<?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 Workflow Pipeline in Azure Databrick is throwing error for EventHubsSourceProvider could not be instantiated in Data Engineering</title>
    <link>https://community.databricks.com/t5/data-engineering/workflow-pipeline-in-azure-databrick-is-throwing-error-for/m-p/19551#M13124</link>
    <description>&lt;P&gt;I am using the sample code which is available in getting start tutorial. And it is simple read the json file and move in another table. But it is throwing error related to EventHubsSourceProvider&amp;nbsp;&lt;/P&gt;</description>
    <pubDate>Thu, 26 May 2022 09:18:24 GMT</pubDate>
    <dc:creator>PawanShukla</dc:creator>
    <dc:date>2022-05-26T09:18:24Z</dc:date>
    <item>
      <title>Workflow Pipeline in Azure Databrick is throwing error for EventHubsSourceProvider could not be instantiated</title>
      <link>https://community.databricks.com/t5/data-engineering/workflow-pipeline-in-azure-databrick-is-throwing-error-for/m-p/19551#M13124</link>
      <description>&lt;P&gt;I am using the sample code which is available in getting start tutorial. And it is simple read the json file and move in another table. But it is throwing error related to EventHubsSourceProvider&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Thu, 26 May 2022 09:18:24 GMT</pubDate>
      <guid>https://community.databricks.com/t5/data-engineering/workflow-pipeline-in-azure-databrick-is-throwing-error-for/m-p/19551#M13124</guid>
      <dc:creator>PawanShukla</dc:creator>
      <dc:date>2022-05-26T09:18:24Z</dc:date>
    </item>
    <item>
      <title>Re: Workflow Pipeline in Azure Databrick is throwing error for EventHubsSourceProvider could not be instantiated</title>
      <link>https://community.databricks.com/t5/data-engineering/workflow-pipeline-in-azure-databrick-is-throwing-error-for/m-p/19553#M13126</link>
      <description>&lt;P&gt;Cluster is creating on the fly...not in interactive cluster&lt;/P&gt;&lt;P&gt;and code is :&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;import dlt&lt;/P&gt;&lt;P&gt;from pyspark.sql.functions import *&lt;/P&gt;&lt;P&gt;from pyspark.sql.types import *&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;json_path = "/databricks-datasets/wikipedia-datasets/data-001/clickstream/raw-uncompressed-json/2015_2_clickstream.json"&lt;/P&gt;&lt;P&gt;@dlt.table(&lt;/P&gt;&lt;P&gt;&amp;nbsp;comment="The raw wikipedia clickstream dataset, ingested from /databricks-datasets."&lt;/P&gt;&lt;P&gt;)&lt;/P&gt;&lt;P&gt;def clickstream_raw():&lt;/P&gt;&lt;P&gt;&amp;nbsp;return (spark.read.format("json").load(json_path))&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;@dlt.table(&lt;/P&gt;&lt;P&gt;&amp;nbsp;comment="Wikipedia clickstream data cleaned and prepared for analysis."&lt;/P&gt;&lt;P&gt;)&lt;/P&gt;&lt;P&gt;@dlt.expect("valid_current_page_title", "current_page_title IS NOT NULL")&lt;/P&gt;&lt;P&gt;@dlt.expect_or_fail("valid_count", "click_count &amp;gt; 0")&lt;/P&gt;&lt;P&gt;def clickstream_prepared():&lt;/P&gt;&lt;P&gt;&amp;nbsp;return (&lt;/P&gt;&lt;P&gt;&amp;nbsp;&amp;nbsp;dlt.read("clickstream_raw")&lt;/P&gt;&lt;P&gt;&amp;nbsp;&amp;nbsp;&amp;nbsp;.withColumn("click_count", expr("CAST(n AS INT)"))&lt;/P&gt;&lt;P&gt;&amp;nbsp;&amp;nbsp;&amp;nbsp;.withColumnRenamed("curr_title", "current_page_title")&lt;/P&gt;&lt;P&gt;&amp;nbsp;&amp;nbsp;&amp;nbsp;.withColumnRenamed("prev_title", "previous_page_title")&lt;/P&gt;&lt;P&gt;&amp;nbsp;&amp;nbsp;&amp;nbsp;.select("current_page_title", "click_count", "previous_page_title")&lt;/P&gt;&lt;P&gt;&amp;nbsp;)&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;@dlt.table(&lt;/P&gt;&lt;P&gt;&amp;nbsp;comment="A table containing the top pages linking to the Apache Spark page."&lt;/P&gt;&lt;P&gt;)&lt;/P&gt;&lt;P&gt;def top_spark_referrers():&lt;/P&gt;&lt;P&gt;&amp;nbsp;return (&lt;/P&gt;&lt;P&gt;&amp;nbsp;&amp;nbsp;dlt.read("clickstream_prepared")&lt;/P&gt;&lt;P&gt;&amp;nbsp;&amp;nbsp;&amp;nbsp;.filter(expr("current_page_title == 'Apache_Spark'"))&lt;/P&gt;&lt;P&gt;&amp;nbsp;&amp;nbsp;&amp;nbsp;.withColumnRenamed("previous_page_title", "referrer")&lt;/P&gt;&lt;P&gt;&amp;nbsp;&amp;nbsp;&amp;nbsp;.sort(desc("click_count"))&lt;/P&gt;&lt;P&gt;&amp;nbsp;&amp;nbsp;&amp;nbsp;.select("referrer", "click_count")&lt;/P&gt;&lt;P&gt;&amp;nbsp;&amp;nbsp;&amp;nbsp;.limit(10)&lt;/P&gt;&lt;P&gt;&amp;nbsp;) &lt;/P&gt;</description>
      <pubDate>Mon, 06 Jun 2022 18:41:37 GMT</pubDate>
      <guid>https://community.databricks.com/t5/data-engineering/workflow-pipeline-in-azure-databrick-is-throwing-error-for/m-p/19553#M13126</guid>
      <dc:creator>PawanShukla</dc:creator>
      <dc:date>2022-06-06T18:41:37Z</dc:date>
    </item>
  </channel>
</rss>

