Results of this run
OPTICS ordering of Wine (UCI wine recognition) (minSamples 5, xi) cuts a reachability plot into 2 valleys. Reachability silhouette is 0.332, reachability Calinski-Harabasz is 69.8, reachability Davies-Bouldin is 1.174. Held-out wine_class versus valleys: adjusted Rand 0.392. 43 noise rows out of 178 stay on the noise floor. Valley 0 on Wine (UCI wine recognition) holds 94 rows (proline 837.3 / color_intensity 4.39). Valley 1 on Wine (UCI wine recognition) holds 41 rows (proline 628.9 / color_intensity 7.28). Reachability sweep: min_samples 3 cuts 0.062 with 3 groups on Wine (UCI wine recognition); min_samples 5 cuts 0.332 with 2 groups on Wine (UCI wine recognition); min_samples 8 cuts not defined with 1 groups on Wine (UCI wine recognition). Ordering plot keeps 55.4%.

| min_samples | Silhouette | Clusters |
|---|---|---|
| 3 | 0.062 | 3 |
| 5 | 0.332 | 2 |
| 8 | — | 1 |
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, wine recognition. License: CC BY 4.0. The wine_class 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.
