{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Building NARX Neural Network using Sysidentpy\n",
    "\n",
    "Example created by Wilson Rocha Lacerda Junior"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Series-Parallen Training and Parallel prediction\n",
    "\n",
    "Currently *SysIdentPy* support a Series-Parallel (open-loop) Feedforward Network training\n",
    "process, which make the training process easier. We convert the NARX network from Series-Parallel to the Parallel (closed-loop) configuration for prediction. \n",
    "\n",
    "Series-Parallel allows us to use Pytorch directly for training, so we can use all the power of the Pytorch library to build our NARX Neural Network model! \n",
    "\n",
    "![](figures/narxnet.png)\n",
    "\n",
    "The reader is referred to the following paper for a more in depth discussion about Series-Parallel and Parallel configurations regarding NARX neural network:\n",
    "\n",
    "[Parallel Training Considered Harmful?: Comparing series-parallel and parallel feedforward\n",
    "network training](https://arxiv.org/pdf/1706.07119.pdf)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Building a NARX Neural Network\n",
    "\n",
    "First, just import the necessary packages"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "pip install sysidentpy"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "from torch import nn\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "from sysidentpy.metrics import mean_squared_error\n",
    "from sysidentpy.utils.generate_data import get_siso_data\n",
    "from sysidentpy.neural_network import NARXNN"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Getting the data\n",
    "\n",
    "The data is generated by simulating the following model:\n",
    "\n",
    "$y_k = 0.2y_{k-1} + 0.1y_{k-1}x_{k-1} + 0.9x_{k-1} + e_{k}$.\n",
    "\n",
    "If *colored_noise* is set to True:\n",
    "\n",
    "$e_{k} = 0.8\\nu_{k-1} + \\nu_{k}$,\n",
    "\n",
    "where $x$ is a uniformly distributed random variable and $\\nu$ is a gaussian distributed variable with $\\mu=0$ and $\\sigma=0.1$"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "x_train, x_valid, y_train, y_valid = get_siso_data(n=1000,\n",
    "                                                   colored_noise=False,\n",
    "                                                   sigma=0.01,\n",
    "                                                   train_percentage=80)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Choosing the NARX parameters, loss function and optmizer\n",
    "\n",
    "One can create a NARXNN object and choose the maximum lag of both input and output for building the regressor matrix to serve as input of the network.\n",
    "\n",
    "In addition, you can choose the loss function, the optmizer, the optinional parameters of the optmizer, the number of epochs.\n",
    "\n",
    "Because we built this feature on top of Pytorch, you can choose any of the loss function of the torch.nn.functional. [Click here](https://pytorch.org/docs/stable/nn.functional.html#loss-functions) for a list of the loss functions you can use. You just need to pass the name of the loss function you want.\n",
    "\n",
    "Similarly, you can choose any of the optimizers of the torch.optim. [Click here](https://pytorch.org/docs/stable/optim.html) for a list of optimizers available.\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\Users\\wilso\\Desktop\\projects\\GitHub\\sysidentpy\\sysidentpy\\utils\\deprecation.py:27: FutureWarning: Function __init__ has been deprecated since v0.1.7.\n",
      " Use NARXNN(ylag=2, xlag=2, basis_function='Some basis function') instead.This module was deprecated in favor of NARXNN(ylag=2, xlag=2, basis_function='Some basis function') module into which all the refactored classes and functions are moved.\n",
      " This feature will be removed in version v0.2.0.\n",
      "  warnings.warn(message, FutureWarning)\n"
     ]
    }
   ],
   "source": [
    "narx_net = NARXNN(ylag=2,\n",
    "                  xlag=2,\n",
    "                  loss_func='mse_loss',\n",
    "                  optimizer='Adam',\n",
    "                  epochs=200,\n",
    "                  verbose=True,\n",
    "                  optim_params={'betas': (0.9, 0.999), 'eps': 1e-05} # optional parameters of the optimizer\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Since we have defined our NARXNN using $ylag=2$ and $xlag=2$, we have a regressor matrix with 4 features. We need the size of the regressor matrix to build the layers of our network. Our input data(x_train) have only one feature, but since we are creating an NARX network, a regressor matrix is built behind the scenes with new features based on the xlag and ylag. \n",
    "\n",
    "You can check the size the of the regressor matrix by using the following line of code:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "4"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(narx_net.regressor_code) # the number of features of the NARX net"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Building the NARX Neural Network\n",
    "\n",
    "The configuration of your network follows exactly the same pattern of a network defined in Pytorch. The following representing our NARX neural network."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "class NARX(nn.Module):\n",
    "    def __init__(self):\n",
    "        super().__init__()\n",
    "        self.lin = nn.Linear(4, 10)\n",
    "        self.lin2 = nn.Linear(10, 10)\n",
    "        self.lin3 = nn.Linear(10, 1)\n",
    "        self.tanh = nn.Tanh()\n",
    "\n",
    "    def forward(self, xb):\n",
    "        z = self.lin(xb)\n",
    "        z = self.tanh(z)\n",
    "        z = self.lin2(z)\n",
    "        z = self.tanh(z)\n",
    "        z = self.lin3(z)\n",
    "        return z"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We have to pass the defined network to our NARXNN estimator."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "narx_net.net = NARX() "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Numpy array to Tensor\n",
    "\n",
    "If your inputs are numpy array, you can transform them to tensor using our *data_transform* method. Our function return a Dataloader object that we use to iterate on our training function. You can transform your inputs mannualy using TensorDataset and Dataloader using Pytorch.\n",
