From 6bda5de223ed1e0d7e47a0fce17a73b7ae14e138 Mon Sep 17 00:00:00 2001 From: Laxmikant Mundhada <150781667+LakshMundhada@users.noreply.github.com> Date: Fri, 23 Feb 2024 16:47:36 +0530 Subject: [PATCH] Add files via upload --- .github/workflows/MYcft2.yaml | 56 +++++++++++++++++++++++++++++++++++ 1 file changed, 56 insertions(+) create mode 100644 .github/workflows/MYcft2.yaml diff --git a/.github/workflows/MYcft2.yaml b/.github/workflows/MYcft2.yaml new file mode 100644 index 0000000..8c988d9 --- /dev/null +++ b/.github/workflows/MYcft2.yaml @@ -0,0 +1,56 @@ +AWSTemplateFormatVersion: "2010-09-09" +Resources: + MyEMRCluster: + Type: AWS::EMR::Cluster + Properties: + Name: MyEMRCluster + ReleaseLabel: emr-7.0.0 + Applications: + - Name: Spark + Instances: + MasterInstanceGroup: + InstanceCount: 1 + InstanceType: m5.xlarge + Name: MASTER + CoreInstanceGroup: + InstanceCount: 2 + InstanceType: m5.xlarge + Name: CORE + Ec2SubnetIds: + - subnet-01b68b68cd8eb4f82 + Ec2KeyName: onekey + JobFlowRole: "EMR_EC2_DefaultRole" + ServiceRole: "EMR_DefaultRole" + + MySparkStep: + Type: AWS::EMR::Step + Properties: + Name: MySparkStep + ActionOnFailure: CONTINUE + HadoopJarStep: + Jar: command-runner.jar + Args: + - spark-submit + - --deploy-mode + - cluster + - --class + - org.apache.spark.deploy.Mysparkob + - --packages + - org.apache.spark:spark-sql-kafka-0-10_2.12:3.2.1 + - --jars + - s3://requiredfiles2323/mysql-connector-java-8.0.23.jar + - s3://requiredfiles2323/ab.py + JobFlowId: !Ref MyEMRCluster + + DataCrawler: + Type: AWS::Glue::Crawler + DependsOn: + - MyEMRCluster + - MySparkStep + Properties: + Name: data-crawler + DatabaseName: default + Targets: + S3Targets: + - Path: s3://athenabucket-231/final.parquet + Role: arn:aws:iam::963746058908:role/LabRole \ No newline at end of file