View source on GitHub

Supports passing a full time series to a model for evaluation/inference.

Note that this TimeSeriesInputFn is not designed for high throughput, and should not be used for training. It allows for sequential evaluation on a full dataset (with sequential in-sample predictions), which then feeds naturally into predict_continuation_input_fn for making out-of-sample predictions. While this is useful for plotting and interactive use, RandomWindowInputFn is better suited to training and quantitative evaluation.

time_series_reader A TimeSeriesReader object.



View source

A suitable input_fn for an Estimator's evaluate().

A dictionary mapping feature names to Tensors, each shape prefixed by 1, data set size.


View source

Call self as a function.