Icon

05-k-means-wine-solution

Input Data Preparation TODO: Clustering with k-means External Evaluation Statistics k-Means Clustering Loop over different k Internal Evaluation with Silhouette combine Data find best k for k means based on silhouette coefficient and with parameter optimization loop find best k based on silhouette coeff. by means of a component Internal Evaluation with Total Squared Distance clustering with k-medoid Normalize columnsShow statisticsAssess QualityExtract QualityCreate possible values for kNode 45Node 46Node 51Node 54Node 55Node 60Node 63Extract QualityNode 67Node 68Node 71labels(contain the "real" groups)winesNode 74loop over k from 2...10type (label col) is not usedNode 78Node 80score with reference clusteringExtract QualityExtract QualityNode 86Node 87do the clustering for best kNode 90Node 93Node 94Node 95create a loop for kNode 98Node 99Node 100Node 101Node 102Node 103Node 104Node 105Silhouette coeff vs. klabelsNode 108SummarizeNode 111combine internal validations into one tablecombine internaland external validationsinto 1 tablevisualizeOptimized K-Means(Silhouette Coefficient) Normalizer Statistics Entropy Scorer Row Filter Table Creator Rank Correlation Linear Correlation Color Manager Shape Manager Scatter Plot(local) k-Means SilhouetteCoefficient Row Filter Column Resorter Sorter Number To String CSV Reader CSV Reader Normalizer Parameter OptimizationLoop Start k-Means SilhouetteCoefficient Number To String Entropy Scorer Row Filter Row Filter ParameterOptimization Loop End Table Columnto Variable k-Means 2D/3D Scatterplot Variable toTable Column Variable toTable Column Variable toTable Column Table Row ToVariable Loop Start Sorter SilhouetteCoefficient Math Formula Bar Chart Number To String k-Medoids Numeric Distances SilhouetteCoefficient Scatter Plot CSV Reader CSV Reader Loop End CalcSquaredDistances Joiner Joiner Joiner Scatter Plot Input Data Preparation TODO: Clustering with k-means External Evaluation Statistics k-Means Clustering Loop over different k Internal Evaluation with Silhouette combine Data find best k for k means based on silhouette coefficient and with parameter optimization loop find best k based on silhouette coeff. by means of a component Internal Evaluation with Total Squared Distance clustering with k-medoid Normalize columnsShow statisticsAssess QualityExtract QualityCreate possible values for kNode 45Node 46Node 51Node 54Node 55Node 60Node 63Extract QualityNode 67Node 68Node 71labels(contain the "real" groups)winesNode 74loop over k from 2...10type (label col) is not usedNode 78Node 80score with reference clusteringExtract QualityExtract QualityNode 86Node 87do the clustering for best kNode 90Node 93Node 94Node 95create a loop for kNode 98Node 99Node 100Node 101Node 102Node 103Node 104Node 105Silhouette coeff vs. klabelsNode 108SummarizeNode 111combine internal validations into one tablecombine internaland external validationsinto 1 tablevisualizeOptimized K-Means(Silhouette Coefficient) Normalizer Statistics Entropy Scorer Row Filter Table Creator Rank Correlation Linear Correlation Color Manager Shape Manager Scatter Plot(local) k-Means SilhouetteCoefficient Row Filter Column Resorter Sorter Number To String CSV Reader CSV Reader Normalizer Parameter OptimizationLoop Start k-Means SilhouetteCoefficient Number To String Entropy Scorer Row Filter Row Filter ParameterOptimization Loop End Table Columnto Variable k-Means 2D/3D Scatterplot Variable toTable Column Variable toTable Column Variable toTable Column Table Row ToVariable Loop Start Sorter SilhouetteCoefficient Math Formula Bar Chart Number To String k-Medoids Numeric Distances SilhouetteCoefficient Scatter Plot CSV Reader CSV Reader Loop End CalcSquaredDistances Joiner Joiner Joiner Scatter Plot

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: tlauer1
Created at: 2018-06-08
On NodePit since: 2021-06-15
Last update: 2024-04-18
Created with KNIME version: v4.5.1

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

Try NodePit Runner!