DbscanFitPredict
DBSCAN — density-based spatial clustering, no preset number of clusters. / DBSCAN — clustering spatial basé sur la densité, sans nombre de clusters prédéfini.
⚡ Rust-native
✓ sklearn parity
Quick start — Python
import seraplot as sp, numpy as np
from sklearn.datasets import make_blobs
X, _ = make_blobs(n_samples=300, centers=4, cluster_std=0.6)
result = sp.DBSCAN(eps=0.8, min_samples=5).fit_predict(X)
print(result)
EN — Drop-in replacement:
FR — Remplacement direct : même API que sklearn, changez l'import.
sp.DbscanFitPredict has the same API as sklearn.FR — Remplacement direct : même API que sklearn, changez l'import.
API Reference
JSON function name
ml_dbscan_fit_predict — aliases: dbscan_fit_predict, ml_dbscan
Python class
sp.DbscanFitPredict(eps=0.5, min_samples=5)
Constructor Parameters
| Parameter | Type | Default | Description |
|---|---|---|---|
eps | float | 0.5 | Neighbourhood radius. |
min_samples | int | 5 | Minimum points to form a core point. |
Returns
JSON with labels (−1 = noise), n_clusters, n_noise.
Algorithm
A point $p$ is a core point if $|\mathcal{N}_{\varepsilon}(p)| \geq m$. Clusters are connected components of core points.
Example
import seraplot as sp, numpy as np
from sklearn.datasets import make_blobs
X, _ = make_blobs(n_samples=300, centers=4, cluster_std=0.6)
result = sp.DBSCAN(eps=0.8, min_samples=5).fit_predict(X)
print(result)
Référence API
Nom de fonction JSON
ml_dbscan_fit_predict — alias : dbscan_fit_predict, ml_dbscan
Classe Python
sp.DbscanFitPredict(eps=0.5, min_samples=5)
Paramètres du constructeur
| Paramètre | Type | Défaut | Description |
|---|---|---|---|
eps | float | 0.5 | Rayon de voisinage. |
min_samples | int | 5 | Minimum de points pour former un point noyau. |
Retourne
JSON avec labels (−1 = bruit), n_clusters, n_noise.
Algorithme
Un point $p$ est un point noyau si $|\mathcal{N}_{\varepsilon}(p)| \geq m$. Les clusters sont des composantes connexes de points noyaux.
Exemple
import seraplot as sp, numpy as np
from sklearn.datasets import make_blobs
X, _ = make_blobs(n_samples=300, centers=4, cluster_std=0.6)
result = sp.DBSCAN(eps=0.8, min_samples=5).fit_predict(X)
print(result)