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

#*****************************************************************************80
#
## cancer_classify_mlp() uses a multilayer perceptron to classify cancer data.
#
#  Licensing:
#
#    This code is distributed under the MIT license.
#
#  Modified:
#
#    06 August 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.model_selection import train_test_split
  from sklearn.neural_network import MLPClassifier
  import matplotlib.pyplot as plt
  import mglearn
  import numpy as np
  import platform
  import sklearn

  print ( '' )
  print ( 'cancer_classify_mlp():' )
  print ( '  Python version: ' + platform.python_version ( ) )
  print ( '  scikit-learn version: '+ sklearn.__version__ )
  print ( '  Use a multilayer perceptron to classify cancer data.' )
#
#  Generate the dataset.
#
  print ( '' )
  print ( '  Retrieve the cancer dataset, (X, y).' )

  cancer = load_breast_cancer ( )
#
#  Split the data.
#
  X_train, X_test, y_train, y_test = train_test_split ( \
    cancer.data, cancer.target, stratify = cancer.target, random_state = 66 )
#
#  Fit the classifier.
#
  mlp = MLPClassifier ( random_state = 42 )
  mlp.fit ( X_train, y_train )
#
#  Compute training and testing accuracy for varying number of neighbors.
#
  print ( '  Training accuracy = ', mlp.score ( X_train, y_train ) )
  print ( '  Testing accuracy  = ', mlp.score ( X_test, y_test ) )

  print ( '' )
  print ( 'Compute mean and standard deviation, and rescale the data.' )
#
#  Compute mean and standard deviation.
#
  mean_on_training = X_train.mean ( axis = 0 )
  std_on_training = ( X_train - mean_on_training ).std ( axis = 0 )
#
#  Rescale the data.
#
  X_train_scaled = ( X_train - mean_on_training ) / std_on_training
  X_test_scaled  = ( X_test  - mean_on_training ) / std_on_training
#
#  Fit the classifier to the rescaled data.
#
  mlp = MLPClassifier ( random_state = 0 )
  mlp.fit ( X_train_scaled, y_train )
#
#  Compute training and testing accuracy for varying number of neighbors.
#
  print ( '  Training accuracy = ', mlp.score ( X_train_scaled, y_train ) )
  print ( '  Testing accuracy  = ', mlp.score ( X_test_scaled, y_test ) )
#
#  Increase the number of iterations, and now
#  fit the classifier to the rescaled data.
#
  print ( '' )
  print ( 'Increase the number of iterations, and repeat classification.' )

  mlp = MLPClassifier ( random_state = 0, max_iter = 1000 )
  mlp.fit ( X_train_scaled, y_train )
#
#  Increase alpha, and now
#  fit the classifier to the rescaled data.
#
  print ( '' )
  print ( 'Increase alpha, and repeat classification.' )

  mlp = MLPClassifier ( random_state = 0, max_iter = 1000, alpha = 1.0 )
  mlp.fit ( X_train_scaled, y_train )
#
#  Compute training and testing accuracy for varying number of neighbors.
#
  print ( '  Training accuracy = ', mlp.score ( X_train_scaled, y_train ) )
  print ( '  Testing accuracy  = ', mlp.score ( X_test_scaled, y_test ) )
#
#  Display the weights that were learned for the first hidden layer.
#
  print ( '' )
  print ( 'Plot the weight learned for the first hidden layer.' )

  plt.clf ( )
  plt.figure ( figsize = ( 20, 5 ) )
  plt.imshow ( mlp.coefs_[0], interpolation = 'none', cmap = 'viridis' )
  plt.yticks ( range ( 30 ), cancer.feature_names )
  plt.xlabel ( 'Columns in weight matrix' )
  plt.ylabel ( 'Input features' )
  plt.colorbar ( )
  filename = 'cancer_classify_mlp.png'
  plt.savefig ( filename )
  print ( '  Graphics saved as "' + filename + '"' )
  plt.close ( )
#
#  Terminate.
#
  print ( '' )
  print ( 'cancer_classify_mlp():' )
  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_classify_mlp ( )
  timestamp ( )