Profile

Onni Koski
Onni Koski
This user account status is Approved
About About
Posts Posts
Comments Comments
A better explanation on pipeline orchestration for testing would have been helpful.
On Create tests for data pipelines
How do you deal with missing values in features?
On Identify features and labels in a dataset for machine learning
Very helpful article. Someone recommended hashing as a solution for partition key issues. Thoughts?
On Calculate and evaluate data distribution based on partition key selection
Are there any performance considerations we should be aware of when using Change Feed?
On Denormalize data by using Change Feed and Azure Functions
You should also consider data quality services for better cleansing results.
On Cleanse data
I found the concept of model versioning while retraining to be really useful.
On Automate model retraining based on new data additions or data changes