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

#*****************************************************************************80
#
## cancer_visualize_pca() uses PCA to visualize malignant/benign differences.
#
#  Licensing:
#
#    This code is distributed under the MIT license.
#
#  Modified:
#
#    20 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_breast_cancer
  from sklearn.decomposition import PCA
  from sklearn.preprocessing import StandardScaler
  import matplotlib.pyplot as plt
  import mglearn
  import numpy as np
  import platform
  import sklearn

  print ( '' )
  print ( 'cancer_visualize_pca():' )
  print ( '  Python version: ' + platform.python_version ( ) )
  print ( '  scikit-learn version: '+ sklearn.__version__ )
  print ( '  Work with data from the cancer dataset.' )
  print ( '  Use principal component analysis to visualize differences' )
  print ( '  between malignant and benign cases.' )
#
#  Generate the dataset.
#
  print ( '' )
  print ( '  Retrieve the cancer dataset, (X, y).' )
  cancer = load_breast_cancer ( )
#
#  Define the standard scaler, calibrate it for the cancer dataset, apply it.
#
  scaler = StandardScaler ( )
  scaler.fit ( cancer.data )
  x_scaled = scaler.transform ( cancer.data )
#
#  Apply PCA, requesting first two components.
#
  pca = PCA ( n_components = 2 )
  pca.fit ( x_scaled )
#
#  Transfer data onto the first two components.
#
  x_pca = pca.transform ( x_scaled )
  print ( '' )
  print ( '  Original shape: ', x_scaled.shape )
  print ( '  Reduced shape:  ', x_pca.shape )
#
#  Plot first versus second component.
#
  plt.figure ( figsize = ( 8, 8 ) )
  mglearn.discrete_scatter ( x_pca[:,0], x_pca[:,1], cancer.target )
  plt.legend ( cancer.target_names, loc = 'best' )
  plt.gca().set_aspect ( 'equal' )
  plt.xlabel ( 'First principal component' )
  plt.ylabel ( 'Second principal component' )
  plt.grid ( True )
  filename = 'cancer_visualize_pca_components.png'
  plt.savefig ( filename )
  print ( '  Graphics saved as "' + filename + '"' )
#
#  View the two PCA components.
#
  print ( '' )
  print ( '  PCA component shape:', pca.components_.shape )
  print ( '' )
  print ( '  PCA components:' )
  print ( pca.components_ )
#
#  Heat map of coefficients.
#
  plt.matshow ( pca.components_, cmap = 'viridis' )
  plt.yticks ( [ 0, 1 ], [ 'First component', 'Second component' ] )
  plt.colorbar ( )
  plt.xticks ( range ( len ( cancer.feature_names ) ),
    cancer.feature_names, rotation = 60, ha = 'left' )
  plt.xlabel ( 'Feature' )
  plt.ylabel ( 'Principal components' )
  filename = 'cancer_visualize_pca_coefficients.png'
  plt.savefig ( filename )
  print ( '  Graphics saved as "' + filename + '"' )
#
#  Terminate.
#
  print ( '' )
  print ( 'cancer_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 ( )
  cancer_visualize_pca ( )
  timestamp ( )