Variable Clustering 1 Variable Clustering Variable clustering finds

  • Slides: 13
Download presentation
Variable Clustering 1

Variable Clustering 1

Variable Clustering Variable clustering finds groups of variables that are as correlated as possible

Variable Clustering Variable clustering finds groups of variables that are as correlated as possible among themselves and as uncorrelated as possible with variables in other clusters. The basic algorithm is binary and divisive. All variables start in one cluster. A principal components analysis is done on the variables in the cluster. 2

If the second eigenvalue is greater than a specified threshold (in other words, there

If the second eigenvalue is greater than a specified threshold (in other words, there is more than one dominant dimension), then the cluster is split. The PC scores are then rotated obliquely so that the variables can be split into two groups. This process is repeated for the two child clusters until the second eigenvalue drops below the threshold. 3

The VARCLUS Procedure PROC VARCLUS DATA=SAS-data-set <options>; VAR variables; RUN; 4

The VARCLUS Procedure PROC VARCLUS DATA=SAS-data-set <options>; VAR variables; RUN; 4

Variable Clustering, the develop data set Mortgage Balance Number of Checks Credit Card Balance

Variable Clustering, the develop data set Mortgage Balance Number of Checks Credit Card Balance Checking Deposits Teller Visits Age 5

Where we are proc contents data=d. imputed; run; 6

Where we are proc contents data=d. imputed; run; 6

Get name of numeric input variables from dictionary. columns /*get names of numeric variables

Get name of numeric input variables from dictionary. columns /*get names of numeric variables in a macro variable note that leaving out brclus 5 gives us 4 indicator variables*/ proc sql; describe table dictionary. columns; select name into : inputs separated by " " from dictionary. columns where memname="IMPUTED" and libname="D" and name ^= "Ins" and name ^="brclus 5" and type="num" ; quit; %put &inputs; 7

Variable Clustering proc varclus data=d. imputed maxeigen=. 7 hi short; var &inputs ; title

Variable Clustering proc varclus data=d. imputed maxeigen=. 7 hi short; var &inputs ; title "Variable Clustering of Imputed Data Set"; run; title; 8

Use ODS to get some stuff. ods output clusterquality=summary rsquare=clusters; proc varclus data=d. imputed

Use ODS to get some stuff. ods output clusterquality=summary rsquare=clusters; proc varclus data=d. imputed maxeigen=. 7 short hi; var &inputs ; run; 9

proc print data=summary; run; 10

proc print data=summary; run; 10

Numerous possibilities for summarizing clusters. Principal Components Pick one variable: Based on subject matter

Numerous possibilities for summarizing clusters. Principal Components Pick one variable: Based on subject matter Statistics 11

proc print data=clusters; where numberofclusters=39; run; 12

proc print data=clusters; where numberofclusters=39; run; 12

One variable per cluster /* Pick one variable per cluster for the first 10

One variable per cluster /* Pick one variable per cluster for the first 10 The others are clusters of one variable */ %let reduced= MIPhone MICCBal Dep MM ILS MTGBal Income POS CD IRA brclus 1 Sav NSF Age Sav. Bal LOCBal NSFAmt Inv MIHMVal CRScore MIAcct. Ag Inv. Bal Dir. Dep CCPurc SDB Cash. Bk Acct. Age In. Area ATMAmt DDABal DDA brclus 2 CC HMOwn Dep. Amt Phone ATM LORes brclus 4; 13

