Skip to content

↑ 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 size and s is the sequence length) are directly mapped to a b x s x 1 tensor and then passed to the different sequential encoders.

The encoder parameters specified at the feature level are:

  • tied (default null): name of another input feature to tie the weights of the encoder with. It needs to be the name of a feature of the same type and with the same encoder parameters.

Example category feature entry in the input features list:

name: timeseries_column_name
type: timeseries
tied: null
    type: parallel_cnn

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.