kNN Classification of digits using scikit-learn

digits-knn.py

from sklearn.metrics import confusion_matrix, accuracy_score
from sklearn import cross_validation

# load sample dataset of digits
digits = datasets.load_digits()

# prepare datasets from training and for validation
X_train, X_test, y_train, y_test = cross_validation.train_test_split(digits.data, digits.target, test_size=0.4, random_state=0)

# runs the kNN classifier for even number of neighbors from 1 to 10
for n in range(1, 10, 2):
        clf = neighbors.KNeighborsClassifier(n)

        # instance based learning
        clf.fit(X_train, y_train)

        # our 'ground truth'
        y_true = y_test

        # predict
        y_pred = clf.predict(X_test)

        # learning metrics
        cm = confusion_matrix(y_true, y_pred)
        acc = accuracy_score(y_true, y_pred)

        print "Neighbors: %d" % n
        print "Confusion Matrix"
        print cm

        print "Accuracy score: %f" % accuracy_score(y_true, y_pred)
        print