Efficient Data Cleaning Techniques in Dataiku?

[Miasm1]

Hi all,

How do you handle missing values and outliers in Dataiku? Any plugins or workflows you'd recommend for efficient data cleaning?

Thanks for your tips!

[AlexT]

Hi @Miasm1 ,

1) For missing values -> https://doc.dataiku.com/dss/latest/machine-learning/features-handling/index.html#features-handling  you can handle as part of feature handling. 
https://knowledge.dataiku.com/latest/ml-analytics/model-design/concept-feature-handling.html#handle-...

2) For outlier on clustering models see :  https://doc.dataiku.com/dss/latest/machine-learning/unsupervised/settings.html#outliers-detection

You can use code -> https://developer.dataiku.com/latest/tutorials/plugins/recipes-clipping-dataset/index.html 

Or prepare recipe
https://doc.dataiku.com/dss/latest/preparation/processors/number-clipping.html

[Turribeach]

@AlexT It's a bot.