Created
April 13, 2021 06:41
-
-
Save pualien/46749519ccf788b147064871ec7057a9 to your computer and use it in GitHub Desktop.
Install Spark/Pyspark 3.1.1 with Google Cloud Storage Connector
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #!/bin/bash | |
| export CUSTOM_SPARK_VERSION="3.1.1" | |
| export CUSTOM_PYSPARK_VERSION="3.1.1" | |
| export CUSTOM_HADOOP_VERSION="3.2" | |
| export CUSTOM_HADOOP_VERSION_INDEX="3" | |
| export JAVA_HOME="/usr/lib/jvm/java-8-openjdk-amd64" | |
| export SPARK_HOME="/content/spark-$CUSTOM_SPARK_VERSION-bin-hadoop$CUSTOM_HADOOP_VERSION" | |
| export CUSTOM_SPARK_JARS="$SPARK_HOME/jars" | |
| apt-get update | |
| #install JDK java that is necessary to correct work of Pyspark and components hadoop | |
| apt-get install openjdk-8-jdk-headless -qq > /dev/null | |
| wget -q https://archive.apache.org/dist/spark/spark-$CUSTOM_SPARK_VERSION/spark-$CUSTOM_SPARK_VERSION-bin-hadoop$CUSTOM_HADOOP_VERSION.tgz | |
| tar xf spark-$CUSTOM_SPARK_VERSION-bin-hadoop$CUSTOM_HADOOP_VERSION.tgz | |
| pip install -q findspark | |
| wget -O /content/spark-$CUSTOM_SPARK_VERSION-bin-hadoop$CUSTOM_HADOOP_VERSION/jars/gcs-connector-hadoop2-latest.jar -q https://storage.googleapis.com/hadoop-lib/gcs/gcs-connector-hadoop$CUSTOM_HADOOP_VERSION_INDEX-latest.jar |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment