salad tomate oignon

from sklearn import datasets
# import some data to play with
import numpy as np
import statistics

data = np.random.randint(0,25,size=(10,2))

def k_means(data,k):
    n = data.shape[0]
    nvar = data.shape[1]
    centroids = np.random.randint(0,25,size=(k,nvar))
    new_centroids = np.zeros(shape=(k,nvar))
    diff_matrix = np.zeros(shape = (n,k))
    counter = 1

    while np.array_equal(new_centroids,centroids) == False:
        if counter > 1:
            centroids = new_centroids
        for i in range(k) :
            distance = (data-centroids[i])**2
            diff_matrix[:,i] = distance.sum(axis=1)

        ## Indices containing the minimum for each diff_matrix
        ind_min = np.argmin(diff_matrix, axis=1)

        ## calculate the centroids with new data
        for i in range(k):
            new_centroids[i]= np.mean(data[ind_min == i], axis =0)
        #for i in range(k):
         #   print("Step", counter, "No convergence yet")
          #  print("Cluster",i,"contains the following data:",data[ind_min == i])
        counter = counter + 1


    for i in range(k):
        print("Cluster",i,"contains the following data:",data[ind_min == i])