Last active
April 15, 2023 15:07
-
-
Save aolwas/53f851d0ac8aa4057cf51fe5bc224d6d to your computer and use it in GitHub Desktop.
Pyspark env setup
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 | |
# This snippet install pyspark and necessary jar dependendies inside a active python environment. | |
# | |
# Using conda: | |
# [Optional] install mambaforge (https://github.com/conda-forge/miniforge)"; exit 1;} | |
# [Optional] mamba create -n MY_ENV python=3.10 pyspark=3.3.2 | |
# conda activate MY_ENV | |
# | |
# Using venv | |
# [Optional] python -m venv venv | |
# source ./venv/bin/activate | |
# [Optional] pip install pyspark==3.3.2 | |
SPARK_EXTRAS_PREFIX=$(python -c 'import site; print(site.getsitepackages().pop())')/pyspark/jars/ | |
HADOOP_AWS_VERSION=3.3.1 | |
JODA_TIME_VERSION=2.12.0 | |
AWS_SDK_VERSION=1.11.999 | |
DELTA_IO_VERSION=2.3.0 | |
DELTA_SCALA_VERSION=2.12 | |
wget -P ${SPARK_EXTRAS_PREFIX} https://repo1.maven.org/maven2/org/apache/hadoop/hadoop-aws/${HADOOP_AWS_VERSION}/hadoop-aws-${HADOOP_AWS_VERSION}.jar | |
wget -P ${SPARK_EXTRAS_PREFIX} https://repo1.maven.org/maven2/joda-time/joda-time/${JODA_TIME_VERSION}/joda-time-${JODA_TIME_VERSION}.jar | |
wget -P ${SPARK_EXTRAS_PREFIX} https://repo1.maven.org/maven2/com/amazonaws/aws-java-sdk/${AWS_SDK_VERSION}/aws-java-sdk-${AWS_SDK_VERSION}.jar | |
wget -P ${SPARK_EXTRAS_PREFIX} https://repo1.maven.org/maven2/com/amazonaws/aws-java-sdk-core/${AWS_SDK_VERSION}/aws-java-sdk-core-${AWS_SDK_VERSION}.jar | |
wget -P ${SPARK_EXTRAS_PREFIX} https://repo1.maven.org/maven2/com/amazonaws/aws-java-sdk-s3/${AWS_SDK_VERSION}/aws-java-sdk-s3-${AWS_SDK_VERSION}.jar | |
wget -P ${SPARK_EXTRAS_PREFIX} https://repo1.maven.org/maven2/com/amazonaws/aws-java-sdk-kms/${AWS_SDK_VERSION}/aws-java-sdk-kms-${AWS_SDK_VERSION}.jar | |
wget -P ${SPARK_EXTRAS_PREFIX} https://repo1.maven.org/maven2/com/amazonaws/aws-java-sdk-dynamodb/${AWS_SDK_VERSION}/aws-java-sdk-dynamodb-${AWS_SDK_VERSION}.jar | |
wget -P ${SPARK_EXTRAS_PREFIX} https://repo1.maven.org/maven2/io/delta/delta-core_${DELTA_SCALA_VERSION}/${DELTA_IO_VERSION}/delta-core_${DELTA_SCALA_VERSION}-${DELTA_IO_VERSION}.jar | |
wget -P ${SPARK_EXTRAS_PREFIX} https://repo1.maven.org/maven2/io/delta/delta-storage/${DELTA_IO_VERSION}/delta-storage-${DELTA_IO_VERSION}.jar |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment