{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:12:28Z","timestamp":1750306348278,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":17,"publisher":"ACM","license":[{"start":{"date-parts":[[2016,6,14]],"date-time":"2016-06-14T00:00:00Z","timestamp":1465862400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2016,6,14]]},"DOI":"10.1145\/2882903.2903744","type":"proceedings-article","created":{"date-parts":[[2016,6,16]],"date-time":"2016-06-16T19:01:52Z","timestamp":1466103712000},"page":"63-75","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Building the Enterprise Fabric for Big Data with Vertica and Spark Integration"],"prefix":"10.1145","author":[{"given":"Jeff","family":"LeFevre","sequence":"first","affiliation":[{"name":"HPE Vertica, Sunnyvale, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Liu","sequence":"additional","affiliation":[{"name":"HPE Vertica, Sunnyvale, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cornelio","family":"Inigo","sequence":"additional","affiliation":[{"name":"HPE Vertica, Sunnyvale, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lupita","family":"Paz","sequence":"additional","affiliation":[{"name":"HPE Vertica, Sunnyvale, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Edward","family":"Ma","sequence":"additional","affiliation":[{"name":"HPE Vertica, Sunnyvale, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Malu","family":"Castellanos","sequence":"additional","affiliation":[{"name":"HPE Vertica, Sunnyvale, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meichun","family":"Hsu","sequence":"additional","affiliation":[{"name":"HPE Vertica, Sunnyvale, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2016,6,14]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Amazon Redshift. https:\/\/aws.amazon.com\/redshift\/.  Amazon Redshift. https:\/\/aws.amazon.com\/redshift\/."},{"key":"e_1_3_2_1_2_1","unstructured":"Amazon Simple Storage Service. https:\/\/aws.amazon.com\/s3\/.  Amazon Simple Storage Service. https:\/\/aws.amazon.com\/s3\/."},{"key":"e_1_3_2_1_3_1","unstructured":"Apache Avro data serialization.  Apache Avro data serialization."},{"key":"e_1_3_2_1_4_1","unstructured":"DataStax Cassandra Connector. https:\/\/github.com\/datastax\/spark-cassandra-connector.  DataStax Cassandra Connector. https:\/\/github.com\/datastax\/spark-cassandra-connector."},{"key":"e_1_3_2_1_5_1","unstructured":"HPE Vertica Connector for Apache Spark. https:\/\/saas.hpe.com\/marketplace\/big-data\/hpe-vertica-connector-apache-spark.  HPE Vertica Connector for Apache Spark. https:\/\/saas.hpe.com\/marketplace\/big-data\/hpe-vertica-connector-apache-spark."},{"key":"e_1_3_2_1_6_1","unstructured":"JavaPMML API. https:\/\/github.com\/jpmml.  JavaPMML API. https:\/\/github.com\/jpmml."},{"key":"e_1_3_2_1_7_1","unstructured":"PMML 4.1 general structure. http:\/\/dmg.org\/pmml\/v4-1\/GeneralStructure.html.  PMML 4.1 general structure. http:\/\/dmg.org\/pmml\/v4-1\/GeneralStructure.html."},{"key":"e_1_3_2_1_8_1","unstructured":"Redshift data source for Spark. https:\/\/github.com\/databricks\/spark-redshift.  Redshift data source for Spark. https:\/\/github.com\/databricks\/spark-redshift."},{"key":"e_1_3_2_1_9_1","unstructured":"Spark MLlib. http:\/\/spark.apache.org\/mllib\/.  Spark MLlib. http:\/\/spark.apache.org\/mllib\/."},{"key":"e_1_3_2_1_10_1","unstructured":"Spark PMML model export. https:\/\/spark.apache.org\/docs\/latest\/mllib-pmml-model-export.html.  Spark PMML model export. https:\/\/spark.apache.org\/docs\/latest\/mllib-pmml-model-export.html."},{"key":"e_1_3_2_1_11_1","volume-title":"OSDI","author":"Dean J.","year":"2004","unstructured":"J. Dean and S. Ghemawat . MapReduce: Simplified data processing on large clusters . In OSDI , 2004 . J. Dean and S. Ghemawat. MapReduce: Simplified data processing on large clusters. In OSDI, 2004."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/1773912.1773922"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.14778\/2367502.2367518"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2723372.2742789"},{"key":"e_1_3_2_1_15_1","volume-title":"VLDB","author":"Stonebraker M.","year":"2005","unstructured":"M. Stonebraker , D. J. Abadi , A. Batkin , X. Chen , M. Cherniack , M. Ferreira , E. Lau , A. Lin , S. Madden , E. O'Neil , P. O'Neil , A. Rasin , N. Tran , and S. Zdonik . C-store: A Column-oriented DBMS . In VLDB , 2005 . M. Stonebraker, D. J. Abadi, A. Batkin, X. Chen, M. Cherniack, M. Ferreira, E. Lau, A. Lin, S. Madden, E. O'Neil, P. O'Neil, A. Rasin, N. Tran, and S. Zdonik. C-store: A Column-oriented DBMS. In VLDB, 2005."},{"key":"e_1_3_2_1_16_1","volume-title":"NSDI","author":"Zaharia M.","year":"2012","unstructured":"M. Zaharia , M. Chowdhury , T. Das , A. Dave , J. Ma , M. McCauley , M. J. Franklin , S. Shenker , and I. Stoica . Resilient Distributed Datasets: A fault-tolerant abstraction for in-memory cluster computing . In NSDI , 2012 . M. Zaharia, M. Chowdhury, T. Das, A. Dave, J. Ma, M. McCauley, M. J. Franklin, S. Shenker, and I. Stoica. Resilient Distributed Datasets: A fault-tolerant abstraction for in-memory cluster computing. In NSDI, 2012."},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of the 2nd USENIX Workshop on Hot Topics in Cloud Computing","author":"Zaharia M.","year":"2010","unstructured":"M. Zaharia , M. Chowdhury , M. J. Franklin , S. Shenker , and I. Stoica . Spark: Cluster computing with working sets . In Proceedings of the 2nd USENIX Workshop on Hot Topics in Cloud Computing , 2010 . M. Zaharia, M. Chowdhury, M. J. Franklin, S. Shenker, and I. Stoica. Spark: Cluster computing with working sets. In Proceedings of the 2nd USENIX Workshop on Hot Topics in Cloud Computing, 2010."}],"event":{"name":"SIGMOD\/PODS'16: International Conference on Management of Data","sponsor":["SIGMOD ACM Special Interest Group on Management of Data"],"location":"San Francisco California USA","acronym":"SIGMOD\/PODS'16"},"container-title":["Proceedings of the 2016 International Conference on Management of Data"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2882903.2903744","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2882903.2903744","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:55:53Z","timestamp":1750222553000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2882903.2903744"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,6,14]]},"references-count":17,"alternative-id":["10.1145\/2882903.2903744","10.1145\/2882903"],"URL":"https:\/\/doi.org\/10.1145\/2882903.2903744","relation":{},"subject":[],"published":{"date-parts":[[2016,6,14]]},"assertion":[{"value":"2016-06-14","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}