#!/usr/bin/env bash
-spark-submit --master spark://n0649:18899 wikiq_users_spark.py --output-format parquet -i "/com/output/wikiq-enwiki-20180301/enwiki-20180301-pages-meta-history*.tsv" -o "/com/output/wikiq-users-enwiki-20180301-parquet/" --num-partitions 500
+spark-submit --master spark://n0649:18899 wikiq_users_spark.py --output-format parquet -i "/com/output/wikiq-enwiki-persist-sequence-20180301/enwiki/enwiki-20180301-pages-meta-history*.tsv" -o "/com/output/wikiq-users-enwiki-20180301-parquet/" --num-partitions 500 --schema-opt persistence+collapse