Clustering a file with COVID data

Dear Knimers,
My current situation is as follows:
My research is about Covid’s effects on a particular industry (private sector).
With the help of some Knime Community members, I got to the following preprocessing (saved in a TXT file, because I couldn’t upload here a CSV file), on which some Covid rates were calculated (as new features):
Brazil-RS-Covid-Data-With-Rates.txt (316.1 KB).
Now I need to cluster those data, which are already grouped on the above file as one row by city, by year, and by month (in a total of 6793 rows). I explain myself: my research covers 16 months of cases in 497 cities (not all of them having Covid cases every month), and I need a “not very large” number of clusters, even though some cities could be be moved from one cluster to another along the period of my analysis.
I intend to evaluate – probably using one of the Scorer nodes – the performance of a few (4 - 6) algorithms.
And, after this clustering process, I need to plot these results.
Can someone help me?
Thank you all.

Hi @rogerius1st,

I’ve attached a workflow that illustrates how to use clustering methods such as k-Means, Hierarchical clustering, and DBSCAN within KNIME (Clustering on the Iris data – KNIME Hub) as well as an example workflow of how to apply the clustering model to new data (Clustering with k-Means – KNIME Hub).

These should be some useful resources to help you create a framework for the clustering process.


1 Like

This topic was automatically closed 90 days after the last reply. New replies are no longer allowed.