1. 巨量資料基礎： MapReduce典範、Hadoop與Spark生態系統
Tamkang University
Tamkang University
Big Data Mining 巨量資料探勘
巨量資料基礎： MapReduce典範、Hadoop與Spark生態系統
(Fundamental Big Data: MapReduce Paradigm, Hadoop and Spark Ecosystem)
1042DM02
MI4 (M2244) (3094)
Tue, 3, 4 (10:10-12:00) (B216)
Min-Yuh Day
戴敏育
Assistant Professor
專任助理教授
Dept. of Information Management, Tamkang University
淡江大學 資訊管理學系
tku.edu.tw/myday/

2. 課程大綱 (Syllabus)
週次 (Week) 日期 (Date) 內容 (Subject/Topics) /02/16 巨量資料探勘課程介紹 (Course Orientation for Big Data Mining) /02/23 巨量資料基礎：MapReduce典範、Hadoop與Spark生態系統 (Fundamental Big Data: MapReduce Paradigm, Hadoop and Spark Ecosystem) /03/01 關連分析 (Association Analysis) /03/08 分類與預測 (Classification and Prediction) /03/15 分群分析 (Cluster Analysis) /03/22 個案分析與實作一 (SAS EM 分群分析)： Case Study 1 (Cluster Analysis – K-Means using SAS EM) /03/29 個案分析與實作二 (SAS EM 關連分析)： Case Study 2 (Association Analysis using SAS EM)

3. 課程大綱 (Syllabus)
週次 (Week) 日期 (Date) 內容 (Subject/Topics) /04/05 教學行政觀摩日 (Off-campus study) /04/12 期中報告 (Midterm Project Presentation) /04/19 期中考試週 (Midterm Exam) /04/26 個案分析與實作三 (SAS EM 決策樹、模型評估)： Case Study 3 (Decision Tree, Model Evaluation using SAS EM) /05/03 個案分析與實作四 (SAS EM 迴歸分析、類神經網路)： Case Study 4 (Regression Analysis, Artificial Neural Network using SAS EM) /05/10 Google TensorFlow 深度學習 (Deep Learning with Google TensorFlow) /05/17 期末報告 (Final Project Presentation) /05/24 畢業班考試 (Final Exam)

4. 2016/02/ 巨量資料基礎： MapReduce典範、 Hadoop與Spark生態系統 (Fundamental Big Data: MapReduce Paradigm, Hadoop and Spark Ecosystem)

5. Architecture of Big Data Analytics
Big Data Analytics Applications
Big Data Sources
Big Data Transformation
Big Data Platforms & Tools
* Internal
* External
* Multiple formats
* Multiple locations
* Multiple applications
Middleware
Hadoop
MapReduce
Pig
Hive
Jaql
Zookeeper
Hbase
Cassandra
Oozie
Avro
Mahout
Others
Queries
Transformed Data
Big Data Analytics
Raw Data
Extract Transform Load
Reports
Data Warehouse
OLAP
Traditional Format CSV, Tables
Data Mining
Source: Stephan Kudyba (2014), Big Data, Mining, and Analytics: Components of Strategic Decision Making, Auerbach Publications

6. Architecture of Big Data Analytics
Big Data Analytics Applications
Big Data Sources
Big Data Transformation
Big Data Platforms & Tools
* Internal
* External
* Multiple formats
* Multiple locations
* Multiple applications
Data Mining
Big Data Analytics Applications
Middleware
Hadoop
MapReduce
Pig
Hive
Jaql
Zookeeper
Hbase
Cassandra
Oozie
Avro
Mahout
Others
Queries
Transformed Data
Big Data Analytics
Raw Data
Extract Transform Load
Reports
Data Warehouse
OLAP
Traditional Format CSV, Tables
Data Mining
Source: Stephan Kudyba (2014), Big Data, Mining, and Analytics: Components of Strategic Decision Making, Auerbach Publications

7. Architecture for Social Big Data Mining (Hiroshi Ishikawa, 2015)
Enabling Technologies
Analysts
Integrated analysis
Model Construction
Explanation by Model
Integrated analysis model
Conceptual Layer
Construction and confirmation of individual hypothesis
Description and execution of application-specific task
Natural Language Processing
Information Extraction
Anomaly Detection
Discovery of relationships among heterogeneous data
Large-scale visualization
Data Mining
Application specific task
Multivariate analysis
Logical Layer
Parallel distrusted processing
Social Data
Software
Hardware
Physical Layer
Source: Hiroshi Ishikawa (2015), Social Big Data Mining, CRC Press

8. Business Intelligence (BI) Infrastructure
Source: Kenneth C. Laudon & Jane P. Laudon (2014), Management Information Systems: Managing the Digital Firm, Thirteenth Edition, Pearson.

