- Open a project by clicking the project in the project list and select Datasets in the Navigation bar.You must select a project before you can access the Datasets module.
- Select Create Template.You must add or set a default Personal Connection before you can Create a Dataset Template.
- In the Catalog tab, set the following properties:
Property Description Name Dataset template name. Description Description of the dataset template. Feature Catalog Catalog type to define a dataset template. Select Vantage for a Vantage type feature catalog and None for no catalog.
Depending on the selection of this property, this template dialog affects the wizard options.Tags Allows you to add tags with the dataset template. Database Specifies database to store data features information. Table Specifies table to store data features information. - Select Next.
- If Feature Catalog is set to None:
- In the Config dialog tab, set the following properties:
Property Description Common Settings Custom Properties: Specifies custom properties in the form of key/value pair. Template Query: Specifies a template query that will fetch data for the dataset template. Scope Settings Specifies properties for different scope levels: Train, Evaluate, Score. Custom Properties: Specifies custom properties in the form of key/value pair for each of the selected scope. Template Query: Specifies a template query that will fetch data to execute training, evaluation and scoring jobs. - Select Create to save the dataset template.
- In the Config dialog tab, set the following properties:
- If Feature Catalog is set to Vantage, use the following steps 7 to 9 to continue creating dataset template.
- In the Features dialog tab, set the following properties:
Property Description Query Defines SQL query to select features and entity key for catalog. Features Displays the metadata of the provided query and ability to perform further operations. - You can define an SQL query to get an introspect on the features fetched directly from database by selecting Run. Retrieved results displays in the following Features table with the ability to further specify collection by selecting or deselecting check boxes adjacent to each feature.
- A small key icon displays in parallel to one and only one row indicating it as Entity Key. You can change entity key by switching between features using the same panel. An entity key cannot be a feature simultaneously, hence upon switching, a prompt appears to confirm selection.
- You can also retrieve actual result of features from SQL query defined earlier by selecting Preview Data.
- Select Next to go to the next tab.
- In the Entity & Target tab, set the following properties
Property Description Query Defines SQL query to select variables (entity sample and targets) for catalog. Features Displays the metadata of the provided query and ability to perform further operations. - You can define an SQL query to retrieve desired variables by selecting Run. Retrieved results display in the Variables table with the ability to further specify sample by selecting or deselecting check boxes adjacent to each row. Entity Key selection and operations are exactly the same as Features step.
- You can also retrieve actual result of sample from SQL query and JOIN result of target variables and features defined earlier by selecting Preview Data.
- Select Next to go to the next tab.
- In the Predictions tab, set the following properties:
Property Description Database Name Defines database name to store dataset template Table Name Defines table name to store dataset template with or without catalog Entity Selection Specifies an SQL query to load entity keys for scoring. - Select Create.