from sklearn.datasets import load_digits
digits = load_digits()

%matplotlib inline
from matplotlib import pyplot as plt

# copied from notebook 02_representation_of_data.ipynb
fig = plt.figure(figsize=(6, 6))  # figure size in inches
fig.subplots_adjust(left=0, right=1, bottom=0, top=1, hspace=0.05, wspace=0.05)

# plot the digits: each image is 8x8 pixels
for i in range(64):
    ax = fig.add_subplot(8, 8, i + 1, xticks=[], yticks=[])
    ax.imshow(digits.images[i], cmap=plt.cm.binary, interpolation='nearest')
    
    # label the image with the target value
    ax.text(0, 7, str(digits.target[i]))

from sklearn.decomposition import RandomizedPCA
pca = RandomizedPCA(n_components=2)
proj = pca.fit_transform(digits.data)

plt.scatter(proj[:, 0], proj[:, 1], c=digits.target)
plt.colorbar()

from sklearn.naive_bayes import GaussianNB
from sklearn.cross_validation import train_test_split

# split the data into training and validation sets
X_train, X_test, y_train, y_test = train_test_split(digits.data, digits.target)

# train the model
clf = GaussianNB()
clf.fit(X_train, y_train)

# use the model to predict the labels of the test data
predicted = clf.predict(X_test)
expected = y_test

fig = plt.figure(figsize=(6, 6))  # figure size in inches
fig.subplots_adjust(left=0, right=1, bottom=0, top=1, hspace=0.05, wspace=0.05)

# plot the digits: each image is 8x8 pixels
for i in range(64):
    ax = fig.add_subplot(8, 8, i + 1, xticks=[], yticks=[])
    ax.imshow(X_test.reshape(-1, 8, 8)[i], cmap=plt.cm.binary,
              interpolation='nearest')
    
    # label the image with the target value
    if predicted[i] == expected[i]:
        ax.text(0, 7, str(predicted[i]), color='green')
    else:
        ax.text(0, 7, str(predicted[i]), color='red')

matches = (predicted == expected)
print(matches.sum())
print(len(matches))

matches.sum() / float(len(matches))

from sklearn import metrics
print(metrics.classification_report(expected, predicted))

print(metrics.confusion_matrix(expected, predicted))