# Creating a training data schema reference

This sections explains how to create a training data schema reference to develop a machine learning routine.

## Procedure

1. Right-click the HDFS connection you previously created and choose Retrieve Schema.
2. Navigate to the pre-loaded training data file located at /user/puccini/machinelearning/decisiontrees/marketing/marketing\_campaign\_train.csv.

   ![](https://help.qlik.com/talend/en-US/components/7.3/Resources/images/developing_a_machine_learning_routine_with_talend_and_spark_06.png)
3. Click Next, name the schema and adjust the data types as needed.

   In this case, the defaults are accurate.

   ![](https://help.qlik.com/talend/en-US/components/7.3/Resources/images/developing_a_machine_learning_routine_with_talend_and_spark_07.png)
4. Click Finish.
5. Add a tHDFSConfiguration component to the palette.
6. Set Property Type to Repository.
7. Select the HDFS connection you created, MarketingCampaignData.

   ![](https://help.qlik.com/talend/en-US/components/7.3/Resources/images/developing_a_machine_learning_routine_with_talend_and_spark_08.png)