    "\n",
    "Since our inputs are numpy arrays, we transform them using the following:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "train_dl = narx_net.data_transform(x_train, y_train)\n",
    "valid_dl = narx_net.data_transform(x_valid, y_valid)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Fit and Predict\n",
    "\n",
    "Because we have a fit (for training) and predict function for Polynomial NARMAX, we create the same pattern for the NARX net. So, you only have to fit and predict using the following:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "tags": [
     "outputPrepend"
    ]
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "10-14 20:48:51 - INFO - Train metrics: 0.04131108850595497 | Validation metrics: 0.04906847903674299\n",
      "10-14 20:48:51 - INFO - Train metrics: 0.028460200656588216 | Validation metrics: 0.03361141151099494\n",
      "10-14 20:48:51 - INFO - Train metrics: 0.003378246061825999 | Validation metrics: 0.0031020104381810835\n",
      "10-14 20:48:51 - INFO - Train metrics: 0.0079599755015551 | Validation metrics: 0.008645726645346543\n",
      "10-14 20:48:51 - INFO - Train metrics: 0.0030233150559307114 | Validation metrics: 0.0029042966809650563\n",
      "10-14 20:48:51 - INFO - Train metrics: 0.002685692424496127 | Validation metrics: 0.0023653891920629474\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.0024652570710146336 | Validation metrics: 0.002304245895386269\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.0019370706455506628 | Validation metrics: 0.0017436911620086794\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.0018388286208439815 | Validation metrics: 0.0016496724818334586\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.0017072744968050816 | Validation metrics: 0.0015464992053110642\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.0015803288069103185 | Validation metrics: 0.0014035090300809554\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.0014880437142493431 | Validation metrics: 0.001310714574605979\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.001387180416216901 | Validation metrics: 0.00122850411924336\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.0013052070630658278 | Validation metrics: 0.0011443916950468914\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.0012339301556722262 | Validation metrics: 0.0010780414890949473\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.001164034145527092 | Validation metrics: 0.001014245996214073\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.0011011369510047267 | Validation metrics: 0.0009561394525908235\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.0010437073418287032 | Validation metrics: 0.0009035104638755773\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.0009949564916854328 | Validation metrics: 0.0008592913750408575\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.0009528849830321109 | Validation metrics: 0.0008202916513328826\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.0009175872632692146 | Validation metrics: 0.000788286452374487\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.0008890533877856432 | Validation metrics: 0.0007620826034308082\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.0008673645819439308 | Validation metrics: 0.0007425071724521166\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.000852728709823599 | Validation metrics: 0.0007292344799321709\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.0008445927789516485 | Validation metrics: 0.0007223037954636219\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.00084247200222882 | Validation metrics: 0.0007208843075792597\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.0008448014216133414 | Validation metrics: 0.0007239887649616735\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.0008500138878878346 | Validation metrics: 0.0007298732390439119\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.0008556014552705438 | Validation metrics: 0.0007365572176911313\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.0008590475113112433 | Validation metrics: 0.0007413987039748315\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.000857649983302515 | Validation metrics: 0.0007421934684371632\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.0008491311236319685 | Validation metrics: 0.0007365068280834215\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.0008318741602489356 | Validation metrics: 0.0007230815932747315\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.000805219337910199 | Validation metrics: 0.0007010652728359958\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.0007696043299382698 | Validation metrics: 0.0006710473028237395\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.0007264798565156161 | Validation metrics: 0.0006342400288717313\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.0006782170217355858 | Validation metrics: 0.0005929736318207825\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.0006277372514686657 | Validation metrics: 0.0005499135216020725\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.000578201490128763 | Validation metrics: 0.0005080612732633723\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.0005325340616422236 | Validation metrics: 0.00047010904697776594\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.0004930378421166571 | Validation metrics: 0.000438175760644648\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.00046103601502943176 | Validation metrics: 0.0004134049531509818\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.0004367199414211295 | Validation metrics: 0.0003958406338980892\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.00041922304839395305 | Validation metrics: 0.0003844970188131838\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.0004069515629257204 | Validation metrics: 0.00037769779223111467\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.0003980788140251934 | Validation metrics: 0.000373578385798016\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.0003910256732216707 | Validation metrics: 0.00037057418552594203\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.0003847462772992778 | Validation metrics: 0.00036770987884150914\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.00037874157091469636 | Validation metrics: 