↑ Time Series Features
Time Series Features Preprocessing¶
Timeseries features are handled as sequence features, with the only difference being that the matrix in the HDF5 preprocessing file uses floats instead of integers.
Since data is continuous, the JSON file, which typically stores vocabulary mappings, isn't needed.
Time Series Input Features and Encoders¶
Time series encoders are the same as for Sequence Features, with one exception:
Time series features don't have an embedding layer at the beginning, so the
b x s placeholders (where
b is the batch
s is the sequence length) are directly mapped to a
b x s x 1 tensor and then passed to the different
Time Series Output Features and Decoders¶
There are no time series decoders at the moment.
If this would unlock an interesting use case for your application, please file a GitHub Issue or ping the Ludwig Slack.