July 2008
Compatibility with Previous Releases of Oracle Data Miner
Oracle Data Miner 10.2 Overview
What’s New in Oracle Data Mining?
Oracle Data Mining Documentation
How to Start Oracle Data Miner
Oracle Data Miner Install and Uninstall
Oracle Data Miner Requirements
Oracle Data Miner Requirements for Mac OS X
Publish as Database Table Requirements
Oracle Data Miner Code Generator Install and Uninstall
Oracle Data Miner Code Generator Extension Requirements
Code Generator Extension Install Using a File
Code Generator Extension Install Using the Update Center
Using the Code Generator Extension
Code Generator Extension Disable
Oracle Data Miner 10.2.0.4.1 is a patch release for Oracle Data Miner 10.2.0.4.
Oracle Data Miner replaces all previous user interfaces to Oracle Data Mining, including Oracle Data Miner 10.1 and Data Mining for Java (DM4J). Models built using Oracle Data Miner 10.1 and DM4J cannot be used with Oracle Data Mining 10.2 and 11.1.
Note: You cannot connect to an Oracle 11g database using Oracle Data Miner 10.2; to connect to an Oracle 11g database, use Oracle Data Miner 11.1.
This document provides a brief overview of new features of Oracle Data Mining 10.2 and Oracle Data Miner 10.2.0.4, along with installation instructions for Oracle Data Miner.
These release notes describe how to install Oracle Data Miner on Mac OS.
Models built using Oracle Data Miner 10.1 cannot be used with Oracle Data Miner 10.2.
Oracle Data Miner requires Oracle 10g Release 2; you cannot connect to any other version of Oracle Database. Any patch version of Oracle 10g Release 2 is compatible with Oracle Data Miner.
Oracle Data Miner 10.1 preferences and connection information will be migrated automatically when you first launch Data Miner 10.2. You may have to reenter passwords.
You can have multiple versions (for example, 10.2 and 11.1) of Oracle Data Miner installed on the same system; they must be unzipped into different directories. Each version of Oracle Data Miner must connect to the correct version of Oracle Database.
If you encounter problems when using Oracle Data Miner, you can report them to Oracle Support (requires current product support contract) at Oracle MetaLink.
You can post general comments and suggestions to the Data Mining Discussion Forum on Oracle Technology Network.
Oracle Data Miner supports the new Oracle Data Mining 10.2 features, as described in What’s New in Oracle Data Mining?.
Oracle Data Mining includes native import/export facilities for moving data mining objects to other schemas. This is often a required step during deployment. Model import/export is not supported by Oracle Data Miner; it is supported by the Oracle Data Mining Java and PL/SQL programmatic interfaces. For information, see Oracle Data Mining Administrator’s Guide.
The rest of this section briefly describes the following new features of Oracle Data Miner 10.2:
A Mining Activity is a step-by-step guide for model build, apply, or test. A Build Activity outlines steps for data preparation, model build, and model test, where appropriate; the exact steps depend on the algorithm selected. An Apply Activity guides users through data preparation and model apply for a model created using a Build Activity or a model created outside of Data Miner using either the Oracle Data Mining 10.2 Java or PL/SQL API. A Test Activity guides users through data preparation and model test for a model created using a Build Activity or a model created outside of Data Miner using either the Oracle Data Mining 10.2 Java or PL/SQL API.
Mining Activities store metadata about model creation to simplify processing. For example, data that a model is applied to must be prepared in the same way as the data used to build the model. An Apply Activity uses the metadata from the Build Activity to prepare the data correctly for the apply operation.
The Mining Activities for Oracle Data Miner 10.2 have improved heuristics, especially for the data preparation steps.
Mining Activities are now available from the Activity menu. You can select a Build activity, an Apply activity, or a Test activity.
Mining Activities support the new functionality of Oracle Data Mining 10.2. For example, there are anomaly detection activities and classification activities that use the Decision Tree algorithm.
Once an activity is created, you can run an activity in several ways:
You can specify data as joins to a case table for input to a mining activity. The joins can be one-to-one or one-to-many. One-to-many joins support transactional data.
Names of tables and views, columns in tables and views, schemas, and
mining
objects except for model names and test metrics names may have mixed
case.
If you want a name to have both uppercase and lowercase letters in it,
enclose the name in double quotation marks (").
Model names and test metric names, however, are restricted to 25 or fewer characters and must be uppercase letters.
Oracle Data Miner has revised versions of the Sample and Stratified Sample transformation wizards that are easier to use.
