Transcript slides - UCLA Computer Science

Data Stream Mining Applications:
Toward Inductive DSMS
CS240B Notes
by
Carlo Zaniolo
UCLA Computer Science Department
Spring 2008
1
Data Stream Mining and DSMS


Mining Data Stream: an emerging area of important
applications
Many fast & light algorithms developed for mining data
streams: Ensembles, Moment, SWIM, etc.

Deployemnt of these algorithms on data streams a challenge



To deal with bursty arrivals, synopses, QoS, scheduling
Analysts want to focus on high-level mining tasks, leaving
such lower-level issues to the DSMS
Integration of mining methods and DSMS technology is
needed—but it faces difficult research challenges:

21-Mar-08
Data mining: a big problem for SQL-based DBMS
http://wis.cs.ucla.edu
2
Road Map for Next Three Weeks

Data Mining query languages and systems

The Inductive DBMS dream and the reality:


Oracle, IBM DB2, MS DMX, Weka

Fast& Light Algorithms for Mining Data Streams

Classifiers and Classifier Ensembles,

Clustering methods,

Association Rules,

Time series
Supporting these Algorithms in a DSMS

21-Mar-08
Data Mining Query Languages and support for
the mining process
http://wis.cs.ucla.edu
3
The DM Experience for DBMS:
from dreams to reality

Initial attempts to support mining queries in relational
DBMS: Unsuccessful



OR-DBMS do not fare much better [Sarawagi’ 98].
In 1996, a ‘high-road’ approach was proposed by Imielinski &
Mannila who called for a quantum leap in functionality based on:

High-level declarative languages for Data Mining (DM)

Technology breakthrough in DM query optimization.
The research area of Inductive DBMS was thus born
 Inspiring significant work: DMQL, Mine Rule, MSQL, …

21-Mar-08
Suffer from limited generality and performance issues.
http://wis.cs.ucla.edu
4
DB2 Intelligent Miner


Model creation
Training:
CALL IDMMX.DM_buildClasModelCmd('IDMMX.CLASTASKS',
'TASK', 'ID', 'HeartClasTask',
'IDMMX.CLASSIFMODELS',
'MODEL', 'MODELNAME', 'HeartClasModel' );



Prediction
Stored procedures and virtual mining views
Outside the DBMS (like Cache Mining)


Data transfer delays
http://www-306.ibm.com/software/data/iminer/
21-Mar-08
http://wis.cs.ucla.edu
5
DB2 Intelligent Miner


Model creation
Training
CALL IDMMX.DM_buildClasModelCmd('IDMMX.CLASTASKS',
'TASK', 'ID', 'HeartClasTask',
'IDMMX.CLASSIFMODELS',
'MODEL', 'MODELNAME', 'HeartClasModel' );



Prediction
Stored procedures and virtual mining views
Outside the DBMS (like Cache Mining)


Data transfer delays
http://www-306.ibm.com/software/data/iminer/
21-Mar-08
http://wis.cs.ucla.edu
6
Oracle Data Miner

Algorithms






PL/SQL with extensions for mining
Models as first class objects


Adaptive Naïve Bayes
SVM regression
K-means clustering
Association rules, text, mining, etc.
Create_Model, Prediction, Prediction_Cost,
Prediction_Details, etc.
http://www.oracle.com/technology/products/bi/odm/index.html
21-Mar-08
http://wis.cs.ucla.edu
7
OLE DB for DM (DMX)

Model creation
Create mining model MemCard_Pred (
CustomerId long key, Age long continuous,
Profession text discrete,
Income long continuous,
Risk text discrete predict)
Using Microsoft_Decision_Tree;

Training
Insert into MemCard_Pred OpenRowSet(
“‘sqloledb’, ‘sa’, ‘mypass’”,
‘SELECT CustomerId, Age,
Profession, Income, Risk from Customers’)

Prediction Join
Select C.Id, C.Risk, PredictProbability(MemCard_Pred.Risk)
From MemCard_Pred AS MP Prediction Join Customers AS C
Where MP.Profession = C.Profession and AP.Income =
C.Income
AND MP.Age = C.Age;
21-Mar-08
http://wis.cs.ucla.edu
8
Defining a Mining Model

