RODM (version 1.1)

RODM_create_ai_model: Create an Attribute Importance (AI) model

Description

This function creates an Oracle Data Mining Attribute Importance (AI) model.

Usage

RODM_create_ai_model(database,  data_table_name,  case_id_column_name = NULL,  target_column_name, model_name = "AI_MODEL", auto_data_prep = TRUE, retrieve_outputs_to_R = TRUE, leave_model_in_dbms = TRUE,  sql.log.file = NULL)

Arguments

database

Database ODBC channel identifier returned from a call to RODM_open_dbms_connection

data_table_name

Database table/view containing the training dataset.

case_id_column_name

Row unique case identifier in data_table_name.

target_column_name

Target column name in data_table_name.

model_name

ODM Model name.

auto_data_prep

Setting that specifies whether or not ODM should perform automatic data preparation.

retrieve_outputs_to_R

Flag controlling if the output results are moved to the R environment.

leave_model_in_dbms

Flag controlling if the model is dropped or left in RDBMS.

sql.log.file

File where to append the log of all the SQL calls made by this function.

Value

If retrieve_outputs_to_R is TRUE, returns a list with the following elements:

model.model_settings

Table of settings used to build the model.

model.model_attributes

Table of attributes used to build the model.

ai.importance

Table of features along with their importance.

Details

Attribute Importance (AI) uses a Minimum Description Length (MDL) based algorithm that ranks the relative importance of attributes in their ability to contribute to the prediction of a specified target attribute. This algorithm can provide insight into the attributes relevance to a specified target attribute and can help reduce the number of attributes for model building to increase performance and model accuracy.

For more details on the algotithm implementation, parameters settings and characteristics of the ODM function itself consult the following Oracle documents: ODM Concepts, ODM Application Developer's Guide, and Oracle PL/SQL Packages: Data Mining, listed in the references below.

References

Oracle Data Mining Concepts 11g Release 1 (11.1) http://download.oracle.com/docs/cd/B28359_01/datamine.111/b28129/toc.htm

Oracle Data Mining Application Developer's Guide 11g Release 1 (11.1) http://download.oracle.com/docs/cd/B28359_01/datamine.111/b28131/toc.htm

Oracle Data Mining Administrator's Guide 11g Release 1 (11.1) http://download.oracle.com/docs/cd/B28359_01/datamine.111/b28130/toc.htm

Oracle Database PL/SQL Packages and Types Reference 11g Release 1 (11.1) http://download.oracle.com/docs/cd/B28359_01/appdev.111/b28419/d_datmin.htm#ARPLS192

See Also

RODM_drop_model

Examples

# Determine attribute importance for survival in the sinking of the Titanic 
# based on pasenger's sex, age, class, etc.

## Not run: 
# DB <- RODM_open_dbms_connection(dsn="orcl11g", uid="rodm", pwd="rodm")
# 
# data(titanic3, package="PASWR")
# db_titanic <- titanic3[,c("pclass", "survived", "sex", "age", "fare", "embarked")]
# db_titanic[,"survived"] <- ifelse(db_titanic[,"survived"] == 1, "Yes", "No")
# RODM_create_dbms_table(DB, "db_titanic")   # Push the table to the database
# 
# # Create the Oracle Data Mining Attribute Importance model
# ai <- RODM_create_ai_model(
#    database = DB,                      # Database ODBC connection
#    data_table_name = "db_titanic",     # Database table containing the input dataset
#    target_column_name = "survived",    # Target column name in data_table_name
#    model_name = "TITANIC_AI_MODEL")    # Oracle Data Mining model name to create
# 
# attribute.importance <- ai$ai.importance
# ai.vals <- as.vector(attribute.importance[,3])
# names(ai.vals) <- as.vector(attribute.importance[,1])
# 
# #windows(height=8, width=12)
# barplot(ai.vals, main="Relative survival importance of Titanic dataset attributes",
#         ylab = "Relative Importance", xlab = "Attribute", cex.names=0.7)
# 
# ai        # look at the model details
# 
# RODM_drop_model(DB, "TITANIC_AI_MODEL")    # Drop the model
# RODM_drop_dbms_table(DB, "db_titanic")     # Drop the database table
# 
# RODM_close_dbms_connection(DB)
# ## End(Not run)