Sklearn Agglomerative Clustering icon

Sklearn Agglomerative Clustering

Agglomerative (hierarchical) clustering using scikit-learn

Sklearn Agglomerative Clustering

AI-generated

Summary

Cluster input data using scikit-learn's AgglomerativeClustering.

Inputs

  • featureColumns (required) — Comma-separated list of feature column names to use for clustering
  • nClusters — Number of clusters to form
  • linkage — Linkage criterion for merging clusters (ward, complete, average, single)
  • metric — Distance metric (euclidean, manhattan, cosine); ward only supports euclidean
  • pythonPath — Path to the Python executable that has scikit-learn installed

Output shape

a list of items, each extended with cluster label and clustering metadata

The operation returns an array; errors either propagate or are added as an error record depending on continueOnFail setting

Examples

Example 1: Basic clustering of a table with three feature columns

Feature Columns: feature1,feature2,feature3; Number of Clusters: 3; Linkage: ward; Metric: euclidean; Python Path: python3

Example 2: Using Manhattan distance and average linkage

Feature Columns: age,salary; Number of Clusters: 2; Linkage: average; Metric: manhattan; Python Path: python3

Discussion