@inproceedings{BraunSchildgenDessloch, author = {Braun, Stefan and Schildgen, Johannes and Deßloch, Stefan}, title = {Visualization of NoSQL transformations using sampling techniques | Visualisierung von NoSQL-Transformationen unter der Verwendung von Sampling-Techniken}, series = {Proceedings of the LWA 2015 workshops: KDML, FGWM, IR, and FGDB : Trier, Germany, October 7-9, 2015}, booktitle = {Proceedings of the LWA 2015 workshops: KDML, FGWM, IR, and FGDB : Trier, Germany, October 7-9, 2015}, publisher = {RWTH Aachen}, address = {Aachen}, pages = {427 -- 438}, abstract = {Analysen auf NoSQL-Datenbanken sind oft langdauernd und die Ergebnisse fur den Benutzer haufig schwer verst ̈andlich. Wir prasentieren eine M{\"o}glichkeit, Datenmengen aus Wide-Column Stores mittels der Transformationssprache NotaQL zu transformieren sowie zu aggregieren und die Ergebnisse in Form von Diagrammen dem Benutzer darzustellen. Dabei kommen Sampling-Techniken zum Einsatz, um die Berechnung auf Kosten der Genauigkeit zu beschleunigen. Das von uns verwendete iterative Samplingverfahren sorgt fur eine kontinuierliche Verbesserung der Berechnungsgenauigkeit und bietet zudem M{\"o}glichkeiten zur Genauigkeitsabsch{\"a}tzung, die in Form von Konfidenzintervallen in den Diagrammen dargestellt werden kann.}, language = {en} } @inproceedings{SchaeferSchildgenDessloch, author = {Sch{\"a}fer, Marc and Schildgen, J{\"u}rgen and Deßloch, Stefan}, title = {Sampling with Incremental MapReduce}, series = {Datenbanksysteme f{\"u}r Business, Technologie und Web (BTW 2015) : Workshopband ; 02. - 03. M{\"a}rz 2015 in Hamburg}, volume = {242}, booktitle = {Datenbanksysteme f{\"u}r Business, Technologie und Web (BTW 2015) : Workshopband ; 02. - 03. M{\"a}rz 2015 in Hamburg}, publisher = {Gesellschaft f{\"u}r Informatik e.V.}, pages = {121 -- 130}, abstract = {The goal of this paper is to increase the computation speed of MapReduce jobs by reducing the accuracy of the result. Often, the timely processing is more important than the precision of the result. Hadoop has no built-in functionality for such an approximation technique, so the user has to implement sampling techniques manually. We introduce an automatic system for computing arithmetic approximations. The sampling is based on techniques from statistics and the extrapolation is done generically. This system is also extended by an incremental component which enables the reuse of already computed results to enlarge the sampling size. This can be used iteratively to further increase the sampling size and also the precision of the approximation. We present a transparent incremental sampling approach, so the developed components can be integrated in the Hadoop framework in a non-invasive manner.}, language = {en} } @inproceedings{SchildgenKrueckDessloch, author = {Schildgen, Johannes and Kr{\"u}ck, Yannick and Deßloch, Stefan}, title = {Transformations on Graph Databases for Polyglot Persistence with NotaQL}, series = {Datenbanksysteme f{\"u}r Business, Technologie und Web, 17. Fachtagung des GI-Fachbereichs "Datenbanken und Informationssyteme" (DBIS) : 06.-10.03.2017 in Stuttgart, Deutschland (BTW 2017)}, booktitle = {Datenbanksysteme f{\"u}r Business, Technologie und Web, 17. Fachtagung des GI-Fachbereichs "Datenbanken und Informationssyteme" (DBIS) : 06.-10.03.2017 in Stuttgart, Deutschland (BTW 2017)}, number = {CD-ROM}, editor = {Mitschang, Bernhard and Nicklas, Daniela and Leymann, Frank and Sch{\"o}ning, Harald and Herschel, Melanie and Teubner, Jens and H{\"a}rder, Theo and Kopp, Oliver and Wieland, Matthias}, publisher = {Gesellschaft f{\"u}r Informatik, Bonn}, pages = {83 -- 102}, language = {en} } @inproceedings{SchildgenDessloch, author = {Schildgen, Johannes and Deßloch, Stefan}, title = {NotaQL is not a query language! It's for data transformation on wide-column stores}, series = {Data Science : 30th British International Conference on Databases, BICOD 2015 Edingburgh, UK, July 6-8, 2015, Proceedings}, volume = {9147}, booktitle = {Data Science : 30th British International Conference on Databases, BICOD 2015 Edingburgh, UK, July 6-8, 2015, Proceedings}, editor = {Maneth, Sebastian}, publisher = {Springer Nature}, isbn = {978-3-319-20423-9}, issn = {1611-3349}, doi = {10.1007/978-3-319-20424-6_14}, pages = {139 -- 151}, abstract = {It is simple to query a relational database because all columns of the tables are known and the language SQL is easily applicable. In NoSQL, there usually is no fixed schema and no query language. In this article, we present NotaQL, a data-transformation language for wide-column stores. NotaQL is easy to use and powerful. Many MapReduce algorithms like filtering, grouping, aggregation and even breadth-first-search, PageRank and other graph and text algorithms can be expressed in two or three short lines of code.}, language = {en} } @article{SchildgenJoergDossingeretal., author = {Schildgen, Johannes and J{\"o}rg, Thomas and Dossinger, Manuel and Deßloch, Stefan}, title = {Marimba: A framework for making MapReduce jobs incremental}, series = {Proceedings - 2014 IEEE International Congress on Big Data, BigData Congress 2014, 27 June 2014 - 02 July 2014, Anchorage, AK, USA}, journal = {Proceedings - 2014 IEEE International Congress on Big Data, BigData Congress 2014, 27 June 2014 - 02 July 2014, Anchorage, AK, USA}, publisher = {IEEE}, doi = {10.1109/BigData.Congress.2014.27}, abstract = {Many MapReduce jobs for analyzing Big Data require many hours and have to be repeated again and again because the base data changes continuously. In this paper we propose Marimba, a framework for making MapReduce jobs incremental. Thus, a recomputation of a job only needs to process the changes since the last computation. This accelerates the execution and enables more frequent recomputations, which leads to results which are more up-to-date. Our approach is based on concepts that are popular in the area of materialized views in relational database systems where a view can be updated only by aggregating changes in base data upon the previous result.