Pig latin: a not-so-foreign language for data processing Export

@inproceedings{citeulike:2972987, abstract = {There is a growing need for ad-hoc analysis of extremely large data sets, especially at internet companies where innovation critically depends on being able to analyze terabytes of data collected every day. Parallel database products, e.g., Teradata, offer a solution, but are usually prohibitively expensive at this scale. Besides, many of the people who analyze this data are entrenched procedural programmers, who find the declarative, SQL style to be unnatural. The success of the more procedural map-reduce programming model, and its associated scalable implementations on commodity hardware, is evidence of the above. However, the map-reduce paradigm is too low-level and rigid, and leads to a great deal of custom user code that is hard to maintain, and reuse.}, address = {New York, NY, USA}, author = {Olston, Christopher and Reed, Benjamin and Srivastava, Utkarsh and Kumar, Ravi and Tomkins, Andrew}, booktitle = {SIGMOD '08: Proceedings of the 2008 ACM SIGMOD international conference on Management of data}, citeulike-article-id = {2972987}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1376616.1376726}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/1376616.1376726}, doi = {10.1145/1376616.1376726}, isbn = {978-1-60558-102-6}, keywords = {database, mapreduce, querylanguage}, location = {Vancouver, Canada}, pages = {1099--1110}, posted-at = {2008-10-29 13:13:15}, priority = {2}, publisher = {ACM}, title = {Pig latin: a not-so-foreign language for data processing}, url = {http://dx.doi.org/10.1145/1376616.1376726}, year = {2008} }

TY - CONF ID - citeulike:2972987 L3 - citeulike-article-id:2972987 N2 - There is a growing need for ad-hoc analysis of extremely large data sets, especially at internet companies where innovation critically depends on being able to analyze terabytes of data collected every day. Parallel database products, e.g., Teradata, offer a solution, but are usually prohibitively expensive at this scale. Besides, many of the people who analyze this data are entrenched procedural programmers, who find the declarative, SQL style to be unnatural. The success of the more procedural map-reduce programming model, and its associated scalable implementations on commodity hardware, is evidence of the above. However, the map-reduce paradigm is too low-level and rigid, and leads to a great deal of custom user code that is hard to maintain, and reuse. CY - Vancouver, Canada SN - 978-1-60558-102-6 AD - New York, NY, USA EP - 1110 TI - Pig latin: a not-so-foreign language for data processing PB - ACM T2 - SIGMOD '08: Proceedings of the 2008 ACM SIGMOD international conference on Management of data SP - 1099 KW - database KW - mapreduce KW - querylanguage AU - Olston, Christopher AU - Reed, Benjamin AU - Srivastava, Utkarsh AU - Kumar, Ravi AU - Tomkins, Andrew PY - 2008/// UR - http://dx.doi.org/10.1145/1376616.1376726 ER -