Numpy实现GradientBoosting

min_samples_split: int

The minimum number of samples needed to make a split when building a tree.

min_impurity: float

The minimum impurity required to split the tree further.

max_depth: int

The maximum depth of a tree.

regression: boolean

True or false depending on if we’re doing regression or classification.

“”"

def init(self, n_estimators, learning_rate, min_samples_split,

min_impurity, max_depth, regression):

self.n_estimators = n_estimators

self.learning_rate = learning_rate

self.min_samples_split = min_samples_split

self.min_impurity = min_impurity

self.max_depth = max_depth

self.regression = regression

self.bar = progressbar.ProgressBar(widgets=bar_widgets)

Square loss for regression

Log loss for classification

self.loss = SquareLoss()

if not self.regression:

self.loss = CrossEntropy()

Initialize regression trees

self.trees = []

for _ in range(n_estimators):

tree = RegressionTree(

min_samples_split=self.min_samples_split,

min_impurity=min_impurity,

max_depth=self.max_depth)

self.trees.append(tree)

def fit(self, X, y):

y_pred = np.full(np.shape(y), np.mean(y, axis=0))

for i in self.bar(range(self.n_estimators)):

gradient = self.loss.gradient(y, y_pred)

self.trees[i].fit(X, gradient)

update = self.trees[i].predict(X)

Update y prediction

y_pred -= np.multiply(self.learning_rate, update)

def predict(self, X):

y_pred = np.array([])

Make predictions

for tree in self.trees:

update = tree.predict(X)

update = np.multiply(self.learning_rate, update)

y_pred = -update if not y_pred.any() else y_pred - update

if not self.regression:

Turn into probability distribution

y_pred = np.exp(y_pred) / np.expand_dims(np.sum(np.exp(y_pred), axis=1), axis=1)

Set label to the value that maximizes probability

y_pred = np.argmax(y_pred, axis=1)

return y_pred

class GradientBoostingRegressor(GradientBoosting):

def init(self, n_estimators=200, learning_rate=0.5, min_samples_split=2,

min_var_red=1e-7, max_depth=4, debug=False):

super(GradientBoostingRegressor, self).init(n_estimators=n_estimators,

learning_rate=learning_rate,

min_samples_split=min_samples_split,

min_impurity=min_var_red,

max_depth=max_depth,

regression=True)

自我介绍一下，小编13年上海交大毕业，曾经在小公司待过，也去过华为、OPPO等大厂，18年进入阿里一直到现在。

深知大多数Python工程师，想要提升技能，往往是自己摸索成长或者是报班学习，但对于培训机构动则几千的学费，着实压力不小。自己不成体系的自学效果低效又漫长，而且极易碰到天花板技术停滞不前！

因此收集整理了一份《2024年Python开发全套学习资料》，初衷也很简单，就是希望能够帮助到想自学提升又不知道该从何学起的朋友，同时减轻大家的负担。

既有适合小白学习的零基础资料，也有适合3年以上经验的小伙伴深入学习提升的进阶课程，基本涵盖了95%以上前端开发知识点，真正体系化！

由于文件比较大，这里只是将部分目录大纲截图出来，每个节点里面都包含大厂面经、学习笔记、源码讲义、实战项目、讲解视频，并且后续会持续更新

如果你觉得这些内容对你有帮助，可以扫码获取！！！（备注Python）

经验的小伙伴深入学习提升的进阶课程，基本涵盖了95%以上前端开发知识点，真正体系化！**

由于文件比较大，这里只是将部分目录大纲截图出来，每个节点里面都包含大厂面经、学习笔记、源码讲义、实战项目、讲解视频，并且后续会持续更新

如果你觉得这些内容对你有帮助，可以扫码获取！！！（备注Python）