Code: Select all
!apt-get install openjdk-8-jdk-headless -qq > /dev/null
!wget -q http://apache.osuosl.org/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
Code: Select all
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"
Code: Select all
import findspark
findspark.init()
from pyspark.sql import SparkSession
spark = SparkSession.builder.master("local[*]").getOrCreate()
Code: Select all
/content/spark-2.4.5-bin-hadoop2.7/python/pyspark/java_gateway.py in _launch_gateway(conf, insecure)
106
107 if not os.path.isfile(conn_info_file):
--> 108 raise Exception("Java gateway process exited before sending its port number")
109
110 with open(conn_info_file, "rb") as info:
Exception: Java gateway process exited before sending its port number
Mobile version