9. Data Warehouse Data Mining and Business Intelligence
Increasing potential
to support
business decisions
End User
Decision Making
Data Presentation
Business
Analyst
Visualization Techniques
Data Mining
Data
Analyst
Information Discovery
Data Exploration
Statistical Summary, Querying, and Reporting
Data Preprocessing/Integration, Data Warehouses
DBA
Data Sources
Paper, Files, Web documents, Scientific experiments, Database Systems
Source: Jiawei Han and Micheline Kamber (2006), Data Mining: Concepts and Techniques, Second Edition, Elsevier

10. The Evolution of BI Capabilities
Source: Turban et al. (2011), Decision Support and Business Intelligence Systems

11. Data Science and Business Intelligence
Source: EMC Education Services, Data Science and Big Data Analytics: Discovering, Analyzing, Visualizing and Presenting Data, Wiley, 2015

12. Data Mining at the Intersection of Many Disciplines
Source: Turban et al. (2011), Decision Support and Business Intelligence Systems

13. Knowledge Discovery (KDD) Process
Data mining: core of knowledge discovery process
Pattern Evaluation
Data Mining
Task-relevant Data
Data Warehouse
Selection
Data Cleaning
Data Integration
Databases
Source: Han & Kamber (2006)

14. A Taxonomy for Data Mining Tasks
Source: Turban et al. (2011), Decision Support and Business Intelligence Systems

15. Deep Learning Intelligence from Big Data
Source:

16. Big Data
Source: EMC Education Services, Data Science and Big Data Analytics: Discovering, Analyzing, Visualizing and Presenting Data, Wiley, 2015

17. Big Data Growth is increasingly unstructured
Source: EMC Education Services, Data Science and Big Data Analytics: Discovering, Analyzing, Visualizing and Presenting Data, Wiley, 2015

18. Typical Analytic Architecture
Source: EMC Education Services, Data Science and Big Data Analytics: Discovering, Analyzing, Visualizing and Presenting Data, Wiley, 2015

19. Data Evolution and the Rise of Big Data Sources
Source: EMC Education Services, Data Science and Big Data Analytics: Discovering, Analyzing, Visualizing and Presenting Data, Wiley, 2015

20. Emerging Big Data Ecosystem
Source: EMC Education Services, Data Science and Big Data Analytics: Discovering, Analyzing, Visualizing and Presenting Data, Wiley, 2015

21. Key Roles for the New Big Data Ecosystem
Source: EMC Education Services, Data Science and Big Data Analytics: Discovering, Analyzing, Visualizing and Presenting Data, Wiley, 2015

22. Profile of a Data Scientist
Quantitative
mathematics or statistics
Technical
software engineering, machine learning, and programming skills
Skeptical mind-set and critical thinking
Curious and creative
Communicative and collaborative
Source: EMC Education Services, Data Science and Big Data Analytics: Discovering, Analyzing, Visualizing and Presenting Data, Wiley, 2015

23. Source: https://www. thalesgroup

24. MapReduce Paradigm Map Reduce Big Data Map0 Map1 Map2 Map3 Reduce0
MapReduce Data
Output Data

25. The Apache™ Hadoop® project develops open-source software for reliable, scalable, distributed computing.
Source:

26. Processing
MapReduce
HDFS
Storage
Source:

27. Big Data with Hadoop Architecture
Source:

28. Big Data with Hadoop Architecture Logical Architecture Processing: MapReduce
Source:

29. Big Data with Hadoop Architecture Logical Architecture Storage: HDFS
Source:

30. Big Data with Hadoop Architecture Process Flow
Source:

31. Big Data with Hadoop Architecture Hadoop Cluster
Source:

32. Hadoop Ecosystem
Source: Shiva Achari (2015), Hadoop Essentials - Tackling the Challenges of Big Data with Hadoop, Packt Publishing

