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

#*****************************************************************************80
#
## faithful_kmeans() does a simple clustering exercise using sklearn kmeans().
#
#  Discussion:
#
#    Clustering data.
#
#  Licensing:
#
#    This code is distributed under the GNU LGPL license.
#
#  Modified:
#
#    26 September 2023
#
#  Author:
#
#    John Burkardt
#
  import matplotlib.pyplot as plt
  import numpy as np
  import platform
  from sklearn.cluster import KMeans

  print ( '' )
  print ( 'faithful_kmeans():' )
  print ( '  Python version: %s' % ( platform.python_version ( ) ) )
  print ( '  Cluster Old Faithful data using scikit-learn kmeans().' )
#
#  Read the data.
#
  data = np.loadtxt ( 'faithful_normalized.txt' )
#
#  Create x and y.
#
  x = data[:,0]
  y = data[:,1]
  n = len ( x )
  print ( '' )
  print ( '  Number of data values is %d' % ( n ) )
#
#  Call kmeans()
#
  k = 2

  kmeans = KMeans ( n_clusters = k, n_init = 'auto' )
  kmeans.fit ( data )

  Z = kmeans.cluster_centers_
  C = kmeans.labels_
  E = kmeans.inertia_

  n0 = np.sum ( C == 0 )
  n1 = np.sum ( C == 1 )

  print ( '  Kmeans cluster centers Z:' )
  print ( Z )
  print ( '  Cluster energy = ', E )
  print ( '  Cluster size = ', n0 + n1, '=', n0, '+', n1 )

  plt.clf ( )
  plt.plot ( x[C==0], y[C==0], 'c.', markersize = 10 )
  plt.plot ( x[C==1], y[C==1], 'm.', markersize = 10 )
  plt.plot ( Z[0,0], Z[0,1], 'bo', markersize = 15 )
  plt.plot ( Z[1,0], Z[1,1], 'ro', markersize = 15 )
  plt.xlabel ( '<-- Duration -->', fontsize = 16 )
  plt.ylabel ( '<-- Wait -->', fontsize = 16 )
  plt.title ( 'Clusters using kmeans()', fontsize = 16 )
  plt.grid ( True )
  filename = 'faithful_kmeans.png'
  plt.savefig ( filename )
  plt.show ( )
  print ( '  Graphics saved as "%s"' % ( filename ) )
#
#  Terminate.
#
  print ( '' )
  print ( 'faithful_kmeans():' )
  print ( '  Normal end of execution.' )

  return

if ( __name__ == '__main__' ):
  faithful_kmeans ( )