Unsupervised learner--k-Nearest Neighbor

K最近接（k-Nearest Neighbor，KNN）分類アルゴリズム

導入背景

げんり

ステップ

長所と短所

Python実現

# === （ KNN ）====
def classify0(x, dataset, labels, k):
    dataset_size = dataset.shape[0]  # shape[0] stands for the num of row
    # step 1: calculate Euclidean distance
    # tile(A, reps): Construct an array by repeating A reps times
    # the following copy numSamples rows for dataSet
    diff_mat = np.tile(x, (dataset_size, 1)) - dataset
    sq_diff_mat = diff_mat ** 2
    sq_distances = sq_diff_mat.sum(axis=1)
    distances = sq_distances ** 0.5
    # step 2: sort the distance
    # argsort() returns the indices that would sort an array in a ascending order
    sorted_dist_indicies = distances.argsort()

    class_count = {}
    for i in range(k):
        # step 3: choose the min k distance
        voted_label = labels[sorted_dist_indicies[i]]
        # step 4: count the times labels occur
        # when the key voteLabel is not in dictionary classCount, get()
        # will return 0
        class_count[voted_label] = class_count.get(voted_label, 0) + 1
        # step 5: the max voted class will return
        # Python 2.x  `class_count.iteritems()
    sorted_class_count = sorted(class_count.iteritems(),
                                key=operator.itemgetter(1),
                                reverse=True)
    return sorted_class_count[0][0]