Finding duplicate records from a Hive Table

SET hive.cli.errors.ignore=true;
SET hive.vectorized.execution.enabled=true;
SET hive.vectorized.execution.reduce.enabled=true;
SET hive.cbo.enable=true;
SET hive.compute.query.using.stats=true;
SET hive.stats.fetch.column.stats=true;
SET hive.stats.fetch.partition.stats=true;
SET hive.optimize.index.filter=true;
SET tez.runtime.sort.threads=2;
SET tez.task.generate.counters.per.io=true;
SET hive.prewarm.enabled=true;
SET hive.prewarm.numcontainers=8;
SET tez.runtime.io.sort.mb=550;
SET tez.runtime.optimize.local.fetch=true;
SET tez.runtime.shuffle.keep-alive.enabled=true;
SET hive.cli.print.header=true;

SELECT column1, column2, column3, column4, dt, time, inst_id, customer_id
FROM SampleDB.SampleTable
GROUP BY column1, column2, column3, column4, dt, time, inst_id, customer_id HAVING COUNT(*) > 1;