def fit(self, x, y):
# 将y转one-hot编码
class_num = np.amax(y) + 1
y_cate = np.zeros(shape=(len(y), class_num))
y_cate[np.arange(len(y)), y] = 1
# 扩展分类器
self.expand_base_estimators = [
copy.deepcopy(self.base_estimator) for _ in range(class_num)
]
# 拟合第一个模型
y_pred_score_ = []
# TODO:并行优化
for class_index in range(0, class_num):
self.expand_base_estimators[class_index][0].fit(
x, y_cate[:, class_index])
y_pred_score_.append(
self.expand_base_estimators[class_index][0].predict(x))
y_pred_score_ = np.c_[y_pred_score_].T
# 计算负梯度
new_y = y_cate - utils.softmax(y_pred_score_)
# 训练后续模型
for index in range(1, self.n_estimators):
y_pred_score = []
for class_index in range(0, class_num):
self.expand_base_estimators[class_index][index].fit(
x, new_y[:, class_index])
y_pred_score.append(
self.expand_base_estimators[class_index][index].predict(x))
y_pred_score_ += np.c_[y_pred_score].T * self.learning_rate
new_y = y_cate - utils.softmax(y_pred_score_)
def fit(self, x):
n_sample = x.shape[0]
self.dbw.fit(x)
x_bins = self.dbw.transform(x)
# 初始化模型参数
self.default_y_prob = np.log(0.5 / self.n_components) # 默认p_y
for y_label in range(0, self.n_components):
self.p_x_y[y_label] = {}
self.p_y[y_label] = np.log(1.0 / self.n_components) # 初始p_y设置一样
self.default_x_prob[y_label] = np.log(0.5 / n_sample) # 默认p_x_y
# 初始p_x_y设置一样
for j in range(0, x_bins.shape[1]):
self.p_x_y[y_label][j] = {}
x_j_set = set(x_bins[:, j])
for x_j in x_j_set:
# 随机抽样计算条件概率
sample_x_index = np.random.choice(
n_sample, n_sample // self.n_components)
sample_x_bins = x_bins[sample_x_index]
p_x_y = (np.sum(sample_x_bins[:, j] == x_j) +
1) / (sample_x_bins.shape[0] + len(x_j_set))
self.p_x_y[y_label][j][x_j] = np.log(p_x_y)
# 计算隐变量
W_log = self.get_log_w(x_bins)
W = utils.softmax(W_log)
W_gen = np.exp(W_log)
current_log_loss = np.log(W_gen.sum(axis=1)).sum()
# 迭代训练
current_epoch = 0
for _ in range(0, self.n_iter):
if self.verbose is True:
utils.plot_decision_function(x, self.predict(x), self)
utils.plt.pause(0.1)
utils.plt.clf()
# 更新模型参数
for k in range(0, self.n_components):
self.p_y[k] = np.log(np.sum(W[:, k]) / n_sample)
for j in range(0, x_bins.shape[1]):
x_j_set = set(x_bins[:, j])
for x_j in x_j_set:
self.p_x_y[k][j][x_j] = np.log(
1e-10 +
np.sum(W[:, k] *
(x_bins[:, j] == x_j)) / np.sum(W[:, k]))
# 更新隐变量
W_log = self.get_log_w(x_bins)
W = utils.softmax(W_log)
W_gen = np.exp(W_log)
# 计算log like hold
new_log_loss = np.log(W_gen.sum(axis=1)).sum()
if new_log_loss - current_log_loss > self.tol:
current_log_loss = new_log_loss
current_epoch += 1
else:
print('total epochs:', current_epoch)
break
if self.verbose:
utils.plot_decision_function(x, self.predict(x), self)
utils.plt.show()
def predict_proba(self, x):
# TODO:并行优化
y_pred_score = []
for class_index in range(0, len(self.expand_base_estimators)):
estimator_of_index = self.expand_base_estimators[class_index]
y_pred_score.append(
np.sum([estimator_of_index[0].predict(x)] + [
self.learning_rate * estimator_of_index[i].predict(x)
for i in range(1, self.n_estimators - 1)
