-name:msonormal;
	mso-margin-top-alt:auto;
	margin-right:0cm;
	mso-margin-bottom-alt:auto;
	margin-left:0cm;
	font-size:11.0pt;
	font-family:"Calibri",sans-serif;}
span.EmailStyle18
	{mso-style-type:personal-reply;
	font-family:"Calibri",sans-serif;
	color:windowtext;}
.MsoChpDefault
	{mso-style-type:export-only;
	font-family:"Calibri",sans-serif;
	mso-fareast-language:EN-US;}
@page WordSection1
	{size:612.0pt 792.0pt;
	margin:72.0pt 72.0pt 72.0pt 72.0pt;}
div.WordSection1
	{page:WordSection1;}
--></style></head><body lang="EN-NZ" link="#0563C1" vlink="#954F72"><div \
class="WordSection1"><p class="MsoNormal"><span \
style="mso-fareast-language:EN-US">What kind of network are you planning to use? If \
you think a multi-layer perceptron with one hidden layer is sufficient, consider \
using MLPRegressor. It has a ridge parameter that you can adjust (ideally, on an \
exponential scale) to combat overfitting. </span></p><p class="MsoNormal"><span \
style="mso-fareast-language:EN-US">  </span></p><p class="MsoNormal"><span \
style="mso-fareast-language:EN-US">If the number of hidden units is tuned properly, \
and the ridge parameter set appropriately, any additional benefit from external \
attribute selection is unlikely to be substantial unless you have an extreme number \
of attributes. I would concentrate on optimising these parameters. You can use \
MultiSearch or GridSearch to tune them.</span></p><p class="MsoNormal"><span \
style="mso-fareast-language:EN-US">  </span></p><p class="MsoNormal"><span \
style="mso-fareast-language:EN-US">Cheers,</span></p><p class="MsoNormal"><span \
style="mso-fareast-language:EN-US">Eibe</span></p><p class="MsoNormal"><span \
style="mso-fareast-language:EN-US">  </span></p><div \
style="border:none;border-left:solid blue 1.5pt;padding:0cm 0cm 0cm 4.0pt"><div><div \
style="border:none;border-top:solid #e1e1e1 1.0pt;padding:3.0pt 0cm 0cm 0cm"><p \
class="MsoNormal"><b><span lang="EN-US">From:</span></b><span lang="EN-US"> <a \
href="mailto:wekalist-bounces@list.waikato.ac.nz">wekalist-bounces@list.waikato.ac.nz</a> \
&lt;<a href="mailto:wekalist-bounces@list.waikato.ac.nz">wekalist-bounces@list.waikato.ac.nz</a>&gt; \
<b>On Behalf Of </b>Juan Sebastian Mejia<br><b>Sent:</b> Sunday, 27 May 2018 4:23 \
AM<br><b>To:</b> Weka machine learning workbench list. &lt;<a \
href="mailto:wekalist@list.waikato.ac.nz">wekalist@list.waikato.ac.nz</a>&gt;<br><b>Subject:</b> \
[Wekalist] Data correlation with WEKA</span></p></div></div><p class="MsoNormal">  \
</p><div><div><p class="MsoNormal">Hello everyone, I&#39;m new using WEKA. I have \
some daily meteorological data such as maximum temperature, minimum temperature, wind \
speed, relative humidity, cloudiness, hours of solar brightness, precipitation and \
solar radiation. I am going to make the prediction of solar radiation with artificial \
neural networks, that is why I need to find the correlation of the other \
meteorological variables with respect to the solar radiation and thus use those most \
relevant variables as inputs of the prediction model, to obtain better \
results.</p></div><div><p class="MsoNormal">  </p></div><div><p class="MsoNormal">How \
can I find the correlation of the data in WEKA? What methods can I use? whether they \
are classifiers or clusters. Finally, how can I interpret the results obtained by the \
methods used? because I have done some tests with classifiers but unfortunately I \
have not been able to understand the results obtained.</p></div><div><p \
class="MsoNormal">  </p></div><div><p class="MsoNormal">Thanks for your \
help.</p></div></div></div></div></body></html>

_______________________________________________
Wekalist mailing list
Send posts to: Wekalist@list.waikato.ac.nz
List info and subscription status: https://list.waikato.ac.nz/mailman/listinfo/wekalist
List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html

[prev in list] [next in list] [prev in thread] [next in thread] 