Define




The format of “training cases” (top-level entity)
Attributes, Input/output type, distribution
Algoritms and parameters
Example
CREATE MINING MODEL CollegePlanModel
(
StudentID
Gender
ParentIncome
Encouragement
CollegePlans
LONG
TEXT
LONG
TEXT
TEXT
KEY,
DISCRETE,
NORMAL CONTINUOUS,
DISCRETE,
DISCRETE PREDICT
) USING Microsoft_Decision_Trees
21-Mar-08
http://wis.cs.ucla.edu
9
Training
INSERT INTO CollegePlanModel
(StudentID, Gender, ParentIncome,
Encouragement, CollegePlans)
OPENROWSET(‘<provider>’, ‘<connection>’,
‘SELECT
StudentID,
Gender,
ParentIncome,
Encouragement,
CollegePlans
FROM CollegePlansTrainData’)
21-Mar-08
http://wis.cs.ucla.edu
10
Prediction Join
SELECT t.ID, CPModel.Plan
FROM CPModel PREDICTION JOIN
OPENQUERY(…,‘SELECT * FROM
NewStudents’) AS t
ON CPModel.Gender = t.Gender AND
CPModel.IQ = t.IQ
CPModel
21-Mar-08
ID
Gender
IQ Plan
ID
Gender
IQ
NewStudents
http://wis.cs.ucla.edu
11
OLE DB for DM (DMX) (cont.)

Mining objects as first class objects

Schema rowsets




Other features



Mining_Models
Mining_Model_Content
Mining_Functions
Column value distribution
Nested cases
http://research.microsoft.com/dmx/DataMining/
21-Mar-08
http://wis.cs.ucla.edu
12
Summary of Vendors’ Approaches

Built-in library of mining methods


Limitations





Script language or GUI tools
Closed systems (internals hidden from users)
Adding new algorithms or customizing old ones -Difficult
Poor integration with SQL
Limited interoperability across DBMSs
Predictive Markup Modeling Language (PMML) as
a palliative
21-Mar-08
http://wis.cs.ucla.edu
13
PMML

