Welcome to niacin’s documentation!

A Python library for replacing the missing variation in your data.

Why should I use niacin?

Data collected for model training necessarily undersamples the likely variance in the input space. This library is a collection of tools for inserting typical kinds of perturbations to better approximate population variance; and, for creating similar-but-incorrect examples to aid in reducing the total size of the hypothesis space. These are commonly known as ENRICHMENT and NEGATIVE SAMPLING, respectively.

Currently, niacin supports augmentation strategies for English language text and timeseries data.

Are you using niacin with PyTorch’s data loaders? See using niacin with pytorch loaders.

• Quickstart
  • How do I install this?
  • How can I install the optional dependencies?
  • How do I use this?
• niacin user guide
  • timeseries usage
    • Time
    • Frequency
  • english text usage
    • Enrichment
    • Negative Sampling
    • Adversarial Inputs
  • using RandAugment with niacin
    • Usage
    • With PyTorch Datasets
  • using niacin with pytorch loaders
    • Available dataset classes
    • Usage
• niacin package
  • Subpackages
    • niacin.augment package
    • niacin.text package
    • niacin.timeseries package
  • Module contents

Indices and tables

• Index
• Module Index
• Search Page