Skip to content

Instantly share code, notes, and snippets.

@jhpoelen
Last active August 5, 2019 20:01
Show Gist options
  • Save jhpoelen/f5f724f4c1cf6c25ceb8d66c29d82980 to your computer and use it in GitHub Desktop.
Save jhpoelen/f5f724f4c1cf6c25ceb8d66c29d82980 to your computer and use it in GitHub Desktop.
idigbio-spark scripts
#!/bin/bash
#
#
WKT_STRING="POLYGON ((-72.77293810620904 -33.196074154826235, -72.77293810620904 6.59516197881252, -28.12450060620904 6.59516197881252, -28.12450060620904 -33.196074154826235, -72.77293810620904 -33.196074154826235))"
spark-submit \
--master mesos://zk://mesos01:2181,mesos02:2181,mesos03:2181/mesos \
--driver-memory 4G \
--conf spark.sql.caseSensitive=true \
--class ChecklistGenerator \
iDigBio-LD-assembly-1.5.9.jar \
-c hdfs:///guoda/data/source=preston.acis.ufl.edu/dwca/core.parquet \
-t hdfs:///guoda/data/traits \
-o hdfs:///user/$USER/checklist \
"Anas|Anura" \
"$WKT_STRING" \
""
#!/bin/bash
#
#
WKT_STRING="POLYGON ((-72.77293810620904 -33.196074154826235, -72.77293810620904 6.59516197881252, -28.12450060620904 6.59516197881252, -28.12450060620904 -33.196074154826235, -72.77293810620904 -33.196074154826235))"
spark-submit \
--driver-memory 4G \
--conf spark.sql.caseSensitive=true \
--class ChecklistGenerator \
iDigBio-LD-assembly-1.5.9.jar \
-c file:///$HOME/preston-amazon/data-processed/core.parquet \
-t file:///$HOME/traits \
-o file:///$HOME/checklist \
"Animalia" \
"$WKT_STRING" \
""
#!/bin/bash
#
#
spark-submit \
--driver-memory 4G \
--conf spark.sql.caseSensitive=true \
--class bio.guoda.preston.spark.PrestonUtil \
iDigBio-LD-assembly-1.5.9.jar \
file:///$HOME/preston-amazon/data \
file:///$HOME/preston-amazon/data-processed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment