Results of this run
Ward agglomerative merges of Iris Flowers stop at k=3, linkage=ward. Ward silhouette is 0.447, Ward Calinski-Harabasz is 222.7, Ward Davies-Bouldin is 0.803. Held-out species versus the Ward cut: adjusted Rand 0.615. 0 noise rows out of 150 after the merges. Ward merge 0 on Iris Flowers holds 30 rows (petal length (cm) 3.93 / petal width (cm) 1.21). Ward merge 1 on Iris Flowers holds 49 rows (petal length (cm) 1.47 / petal width (cm) 0.24). Ward merge 2 on Iris Flowers holds 71 rows (petal length (cm) 5.27 / petal width (cm) 1.85). Ward k path: k 2 merges to 0.577 with 2 groups on Iris Flowers; k 3 merges to 0.447 with 3 groups on Iris Flowers; k 4 merges to 0.401 with 4 groups on Iris Flowers; k 5 merges to 0.331 with 5 groups on Iris Flowers; k 6 merges to 0.315 with 6 groups on Iris Flowers; k 7 merges to 0.317 with 7 groups on Iris Flowers; k 8 merges to 0.311 with 8 groups on Iris Flowers. Ward scatter keeps 95.8%.

| k | Silhouette | Clusters |
|---|---|---|
| 2 | 0.577 | 2 |
| 3 | 0.447 | 3 |
| 4 | 0.401 | 4 |
| 5 | 0.331 | 5 |
| 6 | 0.315 | 6 |
| 7 | 0.317 | 7 |
| 8 | 0.311 | 8 |
from sklearn.cluster import AgglomerativeClustering
from sklearn.preprocessing import StandardScaler
Xs = StandardScaler().fit_transform(X)
labels = AgglomerativeClustering(n_clusters=3, linkage='ward').fit_predict(Xs)
Who, how, and why
Method: StandardScaler, drop constant columns. Code version 3e4afc4b4352 (scripts/seo/build_explore_artifacts.py). scikit-learn 1.4.2. Seed 42. Dataset source: UCI Machine Learning Repository, Iris (Fisher, 1936). License: CC BY 4.0. The species column was held out of the fit and used only for the adjusted Rand score.
Results computed on 2026-11-02.
The results paragraph is filled from these numbers by a fixed template in the site code, so the scores can be checked against the same dataset in the tool.
Maintainer: nikolaou1982.
Contact: nick1982100@gmail.com.
