[ { "key": "VIGMJXHF", "version": 2, "library": { "type": "group", "id": 535447, "name": "MineracaoDadosMassivos", "links": { "alternate": { "href": "https://www.zotero.org/groups/mineracaodadosmassivos", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/535447/items/VIGMJXHF", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/mineracaodadosmassivos/items/VIGMJXHF", "type": "text/html" } }, "meta": { "createdByUser": { "id": 2839101, "username": "CAIONAKASHIMA", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/caionakashima", "type": "text/html" } } }, "creatorSummary": "Chauhan", "parsedDate": "2013-12", "numChildren": 0 }, "data": { "key": "VIGMJXHF", "version": 2, "itemType": "book", "title": "Learning Cloudera Impala", "creators": [ { "creatorType": "author", "firstName": "Avkash", "lastName": "Chauhan" } ], "abstractNote": "This book is an easy-to-follow, step-by-step tutorial where each chapter takes your knowledge to the next level. The book covers practical knowledge with tips to implement this knowledge in real-world scenarios. A chapter with a real-life example is included to help you understand the concepts in full.Using Cloudera Impala is for those who really want to take advantage of their Hadoop cluster by processing extremely large amounts of raw data in Hadoop at real-time speed. Prior knowledge of Hadoop and some exposure to HIVE and MapReduce is expected.", "series": "", "seriesNumber": "", "volume": "", "numberOfVolumes": "", "edition": "", "date": "December 2013", "publisher": "Packt Publishing Ltd", "place": "", "originalDate": "", "originalPublisher": "", "originalPlace": "", "format": "", "numPages": "", "ISBN": "978-1-78328-128-2", "DOI": "", "citationKey": "", "url": "", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "en", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Computers / Databases / General" }, { "tag": "Computers / Programming / Open Source" }, { "tag": "Computers / Programming Languages / SQL" } ], "collections": [], "relations": {}, "dateAdded": "2016-06-08T02:58:51Z", "dateModified": "2016-06-08T02:58:51Z" } }, { "key": "HTJHP52M", "version": 2, "library": { "type": "group", "id": 535447, "name": "MineracaoDadosMassivos", "links": { "alternate": { "href": "https://www.zotero.org/groups/mineracaodadosmassivos", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/535447/items/HTJHP52M", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/mineracaodadosmassivos/items/HTJHP52M", "type": "text/html" } }, "meta": { "createdByUser": { "id": 2839101, "username": "CAIONAKASHIMA", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/caionakashima", "type": "text/html" } } }, "creatorSummary": "George", "parsedDate": "2011-08", "numChildren": 0 }, "data": { "key": "HTJHP52M", "version": 2, "itemType": "book", "title": "HBase: The Definitive Guide", "creators": [ { "creatorType": "author", "firstName": "Lars", "lastName": "George" } ], "abstractNote": "If you're looking for a scalable storage solution to accommodate a virtually endless amount of data, this book shows you how Apache HBase can fulfill your needs. As the open source implementation of Google's BigTable architecture, HBase scales to billions of rows and millions of columns, while ensuring that write and read performance remain constant. Many IT executives are asking pointed questions about HBase. This book provides meaningful answers, whether you’re evaluating this non-relational database or planning to put it into practice right away.Discover how tight integration with Hadoop makes scalability with HBase easierDistribute large datasets across an inexpensive cluster of commodity serversAccess HBase with native Java clients, or with gateway servers providing REST, Avro, or Thrift APIsGet details on HBase’s architecture, including the storage format, write-ahead log, background processes, and moreIntegrate HBase with Hadoop's MapReduce framework for massively parallelized data processing jobsLearn how to tune clusters, design schemas, copy tables, import bulk data, decommission nodes, and many other tasks", "series": "", "seriesNumber": "", "volume": "", "numberOfVolumes": "", "edition": "", "date": "August 2011", "publisher": "O'Reilly Media, Inc.", "place": "", "originalDate": "", "originalPublisher": "", "originalPlace": "", "format": "", "numPages": "", "ISBN": "978-1-4493-1522-1", "DOI": "", "citationKey": "", "url": "", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "HBase", "language": "en", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Computers / Data Modeling & Design" }, { "tag": "Computers / Databases / Data Mining" }, { "tag": "Computers / Databases / Data Warehousing" }, { "tag": "Computers / Desktop Applications / Databases" }, { "tag": "Computers / Programming Languages / SQL" }, { "tag": "Computers / Web / Web Programming" } ], "collections": [], "relations": {}, "dateAdded": "2016-06-08T02:58:51Z", "dateModified": "2016-06-08T02:58:51Z" } }, { "key": "6UHG2FAI", "version": 2, "library": { "type": "group", "id": 535447, "name": "MineracaoDadosMassivos", "links": { "alternate": { "href": "https://www.zotero.org/groups/mineracaodadosmassivos", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/535447/items/6UHG2FAI", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/mineracaodadosmassivos/items/6UHG2FAI", "type": "text/html" } }, "meta": { "createdByUser": { "id": 2839101, "username": "CAIONAKASHIMA", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/caionakashima", "type": "text/html" } } }, "creatorSummary": "Russell", "parsedDate": "2013-11", "numChildren": 0 }, "data": { "key": "6UHG2FAI", "version": 2, "itemType": "book", "title": "Cloudera Impala", "creators": [ { "creatorType": "author", "firstName": "John", "lastName": "Russell" } ], "abstractNote": "Learn about Cloudera Impala–an open source project that's opening up the Apache Hadoop software stack to a wide audience of database analysts, users, and developers. The Impala massively parallel processing (MPP) engine makes SQL queries of Hadoop data simple enough to be accessible to analysts familiar with SQL and to users of business intelligence tools–and it’s fast enough to be used for interactive exploration and