Model and results viewers were redesigned, and new viewers were created for new models and results. The new model viewers are the Decision Tree Viewer, the Residual Plot Viewer, and the Anomaly Detection Viewer. The new results viewers are viewers for Predict and Explain, the new ROC viewer, and combined test metric viewers. The new Association Rules viewer incorporates lookup on item code. Model viewers now support automatic model transparency. A model is built on transformed data such as normalized or binned data; the results are converted based on transformations so that they reflect values in the original input data.
Oracle Data Miner supports Receiver Operator Characteristics (ROC) for classification models. Oracle Data Miner also supports Test activities.
Receiver Operating Characteristics (ROC) analysis is a useful method for evaluating classification models. ROC curves can be used to compare individual models and to determine thresholds which yield a high proportion of positive hits.
Residuals plots for regression models allow you to identify regions where the predictions are more accurate and less accurate.
For classification and regression models, Oracle Data Miner calculates the Predictive Confidence of the model, which measures how much better the model is than a naive model.
Tools | Publish as Database Table publishes data mining results as Database tables or views. You can publish the following results:
You can also compare classification test metrics.
The tables or views can be used by any application that can consume Oracle tables or views. You can publish results using tools such as BI-EE dashboards or OracleBI Discoverer. You can incorporate mining results, such as apply results, into applications created using Oracle Application Express, Oracle JDeveloper, or Oracle SQL Developer.
For requirements, see Publish as Database Table Requirements.
Follow these steps to publish data mining results to OracleBI Discoverer:
Oracle Data Miner include the automated data mining of DBMS_PREDICTIVE_ANALYTICS described at the end of What’s New in Oracle Data Mining 10.2?. Oracle Data Miner includes the following new wizards:
Oracle Data Miner allows you to generate a PL/SQL package based on one or more activities. The generated code allows programmers to easily integrate functionality developed in Data Miner within a separate application. The code generated uses PL/SQL and SQL only. Oracle Data Miner does not generate Java code; however, the generated PL/SQL packages can be called from a Java program using JDBC.
Oracle Data Miner includes Code Generator extensions to Oracle JDeveloper and to Oracle SQL Developer. These extensions allow the generated packages to be installed directly into the database. Both JDeveloper and SQL Developer have features that allow users to easily test and debug PL/SQL packages, further simplifying application integration.
For information about installing these extensions, see Oracle Data Miner Code Generator Install and Uninstall.
Detailed information about the Code Generator is in the online help for Data Miner and the Code Generator Extension; search for "code generator" to find the topics.
If the Code Generator extension to Oracle JDeveloper or to Oracle SQL Developer is installed, the documentation for Code Generator is part of the online help for JDeveloper or SQL Developer. To see the help, go to Help | About, select Contents; expand Oracle Data Miner PL/SQL Code Generator to see the documentation. The topic Code Generation Example shows how to generate and execute code for a simple apply activity.
The model build, apply, and test wizard are no longer supported. The only way to build, apply, or test a model using Oracle Data Miner is to use a mining activity.
The Oracle Data Mining 10g Release 2 (10.2) includes the following new algorithms and features:
Models built using the Oracle Data Mining 10.1 Java interface are not compatible with models built using the Oracle Data Mining 10.2 Java interface. There is no automatic way to migrate Oracle Data Mining programs written using the Oracle Data Mining 10.1 Java interface to programs that use the Oracle Data Mining 10.2 Java interface. Models built using the Oracle Data Mining 10.2 PL/SQL interface and the Oracle Data Mining 10.2 Java interface are compatible.
Data mining models may need to be moved between Oracle databases or schemas. For example, data mining specialists may build and test data mining models on one dedicated system. After the models are built and tested, selected models may be deployed to another system used by applications. Because the system where the models are developed and the system where the models are deployed usually do not share the same database, the model must be exported from the system where it was developed and then imported to system where it will be used by applications.
Anomaly Detection models use the one-class SVM algorithm to build models when there are no counterexamples.
Predictive Analytics is based on the PL/SQL package DBMS_PREDICTIVE_ANALYTICS that automates the later stages of data mining; it provides the following functionality:
Oracle Data Mining 10g Release 2 (10.2) documentation is part of the Oracle Database 10g Release 2 Documentation Library. To find Oracle Data Mining documentation, view or download the library; then click the Data Warehousing tab.
The tutorial for Oracle Data Miner 10.2 is available for download at Oracle Data Miner downloads page.