33. Traditional ETL Architecture
Source:

34. Offload ETL with Hadoop (Big Data Architecture)
Source:

35. Source: http://www.newera-technologies.com/big-data-solution.html
Big Data Solution
Source:

36. HDP A Complete Enterprise Hadoop Data Platform
Source:

37. Lightning-fast cluster computing
Apache Spark is a fast and general engine for large-scale data processing.
Source:

38. Logistic regression in Hadoop and Spark
Run programs up to 100x faster than Hadoop MapReduce in memory, or 10x faster on disk.
Source:

39. Ease of Use Write applications quickly in Java, Scala, Python, R.
Source:

40. Word count in Spark's Python API
text_file = spark.textFile("hdfs://...") text_file.flatMap(lambda line: line.split()) .map(lambda word: (word, 1)) .reduceByKey(lambda a, b: a+b)
Source:

41. Spark and Hadoop
Source:

42. Spark Ecosystem
Source:

43. Mllib (machine learning)
Spark Ecosystem
Spark
Spark
Streaming
Mllib (machine learning)
Spark
SQL
GraphX
(graph)
Kafka
Flume
H2O
Hive
Titan
HBase
Cassandra
HDFS
Source: Mike Frampton (2015), Mastering Apache Spark, Packt Publishing

44. Python for Big Data Analytics
(The column on the left is the 2015 ranking; the column on the right is the 2014 ranking for comparison
2015
2014
Source:

45. Source: http://www. kdnuggets

46. SAS & Hadoop

47. Modern Reality Infrastructure Data Analytics Commoditization
Architectures
Scale
Infrastructure
New Complex Streams
Perishable Considerations
Cost
Data
New Category of Business Problems
Analytical Algorithms
Operationalization
Analytics
Deepak Ramanathan (2014), SAS Modernization architectures - Big Data Analytics,
Source: Deepak Ramanathan (2014), SAS Modernization architectures - Big Data Analytics

48. Copyright © 2011, SAS Institute Inc. All rights reserved.
ADVANCED ANALYTICS
TEXT ANALYTICS
Finding treasures in unstructured data
like social media or survey tools
that could uncover insights
about consumer sentiment
FORECASTING
Leveraging historical data to drive better insight into decision-making
for the future
INFORMATION
MANAGEMENT
OPTIMIZATION
DATA MINING
Analyze massive
amounts of data in
order to accurately
identify areas likely to
produce the most
profitable results
Currently, most organizations use one or more of these techniques to solve a departmental specific business problem. As such, even though valuable, from an enterprise standpoint, the value is somewhat marginalized or not optimized. What we see is that departments, such as Marketing, Finance or Risk are using one technique to solve a problem but not multiple techniques. So, for instance, in a bank, the risk department will use econometric forecasting to manage the treasury portfolio and overall risk…so they think. But they are not proactively looking at text ( s and chat), to see where the bank could be exposed. Or a retailer uses forecasting to predict what will sell, but they are not looking at on line sentiment and customer segmentation to optimize what product they should offer what customer and how to optimize distribution all as part of the same process. These are examples of why these techniques should be pulled together for the greater good.
Source: Deepak Ramanathan (2014), SAS Modernization architectures - Big Data Analytics,
Mine transaction databases for data of spending patterns that indicate a stolen card..
STATISTICS
Copyright © 2011, SAS Institute Inc. All rights reserved.
Source: Deepak Ramanathan (2014)
Copyright © 2011, SAS Institute Inc. All rights reserved.

49. Trends in Analytics
Complex Business Problems Are Driving Analytics Innovation
Speed Will Be Of Essence
Leverage Analytics To Unlock The Information Contained In Unstructured Data
Operationalizing Analytics
Source: Deepak Ramanathan (2014), SAS Modernization architectures - Big Data Analytics

50. Architectures of Big Data Analytics

51. Traditional Analytics
BI and Analytics
Data Mart
Operational Data Sources
Data Mart
EDW
Analytic Mart
Analytic Mart
Unstructured, Semi-structured and Streaming data (i.e. sensor data) handled often outside the Warehouse flow
Source: Deepak Ramanathan (2014), SAS Modernization architectures - Big Data Analytics

