<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" version="2.0">
  <channel>
    <title>topic LIME in SAS without Viya in SAS Data Science</title>
    <link>https://communities.sas.com/t5/SAS-Data-Science/LIME-in-SAS-without-Viya/m-p/600900#M8032</link>
    <description>&lt;P&gt;I have a gradient boosting model that I want to to do some LIME on. But we don't have Viya yet. I have tried using python, but it seems I have to run the model in python as well, so the model I get LIME plots from is not identical to my SAS model.&amp;nbsp;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Is there a way to run LIME in sas without Viya?&lt;/P&gt;</description>
    <pubDate>Fri, 01 Nov 2019 09:06:06 GMT</pubDate>
    <dc:creator>Ullsokk</dc:creator>
    <dc:date>2019-11-01T09:06:06Z</dc:date>
    <item>
      <title>LIME in SAS without Viya</title>
      <link>https://communities.sas.com/t5/SAS-Data-Science/LIME-in-SAS-without-Viya/m-p/600900#M8032</link>
      <description>&lt;P&gt;I have a gradient boosting model that I want to to do some LIME on. But we don't have Viya yet. I have tried using python, but it seems I have to run the model in python as well, so the model I get LIME plots from is not identical to my SAS model.&amp;nbsp;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Is there a way to run LIME in sas without Viya?&lt;/P&gt;</description>
      <pubDate>Fri, 01 Nov 2019 09:06:06 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Data-Science/LIME-in-SAS-without-Viya/m-p/600900#M8032</guid>
      <dc:creator>Ullsokk</dc:creator>
      <dc:date>2019-11-01T09:06:06Z</dc:date>
    </item>
    <item>
      <title>Re: LIME in SAS without Viya</title>
      <link>https://communities.sas.com/t5/SAS-Data-Science/LIME-in-SAS-without-Viya/m-p/600987#M8033</link>
      <description>&lt;P&gt;Unfortunately to my knowledge the only way would be to write a SAS macro that performs the steps of LIME yourself. This might be a little short on details, but cover these steps cover tabular LIME:&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;1) Run an analysis to obtain the variance for each input variable&lt;/P&gt;
&lt;P&gt;2) Choose an observation which you wish to run LIME on&lt;/P&gt;
&lt;P&gt;3) Create N samples, where the observations are sampled from a Gaussian normal distribution with mean equal to the variable value for observation from 2) and the variance equal to the variance from 1)&lt;/P&gt;
&lt;P&gt;4) Calculate weights for each observation using the RBF kernel between the observation in 2) and the generated observations in 3)&lt;/P&gt;
&lt;P&gt;5) Score this new data set using the model&lt;/P&gt;
&lt;P&gt;6) Run a weighted regression on the scored data set using the output of the model as the dependent variable and the inputs of the model as the independent variables&lt;/P&gt;
&lt;P&gt;&amp;nbsp;&lt;/P&gt;
&lt;P&gt;Let me know if this helps.&lt;/P&gt;</description>
      <pubDate>Fri, 01 Nov 2019 15:03:12 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Data-Science/LIME-in-SAS-without-Viya/m-p/600987#M8033</guid>
      <dc:creator>RalphAbbey</dc:creator>
      <dc:date>2019-11-01T15:03:12Z</dc:date>
    </item>
    <item>
      <title>Re: LIME in SAS without Viya</title>
      <link>https://communities.sas.com/t5/SAS-Data-Science/LIME-in-SAS-without-Viya/m-p/601351#M8037</link>
      <description>&lt;P&gt;Thank you! It helps knowing there is no easy sollution. Looks like I will be running the models in python until we are on Viya. Implementing LIME by hand does sound a bit excessive, can't risk spending that much work on something I am not even sure I can pull off.&lt;/P&gt;</description>
      <pubDate>Mon, 04 Nov 2019 12:07:19 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Data-Science/LIME-in-SAS-without-Viya/m-p/601351#M8037</guid>
      <dc:creator>Ullsokk</dc:creator>
      <dc:date>2019-11-04T12:07:19Z</dc:date>
    </item>
  </channel>
</rss>