This tutorial is based on Oracle Data Miner 10.2.0.3; some screens for Oracle Data Miner 10.2.0.4.1 may be slightly different. The tutorial does not describe text mining.
In addition to the discussion in the tutorial, the online help for Oracle Data Miner contains an example that illustrates code generation for an apply activity.
The online help for Oracle Data Miner contains a text mining tutorial that illustrates basic text mining. To see the tutorial go to Help | Help Contents | Text Mining Tutorial.
Start Oracle Data Miner as follows:
data_miner_dir\bin\odminerw.exe,
where data_miner_dir is the folder where Oracle Data Miner is
installed.
Note: odminer.exe (without the w in its
name) displays a console window that can be used for troubleshooting.
odminer
in the directory data_miner_dir/bin, where
data_miner_dir is the directory where Oracle Data Miner is installed.odminer
in the directory where Oracle Data Miner
is installed. For example, if Data Miner is installed in
/Applications/odminer, type
cd /Applications/odminer/bin
./odminer & When you start Oracle Data Miner for the first time, you must define a database connection.
Note: The user name and password that you specify when you
define the connection must satisfy the requirements of Oracle Data
Mining.
Oracle Data Mining requires a small number of database permissions,
plus SELECT
access to the tables containing data for analysis. For details, see the
Oracle Data Mining Administrator’s Guide.
The first time that you start Oracle Data Miner, a dialog appears asking for the following information:
1521.orcl.Note: You must specify either the SID or the Service Name; you cannot specify both.
Click OK when you finish the definition. You are returned to the Choose Connection dialog. You can now select the connection that you just defined from the drop down box.
You may need to contact your Oracle Data Mining DBA for this information.
You can define additional connections and edit existing ones:
If Data Miner is running, you can manage (create, edit, and delete) database connections on the Connections tab of Tools | Preferences.
Oracle Data Miner does not require an installer; to install Data Miner, you simply unzip the download.
Before you can use Oracle Data Miner, you must connect to an appropriate account in an Oracle 10g Release 2 database. Before you can connect, you must install Oracle Data Mining 10g Release 2 and create at least one user account for data mining. For information about how to do this, see Oracle Data Mining Administrator’s Guide and the installation instructions for the platform that you are using.
Before you install Oracle Data Miner make sure that the requirements described in Oracle Data Miner Requirements are satisfied.
Oracle Data Miner requires the following:
Warning: Do not install the Data Mining Scoring Engine. The Data Mining Scoring Engine does not allow you to build models. If you accidentally install the Scoring Engine, you must remove it and install Oracle Data Mining. See the Oracle Data Mining Administrator's Guide for directions.
SELECT access to the tables containing data for analysis; for a
detailed list of privileges, see Required Privileges.Oracle Data Miner and Oracle Data Mining do not have to be installed on the same system. For example, you could install Oracle Data Mining on a system running UNIX and Oracle Data Miner on a PC running Microsoft Windows XP.
here are additional requirements for special purposes:
Oracle Data Miner requires following system privileges:
CREATE JOBCREATE TYPECREATE SESSIONCREATE TABLECREATE SEQUENCECREATE VIEWCREATE SYNONYMCREATE PROCEDUREEXECUTE ON ctxsys.ctx_ddl, required for text mining
only. If not available, text mining is disabled.SELECT privileges on the data being minedThe privileges required by Oracle Data Miner are the same as the privileges required for Oracle Data Mining. See Oracle Data Mining Administrator's Guide for details about how to create a user with these privileges.
CREATE PROCEDURE is satisfied by CREATE ANY
PROCEDURE. EXECUTE ON ctxsys.ctx_ddl is satisfied
by EXECUTE ANY PROCEDURE.
Oracle Data Miner searches for privileges by searching for direct
grants to the user as well as roles assigned to a user.
Oracle Data Miner searches one level deep within a role. For example,
suppose that the role ANALYST includes the role ODM_USER;
if the privileges are granted in the ODM_USER role (which
is "one level down" from the role ANALYST), Oracle Data
Miner will find them; if the privileges are defined in a role included
in ODM_USER, they will not be found.
Oracle Data Miner has the following requirements for Mac OS X:
Oracle Data Mining 10.2 cannot be installed directly on Mac OS X at this time. Therefore, you may have to connect to an Oracle database running on some other platform.
One solution it to use Parallels Desktop for Mac to create a Microsoft Windows virtual machine on your MacIntosh, and install the Microsoft Windows version of Oracle 10.2 EE with the Data Mining option on the Windows virtual machine; you can connect to the Oracle database running in the Microsoft Windows virtual machine. Another solution is to connect to Oracle 10.2 EE with the Data Mining Option on some other machine running Microsoft Windows, UNIX, or Linux.
