Open In Colab

TemplateΒΆ

################ template to run PySpark on Colab #######################
!apt-get install openjdk-8-jdk-headless -qq > /dev/null
!wget -q https://www-us.apache.org/dist/spark/spark-2.4.5/spark-2.4.5-bin-hadoop2.7.tgz
!tar xf spark-2.4.5-bin-hadoop2.7.tgz
!pip install -q findspark
import os
os.environ["JAVA_HOME"] = "/usr/lib/jvm/java-8-openjdk-amd64"
os.environ["SPARK_HOME"] = "/content/spark-2.4.5-bin-hadoop2.7"
import findspark
findspark.init()

from pyspark.sql import SparkSession
spark = SparkSession.builder.master("local[*]").getOrCreate()
spark1 = SparkSession.builder.appName('basic').getOrCreate()
#Test must give no error
import pyspark
################ end template PySpark on Colab ##########################