def knn_classification(k, dist_func, X_train, Y_train, X_predict):
(m_examples, n_dimensions) = X_train.shape
# use kd tree structure for knn searching
labelled_points = np.append(X_train,
Y_train.reshape(m_examples, 1),
axis=1)
t = KDTree.build_tree(labelled_points, n_dimensions)
# store results in the predictions vector
Y_predict = np.empty(X_predict.shape[0])
# record the number of points searched for benchmark/comparison purposes
total_points_searched = 0
# perform knn search for each test data
for i, x in enumerate(X_predict):
(labelled_nearest_neighbors, _, search_space_size) = \
KDTree.knn_search(t, x, k, n_dimensions, dist_func)
# nearest neighbor labels are the last column
nearest_neighbors_labels = np.array(labelled_nearest_neighbors)[:, -1]
Y_predict[i] = mode_with_random_tie_breaking(nearest_neighbors_labels)
total_points_searched += search_space_size
return Y_predict
class KNeighborsBase(object):
def __init__(self):
self.k_neighbors = None
self.tree = None
def fit(self, X, y, k_neighbors=3):
self.k_neighbors = k_neighbors
self.tree = KDTree()
self.tree.build_tree(X, y)
# 1.获取kd_Tree
# 2.建立大顶堆
# 3.建立队列
# 4.外层循环更新大顶堆
# 5.内层循环遍历kd_Tree
# 6.满足堆顶是第k近邻时退出循环
def knn_search(self, Xi):
tree = self.tree
heap = MaxHeap(self.k_neighbors, lambda x: x.dist)
# 搜索Xi时，从根节点到叶节点的路径
nd = tree.search(Xi, tree.root)
# 初始化队列
que = [(tree.root, nd)]
while que:
# 计算Xi和根节点的距离
nd_root, nd_cur = que.pop(0)
nd_root.dist = tree.get_eu_dist(Xi, nd_root)
heap.add(nd_root)
while nd_cur is not nd_root:
# 计算Xi和当前节点的距离
nd_cur.dist = tree.get_eu_dist(Xi, nd_cur)
# 更新最好的节点和距离
heap.add(nd_cur)
if nd_cur.brother and (not heap or heap.items[0].dist > tree.get_hyper_plane_dist(Xi, nd_cur.father)):
_nd = tree.search(Xi, nd_cur.brother)
que.append((nd_cur.brother, _nd))
nd_cur = nd_cur.father
return heap
def _predict(self, Xi):
return NotImplemented
def predict(self, X):
return [self._predict(Xi) for Xi in X]
def one_vs_all_knn_classification(k, dist_func, X_train, Y_train, X_predict):
(m_examples, n_dimensions) = X_train.shape
# use kd tree structure for knn searching
train_indices = (np.arange(0, m_examples)).reshape(m_examples, 1)
indexed_points = np.append(X_train, train_indices, axis=1)
t = KDTree.build_tree(indexed_points, n_dimensions)
# store results in the predictions vector
Y_predict = np.empty(X_predict.shape[0])
# perform knn search for each test data
for i, x in enumerate(X_predict):
indexed_nearest_neighbors = \
KDTree.knn_search(t, x, k, n_dimensions, dist_func)[0]
# http://en.wikipedia.org/wiki/Multiclass_classification
# use one-vs-all strategy to predict the label
possible_labels = set(Y_train) # supposing that each class has at \
# least one representative ...
zero_based_indexed_integer_labels = range(0, len(possible_labels))
assert possible_labels.issubset(zero_based_indexed_integer_labels), \
"accept only zero-based indexed, integer labels"
# the predicted label will be the one from the classifier that gives
# the most votes, so store the votes in a table
classifier_votes_tab = {
c: 0
for c in zero_based_indexed_integer_labels
}
for c in zero_based_indexed_integer_labels:
Y_c = np.zeros(m_examples)
Y_c[Y_train == c] = 1
# neighbor indices are the last column
nearest_neighbors_indices = np.array(indexed_nearest_neighbors)[:,
-1]
votes = int(sum(Y_c[nearest_neighbors_indices.astype(int)]))
classifier_votes_tab[c] = votes
flattened_table = list(Counter(classifier_votes_tab).elements())
Y_predict[i] = mode_with_random_tie_breaking(flattened_table)
return Y_predict
def one_vs_all_knn_classification(k, dist_func, X_train, Y_train, X_predict):
(m_examples, n_dimensions) = X_train.shape
# use kd tree structure for knn searching
train_indices = (np.arange(0, m_examples)).reshape(m_examples, 1)
indexed_points = np.append(X_train, train_indices, axis=1)
t = KDTree.build_tree(indexed_points, n_dimensions)
# store results in the predictions vector
Y_predict = np.empty(X_predict.shape[0])
# perform knn search for each test data
for i, x in enumerate(X_predict):
indexed_nearest_neighbors = \
KDTree.knn_search(t, x, k, n_dimensions, dist_func)[0]
# http://en.wikipedia.org/wiki/Multiclass_classification
# use one-vs-all strategy to predict the label
possible_labels = set(Y_train) # supposing that each class has at \
# least one representative ...
zero_based_indexed_integer_labels = range(0, len(possible_labels))
assert possible_labels.issubset(zero_based_indexed_integer_labels), \
"accept only zero-based indexed, integer labels"
# the predicted label will be the one from the classifier that gives
# the most votes, so store the votes in a table
classifier_votes_tab = {c: 0 for c in zero_based_indexed_integer_labels}
for c in zero_based_indexed_integer_labels:
Y_c = np.zeros(m_examples)
Y_c[Y_train == c] = 1
# neighbor indices are the last column
nearest_neighbors_indices= np.array(indexed_nearest_neighbors)[:,-1]
votes = int(sum(Y_c[nearest_neighbors_indices.astype(int)]))
classifier_votes_tab[c] = votes
flattened_table = list(Counter(classifier_votes_tab).elements())
Y_predict[i] = mode_with_random_tie_breaking(flattened_table)
return Y_predict
def knn_classification(k, dist_func, X_train, Y_train, X_predict):
(m_examples, n_dimensions) = X_train.shape
# use kd tree structure for knn searching
labelled_points = np.append(X_train, Y_train.reshape(m_examples,1),axis=1)
t = KDTree.build_tree(labelled_points, n_dimensions)
# store results in the predictions vector
Y_predict = np.empty(X_predict.shape[0])
# record the number of points searched for benchmark/comparison purposes
total_points_searched = 0
# perform knn search for each test data
for i, x in enumerate(X_predict):
(labelled_nearest_neighbors, _, search_space_size) = \
KDTree.knn_search(t, x, k, n_dimensions, dist_func)
# nearest neighbor labels are the last column
nearest_neighbors_labels = np.array(labelled_nearest_neighbors)[:,-1]
Y_predict[i] = mode_with_random_tie_breaking(nearest_neighbors_labels)
total_points_searched += search_space_size
return Y_predict
