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

#*****************************************************************************80
#
## faces_classify_knn() uses k-nearest neighbor classification on face data.
#
#  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 fetch_lfw_people
  from sklearn.model_selection import train_test_split
  from sklearn.neighbors import KNeighborsClassifier
  import matplotlib.pyplot as plt
  import mglearn
  import numpy as np
  import pandas as pd
  import platform
  import sklearn

  print ( '' )
  print ( 'faces_classify_knn():' )
  print ( '  Python version: ' + platform.python_version ( ) )
  print ( '  scikit-learn version: '+ sklearn.__version__ )
  print ( '  Match a face to an item in the faces dataset.' )
  print ( '  Use the k-nearest neighbor method.' )
  print ( '' )
#
#  Generate the dataset.
#
  print ( '  Generate the dataset' )
  people = fetch_lfw_people ( min_faces_per_person = 20, resize = 0.7 )
  image_shape = people.images[0].shape
#
#  Display 2x5 grid of 10 sample faces.
#
  print ( '  Plot the dataset (X0,X1).' )

  plt.clf ( )

  fig, axes = plt.subplots ( 2, 5, figsize = ( 15, 8 ),
    subplot_kw = { 'xticks': (), 'yticks': () } )

  for target, image, ax in zip ( people.target, people.images, axes.ravel() ):
    ax.imshow ( image )
    ax.set_title ( people.target_names[target] )

  filename = 'faces_sample.png'
  plt.savefig ( filename )
  print ( '  Graphics saved as "' + filename + '"' )

  print ( "  people.images.shape:", people.images.shape )
  print ( "  Number of classes:", len ( people.target_names ) )
#
#  Count how often each target appears.
#
  counts = np.bincount ( people.target )
  for i, ( count, name ) in enumerate ( zip ( counts, people.target_names ) ):
    print ( name, count )
#
#  Trim the dataset so no more than 50 images of any person.
#
  mask = np.zeros ( people.target.shape, dtype = bool )
  for target in np.unique ( people.target ):
    mask[np.where ( people.target == target) [0][:50]] = 1 
  X_people = people.data[mask]
  y_people = people.target[mask]
#
#  Scale the grayscale values to be between 0 and 1.
#
  X_people = X_people / 255.0
#
#  ?
#
  X_train, X_test, y_train, y_test = train_test_split ( 
    X_people, y_people, stratify = y_people, random_state = 0 )
  knn = KNeighborsClassifier ( n_neighbors = 1 )
  knn.fit ( X_train, y_train )
  print ( "" )
  print ( "  Test set score using 1 neighbor", knn.score(X_test,y_test) )
#
#  Terminate.
#
  print ( '' )
  print ( 'faces_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 ( )
  faces_classify_knn ( )
  timestamp ( )