<?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>Question Re: Auto classification Error.Impossible to deal non boolean target variable .multiple categories found in Technology Q&amp;A</title>
    <link>https://community.sap.com/t5/technology-q-a/auto-classification-error-impossible-to-deal-non-boolean-target-variable/qaa-p/342757#M14901</link>
    <description>&lt;P&gt;Thank you so much Abdel for the clarification and detailed explanation. &lt;/P&gt;&lt;P&gt;I agree we would then have to use one of the two methods mentioned above to work around this problem . &lt;/P&gt;&lt;P&gt;I have done multi class based classification using R. ....is there a way we can incorporate this in our SAP PA ...I know we can call R libraries and functions but I would like to see a step by step document which depicts all the processes involved in invoking R via SAP PA. &lt;/P&gt;&lt;P&gt;Thank you again !&lt;/P&gt;</description>
    <pubDate>Thu, 12 Jan 2017 03:57:31 GMT</pubDate>
    <dc:creator>Former Member</dc:creator>
    <dc:date>2017-01-12T03:57:31Z</dc:date>
    <item>
      <title>Auto classification Error.Impossible to deal non boolean target variable .multiple categories found</title>
      <link>https://community.sap.com/t5/technology-q-a/auto-classification-error-impossible-to-deal-non-boolean-target-variable/qaq-p/342755</link>
      <description>&lt;P&gt;Hi Team &lt;/P&gt;&lt;P&gt;I am trying to classify data into multiple categories using Autoclassification in SAP PA 3.0 . &lt;/P&gt;&lt;P&gt;When I use only two categories the classification is done correctly but when the target variable categories increases the Expert analytics as well as automated analytics gives error. &lt;/P&gt;&lt;P&gt;I am not aware of any limitations on SAP PA to classify data into multiple categories. I believe I am doing somehting wrong . Please help me with this issue. &lt;/P&gt;</description>
      <pubDate>Wed, 11 Jan 2017 04:42:44 GMT</pubDate>
      <guid>https://community.sap.com/t5/technology-q-a/auto-classification-error-impossible-to-deal-non-boolean-target-variable/qaq-p/342755</guid>
      <dc:creator>Former Member</dc:creator>
      <dc:date>2017-01-11T04:42:44Z</dc:date>
    </item>
    <item>
      <title>Re: Auto classification Error.Impossible to deal non boolean target variable .multiple categories found</title>
      <link>https://community.sap.com/t5/technology-q-a/auto-classification-error-impossible-to-deal-non-boolean-target-variable/qaa-p/342756#M14900</link>
      <description>&lt;P&gt;Hi,&lt;/P&gt;&lt;P&gt;The Auto-Classification (used via Automated or Expert Analytics) is a "binary" classification and not a "multi-class" classification algorithm. Therefore, your target variable can only have 2 possible values.&lt;/P&gt;&lt;P&gt;If you want to address a "multi-class" classification scenario, you potentially have 2 strategies to choose from:&lt;/P&gt;&lt;UL&gt;&lt;LI&gt;&lt;STRONG&gt;One-vs.-rest (OvR)&lt;/STRONG&gt;&lt;/LI&gt;&lt;/UL&gt;&lt;P&gt;&lt;EM&gt;The one-vs.-rest (or one-vs.-all) strategy involves training a single classifier per class, with the samples of that class as positive samples and all other samples as negatives. This strategy requires the base classifiers to produce a real-valued confidence score for its decision, rather than just a class label; discrete class labels alone can lead to ambiguities, where multiple classes are predicted for a single sample.&lt;/EM&gt;&lt;/P&gt;&lt;UL&gt;
&lt;LI&gt;&lt;STRONG&gt;One-vs.-one (OvO)&lt;/STRONG&gt;&lt;/LI&gt;&lt;/UL&gt;&lt;P&gt;&lt;EM&gt;In the one-vs.-one, one trains K (K − 1) / 2 binary classifiers for a K-way multiclass problem; each receives the samples of a pair of classes from the original training set, and must learn to distinguish these two classes. At prediction time, a voting scheme is applied: all K (K − 1) / 2 classifiers are applied to an unseen sample and the class that got the highest number of “+1” predictions gets predicted by the combined classifier.&lt;/EM&gt;&lt;/P&gt;&lt;P&gt;You can read the following blog post I wrote a while back:&lt;/P&gt;&lt;P&gt;&lt;A href="https://blogs.sap.com/2016/03/09/how-to-handle-multiclass-classification-in-automated-analytics/" target="test_blank"&gt;https://blogs.sap.com/2016/03/09/how-to-handle-multiclass-classification-in-automated-analytics/&lt;/A&gt; &lt;/P&gt;&lt;P&gt;Regards&lt;/P&gt;&lt;P&gt;@bdel&lt;/P&gt;</description>
      <pubDate>Wed, 11 Jan 2017 07:23:52 GMT</pubDate>
      <guid>https://community.sap.com/t5/technology-q-a/auto-classification-error-impossible-to-deal-non-boolean-target-variable/qaa-p/342756#M14900</guid>
      <dc:creator>AbdelhalimDadouche</dc:creator>
      <dc:date>2017-01-11T07:23:52Z</dc:date>
    </item>
    <item>
      <title>Re: Auto classification Error.Impossible to deal non boolean target variable .multiple categories found</title>
      <link>https://community.sap.com/t5/technology-q-a/auto-classification-error-impossible-to-deal-non-boolean-target-variable/qaa-p/342757#M14901</link>
      <description>&lt;P&gt;Thank you so much Abdel for the clarification and detailed explanation. &lt;/P&gt;&lt;P&gt;I agree we would then have to use one of the two methods mentioned above to work around this problem . &lt;/P&gt;&lt;P&gt;I have done multi class based classification using R. ....is there a way we can incorporate this in our SAP PA ...I know we can call R libraries and functions but I would like to see a step by step document which depicts all the processes involved in invoking R via SAP PA. &lt;/P&gt;&lt;P&gt;Thank you again !&lt;/P&gt;</description>
      <pubDate>Thu, 12 Jan 2017 03:57:31 GMT</pubDate>
      <guid>https://community.sap.com/t5/technology-q-a/auto-classification-error-impossible-to-deal-non-boolean-target-variable/qaa-p/342757#M14901</guid>
      <dc:creator>Former Member</dc:creator>
      <dc:date>2017-01-12T03:57:31Z</dc:date>
    </item>
  </channel>
</rss>

