Timeseries data loading

<!DOCTYPE html> <html lang="en"> <head> <meta charset="utf-8"> <meta name="viewport" content="width=device-width, initial-scale=1"> <meta name="description" content="Keras documentation"> <meta name="author" content="Keras Team"> <link rel="shortcut icon" href="https://keras.io/img/favicon.ico"> <link rel="canonical" href="https://keras.io/api/data_loading/timeseries/" />  <meta property="og:title" content="Keras documentation: Timeseries data loading"> <meta property="og:image" content="https://keras.io/img/logo-k-keras-wb.png"> <meta name="twitter:title" content="Keras documentation: Timeseries data loading"> <meta name="twitter:image" content="https://keras.io/img/k-keras-social.png"> <meta name="twitter:card" content="summary"> <title>Timeseries data loading</title>  <link href="/css/bootstrap.min.css" rel="stylesheet">  <link href="https://fonts.googleapis.com/css2?family=Open+Sans:wght@400;600;700;800&display=swap" rel="stylesheet">  <link href="/css/docs.css" rel="stylesheet"> <link href="/css/monokai.css" rel="stylesheet">  <script>(function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start': new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0], j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src= 'https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f); })(window,document,'script','dataLayer','GTM-5DNGF4N'); </script> <script> (function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){ (i[r].q=i[r].q||[]).push(arguments)},i[r].l=1*new Date();a=s.createElement(o), m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m) })(window,document,'script','https://www.google-analytics.com/analytics.js','ga'); ga('create', 'UA-175165319-128', 'auto'); ga('send', 'pageview'); </script>  <script async defer src="https://buttons.github.io/buttons.js"></script> </head> <body>  <noscript><iframe src="https://www.googletagmanager.com/ns.html?id=GTM-5DNGF4N" height="0" width="0" style="display:none;visibility:hidden"></iframe></noscript>  <div class='k-page'> <div class="k-nav" id="nav-menu"> <a href='/'><img src='/img/logo-small.png' class='logo-small' /></a> <div class="nav flex-column nav-pills" role="tablist" aria-orientation="vertical"> <a class="nav-link" href="/about/" role="tab" aria-selected="">About Keras</a> <a class="nav-link" href="/getting_started/" role="tab" aria-selected="">Getting started</a> <a class="nav-link" href="/guides/" role="tab" aria-selected="">Developer guides</a> <a class="nav-link" href="/examples/" role="tab" aria-selected="">Code examples</a> <a class="nav-link active" href="/api/" role="tab" aria-selected="">Keras 3 API documentation</a> <a class="nav-sublink" href="/api/models/">Models API</a> <a class="nav-sublink" href="/api/layers/">Layers API</a> <a class="nav-sublink" href="/api/callbacks/">Callbacks API</a> <a class="nav-sublink" href="/api/ops/">Ops API</a> <a class="nav-sublink" href="/api/optimizers/">Optimizers</a> <a class="nav-sublink" href="/api/metrics/">Metrics</a> <a class="nav-sublink" href="/api/losses/">Losses</a> <a class="nav-sublink active" href="/api/data_loading/">Data loading</a> <a class="nav-sublink2" href="/api/data_loading/image/">Image data loading</a> <a class="nav-sublink2 active" href="/api/data_loading/timeseries/">Timeseries data loading</a> <a class="nav-sublink2" href="/api/data_loading/text/">Text data loading</a> <a class="nav-sublink2" href="/api/data_loading/audio/">Audio data loading</a> <a class="nav-sublink" href="/api/datasets/">Built-in small datasets</a> <a class="nav-sublink" href="/api/applications/">Keras Applications</a> <a class="nav-sublink" href="/api/mixed_precision/">Mixed precision</a> <a class="nav-sublink" href="/api/distribution/">Multi-device distribution</a> <a class="nav-sublink" href="/api/random/">RNG API</a> <a class="nav-sublink" href="/api/utils/">Utilities</a> <a class="nav-link" href="/2.18/api/" role="tab" aria-selected="">Keras 2 API documentation</a> <a class="nav-link" href="/keras_tuner/" role="tab" aria-selected="">KerasTuner: Hyperparam Tuning</a> <a class="nav-link" href="/keras_hub/" role="tab" aria-selected="">KerasHub: Pretrained Models</a> </div> </div> <div class='k-main'> <div class='k-main-top'> <script> function displayDropdownMenu() { e = document.getElementById("nav-menu"); if (e.style.display == "block") { e.style.display = "none"; } else { e.style.display = "block"; document.getElementById("dropdown-nav").style.display = "block"; } } function resetMobileUI() { if (window.innerWidth <= 840) { document.getElementById("nav-menu").style.display = "none"; document.getElementById("dropdown-nav").style.display = "block"; } else { document.getElementById("nav-menu").style.display = "block"; document.getElementById("dropdown-nav").style.display = "none"; } var navmenu = document.getElementById("nav-menu"); var menuheight = navmenu.clientHeight; var kmain = document.getElementById("k-main-id"); kmain.style.minHeight = (menuheight + 100) + 'px'; } window.onresize = resetMobileUI; window.addEventListener("load", (event) => { resetMobileUI() }); </script> <div id='dropdown-nav' onclick="displayDropdownMenu();"> <svg viewBox="-20 -20 120 120" width="60" height="60"> <rect width="100" height="20"></rect> <rect y="30" width="100" height="20"></rect> <rect y="60" width="100" height="20"></rect> </svg> </div> <form class="bd-search d-flex align-items-center k-search-form" id="search-form"> <input type="search" class="k-search-input" id="search-input" placeholder="Search Keras documentation..." aria-label="Search Keras documentation..." autocomplete="off"> <button class="k-search-btn"> <svg width="13" height="13" viewBox="0 0 13 13"><title>search</title><path d="m4.8495 7.8226c0.82666 0 1.5262-0.29146 2.0985-0.87438 0.57232-0.58292 0.86378-1.2877 0.87438-2.1144 0.010599-0.82666-0.28086-1.5262-0.87438-2.0985-0.59352-0.57232-1.293-0.86378-2.0985-0.87438-0.8055-0.010599-1.5103 0.28086-2.1144 0.87438-0.60414 0.59352-0.8956 1.293-0.87438 2.0985 0.021197 0.8055 0.31266 1.5103 0.87438 2.1144 0.56172 0.60414 1.2665 0.8956 2.1144 0.87438zm4.4695 0.2115 3.681 3.6819-1.259 1.284-3.6817-3.7 0.0019784-0.69479-0.090043-0.098846c-0.87973 0.76087-1.92 1.1413-3.1207 1.1413-1.3553 0-2.5025-0.46363-3.4417-1.3909s-1.4088-2.0686-1.4088-3.4239c0-1.3553 0.4696-2.4966 1.4088-3.4239 0.9392-0.92727 2.0864-1.3969 3.4417-1.4088 1.3553-0.011889 2.4906 0.45771 3.406 1.4088 0.9154 0.95107 1.379 2.0924 1.3909 3.4239 0 1.2126-0.38043 2.2588-1.1413 3.1385l0.098834 0.090049z"></path></svg> </button> </form> <script> var form = document.getElementById('search-form'); form.onsubmit = function(e) { e.preventDefault(); var query = document.getElementById('search-input').value; window.location.href = '/search.html?query=' + query; return False } </script> </div> <div class='k-main-inner' id='k-main-id'> <div class='k-location-slug'> ► <a href='/api/'>Keras 3 API documentation</a> / <a href='/api/data_loading/'>Data loading</a> / Timeseries data loading </div> <div class='k-content'> <h1 id="timeseries-data-loading">Timeseries data loading</h1> <a href="https://github.com/keras-team/keras/tree/v3.8.0/keras/src/utils/timeseries_dataset_utils.py#L7">[source]</a> <h3 id="timeseriesdatasetfromarray-function"><code>timeseries_dataset_from_array</code> function</h3> <div class="codehilite"><pre><code>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, ) </code></pre></div> Creates a dataset of sliding windows over a timeseries provided as array. 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. Arguments <ul> <li>data: Numpy array or eager tensor containing consecutive data points (timesteps). Axis 0 is expected to be the time dimension.</li> <li>targets: Targets corresponding to timesteps in <code>data</code>. <code>targets[i]</code> should be the target corresponding to the window that starts at index <code>i</code> (see example 2 below). Pass <code>None</code> if you don't have target data (in this case the dataset will only yield the input data).</li> <li>sequence_length: Length of the output sequences (in number of timesteps).</li> <li>sequence_stride: Period between successive output sequences. For stride <code>s</code>, output samples would start at index <code>data[i]</code>, <code>data[i + s]</code>, <code>data[i + 2 * s]</code>, etc.</li> <li>sampling_rate: Period between successive individual timesteps within sequences. For rate <code>r</code>, timesteps <code>data[i], data[i + r], ... data[i + sequence_length]</code> are used for creating a sample sequence.</li> <li>batch_size: Number of timeseries samples in each batch (except maybe the last one). If <code>None</code>, the data will not be batched (the dataset will yield individual samples).</li> <li>shuffle: Whether to shuffle output samples, or instead draw them in chronological order.</li> <li>seed: Optional int; random seed for shuffling.</li> <li>start_index: Optional int; data points earlier (exclusive) than <code>start_index</code> will not be used in the output sequences. This is useful to reserve part of the data for test or validation.</li> <li>end_index: Optional int; data points later (exclusive) than <code>end_index</code> will not be used in the output sequences. This is useful to reserve part of the data for test or validation.</li> </ul> Returns A <a href="https://www.tensorflow.org/api_docs/python/tf/data/Dataset"><code>tf.data.Dataset</code></a> instance. If <code>targets</code> was passed, the dataset yields tuple <code>(batch_of_sequences, batch_of_targets)</code>. If not, the dataset yields only <code>batch_of_sequences</code>. Example 1: Consider indices <code>[0, 1, ... 