<?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 How can I remove duplicate events? in ArcGIS GeoEvent Server Questions</title>
    <link>https://community.esri.com/t5/arcgis-geoevent-server-questions/how-can-i-remove-duplicate-events/m-p/58080#M257</link>
    <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;P&gt;We're experimenting with replacing a legacy system which uses Python scripts for processing and an Oracle DB for storage with GeoEvent Server for processing and the Spatiotemporal Big Data Store for storage.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;I've been able to replicate our processing (filtering, data validation, geometry creation, etc) in GeoEvent 10.6 with one exception: detecting and removing duplicates. In Python we load data into a Pandas.Dataframe and removing duplicates is as simple as using the .drop_duplicates() method. I haven't found a way to do this in GeoEvent yet. Is it possible? Or can I somehow delete duplicate records from the Big Data Store after the events are pushed in?&lt;/P&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
    <pubDate>Fri, 18 May 2018 13:30:08 GMT</pubDate>
    <dc:creator>RyanClancy</dc:creator>
    <dc:date>2018-05-18T13:30:08Z</dc:date>
    <item>
      <title>How can I remove duplicate events?</title>
      <link>https://community.esri.com/t5/arcgis-geoevent-server-questions/how-can-i-remove-duplicate-events/m-p/58080#M257</link>
      <description>&lt;HTML&gt;&lt;HEAD&gt;&lt;/HEAD&gt;&lt;BODY&gt;&lt;P&gt;We're experimenting with replacing a legacy system which uses Python scripts for processing and an Oracle DB for storage with GeoEvent Server for processing and the Spatiotemporal Big Data Store for storage.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;I've been able to replicate our processing (filtering, data validation, geometry creation, etc) in GeoEvent 10.6 with one exception: detecting and removing duplicates. In Python we load data into a Pandas.Dataframe and removing duplicates is as simple as using the .drop_duplicates() method. I haven't found a way to do this in GeoEvent yet. Is it possible? Or can I somehow delete duplicate records from the Big Data Store after the events are pushed in?&lt;/P&gt;&lt;/BODY&gt;&lt;/HTML&gt;</description>
      <pubDate>Fri, 18 May 2018 13:30:08 GMT</pubDate>
      <guid>https://community.esri.com/t5/arcgis-geoevent-server-questions/how-can-i-remove-duplicate-events/m-p/58080#M257</guid>
      <dc:creator>RyanClancy</dc:creator>
      <dc:date>2018-05-18T13:30:08Z</dc:date>
    </item>
  </channel>
</rss>

