Skip to main content

​
GradientBoostingClassifier

Gradient Boosting Classifier using shallow regression trees. Supports both binary and multiclass classification.
  • Binary: Optimizes log loss using sigmoid function
  • Multiclass: Uses One-vs-Rest (OvR) strategy, training one binary model per class

​
Constructor

new GradientBoostingClassifier(options?: {
  nEstimators?: number;
  learningRate?: number;
  maxDepth?: number;
  minSamplesSplit?: number;
})
​
options.nEstimators
number
default:"100"
Number of boosting stages (trees) to train.
​
options.learningRate
number
default:"0.1"
Learning rate shrinks the contribution of each tree. Smaller values require more trees.
​
options.maxDepth
number
default:"3"
Maximum depth of individual regression trees.
​
options.minSamplesSplit
number
default:"2"
Minimum samples required to split an internal node.

​
Methods

​
fit

fit(X: Tensor, y: Tensor): this
Fit the gradient boosting classifier on training data. Builds an additive model by sequentially fitting regression trees to the pseudo-residuals (gradient of log loss).
​
X
Tensor
required
Training data of shape (n_samples, n_features)
​
y
Tensor
required
Target class labels of shape (n_samples,). Must contain at least 2 classes.
Returns: The fitted estimator

​
predict

predict(X: Tensor): Tensor
Predict class labels for samples in X. Returns: Predicted class labels of shape (n_samples,)

​
predictProba

predictProba(X: Tensor): Tensor
Predict class probabilities for samples in X. Returns: Class probability matrix of shape (n_samples, n_classes)

​
score

score(X: Tensor, y: Tensor): number
Return the mean accuracy on the given test data and labels. Returns: Accuracy score in range [0, 1]

​
Example

import { GradientBoostingClassifier } from 'deepbox/ml';
import { tensor } from 'deepbox/ndarray';

const X = tensor([[1, 2], [2, 3], [3, 1], [4, 2]]);
const y = tensor([0, 0, 1, 1]);

const gbc = new GradientBoostingClassifier({ nEstimators: 100 });
gbc.fit(X, y);
const predictions = gbc.predict(X);
const probabilities = gbc.predictProba(X);

​
GradientBoostingRegressor

Gradient Boosting Regressor that builds an additive model in a forward stage-wise fashion using regression trees as weak learners. Optimizes squared error loss.

​
Constructor

new GradientBoostingRegressor(options?: {
  nEstimators?: number;
  learningRate?: number;
  maxDepth?: number;
  minSamplesSplit?: number;
})
​
options.nEstimators
number
default:"100"
Number of boosting stages (trees).
​
options.learningRate
number
default:"0.1"
Learning rate shrinks the contribution of each tree.
​
options.maxDepth
number
default:"3"
Maximum depth of individual regression trees.
​
options.minSamplesSplit
number
default:"2"
Minimum samples required to split.

​
Methods

​
fit

fit(X: Tensor, y: Tensor): this
Fit the gradient boosting regressor on training data. Builds an additive model by sequentially fitting regression trees to the negative gradient (residuals) of the loss function.
​
X
Tensor
required
Training data of shape (n_samples, n_features)
​
y
Tensor
required
Target values of shape (n_samples,)
Returns: The fitted estimator

​
predict

predict(X: Tensor): Tensor
Predict target values for samples in X. Aggregates the initial prediction and the scaled contributions of all trees. Returns: Predicted values of shape (n_samples,)

​
score

score(X: Tensor, y: Tensor): number
Return the R² score on the given test data and target values. Returns: R² score (best possible is 1.0, can be negative)

​
Example

import { GradientBoostingRegressor } from 'deepbox/ml';
import { tensor } from 'deepbox/ndarray';

const X = tensor([[1], [2], [3], [4], [5]]);
const y = tensor([1.2, 2.1, 2.9, 4.0, 5.1]);

const gbr = new GradientBoostingRegressor({ nEstimators: 100 });
gbr.fit(X, y);
const predictions = gbr.predict(X);

Build docs developers (and LLMs) love

Get started for freeTalk to us