setting up a mini big data architecture, just for you! - bas geerdink

14
Building a (mini) Big Data architecture Bas Geerdink 5 november 2014

Upload: nljug

Post on 02-Jul-2015

341 views

Category:

Technology


2 download

DESCRIPTION

In this session, we'll start from scratch and build a nice little software stack that you can use to experiment with big data software. At the end, I've shown the steps to take for setting up a virtual server with a NoSQL database, Hadoop, stream processing engine, and visualization tools. After importing the data, we'll have a modest result in the form of a visualization of some 'little' big data. This session will give you an introduction to the world of big data architecture, without getting too complex or fuzzy. There will be some theory, but the focus is on the practical things you need to do to get started. Bring your laptop if you want some hands-on experience right away! Join this session ff you want to understand what's under the hood of Cloudera, Hortonworks, and MapR, and want to play with modern open source software!

TRANSCRIPT

Page 1: Setting up a mini big data architecture, just for you! - Bas Geerdink

Building a (mini) Big Data

architectureBas Geerdink5 november 2014

Page 2: Setting up a mini big data architecture, just for you! - Bas Geerdink

About me

• Work: ING

• Education: Master’s degree in AI and Informatics

• Programming since 1998 (C#, Java, Scala, Python, …)

• Twitter: @bgeerdink

• Email: [email protected]

Page 3: Setting up a mini big data architecture, just for you! - Bas Geerdink

Introduction

• Big Data– Volume, Velocity, Variety

• Predictive Analytics / Machine Learning– Classification– Clustering– Recommendation

• Today’s goal:– Start small, create a playground!– Learn some basic tools and techniques

Page 4: Setting up a mini big data architecture, just for you! - Bas Geerdink

Reference big data solution architecture

Page 5: Setting up a mini big data architecture, just for you! - Bas Geerdink

• On-premise:– Hortonworks– Cloudera– MapR– IBM InfoSphere BigInsights– HP Vertica– Oracle– Teradata– SAS

• Cloud-based:– Amazon Elastic MapReduce– Microsoft Azure HDInsight– Google (App Engine, BigTable, Prediction API, …)– SAP HANA

… however, we’ll set up our own environment!

There are several out-of-the-box options to get started with big data development

Page 6: Setting up a mini big data architecture, just for you! - Bas Geerdink
Page 7: Setting up a mini big data architecture, just for you! - Bas Geerdink

Mahout features

• Optimized for large datasets (millions of records)

• Moving from Hadoop to Spark

• Supervised learning

– Classification: Naïve Bayes, Hidden Markov Models(NN), Random Forest

– Logistic Regression (predict a continuous value)

• Unsupervised learning

– Clustering: k-Means, Canopy

– Recommendations

Page 8: Setting up a mini big data architecture, just for you! - Bas Geerdink

Mahout AlgorithmsSize of dataset

Mahoutalgorithm

Executionmodel

Characteristics

Small SGD Sequential Uses all types of predictor vars

Medium (Complementary)Naïve Bayes

Parallel Prefers text, high training cost

Large Random Forest Parallel Uses all types of predictor vars, high training cost

Source: Cloudera (2011)

Page 9: Setting up a mini big data architecture, just for you! - Bas Geerdink
Page 10: Setting up a mini big data architecture, just for you! - Bas Geerdink

Example 1: newsgroups

• Data: newsgroup items

• 20.000 records

• Train with Naïve Bayes Classifier

• Categories: 20 newsgroups

• Prediction: newsgroup of

unclassified item

Page 11: Setting up a mini big data architecture, just for you! - Bas Geerdink

Example 2: hospital treatment

• Data: hospital surgeries in 50s, 60s, 70s

• 306 records

• Train with logistic regression

• Features:– Age of subject

– Year of treatment

– Number of positive axillary nodes

• Prediction: survival rate

• Visualization: D3.js

Page 12: Setting up a mini big data architecture, just for you! - Bas Geerdink
Page 13: Setting up a mini big data architecture, just for you! - Bas Geerdink

Summary

Page 14: Setting up a mini big data architecture, just for you! - Bas Geerdink

Want to move on?

• Follow courses on Coursera– Machine Learning: https://www.coursera.org/course/ml

– Introduction to Data Science: https://www.coursera.org/course/datasci

• Read Hadoop/Mahout/R tutorials and books

• Get some ML datasets: – http://archive.ics.uci.edu/ml/datasets.html

– http://aws.amazon.com/datasets

– http://www.datasciencecentral.com/profiles/blogs/big-data-sets-available-for-free

• Expand the ecosystem: Hive, Pig, HBase, Spark, …