Pen Settings

CSS Base

Vendor Prefixing

Add External Stylesheets/Pens

Any URL's added here will be added as <link>s in order, and before the CSS in the editor. If you link to another Pen, it will include the CSS from that Pen. If the preprocessor matches, it will attempt to combine them before processing.

+ add another resource

You're using npm packages, so we've auto-selected Babel for you here, which we require to process imports and make it all work. If you need to use a different JavaScript preprocessor, remove the packages in the npm tab.

Add External Scripts/Pens

Any URL's added here will be added as <script>s in order, and run before the JavaScript in the editor. You can use the URL of any other Pen and it will include the JavaScript from that Pen.

+ add another resource

Use npm Packages

We can make npm packages available for you to use in your JavaScript. We use webpack to prepare them and make them available to import. We'll also process your JavaScript with Babel.

⚠️ This feature can only be used by logged in users.

Code Indentation


Save Automatically?

If active, Pens will autosave every 30 seconds after being saved once.

Auto-Updating Preview

If enabled, the preview panel updates automatically as you code. If disabled, use the "Run" button to update.

HTML Settings

Here you can Sed posuere consectetur est at lobortis. Donec ullamcorper nulla non metus auctor fringilla. Maecenas sed diam eget risus varius blandit sit amet non magna. Donec id elit non mi porta gravida at eget metus. Praesent commodo cursus magna, vel scelerisque nisl consectetur et.

              <!DOCTYPE html>
<html lang="es">  
        <title>Prueba tensorflow</title>
        <meta charset="UTF-8">
        <meta name="title" content="Prueba tensorflow">
        <!-- Cargamos TensorFlow.js -->
        <script src=""></script>
        <script src=""></script>

        <table border="0">
                    <td><input type="number" id="repeticiones" value="100"/></td>
                    <td>Valor de x</td>
                    <td><input type="number" id="nuevoValX" value="10"/></td>
                    <td> <input type="button" value="Calcular" name="calcular" id="calcular" onclick="learnLinear()" /> </td>
                    <td>Valor de Y</td>
                    <td> <span id="valy"></span> </td>
                    <td> <span id="epocas"></span> </td>
        <canvas id="myChart" width="400" height="400"></canvas>
            // Definimos los parametros en x y en y
            var valX = [1  , 2  , 3 , 4 , 5  , 6];
            var valY = [100, 110, 90, 80, 150, 130];
            var datosGrafica=deArrayAMatriz(valX, valY);
            // Inicializamos la Grafica
            var grafica = new Chart(document.getElementById("myChart"), {
                type: 'scatter',
                data: {
                    datasets: [{
                            label: "Ventas",
                            data: datosGrafica,
                            borderColor: "red",
                options: {
                    responsive: false

            //Creamos una funcion asincrona (para que se active hasta que termine de cargar la pagina)
            async function learnLinear() {

                //Definimos el modelo que sera de regresion lineal
                const model = tf.sequential();
                //Agregamos una capa densa porque todos los nodos estan conectado entre si
                model.add(tf.layers.dense({units: 1, inputShape: [1]}));

                // Compilamos el modelo con un sistema de perdida de cuadratico y optimizamos con sdg
                model.compile({loss: 'meanSquaredError', optimizer: 'sgd'});
                // Creamos los tensores para x y para y
                const xs = tf.tensor2d(valX, [6, 1]);
                const ys = tf.tensor2d(valY, [6, 1]);

                // Obtenemos la epocas (Las veces que se repetira para encontrar el valor de x)
                var epocas = +document.getElementById("repeticiones").value;
                // Obtenemos el valor de x
                var nuevoValX = +document.getElementById("nuevoValX").value;
                // Ciclo que va ir ajustando el calculo
                for (i = 0; i < epocas; i++) {
                    // Entrenamos el modelo una sola vez (pero como esta dentro de un ciclo se va ir entrenando por cada bucle)
                    await, ys, {epochs: 1});
                    // Obtenemos el valor de Y cuando el valor de x sea
                    var prediccionY = model.predict(tf.tensor2d([nuevoValX], [1, 1])).dataSync()[0];
                    // Escribimos el valor de y
                    document.getElementById("valy").innerText = prediccionY;
                    // Escribimos en que epoca vamos
                    document.getElementById("epocas").innerText = i+1;
                    // Redibujamos la grafica con el nuevo valor de X y Y
          [0].data = datosGrafica;

            function deArrayAMatriz(arx, ary) {
                var data = [];
                for (i = 0; i < arx.length; i++) {
                    data.push({x: arx[i], y: ary[i]});
                return data;

🕑 One or more of the npm packages you are using needs to be built. You're the first person to ever need it! We're building it right now and your preview will start updating again when it's ready.