# Numerical

Numerical columns contain numbers. The defining aspect of numerical data is that **the numbers have an order and you can apply a variety of mathematical computations** to them (average, sum, etc.) The actual values may follow a specific format, such as being rounded to 2 decimal digits and remaining between min/max bounds.

![For example, you might be storing product purchase amounts (USD) with 2 decimal digits. You might be storing the ages of your customers as whole numbers that must be 18 or above. ](https://2225246359-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FVGX92M819eIp0rMg5elc%2Fuploads%2FPqDwBxow69Bl96McNfw2%2Frdt_transformers-glossary-numerical_June%2002%202025.png?alt=media\&token=861dbc57-5fb6-4291-a546-703974417b46)

{% hint style="warning" %}
If the data is stored as integers, it does not mean it's necessarily numerical. For example, HTTP response codes such as `200`, `404`, etc. are stored as integers but they are distinct categories. They cannot be combined or averaged.
{% endhint %}

## General Numerical Transformers

These transformers can format, analyze, and reshape your numerical data into simpler shapes for data science.

<table data-view="cards"><thead><tr><th></th><th></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><a href="numerical/floatformatter"><strong>FloatFormatter</strong></a></td><td>A general transformer that imputes missing values.</td><td><a href="numerical/floatformatter">floatformatter</a></td></tr><tr><td><a href="numerical/clusterbasednormalizer"><strong>ClusterBasedNormalizer</strong></a></td><td>Use Gaussian Mixture Models to cluster and normalize the data.</td><td></td></tr><tr><td><a href="numerical/gaussiannormalizer"><strong>GaussianNormalizer</strong></a></td><td>Use a probability integral transform to normalize the data. Choose from several distributions.</td><td></td></tr><tr><td>＊<a href="numerical/outlierencoder"><strong>OutlierEncoder</strong></a></td><td>Detect and encode outliers for more accurate data science.</td><td><a href="numerical/outlierencoder">outlierencoder</a></td></tr><tr><td>❖  <a href="numerical/xgaussiannormalizer"><strong>XGaussianNormalizer</strong></a></td><td>Use a probability integral transform to normalize data. Choose from 100s of distributions.</td><td><a href="numerical/xgaussiannormalizer">xgaussiannormalizer</a></td></tr><tr><td>❖ <a href="numerical/ecdfnormalizer"><strong>ECDFNormalizer</strong></a></td><td>Normalize the data directly instead of using a predefined shape.</td><td><a href="numerical/ecdfnormalizer">ecdfnormalizer</a></td></tr></tbody></table>

{% hint style="info" %}
**＊SDV Enterprise Feature.** This feature is available to our licensed users and is not currently in our public library. For more information, visit our page to [Explore SDV](https://docs.sdv.dev/sdv/explore/sdv-enterprise/compare-features).
{% endhint %}

{% hint style="info" %}
❖ **SDV Enterprise bundle.** This feature is available for purchase as an SDV Enterprise bundle. For more information, visit our page to [Explore SDV](https://docs.sdv.dev/sdv/reference/explore-sdv).
{% endhint %}

## Differential Privacy Transformers

These transformers use differential privacy techniques to add noise or reshape your column of numerical data. As a result, your column — and any statistics about it — can be shared with differential privacy guarantees.

<table data-view="cards"><thead><tr><th></th><th></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td>❖ <a href="numerical/dpecdfnormalizer"><strong>DPECDFNormalizer</strong></a></td><td>Normalize the data by computing CDF function and adding noise.</td><td><a href="numerical/dpecdfnormalizer">dpecdfnormalizer</a></td></tr><tr><td>❖ <a href="numerical/dplaplacenoiser"><strong>DPLaplaceNoiser</strong></a></td><td>Privatize the data by adding Laplacian noise</td><td><a href="numerical/dplaplacenoiser">dplaplacenoiser</a></td></tr></tbody></table>

{% hint style="info" %}
❖ **SDV Enterprise Bundle**. This feature is available as part of the **Differential Privacy Bundle**, an optional add-on to SDV Enterprise. For more information, please visit the [Differential Privacy Bundle](https://docs.sdv.dev/sdv/reference/explore-sdv/differential-privacy-bundle) page. *Coming soon!*
{% endhint %}