{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import tensorflow as tf\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(\"GPU disponible:\", tf.config.list_physical_devices('GPU'))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "N = 10000  # muestras\n",
    "T = 30     # pasos de tiempo\n",
    "F = 10     # features\n",
    "\n",
    "X = np.random.rand(N, T, F)\n",
    "y = np.random.rand(N, 1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from tensorflow.keras.models import Sequential\n",
    "from tensorflow.keras.layers import LSTM, Dense\n",
    "\n",
    "model = Sequential([\n",
    "    LSTM(64, input_shape=(T, F)),\n",
    "    Dense(1)\n",
    "])\n",
    "\n",
    "model.compile(optimizer='adam', loss='mse')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "history = model.fit(X, y, epochs=5, batch_size=64)\n",
    "\n",
    "# 6. Graficar pérdida\n",
    "plt.plot(history.history['loss'])\n",
    "plt.title('Pérdida de entrenamiento')\n",
    "plt.xlabel('Época')\n",
    "plt.ylabel('Loss')\n",
    "plt.grid(True)\n",
    "plt.show()\n"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "name": "python",
   "version": "3.11.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}