Results of this run
Spectral clustering embeds Iris Flowers with an RBF affinity and cuts k=3, affinity=rbf. Graph silhouette is 0.460, graph Calinski-Harabasz is 239.7, graph Davies-Bouldin is 0.831. Held-out species versus the graph cut: adjusted Rand 0.600. 0 noise rows out of 150 in the embedding. Graph group 0 on Iris Flowers holds 49 rows (petal length (cm) 1.47 / sepal length (cm) 5.02). Graph group 1 on Iris Flowers holds 47 rows (petal length (cm) 5.51 / sepal length (cm) 6.78). Graph group 2 on Iris Flowers holds 54 rows (petal length (cm) 4.31 / sepal length (cm) 5.78). Spectral k path: k 2 cuts 0.582 with 2 groups on Iris Flowers; k 3 cuts 0.460 with 3 groups on Iris Flowers; k 4 cuts 0.400 with 4 groups on Iris Flowers; k 5 cuts 0.353 with 5 groups on Iris Flowers; k 6 cuts 0.344 with 6 groups on Iris Flowers; k 7 cuts 0.337 with 7 groups on Iris Flowers; k 8 cuts 0.298 with 8 groups on Iris Flowers. Graph scatter keeps 95.8%.

| k | Silhouette | Clusters |
|---|---|---|
| 2 | 0.582 | 2 |
| 3 | 0.460 | 3 |
| 4 | 0.400 | 4 |
| 5 | 0.353 | 5 |
| 6 | 0.344 | 6 |
| 7 | 0.337 | 7 |
| 8 | 0.298 | 8 |
from sklearn.cluster import SpectralClustering
from sklearn.preprocessing import StandardScaler
Xs = StandardScaler().fit_transform(X)
labels = SpectralClustering(n_clusters=3, random_state=42).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.