}, language = {en} } @inproceedings{SchildgenDessloch, author = {Schildgen, Johannes and Deßloch, Stefan}, title = {SQL-Grundlagen spielend lernen mit dem Text-Adventure SQL Island}, series = {Datenbanksysteme f{\"u}r Business, Technologie und Web : (BTW 2015) ; 16. Fachtagung des GI-Fachbereichs "Datenbanken und Informationssysteme" (DBIS), 04. - 06.03.2015 in Hamburg, Germany}, volume = {241}, booktitle = {Datenbanksysteme f{\"u}r Business, Technologie und Web : (BTW 2015) ; 16. Fachtagung des GI-Fachbereichs "Datenbanken und Informationssysteme" (DBIS), 04. - 06.03.2015 in Hamburg, Germany}, publisher = {Gesellschaft f{\"u}r Informatik e.V.}, pages = {687 -- 690}, abstract = {Wir pr asentieren SQL Island, ein neuartiges browserbasiertes Lernspiel,welches auf dem Konzept der Text-Adventures basiert. Nach einem Flugzeugabsturzlandet die Spielfigur auf einer Insel. Man redet mit Bewohnern, sammelt Gegenst ̈andeund k ̈apft gegen B ̈osewichte. Die Besonderheit bei diesem Spiel ist jedoch, dass derSpieler seine Figur lediglich mittels SQL-Befehlen steuert. Alle n ̈otigen Befehle wer-den zun ̈achst pr ̈asentiert, sodass keine Vorerfahrung notwendig ist. Nach etwa einerStunde Spielzeit beherrscht der Spieler SELECT-, UPDATE- und DELETE-Anfragensowie Gruppierungen, Aggregationsfunktionen und Joins. Das Spiel kann online aufhttp://www.sql-island.de kostenlos und ohne Registrierung gespielt werden.}, language = {de} } @inproceedings{SchildgenLottermannDessloch, author = {Schildgen, Johannes and Lottermann, Thomas and Deßloch, Stefan}, title = {Cross-system NoSQL data transformations with NotaQL}, series = {BeyondMR '16: Proceedings of the 3rd ACM SIGMOD Workshop on Algorithms and Systems for MapReduce and BeyondJune 2016}, booktitle = {BeyondMR '16: Proceedings of the 3rd ACM SIGMOD Workshop on Algorithms and Systems for MapReduce and BeyondJune 2016}, publisher = {ACM}, doi = {10.1145/2926534.2926535}, pages = {1 -- 10}, abstract = {The rising adoption of NoSQL technology in enterprises causes a heterogeneous landscape of different data stores. Different stores provide distinct advantages and disadvantages, making it necessary for enterprises to facilitate multiple systems for specific purposes. This resulting polyglot persistence is difficult to handle for developers since some data needs to be replicated and aggregated between different and within the same stores. Currently, there are no uniform tools to perform these data transformations since all stores feature different APIs and data models. In this paper, we present the transformation language NotaQL that allows cross-system data transformations. These transformations are output-oriented, meaning that the structure of a transformation script is similar to that of the output. Besides, we provide an aggregation-centric approach, which makes aggregation operations as easy as possible.}, language = {en} } @inproceedings{HauboldSchildgenScherzingeretal., author = {Haubold, Florian and Schildgen, Johannes and Scherzinger, Stefanie and Deßloch, Stefan}, title = {ControVol Flex: Flexible Schema Evolution for NoSQL Application Development}, series = {Datenbanksysteme f{\"u}r Business, Technologie und Web (BTW 2017) : 17. Fachtagung des GI-Fachbereichs "Datenbanken und Informationssyteme" (DBIS) : 06.-10.03.2017 in Stuttgart Deutschland}, booktitle = {Datenbanksysteme f{\"u}r Business, Technologie und Web (BTW 2017) : 17. Fachtagung des GI-Fachbereichs "Datenbanken und Informationssyteme" (DBIS) : 06.-10.03.2017 in Stuttgart Deutschland}, editor = {Mitschang, Bernhard}, publisher = {Gesellschaft f{\"u}r Informatik e.V. (GI)}, address = {Bonn}, abstract = {We demonstrate ControVol Flex, an Eclipse plugin for controlled schema evolution in Java applications backed by NoSQL document stores. The sweet spot of our tool are applications that are deployed continuously against the same production data store: Each new release may bring about schema changes that conflict with legacy data already stored in production. The type system internal to the predecessor tool ControVol is able to detect common schema conflicts, and enables developers to resolve them with the help of object-mapper annotations. Our new tool ControVol Flex lets developers choose their schema-migration strategy, whether all legacy data is to be migrated eagerly by means of NotaQL transformation scripts, or lazily, as declared by object-mapper annotations. Our tool is even capable of carrying out both strategies in combination, eagerly migrating data in the background, while lazily migrating data that is meanwhile accessed by the application. From the viewpoint of the application, it remains transparent how legacy data is migrated: Every read access yields an entity that matches the structure that the current application code expects. Our live demo shows how ControVol Flex gracefully solves a broad range of common schema-evolution tasks.}, language = {en} }