Results of this run
OPTICS ordering of Iris Flowers (minSamples 5, xi) cuts a reachability plot into 2 valleys. Reachability silhouette is 0.657, reachability Calinski-Harabasz is 340.7, reachability Davies-Bouldin is 0.494. Held-out species versus valleys: adjusted Rand 0.444. 36 noise rows out of 150 stay on the noise floor. Valley 0 on Iris Flowers holds 45 rows (petal length (cm) 1.47 / petal width (cm) 0.25). Valley 1 on Iris Flowers holds 69 rows (petal length (cm) 4.78 / petal width (cm) 1.63). Reachability sweep: min_samples 3 cuts 0.441 with 22 groups on Iris Flowers; min_samples 5 cuts 0.657 with 2 groups on Iris Flowers; min_samples 8 cuts 0.652 with 2 groups on Iris Flowers. Ordering plot keeps 95.8%.

| min_samples | Silhouette | Clusters |
|---|---|---|
| 3 | 0.441 | 22 |
| 5 | 0.657 | 2 |
| 8 | 0.652 | 2 |
from sklearn.cluster import OPTICS
from sklearn.preprocessing import StandardScaler
Xs = StandardScaler().fit_transform(X)
labels = OPTICS(min_samples=5).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.
