Version 7.0 – March 2020
Dataiku DSS provides the ability to perform exploratory data analysis (EDA) through the Statistics tab of a dataset. Using this feature, you can implement descriptive statistics, inferential statistics, and principal component analysis (PCA). Learn more in our tutorial and in the reference documentation.
Enhanced Git Integration for Projects
Dataiku DSS projects have always been backed by a local Git repository. Now you can connect a project to a remote Git repository, create branches off of the main branch, push your changes to the remote repository and merge the branch into master, and pull those changes from the remote repository back into your original DSS project. Learn more in our tutorial and in the reference documentation.
Individual Prediction Explanations
Row-level interpretability for Machine Learning models allows you to get a detailed explanation of why a Dataiku model made a given prediction, even when the model is a “black-box” model. Learn more in the machine learning tutorial and in the reference documentation.
Project Creation Macros
Project creation macros are a new type of plugin component. Administrators can define special conditions and setup actions within the macro. This, in turn, allows users to safely create projects on the DSS instance with the correct code environments and security settings. Learn more in the reference documentation.
Merge Folders Recipe
The Merge Folders recipe is a no-code solution to the need to gather together files spread across multiple folders.
Find all details in our release notes.