Changes between Version 7 and Version 8 of PDAD_Introduction

Timestamp:

Jan 15, 2010, 7:57:12 PM (14 years ago)

Author:

claudiu.gheorghe

Comment:

--

PDAD_Introduction

@@ -20 +20 @@
 
 Apache Hadoop is an open-source implementation of the popular MapReduce paradigm introduced by Google for large-scale data processing. Hadoop is written in Java, but it provides support for specifying jobs in multiple languages like Python for example. 
+
 Hadoop provides a solid infrastructure that contains a distributed filesystem and a centralized fault-tolerant cluster architecture. 
+Even the framework is not so mature, multiple sub-projects appeared, being built on the Hadoop's MapReduce and targeting different types of application. We found interesting the Pig project, which is a high-level scripting language very similar to SQL used to analyze huge data sets.
+
+Our curiosity is: it's this language so cool? Is it so hard to design and implement data analysis problems in MapReduce? 
 
 == MPI ==