---
title: "Extra Tree Classifier in JavaScript with @kanaries/ml"
description: "Learn what Extra Tree Classifier does, when to use it, and how to run ExtraTreeClassifier in JavaScript or TypeScript with @kanaries/ml for browser and Node.js applications."
canonical_url: "https://ml.kanaries.net/docs/apis/tree/extraTreeClassifier"
markdown_url: "https://ml.kanaries.net/docs/apis/tree/extraTreeClassifier.md"
---
# Extra Tree Classifier in JavaScript

## Algorithm overview

ExtraTreeClassifier injects additional split randomness to reduce variance and improve generalization in noisy settings.

This algorithm is especially useful when:

- Standard decision trees overfit your training set.
- You need fast tree-based classification with stronger randomization.
- You plan to combine trees in ensemble-style workflows.

## JavaScript implementation

@kanaries/ml exposes Extra Tree classification in JavaScript for workflows that want tree-based decisions with more randomized splitting behavior. This is useful for experimentation and for teams that want a fast tree baseline with slightly different bias-variance behavior than a standard decision tree.

Because it runs in JS, you can compare deterministic and randomized tree variants directly inside the same product or service codebase.

## Interactive Extra Tree playground

Extra Trees choose randomized candidate thresholds. Keep the data and parameters fixed, then use **Reroll splits** to see how that randomness changes the learned regions. The model below runs with `Tree.ExtraTreeClassifier` directly in your browser.

> The HTML version includes an interactive Extra Tree Classifier playground. You can tune the tree depth, split constraints, dataset noise, and criterion; add observations; and inspect the fitted predictions and tree structure. The guide, runnable example, and API reference continue below. [Open the HTML page](https://ml.kanaries.net/docs/apis/tree/extraTreeClassifier).

## Quick start

### ExtraTreeClassifier: Python and JavaScript / TypeScript

The Python example uses scikit-learn; the TypeScript example uses @kanaries/ml in browser or Node.js runtimes.

#### Python (scikit-learn)

```python
from sklearn.tree import ExtraTreeClassifier

X = [[0, 0], [1, 1], [1, 0], [0, 1]]
y = [0, 1, 1, 0]

clf = ExtraTreeClassifier(max_depth=3, criterion='gini', random_state=0)
clf.fit(X, y)
pred = clf.predict([[0.9, 0.8], [0.1, 0.2]])
```

#### JavaScript / TypeScript (@kanaries/ml)

```ts
import { Tree } from '@kanaries/ml';

const X = [[0, 0], [1, 1], [1, 0], [0, 1]];
const y = [0, 1, 1, 0];

const clf = new Tree.ExtraTreeClassifier({ max_depth: 3, criterion: 'gini' });
clf.fit(X, y);
const pred = clf.predict([[0.9, 0.8], [0.1, 0.2]]);
```

### Quick JavaScript example

```ts
import { Tree } from '@kanaries/ml';

const X = [[0, 0], [1, 1], [1, 0], [0, 1]];
const y = [0, 1, 1, 0];

const clf = new Tree.ExtraTreeClassifier({ max_depth: 3, criterion: 'gini' });
clf.fit(X, y);
const pred = clf.predict([[0.9, 0.8], [0.1, 0.2]]);
console.log(pred);
```

## Detailed API reference

```ts
interface ExtraTreeProps {
    max_depth?: number;
    min_samples_split?: number;
    criterion?: 'entropy' | 'gini';
    max_features?: number;
}

constructor(props: ExtraTreeProps = {})
```

### Implementation workflow

1. Train with randomized split behavior on cleaned tabular inputs.
2. Compare validation stability against DecisionTreeClassifier.
3. Tune depth and split constraints based on overfit indicators.

### JavaScript deployment notes

- Use Extra Tree classification when you want a randomized tree baseline for tabular data.
- Compare it against the standard decision tree because the better choice depends on variance and data noise.
- It is especially useful in experiments that later feed into larger tree ensembles.