import matplotlib.pyplot as plt from sklearn import datasets, neighbors from sklearn.model_selection import train_test_split # Load the digits data set digits = datasets.load_digits() # Visualize an example digit image plt.gray() plt.matshow(digits.images[0]) # Use the first digit in the data set plt.show()

# Extract the input data, force values to be between 0.0 and 1.0 (NORMALIZE the data) X_digits = digits.data / digits.data.max() # Extract the true values for each sample (each a digit between 0-9) y_digits = digits.target # Print the first 20 target values y_digits[:20]

# Training set will be 90% of available samples, # testing set will be remaining 10% X_train, X_test, y_train, y_test = train_test_split(X_digits, y_digits, train_size=0.9)

# Import the default K-Nearest Neighbors classifier # What does the 5 represent in the line of code below? knn = neighbors.KNeighborsClassifier(n_neighbors=5) # Train the classifer knn.fit(X_train, y_train) # Compute the score (mean accuracy) on test set score = knn.score(X_test, y_test) print('KNN score: %f' % score)

#Create a new knn model with a different k value # Train the classifer # Compute the score (mean accuracy) on test set

#Print out the y for the test set print(y_test) #Create the y^ (predictions) for the test set and print