flaviagiammarino/brits-tensorflow

TensorFlow implementation of BRITS model for multivariate time series imputation with bidirectional recurrent neural networks.

32
/ 100
Emerging

This tool helps data scientists and machine learning engineers prepare multivariate time series data for analysis by filling in gaps. It takes your raw time series, which might have missing observations, and outputs a complete time series where those gaps are intelligently estimated. This is useful for anyone working with sensor data, financial logs, or any sequential measurements where some data points might be absent.

No commits in the last 6 months.

Use this if you have time series data with multiple related variables where some data points are missing, and you need a robust way to estimate those missing values.

Not ideal if you are working with single time series, or if your data gaps are very long and frequent, as the model's ability to accurately infer missing information will be limited.

time-series-analysis data-preprocessing predictive-maintenance financial-modeling sensor-data-analysis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

13

Forks

2

Language

Python

License

MIT

Last pushed

Apr 15, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/flaviagiammarino/brits-tensorflow"

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