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

#*****************************************************************************80
#
## cancer_classify_knn() uses k-nearest neighbor classification on cancer data.
#
#  Licensing:
#
#    This code is distributed under the MIT license.
#
#  Modified:
#
#    15 June 2023
#
#  Author:
#
#    Andreas Mueller, Sarah Guido.
#    Modifications by John Burkardt.
#
#  Reference:
#
#    Andreas Mueller, Sarah Guido,
#    Introduction to Machine Learning with Python,
#    OReilly, 2017,
#    ISBN: 978-1-449-36941-5
#
  import matplotlib.pyplot as plt
  import mglearn
  import numpy as np
  import pandas as pd
  import platform
  import sklearn

  print ( '' )
  print ( 'cancer_classify_knn():' )
  print ( '  Python version: ' + platform.python_version ( ) )
  print ( '  scikit-learn version: '+ sklearn.__version__ )
#
#  Generate the dataset.
#
  print ( '' )
  print ( '  Retrieve the cancer dataset, (X, y).' )
  from sklearn.datasets import load_breast_cancer
  cancer = load_breast_cancer ( )

  from sklearn.model_selection import train_test_split
  X_train, X_test, y_train, y_test = train_test_split ( \
    cancer.data, cancer.target, stratify = cancer.target, random_state = 66 )
#
#  Compute training and testing accuracy for varying number of neighbors.
#
  from sklearn.neighbors import KNeighborsClassifier
  training_accuracy = []
  test_accuracy = []
  for n_neighbors in range ( 1, 11 ):
    clf = KNeighborsClassifier ( n_neighbors = n_neighbors )
    clf.fit ( X_train, y_train )
    training_accuracy.append ( clf.score ( X_train, y_train ) )
    test_accuracy.append ( clf.score ( X_test, y_test ) )

  plt.clf ( )
  plt.plot ( range ( 1, 11 ), training_accuracy, label = 'Training accuracy' )
  plt.plot ( range ( 1, 11 ), test_accuracy, label = 'Test accuracy' )
  plt.ylabel ( 'Accuracy' )
  plt.xlabel ( 'n_neighbors' )
  plt.legend ( )
  filename = 'cancer_classify_knn.png'
  plt.savefig ( filename )
  print ( '  Graphics saved as "' + filename + '"' )
#
#  Terminate.
#
  print ( '' )
  print ( 'cancer_classify_knn():' )
  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_knn ( )
  timestamp ( )