Pyspark and amazon s3 integration
# Create SparkSession from builder
import pyspark
from pyspark.sql
import SparkSession spark = SparkSession.builder.master("local[6]") \ .appName('SparkByExamples.com') \ .getOrCreate()
conf = pyspark.SparkConf()
sc = pyspark.SparkContext.getOrCreate(conf=conf)
accessKeyId='AKIAYH7INJR2EIYR422G'secretAccessKey='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'
hadoopConf = sc._jsc.hadoopConfiguration()
hadoopConf.set('fs.s3a.access.key',accessKeyId)
hadoopConf.set('fs.s3a.secret.key', secretAccessKey)
s3_df=spark.read.csv('s3a://learnomate.spark/partition_zipcodes20.csv',header=True,inferSchema=True)
s3_df.show(5)
Spark submit
spark-submit –jars
C:\Users\Acer\Downloads\aws-java-sdk-1.7.4.jar,
C:\Users\Acer\Downloads\hadoop-aws-2.7.7.jar
C:\Users\Acer\PycharmProjects\DecHadoopBatch\readS3.py
