---
metadata:
  - name: generator
    content: Diplodoc Platform v5.52.0
alternate:
  - https://catboost.ai/docs/en/concepts/python-reference_datasets_epsilon.md
  - href: en/concepts/python-reference_datasets_epsilon.md
    type: text/markdown
    title: Markdown version
  - href: ../llms.txt
    type: text/markdown
    title: llms.txt
---
> **Documentation Index:** Fetch the complete configuration index at https://catboost.ai/docs/en/llms.txt

# epsilon

<!-- source: en/_includes/work_src/reusage-python/datasets__epsilon.md -->
Load the [Epsilon dataset](https://www.csie.ntu.edu.tw/~cjlin/libsvmtools/datasets/binary.html#epsilon).
<!-- endsource: en/_includes/work_src/reusage-python/datasets__epsilon.md -->


This dataset is best suited for binary classification.

The training dataset contains 400000 objects. Each object is described by 2001 columns. The first column contains the label value, all other columns contain numerical features.

The validation dataset contains 100000 objects. The structure is identical to the training dataset.

## Method call format {#method-call}

```python
epsilon()
```

## Type of return value {#type-of-return-value}

<!-- source: en/_includes/work_src/reusage-python/datasets__output.md -->
A two pandas.DataFrame tuple (for train and validation datasets).
<!-- endsource: en/_includes/work_src/reusage-python/datasets__output.md -->


## Usage examples {#usage-examples}

```python
from catboost.datasets import epsilon
epsilon_train, epsilon_test = epsilon()
```