98]</code>. With <code>sequence_length=10, sampling_rate=2, sequence_stride=3</code>, <code>shuffle=False</code>, the dataset will yield batches of sequences composed of the following indices: <div class="codehilite"><pre><code>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] </code></pre></div> In this case the last 2 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 98). Example 2: Temporal regression. Consider an array <code>data</code> of scalar values, of shape <code>(steps,)</code>. To generate a dataset that uses the past 10 timesteps to predict the next timestep, you would use: <div class="codehilite"><pre><code>input_data = data[:-10] targets = data[10:] dataset = timeseries_dataset_from_array( input_data, targets, sequence_length=10) for batch in dataset: inputs, targets = batch assert np.array_equal(inputs[0], data[:10]) # First sequence: steps [0-9] # Corresponding target: step 10 assert np.array_equal(targets[0], data[10]) break </code></pre></div> Example 3: Temporal regression for many-to-many architectures. Consider two arrays of scalar values <code>X</code> and <code>Y</code>, both of shape <code>(100,)</code>. 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: <div class="codehilite"><pre><code>X = np.arange(100) Y = X*2 sample_length = 20 input_dataset = timeseries_dataset_from_array( X, None, sequence_length=sample_length, sequence_stride=sample_length) target_dataset = 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[0], X[:sample_length]) # second sample equals output timestamps 20-40 assert np.array_equal(targets[1], Y[sample_length:2*sample_length]) break </code></pre></div> <hr /> <a href="https://github.com/keras-team/keras/tree/v3.8.0/keras/src/utils/sequence_utils.py#L6">[source]</a> <h3 id="padsequences-function"><code>pad_sequences</code> function</h3> <div class="codehilite"><pre><code>keras.utils.pad_sequences( sequences, maxlen=None, dtype="int32", padding="pre", truncating="pre", value=0.0 ) </code></pre></div> Pads sequences to the same length. This function transforms a list (of length <code>num_samples</code>) of sequences (lists of integers) into a 2D NumPy array of shape <code>(num_samples, num_timesteps)</code>. <code>num_timesteps</code> is either the <code>maxlen</code> argument if provided, or the length of the longest sequence in the list. Sequences that are shorter than <code>num_timesteps</code> are padded with <code>value</code> until they are <code>num_timesteps</code> long. Sequences longer than <code>num_timesteps</code> are truncated so that they fit the desired length. The position where padding or truncation happens is determined by the arguments <code>padding</code> and <code>truncating</code>, respectively. Pre-padding or removing values from the beginning of the sequence is the default. <div class="codehilite"><pre><code>>>> sequence = [[1], [2, 3], [4, 5, 6]] >>> keras.utils.pad_sequences(sequence) array([[0, 0, 1], [0, 2, 3], [4, 5, 6]], dtype=int32) </code></pre></div> <div class="codehilite"><pre><code>>>> keras.utils.pad_sequences(sequence, value=-1) array([[-1, -1, 1], [-1, 2, 3], [ 4, 5, 6]], dtype=int32) </code></pre></div> <div class="codehilite"><pre><code>>>> keras.utils.pad_sequences(sequence, padding='post') array([[1, 0, 0], [2, 3, 0], [4, 5, 6]], dtype=int32) </code></pre></div> <div class="codehilite"><pre><code>>>> keras.utils.pad_sequences(sequence, maxlen=2) array([[0, 1], [2, 3], [5, 6]], dtype=int32) </code></pre></div> Arguments <ul> <li>sequences: List of sequences (each sequence is a list of integers).</li> <li>maxlen: Optional Int, maximum length of all sequences. If not provided, sequences will be padded to the length of the longest individual sequence.</li> <li>dtype: (Optional, defaults to <code>"int32"</code>). Type of the output sequences. To pad sequences with variable length strings, you can use <code>object</code>.</li> <li>padding: String, "pre" or "post" (optional, defaults to <code>"pre"</code>): pad either before or after each sequence.</li> <li>truncating: String, "pre" or "post" (optional, defaults to <code>"pre"</code>): remove values from sequences larger than <code>maxlen</code>, either at the beginning or at the end of the sequences.</li> <li>value: Float or String, padding value. (Optional, defaults to <code>0.</code>)</li> </ul> Returns NumPy array with shape <code>(len(sequences), maxlen)</code> <hr /> </div> <div class='k-outline'> <div class='k-outline-depth-1'> <a href='#timeseries-data-loading'>Timeseries data loading</a> </div> <div class='k-outline-depth-3'> <a href='#timeseriesdatasetfromarray-function'><code>timeseries_dataset_from_array</code> function</a> </div> <div class='k-outline-depth-3'> <a href='#padsequences-function'><code>pad_sequences</code> function</a> </div> </div> </div> </div> </div> </body> <footer style="float: left; width: 100%; padding: 1em; border-top: solid 1px #bbb;"> <a href="https://policies.google.com/terms">Terms</a> | <a href="https://policies.google.com/privacy">Privacy</a> </footer> </html>

CINXE.COM

Timeseries data loading