Class for obtaining mini-batch iterators of sliding windows. Each mini-batch will have `batch_size` windows. If the final batch contain

Class for constructing Donut model. This class provides :meth:`get_training_loss` for deriving the training loss :class:`tf.Tensor`, and

Donut trainer. Args: model (Donut): The :class:`Donut` model instance. model_vs (str or tf.VariableScope): If specified, wil

Base class for data augmentation in training. Args: mean (float): Mean of the training data. std (float): Standard deviation

Donut predictor. Args: model (Donut): The :class:`Donut` model instance. n_z (int or None): Number of `z` samples to take fo

Data augmentation by injecting missing points into training data. Args: mean (float): Mean of the training data. std (float)

Tests for :class:`DonutPredictor`. It is very difficult to check the outputs of a :class:`DonutPredictor`, since it involves random samp

Tests for :class:`DonutTrainer`. It is very difficult to test a :class:`DonutTrainer`. We just check whether or not the :class:`DonutTra