{[ promptMessage ]}

Bookmark it

{[ promptMessage ]}

USE_EM_61 - Using SAS Enterprise Miner 6.1 SEMMA 1 Opening...

Info iconThis preview shows pages 1–10. Sign up to view the full content.

View Full Document Right Arrow Icon
Using SAS Enterprise Miner 6.1 - SEMMA 1. Opening Enterprise Miner 2 1.1 Initiating Project 3 1.2 Starting Project and Diagram 5 1.3 Initiating Data Exploration 6 1.4 Setting Prior Probability and Profit Matrix 13 2. SEMMA Data Mining Process Used in Enterprise Miner 16 2.1 Sample 16 2.2 Explore 18 2.3 Modify 22 2.4 Model 24 2.5 Assess 28 2.6 Utilities 29 2.7 Text Mining 31 3. A Simple Data Mining Flow 34 3.1. E xploration with Graphics Explore node 34 3.2 . E xploration with MultiPlot node 37 3.3. E xploration with StatExplore node 38 3.4. S ampling with Data Partition node 44 3.5. M odify with Impute node 46 3.6. M odify with Transformation node 50 3.7. Fitting Candidate M odel Decision Trees 55 3.8. Fitting Candidate M odel Logistic Regression 56 3.9. Fitting Candidate M odel Neural Network 63 3.10. Models A ssessment Model Comparison 64 3.11. S coring New Data Set 65 Appendix 1 Data Used in Lecture 70
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
2 1. Opening SAS Enterprise Miner To begin, select Start => Program => SAS => Enterprise Miner 6.1 . This opens the Start Enterprise Miner Window. Click Log On
Background image of page 2
3 1.1 Initiating Project Select New Project.. from the Welcome to Enterprise Miner Screen Click Next Type your project title (such as My Project ) in the Name box Select Server Directory , e.g., ― F:\ Click Next
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
4 Click Next Click Finish
Background image of page 4
5 1.2 Starting Project and Diagram Select the Start-Up Code Tab and Type in the appreciate code to define the library for the course data. Select Run Now . Select OK Right Click Diagrams Type in the diagram name, for example, Diag01. Select OK to get into the Enterprise Miner working environment Components in the Enterprise Miner Window Tool Bar Tool Bar Short Cut Button Project Panel Properties Panel Diagram Workspace Help Panel Status Bar
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
6 1.3 Initiating Data Exploration Defining a Data Source This example uses the DONORS data set in the DLEC1 library. 1. To define a data source, right-click on Data Sources in the Project Panel and select Create Data Source .
Background image of page 6
7 2. In the Data Source Wizard Metadata Source window, be sure SAS Table is selected as the source and select Next> . 3. To choose the desired data table select Browse… . 4. Double-click on the DLEC1 library to see the data tables in the library.
Background image of page 7

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
8 5. Select the DONORS data set, and then select OK . 6. Select Next> . Observe that this data table has 6,974 observations (rows) and 21 variables (columns). 7. Select Next> after examining the data table properties
Background image of page 8
9 All analysis packages must determine how to use variables in the analysis. If you choose the basic option here, the initial role and level of the variables will be determined by the variable type and format values. If you choose the advanced option here, initial roles and levels are based on the variable type, format values, and the number of distinct values contained in the variable.
Background image of page 9

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Image of page 10
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}