] + [estimator_of_index[self.n_estimators - 1].predict(x)],
axis=0))
return utils.softmax(np.c_[y_pred_score].T)
def fit(self, x, y):
# 将y转one-hot编码
class_num = np.amax(y) + 1
y_cate = np.zeros(shape=(len(y), class_num))
y_cate[np.arange(len(y)), y] = 1
# 扩展分类器
self.expand_base_estimators = [
copy.deepcopy(self.base_estimator) for _ in range(class_num)
]
# 第一个模型假设预测为0
y_pred_score_ = np.zeros(shape=(x.shape[0], class_num))
# 计算一阶、二阶导数
g = utils.softmax(y_pred_score_) - y_cate
h = utils.softmax(y_pred_score_) * (1 - utils.softmax(y_pred_score_))
# 训练后续模型
for index in range(0, self.n_estimators):
y_pred_score = []
for class_index in range(0, class_num):
self.expand_base_estimators[class_index][index].fit(
x, g[:, class_index], h[:, class_index])
y_pred_score.append(
self.expand_base_estimators[class_index][index].predict(x))
y_pred_score_ += np.c_[y_pred_score].T * self.learning_rate
g = utils.softmax(y_pred_score_) - y_cate
h = utils.softmax(y_pred_score_) * (1 -
utils.softmax(y_pred_score_))
def fit(self, x, y):
# 将y转one-hot编码
class_num = np.amax(y) + 1
self.class_num = class_num
y_cate = np.zeros(shape=(len(y), class_num))
y_cate[np.arange(len(y)), y] = 1
self.weights = [[] for _ in range(0, class_num)]
# 扩展分类器
self.expand_base_estimators = [
copy.deepcopy(self.base_estimator) for _ in range(class_num)
]
# 拟合第一个模型
y_pred_score_ = [[] for _ in range(0, self.class_num)]
# TODO:并行优化
for class_index in range(0, class_num):
self.expand_base_estimators[class_index][0].fit(
x, y_cate[:, class_index])
y_pred_score_[class_index].append(
self.expand_base_estimators[class_index][0].predict(x))
self.weights[class_index].append(1.0)
y_pred_result, ks = self._dropout(y_pred_score_)
y_pred_result = np.c_[y_pred_result].T
# 计算负梯度
new_y = y_cate - utils.softmax(y_pred_result)
# 训练后续模型
for index in range(1, self.n_estimators):
for class_index in range(0, class_num):
self.expand_base_estimators[class_index][index].fit(
x, new_y[:, class_index])
y_pred_score_[class_index].append(
self.expand_base_estimators[class_index][index].predict(x))
self.weights[class_index].append(1.0 / (ks[class_index] + 1))
y_pred_result, ks = self._dropout(y_pred_score_)
y_pred_result = np.c_[y_pred_result].T
new_y = y_cate - utils.softmax(y_pred_result)
def predict_proba(self, x):
rst = []
for x_row in x:
tmp = []
for y_index in range(0, self.n_components):
try:
p_y_log = self.p_y[y_index]
except:
p_y_log = self.default_y_prob
for i, xij in enumerate(x_row):
p_y_log += np.log(
1e-12 +
utils.gaussian_1d(xij, self.p_x_y[y_index][i][0],
self.p_x_y[y_index][i][1]))
tmp.append(p_y_log)
rst.append(tmp)
return utils.softmax(np.asarray(rst))
def predict_proba(self, x):
x_bins = self.dbw.transform(x)
rst = []
for x_row in x_bins:
tmp = []
for y_index in range(0, self.n_components):
try:
p_y_log = self.p_y[y_index]
except:
p_y_log = self.default_y_prob
for i, xij in enumerate(x_row):
try:
p_y_log += self.p_x_y[y_index][i][xij]
except:
p_y_log += self.default_x_prob[y_index]
tmp.append(p_y_log)
rst.append(tmp)
return utils.softmax(np.asarray(rst))
