Timeseries to Tensor

Synopsis

This Operator converts time-series like data from a Collection of ExampleSets into a Tensor object for Deep Learning purposes.

Description

This Operator expects a Collection of ExampleSets containing time-series like data. Each ExampleSet is treated as one Example, while each row of a given ExampleSet is seen as a time-step, of a given Attribute given as a column. The number, naming and type of columns has to be the same across all provided ExampleSets, while the number of rows (and hence time-steps) can differ.

After converting time-series like data to a Tensor object, use the "Deep Learning (Tensor)" Operator to train a Deep Learning model on it and the "Apply Model (Generic)" Operator for application.

Input

Collection

A collection of ExampleSets containing time-series like data. A single ExampleSet is treated as one Example in the tensor, while each row of an ExampleSet is seen as a time-step with columns representing the given Attributes. Make sure that all ExampleSets have the same Attribute structure, the number of time-steps (rows) can differ.

Output

Tensor

A Tensor object suitable for the use with the "Deep Learning (Tensor)"- and the "Apply Model (Generic)"-Operators.