experimentation.", "series": "", "seriesNumber": "", "volume": "", "numberOfVolumes": "", "edition": "", "date": "November 2013", "publisher": "O'Reilly Media, Inc.", "place": "", "originalDate": "", "originalPublisher": "", "originalPlace": "", "format": "", "numPages": "", "ISBN": "978-1-4919-4950-4", "DOI": "", "citationKey": "", "url": "", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "en", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Computers / Databases / General" } ], "collections": [], "relations": {}, "dateAdded": "2016-06-08T02:58:51Z", "dateModified": "2016-06-08T02:58:51Z" } }, { "key": "UBQQUXPB", "version": 2, "library": { "type": "group", "id": 535447, "name": "MineracaoDadosMassivos", "links": { "alternate": { "href": "https://www.zotero.org/groups/mineracaodadosmassivos", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/535447/items/UBQQUXPB", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/mineracaodadosmassivos/items/UBQQUXPB", "type": "text/html" } }, "meta": { "createdByUser": { "id": 2839101, "username": "CAIONAKASHIMA", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/caionakashima", "type": "text/html" } } }, "creatorSummary": "White", "parsedDate": "2012-05", "numChildren": 0 }, "data": { "key": "UBQQUXPB", "version": 2, "itemType": "book", "title": "Hadoop: The Definitive Guide", "creators": [ { "creatorType": "author", "firstName": "Tom", "lastName": "White" } ], "abstractNote": "Ready to unlock the power of your data? With this comprehensive guide, you’ll learn how to build and maintain reliable, scalable, distributed systems with Apache Hadoop. This book is ideal for programmers looking to analyze datasets of any size, and for administrators who want to set up and run Hadoop clusters. You’ll find illuminating case studies that demonstrate how Hadoop is used to solve specific problems. This third edition covers recent changes to Hadoop, including material on the new MapReduce API, as well as MapReduce 2 and its more flexible execution model (YARN). Store large datasets with the Hadoop Distributed File System (HDFS) Run distributed computations with MapReduce Use Hadoop’s data and I/O building blocks for compression, data integrity, serialization (including Avro), and persistence Discover common pitfalls and advanced features for writing real-world MapReduce programs Design, build, and administer a dedicated Hadoop cluster—or run Hadoop in the cloud Load data from relational databases into HDFS, using Sqoop Perform large-scale data processing with the Pig query language Analyze datasets with Hive, Hadoop’s data warehousing system Take advantage of HBase for structured and semi-structured data, and ZooKeeper for building distributed systems", "series": "", "seriesNumber": "", "volume": "", "numberOfVolumes": "", "edition": "", "date": "May 2012", "publisher": "O'Reilly Media, Inc.", "place": "", "originalDate": "", "originalPublisher": "", "originalPlace": "", "format": "", "numPages": "", "ISBN": "978-1-4493-1152-0", "DOI": "", "citationKey": "", "url": "", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "Hadoop", "language": "en", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Computers / Data Processing" }, { "tag": "Computers / Databases / Data Mining" }, { "tag": "Computers / General" }, { "tag": "Computers / Programming / General" }, { "tag": "Computers / Programming / Parallel" }, { "tag": "Computers / Programming Languages / Java" } ], "collections": [], "relations": {}, "dateAdded": "2016-06-08T02:58:51Z", "dateModified": "2016-06-08T02:58:51Z" } }, { "key": "4KPGAZ93", "version": 2, "library": { "type": "group", "id": 535447, "name": "MineracaoDadosMassivos", "links": { "alternate": { "href": "https://www.zotero.org/groups/mineracaodadosmassivos", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/535447/items/4KPGAZ93", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/mineracaodadosmassivos/items/4KPGAZ93", "type": "text/html" } }, "meta": { "createdByUser": { "id": 2839101, "username": "CAIONAKASHIMA", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/caionakashima", "type": "text/html" } } }, "creatorSummary": "Russell", "parsedDate": "2014-09", "numChildren": 0 }, "data": { "key": "4KPGAZ93", "version": 2, "itemType": "book", "title": "Getting Started with Impala: Interactive SQL for Apache Hadoop", "creators": [ { "creatorType": "author", "firstName": "John", "lastName": "Russell" } ], "abstractNote": "Learn how to write, tune, and port SQL queries and other statements for a Big Data environment, using Impala—the massively parallel processing SQL query engine for Apache Hadoop. The best practices in this practical guide help you design database schemas that not only interoperate with other Hadoop components, and are convenient for administers to manage and monitor, but also accommodate future expansion in data size and evolution of software capabilities.Ideal for database developers and business analysts, Getting Started with Impala includes advice from Cloudera’s development team, as well as insights from its consulting engagements with customers.Learn how Impala integrates with a wide range of Hadoop componentsAttain high performance and scalability for huge data sets on production clustersExplore common developer tasks, such as porting code to Impala and optimizing performanceUse tutorials for working with billion-row tables, date- and time-based values, and other techniquesLearn how to transition from rigid schemas to a flexible model that evolves as needs changeTake a deep dive into joins and the roles of statistics", "series": "", "seriesNumber": "", "volume": "", "numberOfVolumes": "", "edition": "", "date": "September 2014", "publisher": "O'Reilly Media, Inc.", "place": "", "originalDate": "", "originalPublisher": "", "originalPlace": "", "format": "", "numPages": "", "ISBN": "978-1-4919-0574-6", "DOI": "", "citationKey": "", "url": "", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "Getting Started with Impala", "language": "en", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Computers / Data Processing" }, { "tag": "Computers / Databases / General" } ], "collections": [], "relations": {}, "dateAdded": "2016-06-08T02:58:51Z", "dateModified": "2016-06-08T02:58:51Z" } } ]