1 Day Retention v2

retention_dev_v2.ipynb

retention_dev_v2.sh

#!/bin/bash

if [[ -z "$bucket" ]]; then
    echo "Missing arguments!" 1>&2
    exit 1
fi

cd /tmp
git clone https://github.com/mozilla/telemetry-batch-view.git
cd telemetry-batch-view
sbt assembly

group=$(cat << END
subsession_start,cohort_date,day_number,channel,current_version,country,distribution_id,is_funnelcake
END
)

echo $group
spark-submit --master yarn \
             --deploy-mode client \
             --class com.mozilla.telemetry.views.GenericCountView \
             target/scala-2.11/telemetry-batch-view-1.1.jar \
             --files "s3://net-mozaws-prod-us-west-2-pipeline-analysis/amiyaguchi/retention_intermediate/cleaned/v2" \
             --submission-date-col "submission_date" \
             --count-column "client_id" \
             --select "*, date_format(subsession_start, 'yyyyMMdd') as submission_date" \
             --grouping-columns "$group" \
             --where "client_id IS NOT NULL" \
             --output "$bucket/retention_dev" \
	     --version "v2"