So I can run
kmeans = KMeans(n_clusters=3,init='random',n_init=10,max_iter=500)
Number of time the k-means algorithm will be run with different centroid seeds. The final results will be the best output of n_init consecutive runs in terms of inertia.
Maximum number of iterations of the k-means algorithm for a single run.
n_init=15, kmeans will choose initial centroids 15 times and move up to twice on each of the 15 runs.
The default values are
max_iter=300. This means the initial centroids will be chosen 10 times, and each run will use up to 300 iterations. The best out of those 10 runs will be the final result.