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

#*****************************************************************************80
#
## digits_visualize_pca() uses PCA to visualize digit images.
#
#  Licensing:
#
#    This code is distributed under the MIT license.
#
#  Modified:
#
#    22 September 2023
#
#  Author:
#
#    Andreas Mueller, Sarah Guido.
#    This version by John Burkardt.
#
#  Reference:
#
#    Andreas Mueller, Sarah Guido,
#    Introduction to Machine Learning with Python,
#    OReilly, 2017,
#    ISBN: 978-1-449-36941-5
#
  from sklearn.datasets import load_digits
  from sklearn.decomposition import PCA
  import matplotlib.pyplot as plt
  import mglearn
  import numpy as np
  import platform
  import sklearn

  print ( '' )
  print ( 'digits_visualize_pca():' )
  print ( '  Python version: ' + platform.python_version ( ) )
  print ( '  scikit-learn version: '+ sklearn.__version__ )
  print ( '  Work with data from the digits dataset.' )
  print ( '  Use principal component analysis to visualize differences.' )
#
#  Generate the dataset.
#
  print ( '' )
  print ( '  Retrieve the digits dataset:' )
  digits = load_digits ( )
#
#  Display the data.
#
  fig, axes = plt.subplots ( 2, 5, figsize = ( 10, 5 ),
    subplot_kw = { 'xticks':(), 'yticks':() } )

  for ax, img in zip ( axes.ravel(), digits.images ):
    ax.imshow ( img )

  filename = 'digits_data.png'
  plt.savefig ( filename )
  print ( '  Graphics saved as "' + filename + '"' )
#
#  Create a PCA model of the data.
#
  pca = PCA ( n_components = 2 )
  pca.fit ( digits.data )
#
#  Project the digits data into the two-component PCA basis.
#
  digits_pca = pca.transform ( digits.data )
#
#  Define colors for a plot.
#
  colors = [ '#476A2A', '#785188', '#BD3430', '#4A2D4E', '#875525',
             '#A83683', '#4E655E', '#853541', '#3A3120', '#535D8E' ]
#
#  Plot.
#
  plt.figure ( figsize = ( 10, 10 ) )
  plt.xlim ( digits_pca[:,0].min(), digits_pca[:,0].max() )
  plt.ylim ( digits_pca[:,1].min(), digits_pca[:,1].max() )

  for i in range ( len ( digits.data ) ):
    plt.text ( digits_pca[i,0], digits_pca[i,1], str ( digits.target[i] ),
      color = colors[digits.target[i] ],
      fontdict = { 'weight': 'bold', 'size' : 9 } )
  plt.xlabel ( 'First principal component' )
  plt.ylabel ( 'Second principal component' )

  filename = 'digits_pca.png'
  plt.savefig ( filename )
  print ( '  Graphics saved as "' + filename + '"' )
#
#  Terminate.
#
  print ( '' )
  print ( 'digits_visualize_pca():' )
  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 ( )
  digits_visualize_pca ( )
  timestamp ( )