ImputeGAP Documentation

ImputeGAP is a comprehensive Python library for imputation of missing values in time series data. It implements user-friendly APIs to easily visualize, analyze, and repair time series datasets. The library supports a diverse range of imputation algorithms and modular missing data simulation catering to datasets with varying characteristics. ImputeGAP includes extensive customization options, such as automated hyperparameter tuning, benchmarking, explainability, and downstream evaluation.

In detail, the library provides:

  • Access to commonly used datasets in the time series imputation field (Datasets).

  • Configurable contamination module that simulates real-world missingness patterns (Patterns).

  • Parameterizable state-of-the-art time series imputation algorithms (Algorithms).

  • Extensive benchmarking to compare the performance of imputation algorithms (Benchmark).

  • Modular tools to assess the impact of imputation on key downstream tasks (Downstream).

  • Fine-grained analysis of the impact of time series features on imputation results (Explainer).

  • Seamless integration of new algorithms in Python, C++, Matlab, Java, and R (Integration).


Note

If you like our library, please add a ⭐ in our GitHub repository.


Data Format

Please ensure that your input data satisfies the following format:

Note

  • Columns are the series’ values, and rows are the timestamps

  • Column separator: empty space

  • Row separator: newline

  • Missing values are NaNs


Get Started

🚀 Installation

Read the guide on how to install ImputeGAP on your system.

📖 Tutorials

Check the tutorials to learn how to use ImputeGAP efficiently.

📦 API

Find the main API for each submodule in the index.

🧠 Algorithms

Explore the core algorithms used in ImputeGAP.


Citing

If you use ImputeGAP in your research, please cite the paper:

@article{nater2025imputegap,
  title = {ImputeGAP: A Comprehensive Library for Time Series Imputation},
  author = {Nater, Quentin and Khayati, Mourad and Pasquier, Jacques},
  year = {2025},
  eprint = {2503.15250},
  archiveprefix = {arXiv},
  primaryclass = {cs.LG},
  url = {https://arxiv.org/abs/2503.15250}
}

Contributors

Quentin Nater - ImputeGAP Mourad Khayati - ImputeGAP

Quentin Nater

Mourad Khayati