Skip to content

CESNET TSZoo

This is documentation of the CESNET TSZoo project.

The goal of cesnet-tszoo project is to provide time series datasets with useful tools for preprocessing and reproducibility. Such as:

  • API for downloading, configuring and loading CESNET-TimeSeries24, CESNET-AGG23 datasets. Each with various sources and aggregations. Check dataset overview page for details about datasets.
  • Example of configuration options:
    • Data can be split into train/val/test sets. Split can be done by time series, check SeriesBasedCesnetDataset, by time periods, check TimeBasedCesnetDataset, or by both, check DisjointTimeBasedCesnetDataset.
    • Transforming of data with built-in transformers or with custom transformers. Check transformers for details.
    • Handling missing values built-in fillers or with custom fillers. Check fillers for details.
    • Handling anomalies with built-in anomaly handlers or with custom anomaly handlers. Check anomaly handlers for details.
    • Applying custom handlers. Check custom handlers for details.
    • Changing order of when are preprocesses applied/fitted
  • Creation and import of benchmarks, for easy reproducibility of experiments.
  • Creation and import of annotations. Can create annotations for specific time series, specific time or specific time in specific time series.