from sklearn.datasets import load_digits
digits = load_digits()

%pylab inline

# copied from notebook 02_sklearn_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)
    
    # 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.manifold import Isomap
iso = Isomap(n_neighbors=5, n_components=2)
proj = iso.fit_transform(digits.data)

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

from sklearn.naive_bayes import GaussianNB
from sklearn import cross_validation

# split the data into training and validation sets
data_train, data_test, target_train, target_test = cross_validation.train_test_split(digits.data, digits.target)

# train the model
clf = GaussianNB()
clf.fit(data_train, target_train)

# predict the labels of the test data
predicted = clf.predict(data_test)
expected = target_test

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

print metrics.confusion_matrix(expected, predicted)

cv = cross_validation.KFold(digits.data.shape[0], 5, shuffle=True, random_state=0)

clf = GaussianNB()

print cross_validation.cross_val_score(clf, digits.data, digits.target, cv=cv)