!apt-get install openjdk-8-jdk-headless -qq > /dev/null
!wget -q https://www-us.apache.org/dist/spark/spark-2.4.7/spark-2.4.7-bin-hadoop2.7.tgz
!tar xf spark-2.4.7-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-2.4.7-bin-hadoop2.7"
import findspark
findspark.init()
from pyspark.sql import SparkSession
spark = SparkSession.builder.master("local[*]").appName("spark_app").getOrCreate()
Created
September 30, 2020 12:52
-
-
Save masdeseiscaracteres/af9c915393a929e0c535a2f00af34abd to your computer and use it in GitHub Desktop.
Instalar Spark en Google Colab
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment