# Author: Gael Varoquaux <gael dot varoquaux at normalesup dot org>
# License: BSD 3 clause
import numpy as np
from sklearn import datasets, svm, metrics
from matplotlib import pyplot as plt
%matplotlib inline
# digitsデータ読込
digits = datasets.load_digits()
# digitsの画像の一部を例示(4例のみ)
images_and_labels = list(zip(digits.images, digits.target))
for index, (image, label) in enumerate(images_and_labels[:4]):
plt.subplot(2, 4, index + 1)
plt.axis('off')
plt.imshow(image, cmap=plt.cm.gray_r, interpolation='nearest')
plt.title('Training: %i' % label)
# To apply a classifier on this data, we need to flatten the image, to
# turn the data in a (samples, feature) matrix:
n_samples = len(digits.images)
data = digits.images.reshape((n_samples, -1))
# 識別器生成(SVC)
classifier = svm.SVC(gamma=0.001)
# digitsデータの前半半分で学習
classifier.fit(data[:n_samples / 2], digits.target[:n_samples / 2])
# 次にdigitsデータの後半半分で推定
# 期待される結果(正解識別結果となる)
expected = digits.target[n_samples / 2:]
# 推定
predicted = classifier.predict(data[n_samples / 2:])
# 推定結果の一部を例示(4例)
images_and_predictions = list(zip(digits.images[n_samples / 2:], predicted))
for index, (image, prediction) in enumerate(images_and_predictions[:4]):
plt.subplot(2, 4, index + 5)
plt.axis('off')
plt.imshow(image, cmap=plt.cm.gray_r, interpolation='nearest')
plt.title('Prediction: %i' % prediction)
plt.show()
print("Classification report for classifier %s:\n%s\n"
% (classifier, metrics.classification_report(expected, predicted)))
print("Confusion matrix:\n%s" % metrics.confusion_matrix(expected, predicted))