nycdsa_p5_prediction.py

from sklearn.metrics import mean_squared_error

prediction = similarity_user.dot(train_matrix) / np.array([np.abs(similarity_user).sum(axis=1)]).T
prediction = prediction[test_matrix.nonzero()].flatten()
test_vector = test_matrix[test_matrix.nonzero()].flatten()
mse = mean_squared_error(prediction, test_vector)

print 'MSE = ' + str(mse)