from time import time
import logging
import pylab as pl
import numpy as np
import matplotlib.pyplot as plt

# !pip install -U scikit-learn
from sklearn.model_selection import train_test_split
from sklearn.model_selection import GridSearchCV
from sklearn.datasets import fetch_lfw_people
from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix
from sklearn.decomposition import PCA
from sklearn.svm import SVC


#Display progress
logging.basicConfig(level=logging.INFO, format='%(asctime)s %(message)s')


#Download the data
lfw_people =fetch_lfw_people(min_faces_per_person=70, resize=0.4)

#Find out shape infomration about the images to help with plotting them
n_samples, h, w=lfw_people.images.shape

np.random.seed(42)

# for machine learning we use the data directly (as relative pixel
# position info is ignored by this model)
X = lfw_people.data
n_features = X.shape[1]

# the label to predict is the ID of the person
y = lfw_people.target
target_names = lfw_people.target_names
n_classes = target_names.shape[0]

print ("Total dataset size:")
print ("n_samples: %d" % n_samples)
print ("n_features: %d" % n_features)
print ("n_classes: %d" % n_classes)
print ("Classes: %s" % target_names)

#Lets look at the data to see what they look like

pl.figure
for i in range(0,3):
  pl.subplot(1,3,i+1)
  pl.imshow(X[i].reshape((h,w)), cmap=pl.cm.bone)
  pl.title(target_names[lfw_people.target[i]])
  pl.xticks(())
  pl.yticks(())
  

X_train, X_test, y_train, y_test =train_test_split(X,y, test_size=0.25, random_state=42)
y_test.dtype


# Compute a PCA (eigenfaces) on the face dataset (treated as unlabeled
# dataset): unsupervised feature extraction / dimensionality reduction
n_components = 250

print("Extracting the top %d eignefaces from %d faces" % (n_components, X_train.shape[0]))

#Initiate a time counter (kinda like tic toc)
t0=time()

#Here we take the training data and compute the PCs
pca=PCA(n_components=n_components, whiten=True).fit(X_train)


#Print the time it took to compute
print("Done in %0.3fs" % (time()-t0))



#Reshape the PCs to the image format
eigenfaces =pca.components_.reshape((n_components,h,w))

pl.figure
for i in range(0,3):
  pl.subplot(1,3,i+1)
  pl.imshow(eigenfaces[i], cmap=pl.cm.bone)
  pl.title("Eigenface PC- %d" % (i+1))
  pl.xticks(())
  pl.yticks(())
#   cbar = pl.colorbar()
#   cbar.solids.set_edgecolor("face")
#   pl.draw()

# print(pca.explained_variance_ )
# print(pca.explained_variance_ratio_)



top_pcs=21
plt.figure( figsize=(9, 3))
plt.subplot(121)
plt.bar(np.arange(top_pcs),pca.explained_variance_[0:top_pcs])
plt.xlabel('PCs')
plt.ylabel('Var')

plt.subplot(122)
plt.bar(np.arange(top_pcs),pca.explained_variance_ratio_[0:top_pcs])
plt.xlabel('PCs')
plt.ylabel('Ratio')

np.shape(pca.explained_variance_)

print("Projecting the input data on the eignefaces orthonormal basis")

t0=time()#tic

X_train_pca = pca.transform(X_train) #take the training data and project it to eigenfaces
X_test_pca  = pca.transform(X_test)#take the test data and project it to eigenfaces
print("Done in %0.3fs" % (time()- t0)) #toc

#Training

print ("Fitting the classifier to the training set")
t0 = time()
#These set parameters that we want to optimize. These are passed to GridSearch
#which uses the optimal paramters in the fitting classifier =clf
param_grid = {
         'C': [1e3, 5e3, 1e4, 5e4, 1e5],
          'gamma': [0.0001, 0.0005, 0.001, 0.005, 0.01, 0.1],
          }
# for sklearn version 0.16 or prior, the class_weight parameter value is 'auto'
clf = GridSearchCV(SVC(kernel='rbf', class_weight='balanced'), param_grid)
clf = clf.fit(X_train_pca, y_train)
print ("done in %0.3fs" % (time() - t0))
print ("Best estimator found by grid search:")
print (clf.best_estimator_)

#Testing the classifier 

print ("Predicting the people names on the testing set")
t0 = time()
y_pred = clf.predict(X_test_pca)
print ("done in %0.3fs" % (time() - t0))

print (classification_report(y_test, y_pred, target_names=target_names))
print (confusion_matrix(y_test, y_pred, labels=range(n_classes)))



#Create a helper function to look at the pictures
                         
def plot_gallery(images, titles, h, w, n_row=3, n_col=4):
    """Helper function to plot a gallery of portraits"""
    pl.figure(figsize=(1.8 * n_col, 2.4 * n_row))
    pl.subplots_adjust(bottom=0, left=.01, right=.99, top=.90, hspace=.35)
    for i in range(n_row * n_col):
        pl.subplot(n_row, n_col, i + 1)
        pl.imshow(images[i].reshape((h, w)), cmap=pl.cm.gray)
        pl.title(titles[i], size=12)
        pl.xticks(())
        pl.yticks(())


# plot the result of the prediction on a portion of the test set

def title(y_pred, y_test, target_names, i):
    pred_name = target_names[y_pred[i]].rsplit(' ', 1)[-1]
    true_name = target_names[y_test[i]].rsplit(' ', 1)[-1]
    return 'predicted: %s\ntrue:      %s' % (pred_name, true_name)

prediction_titles = [title(y_pred, y_test, target_names, i)
                         for i in range(y_pred.shape[0])] 

#Now print out preductions
# prediction_titles=(X_test, prediction_titles,h,w)

plot_gallery(X_test, prediction_titles, h, w )

#Plot the eignefaces

eigenface_titles =["Eigneface %d " % i for i in range(eigenfaces.shape[0])]
plot_gallery(eigenfaces, eigenface_titles, h, w)

plt.show()