The following restrictions apply to text mining using Oracle Data Miner:
CLOB, BLOB,
BFILE, LONG,
VARCHAR2, XMLType, CHAR, RAW,
or LONG RAW.INDEXTYPE ctxsys.context
is
part of the Seed Database. Oracle Text is installed by default when you
install the
Oracle Database. If you explicitly exclude it, you will not be able to
use Oracle Data Miner for text mining.If you just want to publish data mining results as Oracle Database tables or views, use the Oracle Data Miner menu selection Tools | Publish as Database Table. No additional software is required to publish the selected object; however, it may be necessary to configure the program that consumes the table. For detailed requirements for publishing to OracleBI Discover, see Publish to OracleBI Discoverer.
If you intend to use published mining results in OracleBI Discoverer, the following software is required; in each case click the link to download the software:
After you install the software, register the Oracle Data Miner Discoverer Gateway in the EUL to be able to access the published data mining results from a Discoverer Administrator:
These links describe creating an a EUL in two different cases:
Execute the following SQL script in the EUL user to register the Oracle Data Miner Discoverer Gateway with the EUL:
-- registration script
insert into EUL5_GATEWAYS(
gw_id, -- Gateway ID
gw_type, -- Type of Gateway
gw_gateway_name, -- Name of Gateway
gw_product_name, -- Name of the product
gw_description, -- Description of the gateway
egw_version, -- version of the gateway
egw_database_link, -- For remote DB provide dblink
egw_schema, -- Gateway owner
egw_sql_paradigm, -- SQL paradigm
gw_element_state, -- element state
gw_created_by, -- who created this gateway
gw_created_date, -- when it was created
gw_updated_by, -- who updated this gateway
gw_updated_date, -- when it was updated
notm
)
values
(
EUL5_ID_SEQ.NEXTVAL,
'EGW',
'ODMr 10.2 Discoverer Gateway',
'Oracle Data Mining',
'This gateway provides data mining results accessible to OracleBI',
'1.1',
NULL, -- dblink if dmuser is in remote
'DMUSER', -- Change to the schema as needed
'OBJECT',
0,
USER,
SYSDATE,
USER,
SYSDATE,
0
)Oracle Data Miner does not require an installer. To install Oracle Data Miner, you download a zip archive and unzip it. You must have an unzip tool.
You can have multiple versions of Data Miner installed on the same system. For example, you can have Data Miner 10.2 and Data Miner 11.1 installed on the same system.
It is not necessary to uninstall existing versions of Data Miner before you install new versions. However, you should unzip different versions of Data Miner into different directories.
Exact installation steps depend on the target operating system; you can install Oracle Data Miner on the following operating systems:
Data Miner does not require an installer. To install Data Miner, you need an unzip tool. If your system does not include an unzip tool, you can download a free, cross-platform unzip tool, Info-Zip, available at http://www.info-zip.org/.
Note: Do not install this Data Miner release into
any existing ORACLE_HOME.
You will not be able to uninstall it using Oracle Universal Installer.
Follow these steps to install Oracle Data Miner on Microsoft Windows:
java -version
in a Command Prompt window.odminer102.zip.odminer102.zip to the
desired directory, for example, unzip to C:\odminer.data_miner_dir\bin\odminerw.exe,
where data_miner_dir
is the folder where Oracle Data Miner is installed. For example,
execute C:\odminer\bin\odminerw.exeNote: odminer.exe (without the w in its
name) displays a console window that can be used for troubleshooting.
Data Miner does not require an installer. To install Data Miner, you need an unzip tool. If your system does not include an unzip tool, you can download a free, cross-platform unzip tool, Info-Zip, available at http://www.info-zip.org/.
Note: Do not install this Data Miner release into
any existing ORACLE_HOME.
You will not be able to uninstall it using Oracle Universal Installer.
Follow these steps to install Data Miner on UNIX or Linux:
java -version.odminer102.zip.odminer102.zip.odminer102.zip to the desired Oracle Data Miner
root directory; for example, use the following command to unzip the
file to the
directory odminer in the current working directory using
the unzip command unzip odminer102.zip -d odminer.
This command creates the directory odminer (in the
current working directory) and extracts the archive into it.odminer
in the directory data_miner_dir/bin,
where data_miner_dir is the directory where Oracle Data Miner
is installed.
