Icon

kmeans & EM

Clustering using Weka EM (Expectation Maximization) algorithm
Compare generated clusters to actual values. But before that merge low risk and mid risk. #Last amended: 26th Feb, 2022#Data source: https://www.kaggle.com/csafrit2/maternal-health-risk-dataClustering using Expectation-Maximization (EM) algorithm of Maternal Health Risk Data Check shape ofcont datanormalizenumeric colsfilter out RiskLevelkey should not be enclosed inquotation marksMap Winner clusterto digits84.7% accuracyTry bothEuclidean &Manhattan distanceObservelength ofbars inthree clusterssetnumClusters=3Node 23Node 25 Multiple boxplots ordensity plots side-by-side Normalizer Column Filter String Replace(Dictionary) Number To String String Replace(Dictionary) Scorer SimpleKMeans (3.7) Weka ClusterAssigner (3.7) EM (3.7) Weka ClusterAssigner (3.7) Statistics Table Reader Compare generated clusters to actual values. But before that merge low risk and mid risk. #Last amended: 26th Feb, 2022#Data source: https://www.kaggle.com/csafrit2/maternal-health-risk-dataClustering using Expectation-Maximization (EM) algorithm of Maternal Health Risk Data Check shape ofcont datanormalizenumeric colsfilter out RiskLevelkey should not be enclosed inquotation marksMap Winner clusterto digits84.7% accuracyTry bothEuclidean &Manhattan distanceObservelength ofbars inthree clusterssetnumClusters=3Node 23Node 25Multiple boxplots ordensity plots side-by-side Normalizer Column Filter String Replace(Dictionary) Number To String String Replace(Dictionary) Scorer SimpleKMeans (3.7) Weka ClusterAssigner (3.7) EM (3.7) Weka ClusterAssigner (3.7) Statistics Table Reader

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: ashok
Created at: 2022-02-26
On NodePit since: 2022-02-27
Last update: 2024-04-18
Created with KNIME version: v4.5.1
Tags: Weka EMExpectation Maximization algorithmClustering

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

Try NodePit Runner!