Name | Version | Summary | date |
---|---|---|---|
eventdetector-ts | 1.1.0 | EventDetector introduces a universal event detection method for multivariate time series. Unlike traditional deep-learning methods, it's regression-based, requiring only reference events. The robust stacked ensemble, from Feed-Forward Neural Networks to Transformers, ensures accuracy by mitigating biases. The package supports practical implementation, excelling in detecting events with precision, validated across diverse domains. | 2023-11-28 15:31:31 |
pyloras | 0.1.0b6 | Experimental implementations of several (over/under)-sampling techniques not yet available in the imbalanced-learn library. | 2023-04-29 21:49:14 |
hour | day | week | total |
---|---|---|---|
56 | 1302 | 6217 | 276948 |