Icon

Churn

Here I am using up all the churn records andselecting the exact number of not churn records thatwill give me a 60/40 (not churn/churn) split.I have 1498 churn records and this is 40% of someunknown total. I will simply create an equation andsolve for this unknown total, then use that value tofind out how many non-churn records I need.0.4 of x = 1498x = 1498/0.4x = 3745 (Total records we can have in a samplewhere we use all our churn records, where churnrecords constitute 40% of our data based on a churncount of 1498). Now we know the total number of records we wouldhave, and the number of churn. The number of notchurn is therefore 3745-1498 = 2247. Plug this valueinto the row sampling node to select this many nonchurn records giving you a 60/40 not churn/churndistribution. Node 173.5% Not Churn26.5% ChurnSplit into churn and not churnChurn top (N=1498)Draw a random sample of60% not churn casesStack churn and not churn rows60% Not Churn40% Churn80/20test/train split CSV Reader GroupBy Row Splitter Row Sampling Concatenate GroupBy Partitioning Here I am using up all the churn records andselecting the exact number of not churn records thatwill give me a 60/40 (not churn/churn) split.I have 1498 churn records and this is 40% of someunknown total. I will simply create an equation andsolve for this unknown total, then use that value tofind out how many non-churn records I need.0.4 of x = 1498x = 1498/0.4x = 3745 (Total records we can have in a samplewhere we use all our churn records, where churnrecords constitute 40% of our data based on a churncount of 1498). Now we know the total number of records we wouldhave, and the number of churn. The number of notchurn is therefore 3745-1498 = 2247. Plug this valueinto the row sampling node to select this many nonchurn records giving you a 60/40 not churn/churndistribution. Node 173.5% Not Churn26.5% ChurnSplit into churn and not churnChurn top (N=1498)Draw a random sample of60% not churn casesStack churn and not churn rows60% Not Churn40% Churn80/20test/train split CSV Reader GroupBy Row Splitter Row Sampling Concatenate GroupBy Partitioning

Nodes

Extensions

Links

Download

To use this workflow in KNIME, download it from the below URL and open it in KNIME:

Download Workflow
Created by: sntra
Created at: 2023-04-30
On NodePit since: 2023-04-30
Last update: 2024-11-21
Created with KNIME version: v4.7.2

Deploy, schedule, execute, and monitor your KNIME workflows locally, in the cloud or on-premises – with our brand new NodePit Runner.

Try NodePit Runner!