<?xml version="1.0" encoding="UTF-8"?>
<!-- generator="FeedCreator 1.8" -->
<?xml-stylesheet href="https://w.ublo.ro/lib/exe/css.php?s=feed" type="text/css"?>
<rdf:RDF
    xmlns="http://purl.org/rss/1.0/"
    xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
    xmlns:slash="http://purl.org/rss/1.0/modules/slash/"
    xmlns:dc="http://purl.org/dc/elements/1.1/">
    <channel rdf:about="https://w.ublo.ro/feed.php">
        <title>Bogdan&#039;s Docs - cheat-sheets</title>
        <description></description>
        <link>https://w.ublo.ro/</link>
        <image rdf:resource="https://w.ublo.ro/_media/wiki/dokuwiki.svg" />
       <dc:date>2026-04-07T11:36:00+00:00</dc:date>
        <items>
            <rdf:Seq>
                <rdf:li rdf:resource="https://w.ublo.ro/cheat-sheets/pyspark?rev=1682080768&amp;do=diff"/>
            </rdf:Seq>
        </items>
    </channel>
    <image rdf:about="https://w.ublo.ro/_media/wiki/dokuwiki.svg">
        <title>Bogdan's Docs</title>
        <link>https://w.ublo.ro/</link>
        <url>https://w.ublo.ro/_media/wiki/dokuwiki.svg</url>
    </image>
    <item rdf:about="https://w.ublo.ro/cheat-sheets/pyspark?rev=1682080768&amp;do=diff">
        <dc:format>text/html</dc:format>
        <dc:date>2023-04-21T12:39:28+00:00</dc:date>
        <dc:creator>Anonymous (anonymous@undisclosed.example.com)</dc:creator>
        <title>pyspark</title>
        <link>https://w.ublo.ro/cheat-sheets/pyspark?rev=1682080768&amp;do=diff</link>
        <description>PySpark CheatSheet

	*  Initialize Spark session:


from pyspark.sql import SparkSession

spark = SparkSession.builder.appName(__file__).getOrCreate()


	*  Create a DataFrame:


from pyspark.sql import Row
from pyspark.sql.types import StructType, StructField. StringType, IntegerType

columns = [ &quot;programming_language&quot;, &quot;users_count&quot; ]
data = [(&quot;Python&quot;, 100000), (&quot;Java&quot;, 70000), (&quot;C++&quot;, 50000)]

rdd = spark.sparkContext.parallelize(data) # Resilient Distributed Dataset
df_v1 = rdd.toDF() # Dat…</description>
    </item>
</rdf:RDF>
