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

#*****************************************************************************80
#
## blobs_energy() monitors cluster energy as K increases.
#
#  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
  from sklearn.datasets import make_blobs

  print ( '' )
  print ( 'blobs_energy():' )
  print ( '  Python version: %s' % ( platform.python_version ( ) ) )
  print ( '  Evaluate cluster energy for increasing K on 6 blobs data.' )
#
#  Read the data.
#
  Z = np.array ( [
    [-7,-5],
    [-3,-1],
    [8,-2],
    [-4,8],
    [0,4],
    [6,3] ] )

  data, labels = make_blobs ( n_samples = 500, n_features = 2, centers = Z, 
    random_state = 42 )
#
#  Create x and y.
#
  x = data[:,0]
  y = data[:,1]
  n = len ( x )
  print ( '' )
  print ( '  Number of data values is %d' % ( n ) )

  plt.plot ( x, y, 'k.', markersize = 10 )
  plt.xlabel ( '<-- X -->', fontsize = 16 )
  plt.ylabel ( '<-- Y -->', fontsize = 16 )
  plt.title ( 'Six blobs', fontsize = 16 )
  plt.grid ( True )
  plt.axis ( 'equal' )
  filename = 'blobs_data.png'
  plt.savefig ( filename )
  plt.show ( )
  plt.clf ( )
  print ( '' )
  print ( '  Graphics saved as "%s"' % ( filename ) )
#
#  Call kmeans()
#
  kmax = 10
  kplot = list ( range ( 1, kmax + 1 ) )
  eplot = np.zeros ( kmax )

  for i in range ( 0, kmax ):
    k = kplot[i]
    kmeans = KMeans ( n_clusters = k, n_init = 'auto' )
    kmeans.fit ( data )
    eplot[i] = kmeans.inertia_

  plt.clf ( )
  plt.plot ( kplot, eplot, 'r-o', linewidth = 3 )
  plt.xlabel ( '<-- K -->', fontsize = 16 )
  plt.ylabel ( '<-- Energy(K) -->', fontsize = 16 )
  plt.title ( 'Cluster energy with increasing K, blobs data', fontsize = 16 )
  plt.grid ( True )
  filename = 'blobs_energy.png'
  plt.savefig ( filename )
  plt.show ( )
  plt.clf ( )
  print ( '' )
  print ( '  Graphics saved as "%s"' % ( filename ) )
#
#  Terminate.
#
  print ( '' )
  print ( 'blobs_energy():' )
  print ( '  Normal end of execution.' )

  return

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