Every complete example in this document is available in a zip file that you can download. The zip file includes a SQL script file that creates the input tables for the examples. If you are reading this document on https://docs.teradata.com/, you can download the zip file from the attachment in the left sidebar.
This section shows the input table, SQL query, and output tables of an example using TD_NaiveBayes.
The following table contains a subset of housing dataset.
Only part of the dataset is shown in this example.
DROP TABLE housing_train; CREATE TABLE housing_train (sn integer, price real, lotsize real, bedrooms integer, bathrms integer, stories integer, driveway varchar(10), recroom varchar(10), fullbase varchar(10), gashw varchar(10), airco varchar(10), garagepl integer, prefarea varchar(10), homestyle varchar(10)) PRIMARY INDEX(sn); Insert into housing_train values(1,42000,5850,3,1,2,'yes','no','yes','no','no',1,'no','Classic'); Insert into housing_train values(2,38500,4000,2,1,1,'yes','no','no','no','no',0,'no','Classic'); Insert into housing_train values(3,49500,3060,3,1,1,'yes','no','no','no','no',0,'no','Classic'); Insert into housing_train values(4,60500,6650,3,1,2,'yes','yes','no','no','no',0,'no','Eclectic'); Insert into housing_train values(5,61000,6360,2,1,1,'yes','no','no','no','no',0,'no','Eclectic'); ...
SELECT * FROM housing_train ORDER BY 1;
TD_NaiveBayes SQL Call
SELECT * FROM TD_NaiveBayes( ON housing_train AS InputTable USING ResponseColumn('homestyle') NumericInputs('price','lotsize','bedrooms','bathrms','stories','garagepl') CategoricalInputs('driveway','recroom','fullbase','gashw','airco','prefarea') ) AS dt ORDER BY 1,2;
class | variable | type | category | cnt | sum | sumsq | totalcnt | smoothingfactor |
---|---|---|---|---|---|---|---|---|
bungalow | airco | CATEGORICAL | no | 14 | ? | ? | 392 | 1.72413793103448E-002 |
bungalow | airco | CATEGORICAL | yes | 42 | ? | ? | 392 | 1.72413793103448E-002 |
bungalow | bathrms | NUMERIC | ? | 56 | 1.05000000000000E 002 | 2.19000000000000E 002 | 392 | ? |
... | ... | ... | ... | ... | ... | ... | ... | ... |
Classic | recroom | CATEGORICAL | no | 133 | ? | ? | 980 | 7.04225352112676E-003 |
Classic | recroom | CATEGORICAL | yes | 7 | ? | ? | 980 | 7.04225352112676E-003 |
Classic | stories | NUMERIC | ? | 140 | 2.07000000000000E 002 | 3.49000000000000E 002 | 980 | ? |
... | ... | ... | ... | ... | ... | ... | ... | ... |
Eclectic | recroom | CATEGORICAL | no | 233 | ? | ? | 2072 | 3.35570469798658E-003 |
Eclectic | recroom | CATEGORICAL | yes | 63 | ? | ? | 2072 | 3.35570469798658E-003 |
Eclectic | stories | NUMERIC | ? | 296 | 5.31000000000000E 002 | 1.15300000000000E 003 | 2072 | ? |
As the data is in dense format, you need to use TD_Unpivoting function to change the data to sparse format.
DROP TABLE housing_train_sparse; CREATE MULTISET TABLE housing_train_sparse AS( SELECT * FROM TD_UNPIVOTING( ON housing_train AS InputTable USING IDColumn('sn') TargetColumns('price','lotsize','bedrooms','bathrms','stories','garagepl','driveway','recroom','fullbase','gashw','airco','prefarea') AttributeColName('AttributeName') ValueColName('AttributeValue') Accumulate('homestyle') ) AS dt) WITH data;
TD_NaiveBayes SQL Call
SELECT * FROM TD_NaiveBayes( ON housing_train_sparse AS InputTable USING ResponseColumn('homestyle') AttributeNameColumn('AttributeName') AttributeValueColumn('AttributeValue') NumericAttributes('price','lotsize','bedrooms','bathrms','stories','garagepl') CategoricalAttributes('driveway','recroom','fullbase','gashw','airco','prefarea') ) AS dt Order by 1,2, 3, 4;
class | variable | type | category | cnt | sum | sumsq | totalcnt | smoothingfactor |
---|---|---|---|---|---|---|---|---|
bungalow | airco | CATEGORICAL | no | 14 | ? | ? | 392 | 1.72413793103448E-002 |
bungalow | airco | CATEGORICAL | yes | 42 | ? | ? | 392 | 1.72413793103448E-002 |
bungalow | bathrms | NUMERIC | ? | 56 | 1.05000000000000E 002 | 2.19000000000000E 002 | 392 | ? |
... | ... | ... | ... | ... | ... | ... | ... | ... |
Classic | recroom | CATEGORICAL | no | 133 | ? | ? | 980 | 7.04225352112676E-003 |
Classic | recroom | CATEGORICAL | yes | 7 | ? | ? | 980 | 7.04225352112676E-003 |
Classic | stories | NUMERIC | ? | 140 | 2.07000000000000E 002 | 3.49000000000000E 002 | 980 | ? |
... | ... | ... | ... | ... | ... | ... | ... | ... |
Eclectic | recroom | CATEGORICAL | no | 233 | ? | ? | 2072 | 3.35570469798658E-003 |
Eclectic | recroom | CATEGORICAL | yes | 63 | ? | ? | 2072 | 3.35570469798658E-003 |
Eclectic | stories | NUMERIC | ? | 296 | 5.31000000000000E 002 | 1.15300000000000E 003 | 2072 | ? |