for k in k_choices:
accuracies = k_to_accuracies[k]
plt.scatter([k] * len(accuracies), accuracies)
# plot the trend line with error bars that correspond to standard deviation
accuracies_mean = np.array(
[np.mean(v) for k, v in sorted(k_to_accuracies.items())])
accuracies_std = np.array(
[np.std(v) for k, v in sorted(k_to_accuracies.items())])
plt.errorbar(k_choices, accuracies_mean, yerr=accuracies_std)
plt.title('Cross-validation on k')
plt.xlabel('k')
plt.ylabel('Cross-validation accuracy')
plt.show()
# In[ ]:
# Based on the cross-validation results above, choose the best value for k,
# retrain the classifier using all the training data, and test it on the test
# data. You should be able to get above 28% accuracy on the test data.
best_k = 1
classifier = KNearestNeighbor()
classifier.train(X_train, y_train)
y_test_pred = classifier.predict(X_test, k=best_k)
# Compute and display the accuracy
num_correct = np.sum(y_test_pred == y_test)
accuracy = float(num_correct) / num_test
print 'Got %d / %d correct => accuracy: %f' % (num_correct, num_test, accuracy)
xdev = np.array(X_train_folds[i])
ydev = np.array(y_train_folds[i])
xtr = np.reshape(xtr,
((X_train.shape[0] *
(num_folds - 1)) / num_folds, -1)) # (4000, 3072)
ytr = np.reshape(ytr, ((y_train.shape[0] *
(num_folds - 1)) / num_folds, -1)) # (4000, 1)
xdev = np.reshape(xdev,
(X_train.shape[0] / num_folds, -1)) # (1000, 3072)
ydev = np.reshape(ydev,
(y_train.shape[0] / num_folds, -1)) # (1000, 1)
nn = KNearestNeighbor()
nn.train(xtr, ytr)
y_predict = nn.predict(xdev, k=k, num_loops=0) # (1000, )
# print(np.shape(y_predict)) 注意维度匹配
y_predict = np.reshape(y_predict, (y_predict.shape[0], -1))
num_correct = np.sum(y_predict == ydev)
accuracy = num_correct / float(xdev.shape[0])
k_to_accuracies[k][i] = accuracy
################################################################################
# END OF YOUR CODE #
################################################################################
# Print out the computed accuracies
print("the computed accuracies.....")
for k in sorted(k_to_accuracies):
for accuracy in k_to_accuracies[k]:
print('k = %d, accuracy = %f' % (k, accuracy))
for k in k_choices:
accuracies = k_to_accuracies[k]
plt.scatter([k] * len(accuracies), accuracies)
# plot the trend line with error bars that correspond to standard deviation
accuracies_mean = np.array([np.mean(v) for k,v in sorted(k_to_accuracies.items())])
accuracies_std = np.array([np.std(v) for k,v in sorted(k_to_accuracies.items())])
plt.errorbar(k_choices, accuracies_mean, yerr=accuracies_std)
plt.title('Cross-validation on k')
plt.xlabel('k')
plt.ylabel('Cross-validation accuracy')
plt.show()
# In[ ]:
# Based on the cross-validation results above, choose the best value for k,
# retrain the classifier using all the training data, and test it on the test
# data. You should be able to get above 28% accuracy on the test data.
best_k = 1
classifier = KNearestNeighbor()
classifier.train(X_train, y_train)
y_test_pred = classifier.predict(X_test, k=best_k)
# Compute and display the accuracy
num_correct = np.sum(y_test_pred == y_test)
accuracy = float(num_correct) / num_test
print 'Got %d / %d correct => accuracy: %f' % (num_correct, num_test, accuracy)