Large Scale Distributed Data Science from scratch using Apache Spark 2.0.

@inproceedings{shanahan-2017-large, author = {James G. Shanahan and Valentin Zacharias and Liang Dai and James G. Shanahan and Valentin Zacharias}, editor = {Rick Barrett and Rick Cummings and Eugene Agichtein and Evgeniy Gabrilovich}, title = {{Large Scale Distributed Data Science from scratch using Apache Spark 2.0}}, booktitle = {{Proceedings of the 26th International Conference on World Wide Web Companion, Perth, Australia, April 3-7, 2017}}, pages = {955--957}, publisher = {ACM}, year = {2017}, url = {https://doi.org/10.1145/3041021.3051108}, doi = {https://doi.org/10.1145/3041021.3051108} }