IvanBongiorni/GAN-RNN_Timeseries-imputation

Recurrent GAN for imputation of time series data. Implemented in TensorFlow 2 on Wikipedia Web Traffic Forecast dataset from Kaggle.

44
/ 100
Emerging

This project helps data scientists fill in missing values within time-series datasets, ensuring a complete and accurate foundation for analysis or forecasting. It takes your raw time-series data with gaps and outputs a cleaned version where those gaps have been intelligently estimated and filled. Data scientists working with sequential data, such as sensor readings, financial logs, or website traffic, would use this tool.

174 stars. No commits in the last 6 months.

Use this if you need to reliably impute missing data points in your time series, especially when traditional methods fall short or you're dealing with complex patterns.

Not ideal if your dataset is not time-series based or if you only have a few isolated missing values that can be handled with simpler statistical methods.

time-series-analysis data-cleaning predictive-modeling data-forecasting
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

174

Forks

27

Language

Jupyter Notebook

License

MIT

Last pushed

Oct 29, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/IvanBongiorni/GAN-RNN_Timeseries-imputation"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.