#! /usr/bin/env python3
#
def blob_cluster_kmeans ( ):

#*****************************************************************************80
#
## blob_cluster_kmeans() clusters blob data using kmeans.
#
#  Licensing:
#
#    This code is distributed under the MIT license.
#
#  Modified:
#
#    08 July 2023
#
#  Author:
#
#    John Burkardt
#
  from sklearn.cluster import KMeans
  from sklearn.datasets import make_blobs
  import matplotlib.pyplot as plt
  import platform
  import sklearn

  print ( "" )
  print ( "blob_cluster_kmeans():" )
  print ( '  python version: %s' % ( platform.python_version ( ) ) )
  print ( '  scikit-learn version: %s' % ( sklearn.__version__ ) )
#
#  Generate sample data
#
  n_samples = 4000
  n_components = 4

  X, y_true = make_blobs ( 
    n_samples = n_samples,
    centers = n_components,
    cluster_std = 0.60,
    random_state = 0 )

  X = X[:, ::-1]
#
#  Now apply kmeans.
#
  kmeans = KMeans ( 
    init = 'k-means++', 
    n_clusters = 4, 
    random_state = 0, 
    n_init = "auto" )

  kmeans.fit ( X )
#
#  Display data and computed cluster centers.
#
  plt.clf ( )
  colors = [ '#4EACC5', '#FF9C34', '#4E9A06', 'm' ]

  for k, col in enumerate(colors):
    cluster_data = ( y_true == k )
    plt.scatter ( 
      X[cluster_data, 0], X[cluster_data, 1],
      c = col, 
      marker = '.', 
      s = 10 )

  plt.scatter ( kmeans.cluster_centers_[:, 0], kmeans.cluster_centers_[:, 1], 
    c = 'b', 
    s = 50 )
  plt.title ( "K-Means++" )
  plt.xticks([])
  plt.yticks([])
  plt.grid ( True )
  filename = 'blob_cluster_kmeans.png'
  plt.savefig ( filename )
  print ( '  Graphics saved as "' + filename + '"' )
  plt.close()
#
#  Terminate.
#
  print ( '' )
  print ( 'blob_cluster_kmeans()' )
  print ( '  Normal end of execution.' )

  return

def timestamp ( ):

#*****************************************************************************80
#
## timestamp() prints the date as a timestamp.
#
#  Licensing:
#
#    This code is distributed under the MIT license. 
#
#  Modified:
#
#    21 August 2019
#
#  Author:
#
#    John Burkardt
#
  import time

  t = time.time ( )
  print ( time.ctime ( t ) )

  return

if ( __name__ == '__main__' ):
  timestamp ( )
  blob_cluster_kmeans ( )
  timestamp ( )