aws emr create-cluster --name "Test cluster ngramcount" --release-label emr-5.22.0 \
--service-role EMR_DefaultRole \
--ec2-attributes InstanceProfile=EMR_EC2_DefaultRole \
--log-uri s3://sy.log-uri.ngramcount --enable-debugging \
--instance-groups InstanceGroupType=MASTER,InstanceCount=1,InstanceType=c4.large InstanceGroupType=CORE,InstanceCount=4,InstanceType=c4.large \
--steps Type=CUSTOM_JAR,Jar=s3://sy.fcode/18645-proj3-0.1-latest.jar,Args=["-input","s3://sy.tweets10m/tweets10m.txt","-output","s3://sy.output/ngram10m","-program","ngramcount"] \
--auto-terminate


aws emr create-cluster --name "Test cluster hashtagsim" --release-label emr-5.22.0 \
--service-role EMR_DefaultRole \
--ec2-attributes InstanceProfile=EMR_EC2_DefaultRole \
--log-uri s3://sy.log-uri.ngramcount --enable-debugging \
--instance-groups InstanceGroupType=MASTER,InstanceCount=1,InstanceType=c4.large InstanceGroupType=CORE,InstanceCount=4,InstanceType=c4.large \
--steps Type=CUSTOM_JAR,Jar=s3://sy.fcode/18645-proj3-0.1-latest.jar,Args=["-input","s3://sy.tweets1m/tweets1m.txt","-output","s3://sy.output/hashtag1m","-program","hashtagsim","-tmpdir","s3://sy.tmp"] \
--auto-terminate



TMP need to be on s3


aws emr create-cluster --name "Test cluster hashtagsim" --release-label emr-5.22.0 \
--service-role EMR_DefaultRole \
--ec2-attributes InstanceProfile=EMR_EC2_DefaultRole \
--log-uri s3://sy.log-uri.hashtagsim --enable-debugging \
--instance-groups InstanceGroupType=MASTER,InstanceCount=1,InstanceType=c4.large InstanceGroupType=CORE,InstanceCount=4,InstanceType=c4.large \
--steps Type=CUSTOM_JAR,Jar=s3://sy.fcode/18645-proj3-0.1-latest.jar,Args=["-input","s3://sy.tweets1m/tweets1m.txt","-output","s3://sy.output/hashtag1m","-program","hashtagsim","-tmpdir","s3://sy.tmp"]