|View source on GitHub|
Creates a dataset of sliding windows over a timeseries provided as array.
tf.keras.utils.timeseries_dataset_from_array( data, targets, sequence_length, sequence_stride=1, sampling_rate=1, batch_size=128, shuffle=False, seed=None, start_index=None, end_index=None )
Used in the notebooks
|Used in the tutorials|
This function takes in a sequence of data-points gathered at equal intervals, along with time series parameters such as length of the sequences/windows, spacing between two sequence/windows, etc., to produce batches of timeseries inputs and targets.
||Numpy array or eager tensor containing consecutive data points (timesteps). Axis 0 is expected to be the time dimension.|
Targets corresponding to timesteps in
||Length of the output sequences (in number of timesteps).|
Period between successive output sequences.
Period between successive individual timesteps
within sequences. For rate
||Number of timeseries samples in each batch (except maybe the last one).|
||Whether to shuffle output samples, or instead draw them in chronological order.|
||Optional int; random seed for shuffling.|
Optional int; data points earlier (exclusive)
Optional int; data points later (exclusive) than
A tf.data.Dataset instance. If
[0, 1, ... 99].
sequence_length=10, sampling_rate=2, sequence_stride=3,
shuffle=False, the dataset will yield batches of sequences
composed of the following indices:
First sequence: [0 2 4 6 8 10 12 14 16 18] Second sequence: [3 5 7 9 11 13 15 17 19 21] Third sequence: [6 8 10 12 14 16 18 20 22 24] ... Last sequence: [78 80 82 84 86 88 90 92 94 96]
In this case the last 3 data points are discarded since no full sequence can be generated to include them (the next sequence would have started at index 81, and thus its last step would have gone over 99).
Example 2: Temporal regression.
Consider an array
data of scalar values, of shape
To generate a dataset that uses the past 10
timesteps to predict the next timestep, you would use:
input_data = data[:-10] targets = data[10:] dataset = tf.keras.preprocessing.timeseries_dataset_from_array( input_data, targets, sequence_length=10) for batch in dataset: inputs, targets = batch assert np.array_equal(inputs, data[:10]) # First sequence: steps [0-9] assert np.array_equal(targets, data) # Corresponding target: step 10 break
Example 3: Temporal regression for many-to-many architectures.
Consider two arrays of scalar values
both of shape
(100,). The resulting dataset should consist samples with
20 timestamps each. The samples should not overlap.
To generate a dataset that uses the current timestamp
to predict the corresponding target timestep, you would use:
X = np.arange(100) Y = X*2 sample_length = 20 input_dataset = tf.keras.preprocessing.timeseries_dataset_from_array( X, None, sequence_length=sample_length, sequence_stride=sample_length) target_dataset = tf.keras.preprocessing.timeseries_dataset_from_array( Y, None, sequence_length=sample_length, sequence_stride=sample_length) for batch in zip(input_dataset, target_dataset): inputs, targets = batch assert np.array_equal(inputs, X[:sample_length]) # second sample equals output timestamps 20-40 assert np.array_equal(targets, Y[sample_length:2*sample_length]) break