# tf.contrib.timeseries.RandomWindowInputFn

<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/contrib/timeseries/python/timeseries/input_pipeline.py#L622-L802) |

Wraps a `TimeSeriesReader` to create random batches of windows.

    tf.contrib.timeseries.RandomWindowInputFn(
        time_series_reader, window_size, batch_size, queue_capacity_multiplier=1000,
        shuffle_min_after_dequeue_multiplier=2, discard_out_of_order=True,
        discard_consecutive_batches_limit=1000, jitter=True, num_threads=2,
        shuffle_seed=None
    )

Tensors are first collected into sequential windows (in a windowing queue
created by [`tf.compat.v1.train.batch`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/train/batch), based on the order returned from
`time_series_reader`), then these windows are randomly batched (in a
`RandomShuffleQueue`), the Tensors returned by `create_batch` having shapes
prefixed by \[`batch_size`, `window_size`\].

This `TimeSeriesInputFn` is useful for both training and quantitative
evaluation (but be sure to run several epochs for sequential models such as
`StructuralEnsembleRegressor` to completely flush stale state left over from
training). For qualitative evaluation or when preparing for predictions, use
`WholeDatasetInputFn`.

<br />

<br />

<br />

| ## Args ||
|---|---|
| `time_series_reader` | A TimeSeriesReader object. |
| `window_size` | The number of examples to keep together sequentially. This controls the length of truncated backpropagation: smaller values mean less sequential computation, which can lead to faster training, but create a coarser approximation to the gradient (which would ideally be computed by a forward pass over the entire sequence in order). |
| `batch_size` | The number of windows to place together in a batch. Larger values will lead to more stable gradients during training. |
| `queue_capacity_multiplier` | The capacity for the queues used to create batches, specified as a multiple of `batch_size` (for RandomShuffleQueue) and `batch_size * window_size` (for the FIFOQueue). Controls the maximum number of windows stored. Should be greater than `shuffle_min_after_dequeue_multiplier`. |
| `shuffle_min_after_dequeue_multiplier` | The minimum number of windows in the RandomShuffleQueue after a dequeue, which controls the amount of entropy introduced during batching. Specified as a multiple of `batch_size`. |
| `discard_out_of_order` | If True, windows of data which have times which decrease (a higher time followed by a lower time) are discarded. If False, the window and associated features are instead sorted so that times are non-decreasing. Discarding is typically faster, as models do not have to deal with artificial gaps in the data. However, discarding does create a bias where the beginnings and endings of files are under-sampled. |
| `discard_consecutive_batches_limit` | Raise an OutOfRangeError if more than this number of batches are discarded without a single non-discarded window (prevents infinite looping when the dataset is too small). |
| `jitter` | If True, randomly discards examples between some windows in order to avoid deterministic chunking patterns. This is important for models like AR which may otherwise overfit a fixed chunking. |
| `num_threads` | Use this number of threads for queues. Setting a value of 1 removes one source of non-determinism (and in combination with shuffle_seed should provide deterministic windowing). |
| `shuffle_seed` | A seed for window shuffling. The default value of None provides random behavior. With `shuffle_seed` set and `num_threads=1`, provides deterministic behavior. |

<br />

## Methods

### `create_batch`

[View source](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/contrib/timeseries/python/timeseries/input_pipeline.py#L705-L802)

    create_batch()

Create queues to window and batch time series data.

<br />

<br />

<br />

| Returns ||
|---|---|
| A dictionary of Tensors corresponding to the output of `self._reader` (from the `time_series_reader` constructor argument), each with shapes prefixed by \[`batch_size`, `window_size`\]. ||

<br />

### `__call__`

[View source](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/contrib/timeseries/python/timeseries/input_pipeline.py#L573-L575)

    __call__()

Call self as a function.