52. Hadoop as a “new data” Store
BI and Analytics
Data Mart
Operational Data Sources
Data Mart
EDW
Analytic Mart
Analytic Mart
Source: Deepak Ramanathan (2014), SAS Modernization architectures - Big Data Analytics

53. Hadoop as an additional input to the EDW
BI and Analytics
Data Mart
Operational Data Sources
Data Mart
EDW
Analytic Mart
Analytic Mart
Analytic Mart
Data Mart
Source: Deepak Ramanathan (2014), SAS Modernization architectures - Big Data Analytics

54. Operational Data Sources
Hadoop Data Platform As a “staging Layer” as part of a “data Lake” – Downstream stores could be Hadoop, data appliances or an RDBMS
BI and Analytics
Operational Data Sources
EDW
Data Mart
Data Mart
Analytic Mart
Analytic Mart
Source: Deepak Ramanathan (2014), SAS Modernization architectures - Big Data Analytics

55. SAS Big data Strategy – SAS areas
Source: Deepak Ramanathan (2014), SAS Modernization architectures - Big Data Analytics

56. SAS Big data Strategy – SAS areas
Source: Deepak Ramanathan (2014), SAS Modernization architectures - Big Data Analytics

57. SAS® Within the HADOOP ECOSYSTEMEG EM VA
SAS® Enterprise
Guide®
SAS® Data Integration
SAS® Enterprise Miner™
SAS® Visual Analytics
SAS® In-Memory Statistics for Haodop
User Interface
SAS Metadata
Metadata
Next-Gen
SAS® User
SAS® User
Base SAS & SAS/ACCESS® to Hadoop™
In-Memory
Data Access
Data Access
Impala
Pig
Hive
SAS Embedded
Process
Accelerators
SAS® LASR™ Analytic
Server
SAS® High-
Performance
Analytic Procedures
Data Processing
Map Reduce
MPI Based
HDFS
File System
Source: Deepak Ramanathan (2014), SAS Modernization architectures - Big Data Analytics

58. SAS enables the entire lifecycle around HADOOP
Done using either the Data Preparation, Data Exploration or Build Model Tools
SAS Visual Analytics
Decision Manager
IDENTIFY /
FORMULATE
PROBLEM
DATA
PREPARATION
EXPLORATION
TRANSFORM
& SELECT
BUILD
MODEL
VALIDATE
DEPLOY
EVALUATE /
MONITOR
RESULTS
SAS Visual Analytics SAS Visual Statistics
SAS In-Memory Statistics for Hadoop
SAS Scoring Accelerator for Hadoop
SAS Code Accelerator for Hadoop
Done using either the Data Preparation, Data Exploration or Build Model Tools
Decision Manager
SAS High Performance Analytics Offerings supported by relevant clients like SAS Enterprise Miner, SAS/STAT etc.
Source: Deepak Ramanathan (2014), SAS Modernization architectures - Big Data Analytics

59. SAS® VISUAL ANALYTICS A Single solution for Data Discovery, Visualization, analytics and reporting
Source: Deepak Ramanathan (2014), SAS Modernization architectures - Big Data Analytics

60. Visualization Powered by SAS Analytics
SAS® VISUAL ANALYTICS
Example: text analysis gives you insight to customer experience and opinion
Example:
Applying text analysis to twitter streams, or to customer comments in call logs, can give quick insight into the “hot topics” discussed.
It’s more than a simple world=cloud that shows which topics are being discussed, but the analytics applied behind the scenes determine which words are used most frequently –so you can determine which topics are the most “important” and warrant further understanding/exploration.
Visualization Powered by SAS Analytics
Analytics applied to text provides real MEANING
Source: Deepak Ramanathan (2014), SAS Modernization architectures - Big Data Analytics

61. Visualization
Source: Deepak Ramanathan (2014), SAS Modernization architectures - Big Data Analytics

62. References
EMC Education Services (2015), Data Science and Big Data Analytics: Discovering, Analyzing, Visualizing and Presenting Data, Wiley
Shiva Achari (2015), Hadoop Essentials - Tackling the Challenges of Big Data with Hadoop, Packt Publishing
Mike Frampton (2015), Mastering Apache Spark, Packt Publishing
Deepak Ramanathan (2014), SAS Modernization architectures - Big Data Analytics,