Concept: Statistics Worksheet¶
This content is also included in the free Dataiku Academy course, Basics 102, which is part of the Core Designer learning path. Register for the course there if you’d like to track and validate your progress alongside concept videos, summaries, hands-on tutorials, and quizzes.
For a dataset in Dataiku, it is quite useful to have a designated space with the tools for performing statistical analyses. This is just what a statistics worksheet provides.
A Worksheet provides a visual summary of exploratory data analysis (EDA) tasks. To create or access worksheets, go to the Statistics tab of your dataset.
The worksheet header consists of a worksheet menu. You can use the worksheet menu to create a new worksheet or rename, duplicate, and delete worksheets. You can also switch from one worksheet to another.
There are also buttons and menu items for creating a new card, running the worksheet in a container, changing the global confidence level for statistical tests, and specifying how to sample the dataset used in the worksheet. Note that by default, Dataiku computes statistics on a sample of first records in your dataset.
For more information about worksheets, see The Worksheet Interface in the reference documentation.