FLAT CLUSTERING HIERARCHICAL CLUSTERING What is clustering GroupingFLAT CLUSTERING HIERARCHICAL CLUSTERING What is clustering Grouping
DATA MINING CLUSTERING Clustering 4 Clustering unsupervised classificationDATA MINING CLUSTERING Clustering 4 Clustering unsupervised classification
Clustering Kmeans Clustering 2 means Clustering Curve ShowsClustering Kmeans Clustering 2 means Clustering Curve Shows
Kmeans Clustering Kmeans Clustering What is clustering WhyKmeans Clustering Kmeans Clustering What is clustering Why
C 0 clustering Liang Zheng Clustering Clustering alongC 0 clustering Liang Zheng Clustering Clustering along
Variable o Local Variable o Global Variable FunctionVariable o Local Variable o Global Variable Function
Variable Scope Mendeskripsikan Variable Scope Variable Scope ruangVariable Scope Mendeskripsikan Variable Scope Variable Scope ruang
Variable Scope Mendeskripsikan Variable Scope Variable Scope ruangVariable Scope Mendeskripsikan Variable Scope Variable Scope ruang
1 Facility Training 2 AGENDA e FINDS INTRODUCTION1 Facility Training 2 AGENDA e FINDS INTRODUCTION
HMM finds behavioral patterns Zoltn Szab Etvs LorndHMM finds behavioral patterns Zoltn Szab Etvs Lornd
The Duel for North America France Finds aThe Duel for North America France Finds a
Latif finds a coincidence time resolution of 0Latif finds a coincidence time resolution of 0
13 Fundamentals wc 25319 Domestic Sentiment Mueller finds13 Fundamentals wc 25319 Domestic Sentiment Mueller finds
MICROSOFT GOTOMARKET SERVICES SUCCESS STORY Audioteka Finds NewMICROSOFT GOTOMARKET SERVICES SUCCESS STORY Audioteka Finds New
Fast Finds Making Google BLAST Faster Dr LaurenceFast Finds Making Google BLAST Faster Dr Laurence
A cohort study of mammography screening finds thatA cohort study of mammography screening finds that
National dosimetric audit network finds discrepancies in AAANational dosimetric audit network finds discrepancies in AAA
Archival Archaeology Unearthing finds about archives and specialArchival Archaeology Unearthing finds about archives and special
The Silent Second An HR manager finds hisThe Silent Second An HR manager finds his
WITH Ada TextIO PROCEDURE ThreeDays IS Finds yesterdayWITH Ada TextIO PROCEDURE ThreeDays IS Finds yesterday
Warm Up PointSlope Form Alice finds her flowerWarm Up PointSlope Form Alice finds her flower
Gyges Ring A lowly shepherd finds a ringGyges Ring A lowly shepherd finds a ring
Tavira finds in tourism an important component ofTavira finds in tourism an important component of
Sensitivity analysis Finds most important issues that matterSensitivity analysis Finds most important issues that matter
Lesson 1 Excuse me A man finds aLesson 1 Excuse me A man finds a
GOALSEEK Part of Standard Excel Installation Finds theGOALSEEK Part of Standard Excel Installation Finds the
This presentation relates to the finds of aThis presentation relates to the finds of a
MICROSOFT GOTOMARKET SERVICES SUCCESS STORY Scorpion Software FindsMICROSOFT GOTOMARKET SERVICES SUCCESS STORY Scorpion Software Finds
He who finds his life will lose itHe who finds his life will lose it
Using Alloy to model an algorithm that findsUsing Alloy to model an algorithm that finds
NIGHT BY ELIE WIESEL QUICKWRITES Mentor Eliezer findsNIGHT BY ELIE WIESEL QUICKWRITES Mentor Eliezer finds
Nelder Mead Fminsearch uses Nelder Mead Fminsearch findsNelder Mead Fminsearch uses Nelder Mead Fminsearch finds
Firefighter Indoor Navigation using Distributed SLAM FINDS MajorFirefighter Indoor Navigation using Distributed SLAM FINDS Major
Faster finds from Gallo to Google Applications toFaster finds from Gallo to Google Applications to
King David Finds the Heart of God 1King David Finds the Heart of God 1
DWP finds out customer How to market ProgramDWP finds out customer How to market Program
Hello Year 9 I hope this finds youHello Year 9 I hope this finds you
Dijkstras Algorithm Dijkstras Algorithm This algorithm finds theDijkstras Algorithm Dijkstras Algorithm This algorithm finds the
Regulatory Permits for Activities Funded Under FINDs AssistanceRegulatory Permits for Activities Funded Under FINDs Assistance
King David Finds the Heart of God 1King David Finds the Heart of God 1