Sign up to take part
Registered users can ask their own questions, contribute to discussions, and be part of the Community!
Registered users can ask their own questions, contribute to discussions, and be part of the Community!
For our 16th Conundrum we will be beginning a series focused on taking you through a journey. Each Conundrum will use the output data from the previous - although we will also provide data to start with if you want to start in the middle! With that in mind - letโs get started!
Situation: We have obtained a dataset of user reviews for fashion items in our store. Before this information becomes useful for our Machine Learning processes, we need to prepare, clean and shape it into a useful format. In addition, we should also explore what this data contains and perhaps gain some initial insights.
But this is not a one-off exercise, we need to be able to run this pipeline on demand, hence once it is built, a scenario has to be configured to refresh the data, and run metrics and checks where applicable.
There are two paths that could be taken, one purely using the DSS visual elements and another using pure code (Python or R), of course something in between could work too!
Objective: We need to bring our data into DSS, explore the dataset, clean and prepare for a ML pipeline.
To do list:
Good luck - and don't forget to share your results!