Introduction to ESTARD Data Miner

Introduction to Data Mining

Step By Step Guide

Program Interface

Using Databases

Using Rules & Decision Trees

BI Functions

Reporting & Saving 
 Home page

Query Wizard

Query Wizard is the easiest way to obtain Statistics, and Decision Rules or Decision Trees in a few steps. The wizard can be started by pressing "Query Wizard" button or selecting a corresponding menu item in the "Query Forming" menu.

Note: All controls, displayed within the wizard are also placed all together on the "Query Forming" page.

 

Step 1. Class/Examined Field Selection

  
  • "Class/Examined Field Selection" list - a list of fields grouped by tables from the Learning Database ("Database" page). Determine the Class field by selecting a field from the list. View recommendations for class field selecting.

Step 2. Selecting Examined Values - Classes

  
In case if the type of the selected Class/Examined Field is:
  • Text
  • Logical

the corresponding page will be displayed. All Classes will be displayed in the "Classes List" control. Select Classes  for analysis from the list of detected Classes.

Total number of Classes is shown below the "Classes List".
If the type of the selected Class/Examined Field is numeral (for example - "Cash"), you will be asked to create Classes manually with the help of controls on this page.

You can easily add, edit or remove Classes before their Ccreation, or recreate them in case if you've made some mistakes.

  • "From(min)" edit - put in the minimum value for the created Class.
  • "To(max)"  edit - put in the maximum value for the created Class..
  • "Add Class to the List" button - adds the values (from "From(min)" and "To(max)" controls) to the "Classes List".
  • "Classes List" control - displays the list of Classes to be created. The content of this control can be edited with the help of buttons on the right: "Delete from the List" and "Clear "Classes List"" buttons.
  • "Delete from the List" button - pressing this button will remove the selected Class from the "Classes List".
  • "Clear "Classes List" button - removes all Classes from the "Classes List".
  • "View Field Values" button - press this button to view statistics for values met in the class field.

 

Step 3. Fields Selection
Next step is selecting the fields to be used for analysis. For example: if fields "Company Name" and "Address" are not selected, then no Decision Rules or Decision Trees will be created with the use of these fields.

It is important to mark fields, that might contain important information.

For example: "Company Name" field can be marked, but it is expected, that it will contain unique text values that do not correlate with other values. More important in this case are fields that contain economic or statistical data.

Class field is marked with red color. Fields, that are not recommended for use, are marked with grey color.

Step 4. Query Type Selection
Select the type of query you want to process. You can create Decision Rules or Decision Tree.

Step 5. Query Settings
To find out how to start working with settings view "Getting Started".

Depending on the Type of the Query you have selected you will be asked to form Query Settings.

In case if you have selected Rules Query, the"Rules Query Settings"  page will be shown.

  • "Element belongs to class(%)" - input the probability for Decision Rules.
  • "Minimum number of cases for a Rule" - the rules, describing less than minimum  number of cases, will be ignored by the program.
  • "Float fields minimum value" - determines minimum rational values that Estard Data Miner will use for the analysis.
  • "Maximum Rules number for a Class" - this control allows to limit the number of created Rules. For example, if setting controls value to 10, the program will create no more than 10 Rules for each Class.

 
If you have selected Decision Tree Query, the "Decision Tree Query Settings" page will be displayed .

Decision Trees can be created in various ways.

  • "Build Automatically" control- mark it if you want the program to decide how to create the Decision Tree.
  • "Build Tree for Each Field" control - mark it if you want to recieve a Decision Tree for each Field, marked in the "Selection of Fields" control. Time, necessary to obtain Decision Trees is proportional to number of Fields used in analysis processing.
  • "Build starting with Field" control - mark it to create a concrete Decision Tree, strarting with the Field selected in the list below the control.
  • "Build a Single Tree"  - in case if some Classes were not defined after building the first Tree, Estard Data Miner will try to build a new Tree. Marking this control will make Estard Data Miner to create a single Decision Tree.
  • "Stop After defining All Classes" control - will stop Decision Trees creation in case if all Classes were defined.

Decision Tree Output Settings:

  • "Clear previous Trees before adding new ones" option - clears up the displayed Decision Trees before adding new Decision Trees.
  • "Add new Decision Trees to previously created"  - if some Decision Trees are displayed in the control on the "Decision Tree Output" page, they won't be removed when creating a new Tree.
Exceptions settings allow to set the program to search for exceptions from dependencies in data. You also can make the program to search for exceptions only for classes met in some number of cases.

"Search for exceptions" control - allows to turn on and off exceptions searching.

"Minimum number of Class cases" control - Classes, met in less number of cases than set in this control, will not be searched for exceptions.

"Minimum exception difference(%)" control - allows to set the program sensitivity to exceptions.

"Other classes occurance for exception" - how many cases of other classes can be met for the exception.

Step 6. Finishing

 
Press the "Finish" button to start the data mining process.