If the script is not executable, reset the permissions: chmod +x
odminerData Miner does not require an installer.
Note: Do not install this Data Miner release into
any existing ORACLE_HOME.
You will not be able to uninstall it using Oracle Universal Installer.
Follow these steps to install Data Miner on Mac OS X:
odminer102.zip.odminer102.zip to the desired Oracle Data Miner
root directory; you can use StuffIt Expander or similar software to unzip the
downloaded file.odminer
in the directory where Oracle Data Miner
is installed. For example, if Data Miner is installed in /Applications/odminer,
type
cd /Applications/odminer/bin
./odminer & It is not necessary to uninstall existing versions of Data Miner before you install new versions. However, you should unzip different versions of Data Miner into different directories.
If you wish to uninstall Oracle Data Miner on any platform, delete data_miner_dir, the
directory where Oracle Data Miner is installed. Make sure that you delete all of the
subdirectories of data_miner_dir.
Oracle Data Miner includes a wizard and extensions for Oracle JDeveloper and for Oracle SQL Developer that support using generated code in applications.
The Code Generator Extension requires Oracle JDeveloper 10.1.3.3 or Oracle SQL Developer 1.5.1 (or a patch release of 1.5.1, such as 1.5.2).
The requirements for installing the Oracle Data Miner PL/SQL Code Generator Extension are the same as those for Oracle Data Miner 10.2.0.4.
Certain tasks have additional requirements, as follows:
DEBUG ANY PROCEDUREDEBUG CONNECT SESSION Follow these steps to install the Oracle Data Miner PL/SQL Code Generator Extension for either Oracle JDeveloper or Oracle SQL Developer:
ODMrExtJDev.zip for JDeveloper or
ODMrExtSQLDev15.zip for SQL Developer and save it into a temporary location;
do not save it in either the jdev_install\jdev\extensions or
sqldev_install\sqldeveloper\jdev\extensions directory.ODMrExtJDev.zip for
JDEveloper or ODMrExtSQLDev15.zip.
Click Next, and finish the wizard. Note: If the extensions that you wish to install are not in the update center, install them using the directions in Code Generator Extension Install Using a File.
Follow these steps to install the extension using the Update Center:
For a brief tutorial illustrating how to generate and execute code for an apply activity, see the Code Generation Example in Oracle Data Miner Help Contents.
To verify that the latest version of the Code Generator extension is installed, select Help | About in JDeveloper or SQL Developer and look for the following entry:
Oracle Data Mining PL/SQL Package oracle.dmt.dm4j.extension.codegenerator Version Number Loaded
Follow these steps to generate code for an already-built activity:
For a brief tutorial illustrating how to generate and execute code for an apply activity, see the Code Generation Example in Oracle Data Miner Help Contents. For more examples, see the Oracle Data Miner Tutorial.
Follow these steps to disable Oracle Data Miner PL/SQL Code Generator Extension from either Oracle SQL Developer or JDeveloper:
The following notes apply to Oracle Data Miner:
ORACLE_HOME\BIN\sqldr.exe.
You specify the location of SQL*Loader in
Tools | Preferences in Data Miner.
SYSDBA.SELECT VALUE FROM V$OPTION WHERE PARAMETER = 'Data Mining Scoring Engine';
VALUE
----------------------------------------------------------------
TRUE
then the Scoring Option is installed, and the Data Mining Option is not installed.
You must install the Data Mining Option. See the Oracle Data
Mining Administrator's Guide for directions.DM4J$.
All such tables and views contain metadata used by Oracle Data Miner.
If you delete any of these tables or views, Oracle Data Miner will not
function and no recovery is possible. In addition, Oracle Data Mining
creates tables in the user's schema with names that start with DM$;
do not delete any of these files, either. data_miner_dir, the directory where Data Miner is installed.jre directory to jrebackup.data_miner_dir. If you installed the
downloaded JRE to the default location for Microsoft Windows, the JRE directory
is C:\Program Files\Java\jre1.6.0_rel, for example,
C:\Program Files\Java\jre1.6.0_07, if you downloaded version 7.jre, for example,
rename jre1.6.0_07 to jre.The following are Oracle Data Miner bugs and Oracle Data Mining bugs that affect Oracle Data Miner:
Copyright © 2006, 2008, Oracle. All rights reserved.
Oracle, JD Edwards, PeopleSoft, and Siebel are registered trademarks of Oracle Corporation and/or its affiliates. Other names may be trademarks of their respective owners.