Classifier

make samples

from sklearn.datasets import make_blobsX,y = make_blobs(n_samples=500, n_features=3,centers=4,cluster_std=2,center_box=(-10,10,10), shuffle=True, random_state=1)

KNeighborsClassifier

sklearn

class sklearn.neighbors.KNeighborsClassifier(n_neighbors=5, weights='uniform', algorithm='auto', leaf_size=30, p=2, metric='minkowski', metric_params=None, n_jobs=1, **kwargs)

from sklearn.neighbors import KNeighborsClassifier as KNNknn = KNN(n_neighbors=3)knn.firt(X,y)p = knn.predict_proba(X)

KMeans

from sklearn.cluster import kMeansclusterer = KMeans(n_clusters=n_clusters, random_state=10)clusterer = KMeans(n_clusters=n_clusters, random_state=10)cluster_labels = clusterer.fit_predict(X)

determine the number of cluster

silhouette

sklearn document

from sklearn.metrics import silhouette_samples, silhouette_score#The silhouette_score gives the average value for all the samples.This gives a perspective into the density and separation of the formed clusterssilhouette_avg = silhouette_score(X, cluster_labels)#Compute the silhouette scores for each samplesample_silhouette_values = silhouette_samples(X, cluster_labels)

---

Finding the K in K-Means Clustering

Using BIC to estimate the number of k in KMEANS

DBSCAN

wiki