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

#*****************************************************************************80
#
## cancer_visualize_histogram() histograms features for benign/malignant.
#
#  Licensing:
#
#    This code is distributed under the MIT license.
#
#  Modified:
#
#    19 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.model_selection import train_test_split
  from sklearn.preprocessing import StandardScaler
  from sklearn.svm import SVC
  import matplotlib.pyplot as plt
  import mglearn
  import numpy as np
  import platform
  import sklearn

  print ( '' )
  print ( 'cancer_visualize_histogram():' )
  print ( '  Python version: ' + platform.python_version ( ) )
  print ( '  scikit-learn version: '+ sklearn.__version__ )
  print ( '  Work with data from the cancer dataset.' )
  print ( '  Make histograms of benign/malignant feature frequencies.' )
#
#  Generate the dataset.
#
  print ( '' )
  print ( '  Retrieve the cancer dataset, (X, y).' )
  cancer = load_breast_cancer ( )
#
#  Split the dataset into benign and malignant subsets.
#
  malignant = cancer.data[ cancer.target == 0 ]
  benign    = cancer.data[ cancer.target == 1 ]
#
#  Plot 30 histograms comparing malignant and benign feature frequencies.
#
  fig, axes = plt.subplots ( 15, 2, figsize = ( 10, 20 ) )
  ax = axes.ravel ( )

  for i in range ( 30 ):
    _, bins = np.histogram ( cancer.data[:,i], bins = 59 )
    ax[i].hist(malignant[:,i], bins=bins, color=mglearn.cm3(0), alpha = 0.5 )  
    ax[i].hist(benign[:,i],    bins=bins, color=mglearn.cm3(2), alpha = 0.5 )
    ax[i].set_title(cancer.feature_names[i] )
    ax[i].set_yticks(())
  ax[0].set_xlabel ( "Feature magnitude" )
  ax[0].set_ylabel ( "Frequency" )
  ax[0].legend ( [ "Malignant", "Benign" ], loc = "best" )
  fig.tight_layout ( )

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