#! /usr/bin/env python3
#
def faithful_kmeans2 ( ):

#*****************************************************************************80
#
## faithful_kmeans2() does a simple clustering exercise using scipy kmeans2().
#
#  Discussion:
#
#    Clustering data.
#
#  Licensing:
#
#    This code is distributed under the GNU LGPL license.
#
#  Modified:
#
#    19 September 2019
#
#  Author:
#
#    John Burkardt
#
  import matplotlib.pyplot as plt
  import numpy as np
  import platform
  from scipy.cluster.vq import kmeans2

  print ( '' )
  print ( 'faithful_kmeans2():' )
  print ( '  Python version: %s' % ( platform.python_version ( ) ) )
  print ( '  Cluster Old Faithful data using scipy kmeans2().' )
#
#  Read the data.
#
  data = np.loadtxt ( 'faithful_data.txt' )
#
#  Create x and y.
#
  x = data[:,0]
  y = data[:,1]
  n = len ( x )
  print ( '' )
  print ( '  Number of data values is %d' % ( n ) )
#
#  Normalize the data.
#
  xmin = np.min ( x )
  xmax = np.max ( x )
  ymin = np.min ( y )
  ymax = np.max ( y )
  data[:,0] = ( data[:,0] - xmin ) / ( xmax - xmin )
  data[:,1] = ( data[:,1] - ymin ) / ( ymax - ymin )

  x = data[:,0]
  y = data[:,1]

  plt.plot ( x, y, 'k.', markersize = 10 )
  plt.xlabel ( '<-- Duration (normalized) -->', fontsize = 16 )
  plt.ylabel ( '<-- Wait (normalized) -->', fontsize = 16 )
  plt.title ( 'Old Faithful eruption durations and waits', fontsize = 16 )
  plt.grid ( True )
  plt.axis ( 'equal' )
  filename = 'faithful_data.png'
  plt.savefig ( filename )
  plt.show ( )
  plt.clf ( )
  print ( '' )
  print ( '  Graphics saved as "%s"' % ( filename ) )
#
#  Call kmeans2()
#
  k = 2
  c, label = kmeans2 ( data, k )
  print ( '  Kmeans2 cluster centers C:' )
  print ( c )

  bd = ( x - c[0,0] )**2 + ( y - c[0,1] )**2
  rd = ( x - c[1,0] )**2 + ( y - c[1,1] )**2
  bc = np.where ( bd < rd )
  rc = np.where ( rd < bd )
  cost0 = sum ( bd[bc] )
  cost1 = sum ( rd[rc] )

  bn = len ( bd[bc] )
  cn = len ( rd[rc] )

  cost = cost0 + cost1
  print ( '  Cluster variance = ', 
    cost, '=', cost0, '+', cost1 )
  print ( '  Cluster size = ', 
    bn + cn, '=', bn, '+', cn )

  plt.plot ( x[label==0], y[label==0], 'c.', markersize = 10 )
  plt.plot ( x[label==1], y[label==1], 'm.', markersize = 10 )
  plt.plot ( c[0,0], c[0,1], 'bo', markersize = 15 )
  plt.plot ( c[1,0], c[1,1], 'ro', markersize = 15 )
  plt.xlabel ( '<-- Duration -->', fontsize = 16 )
  plt.ylabel ( '<-- Wait -->', fontsize = 16 )
  plt.title ( 'Clusters using kmeans2()', fontsize = 16 )
  plt.grid ( True )
  filename = 'faithful_kmeans2.png'
  plt.savefig ( filename )
  plt.show ( )
  plt.clf ( )
  print ( '' )
  print ( '  Graphics saved as "%s"' % ( filename ) )
#
#  Terminate.
#
  print ( '' )
  print ( 'faithful_kmeans2():' )
  print ( '  Normal end of execution.' )

  return

if ( __name__ == '__main__' ):
  faithful_kmeans2 ( )