Predictive Markup Model Language




XML based language for vendor independent definition
of statistical and data mining models
Share models among PMML compliant products
A descriptive language
Supported by all major vendors
21-Mar-08
http://wis.cs.ucla.edu
14
PMML Example
21-Mar-08
http://wis.cs.ucla.edu
15
The Data Mining World According to
The Data Mining Software Vendors
Market Competition
Disclaimer
Disclaimer
This presentation contains preliminary information that may be changed substantially prior to final
commercial release of the software described herein.
The information contained in this presentation represents the current view of Microsoft Corporation on the
issues discussed as of the date of the presentation. Because Microsoft must respond to changing
market conditions, it should not be interpreted to be a commitment on the part of Microsoft, and Microsoft
cannot guarantee the accuracy of any information presented after the date of the presentation.
This presentation is for informational purposes only. MICROSOFT MAKES NO WARRANTIES,
EXPRESS, IMPLIED OR STATUTORY, AS TO THE INFORMATION IN THIS PRESENTATION.
Microsoft may have patents, patent applications, trademarks, copyrights, or other intellectual property
rights covering subject matter in this presentation. Except as expressly provided in any written license
agreement from Microsoft, the furnishing of this information does not give you any license to these
patents, trademarks, copyrights, or other intellectual property.
© 2005 Microsoft Corporation. All rights reserved.
Major Data Mining Vendors
• Platforms
 IBM
 Oracle
 SAS
• Tools
 SPSS
 Angoss
 KXEN
 Megaputer
 FairIsaac
 Insightful
Competition
Product
SQL Server 2005
Oracle 10g
IBM
SAS
SQL Server Analysis
Services
Oracle Data Mining
DB2 Intelligent Miner,
WebSphere
Enterprise Miner
http://otn.oracle.com/pr
oducts/bi/odm/odminin
g.html
http://www306.ibm.com/software/data/imin
er/
http://www.sas.com/technologies/analytics/data
mining/miner/factsheet.pdf
Link
API
OLEDB/DM, DMX,
XMLA, ADOMD.Net
Java DM, PL/SQL
SQL MM/6 based on UDF,
SQL SPROC
SAS Script
Algorithms
7 (+2)
8
6
8+
Text Mining
Yes
Yes
Yes
Yes
Marketing Pages
N/A
18
10
Dozens
Client Tools
Embeddable Viewers,
Reporting Services
Analysis tools, Webbased targeted
reports
WebSphere Portal (vertical
solution)
None
Discoverer
Excel AddIn
IM Visualization
Distribution
Included
Additional Package
Additional Packages
Separate Product
Target
Developers
Developers
DB2 IM Scoring module is for
developers; Other modules
are for analysts.
Analysts
Strengths
Powerful yet simple
API
Good credibility with
enterprise customers
Integration with other
BI technologies
New GUI, Leader of
JDM API
Mature, Market Leader. Extensive
customization and modelling abilities. Robust,
industry tested and accepted algorithms and
methodologies. Export to DB2 Scoring.
New GUI
CRM Integration
Mature product (6 years).
Good service model.
Scoring inside relational
engine. Strong partnership
with SAS
Not in-process with
relational engine Lacking
statistical functions
Poor Analyst experience
API overly complex
High price. Standard
Functionality. Poor API
(SQL MM). Confusing
product line.
Expensive. Proprietary. Customer relations
range from congenial to hostile.
Weaknesses
Inconsistent
Major DM
Vendors
 SAS Institute (Enterprise Miner)
 IBM (DB2 Intelligent Miner for Data)
 Oracle (ODM option to Oracle 10g)
 SPSS (Clementine)
 Unica Technologies, Inc. (Pattern
Recognition Workbench)
 Insightsful (Insightful Miner)
 KXEN (Analytic Framework)
 Prudsys (Discoverer and its family)
 Microsoft (SQL Server 2005)
 Angoss (KnowledgeServer and its
family)
 DBMiner (DBMiner)
 etc…
Platforms
 IBM
 Oracle
 SAS,
Tools
 SPSS
 Angoss
 KXEN
 Megaputer
 FairIsaac
 Insightful
ORACLE
Strengths
 Oracle Data Mining (ODM) Integrated into relational engine
– Performance benefits
– Management integration
– SQL Language integration
 ODM Client
– “Walks through” Data Mining Process
– Data Mining tailored data preparation
– Generates code
 Integration into Oracle CRM
– “EZ” Data Mining for customer churn, other applications
 Full suite of algorithms
– Typical algorithms, plus text mining and bioinformatics
 Nice marketing/user education
ORACLE
Weaknesses
 Additional Licensing Fees (base $400/user, $20K proc)
 Confusing API Story
– Certain features only work with Java API
– Certain features only work with PL/SQL API
– Same features work differently with different API’s
 Difficult to use
– Different modeling concepts for each algorithm
 Poor connectivity – ORACLE only
SAS
• Entrenched Data Mining Leader
 Market Share
 Mind Share
• “Best of Breed”
 Always will attract the top ?% of customers
• Overall poor product
 Only for the expert user (SAS Philosophy)
 Integration of results generally involves source code
• Integrated with ETL, other SAS tools
• Partnership with IBM
 Model in SAS, deploy in DB2
Our View ...




21-Mar-08
Progress toward high level data models and
integration with SQL, but
Closed systems,
Lacking in coverage and user-extensibility.
Not as popular as dedicated, stand-alone DM
systems, such as Weka.
http://wis.cs.ucla.edu
24
Weka

A comprehensive set of DM algorithms, and tools.

Generic algorithms over arbitrary data sets.


Independent on the number of columns in tables.
Open and extensible system based on Java.
These are the features that we want in our Inductive
DSMS---starting from SQL rather than Java!
21-Mar-08
http://wis.cs.ucla.edu
25
References


[Imielinski’ 96] Tomasz Imielinski and Heikki Mannila. A database
perspective on knowledge discovery. Commun. ACM, 39(11):58–64, 1996.
Carlo Zaniolo: Mining Databases and Data Streamswith Query Languages and Rules:
Invited Talk, Fourth International Workshop on Knowledge Discovery in Inductive
Databases, KDID 2005.
21-Mar-08
http://wis.cs.ucla.edu
26
Thank you!
21-Mar-08
http://wis.cs.ucla.edu
27