K-Means clustring with faiss library

kmeans_with_faiss.py

import faiss
import numpy as np


class FaissKMeans:
    def __init__(self, n_clusters=8, n_init=10, max_iter=300):
        self.n_clusters = n_clusters
        self.n_init = n_init
        self.max_iter = max_iter
        self.kmeans = None
        self.cluster_centers_ = None
        self.inertia_ = None

    def fit(self, X, y):
        self.kmeans = faiss.Kmeans(d=X.shape[1],
                                   k=self.n_clusters,
                                   niter=self.max_iter,
                                   nredo=self.n_init)
        self.kmeans.train(X.astype(np.float32))
        self.cluster_centers_ = self.kmeans.centroids
        self.inertia_ = self.kmeans.obj[-1]

    def predict(self, X):
        return self.kmeans.index.search(X.astype(np.float32), 1)[1]

Can you add a GPU version as well?

@NightMachinary sure, that should be simple, I'll write about it in a 2-3 weeks

Could you please check that the inertia is reported correctly for kmeans clustering with faiss? For me it goes up with the number of clusters, which is suspicious... Thanks!

@spokatee how would an increase in inertia reporting effect the model?