0.00036459527068978385\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.00037287430470706636 | Validation metrics: 0.00036121022827556413\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.0003671492582693565 | Validation metrics: 0.0003576481884176081\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.00036156881249913556 | Validation metrics: 0.00035395805672225024\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.0003560989457480189 | Validation metrics: 0.0003501209600903846\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.00035071165983933944 | Validation metrics: 0.0003461223924673642\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.00034542367641900417 | Validation metrics: 0.0003420121296346564\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.00034027772209838146 | Validation metrics: 0.00033787745456775707\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.0003352946501731742 | Validation metrics: 0.000333770081833607\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.0003304667089584944 | Validation metrics: 0.00032969446608213464\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.00032579059826961734 | Validation metrics: 0.0003256509162843077\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.0003212813433784324 | Validation metrics: 0.00032166705726683514\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.00031694856922802767 | Validation metrics: 0.0003177673562378105\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.0003127835939050696 | Validation metrics: 0.0003139520157481346\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.0003087814602394586 | Validation metrics: 0.000310222348997915\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.00030494278648700144 | Validation metrics: 0.0003065886887288982\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.0003012649268615071 | Validation metrics: 0.00030305310895647667\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.00029774067429901523 | Validation metrics: 0.0002996141456697851\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.00029436565246602245 | Validation metrics: 0.00029627347424993235\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.0002911338326025213 | Validation metrics: 0.0002930317996563672\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.00028803499875342783 | Validation metrics: 0.00028988393288190394\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.0002850635615244559 | Validation metrics: 0.000286828468123338\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.00028221057859957827 | Validation metrics: 0.0002838623791702581\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.0002794661175489967 | Validation metrics: 0.0002809803611881128\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.00027682226847677507 | Validation metrics: 0.00027817885527819995\n",
      "10-14 20:48:52 - INFO - Train metrics: 0.00027426962552091485 | Validation metrics: 0.0002754517660988965\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.000271798315334582 | Validation metrics: 0.00027279472454789686\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00026939982289558086 | Validation metrics: 0.000270201724946894\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00026706552785356764 | Validation metrics: 0.00026766780303494835\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00026478664676004085 | Validation metrics: 0.0002651870322138579\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00026255594884491245 | Validation metrics: 0.00026275533985821626\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00026036634663251793 | Validation metrics: 0.00026036672278853003\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00025821148327004426 | Validation metrics: 0.00025801822549611743\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.0002560851644922426 | Validation metrics: 0.00025570412937227184\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.000253982745138123 | Validation metrics: 0.00025342212654203363\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.0002519003293426815 | Validation metrics: 0.0002511690098514799\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00024983328664272716 | Validation metrics: 0.00024894138106093224\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00024777906330478584 | Validation metrics: 0.0002467375799291532\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00024573513320390425 | Validation metrics: 0.0002445551682019023\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00024369899651069513 | Validation metrics: 0.00024239280122341682\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00024166981016232033 | Validation metrics: 0.0002402500224457301\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00023964487333790187 | Validation metrics: 0.00023812429410301976\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00023762422808846297 | Validation metrics: 0.00023601648387160492\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00023560689133912894 | Validation metrics: 0.0002339251496419875\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00023359169073071433 | Validation metrics: 0.0002318503766678123\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00023157888458706766 | Validation metrics: 0.00022979204000839304\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00022956847743058862 | Validation metrics: 0.00022775086387874315\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00022756056113163928 | Validation metrics: 0.00022572696234235973\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00022555519812851257 | Validation metrics: 0.0002237209627484771\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00022355343316848573 | Validation metrics: 0.00022173405100469186\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00022155712893317899 | Validation metrics: 0.0002197675861716929\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.0002195671117817283 | Validation metrics: 0.00021782347043468192\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00021758560476536375 | Validation metrics: 0.00021590344943553022\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00021561601945113877 | Validation metrics: 0.0002140102098399604\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00021366173793756658 | Validation metrics: 0.00021214681769241437\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00021172691536174484 | Validation metrics: 0.00021031662419607693\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00020981624746989263 | Validation metrics: 0.00020852305978122685\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00020793562246291644 | Validation metrics: 0.0002067698150487485\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00020609069866522737 | Validation metrics: 0.00020506123381883206\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00020428779219156996 | Validation metrics: 0.0002034011799924433\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.0002025324626394517 | Validation metrics: 0.00020179211651798188\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00020083148175538903 | Validation metrics: 0.00020023822097103063\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00019918997411121309 | Validation metrics: 0.00019874170950538657\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00019761347403005232 | Validation metrics: 0.00019730537197308032\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00019610731732357003 | Validation metrics: 0.00019593196221382705\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00019467859693807563 | Validation metrics: 0.00019462566015503434\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00019333537653109576 | Validation metrics: 0.00019339199993416027\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00019208929004885236 | Validation metrics: 0.00019224008752240075\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00019095592270196792 | Validation metrics: 0.00019118080216676297\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00018995357193735506 | Validation metrics: 0.00019022788690177328\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.0001891028112089985 | Validation metrics: 0.00018939580603719058\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00018842456153918402 | Validation metrics: 0.00018869916690311236\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00018793651047086852 | Validation metrics: 0.0001881494125965136\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00018764981666065164 | Validation metrics: 0.00018775241532965065\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.0001875660618178355 | Validation metrics: 0.0001875083613376406\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.0001876735459837507 | Validation metrics: 0.00018740783773616633\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00018794704445277137 | Validation metrics: 0.00018743240871852397\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00018835156428176014 | Validation metrics: 0.00018755609470635953\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00018884096404637925 | Validation metrics: 0.00018774680946153974\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00018936896723383492 | Validation metrics: 0.00018797117691708146\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00018988934397769807 | Validation metrics: 0.00018819636001482116\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00019036637114963137 | Validation metrics: 0.00018839627275633804\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00019077265467804 | Validation metrics: 0.00018855136750980912\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00019109499962290837 | Validation metrics: 0.0001886511182428968\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00019132816587238665 | Validation metrics: 0.00018869216890177794\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00019147770226504748 | Validation metrics: 0.0001886779399214764\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00019155357409102893 | Validation metrics: 0.00018861645602178995\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00019156966085036875 | Validation metrics: 0.00018851777683882363\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00019154172744613636 | Validation metrics: 0.00018839370676861943\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00019148450643425216 | Validation metrics: 0.00018825615074772464\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.0001914106682293061 | Validation metrics: 0.00018811439451493436\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00019133323894721457 | Validation metrics: 0.00018797877463371014\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00019126198387134092 | Validation metrics: 0.0001878568060658496\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00019120595677298282 | Validation metrics: 0.00018775488592148054\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.000191170370447237 | Validation metrics: 0.00018767716943385136\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.00019115919968227675 | Validation metrics: 0.00018762690417887173\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.0001911740405204937 | Validation metrics: 0.0001876046279894489\n",
      "10-14 20:48:53 - INFO - Train metrics: 0.0001912164306872055 | Validation metrics: 0.00018761166156213167\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.00019128647645880563 | Validation metrics: 0.00018764688586933782\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.00019138249079784364 | Validation metrics: 0.00018770976542998482\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.0001915014360740753 | Validation metrics: 0.00018779738501038855\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.00019164143279276527 | Validation metrics: 0.0001879076470769095\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.00019179775500973513 | Validation metrics: 0.00018803681222830118\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.00019196732311665938 | Validation metrics: 0.00018818214646836913\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.0001921473529929748 | Validation metrics: 0.000188341015900457\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.0001923350061763797 | Validation metrics: 0.00018851098359322572\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.00019252678510128405 | Validation metrics: 0.000188689264545283\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.00019272048228956003 | Validation metrics: 0.0001888738867516319\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.00019291485586836186 | Validation metrics: 0.00018906335724456556\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.00019310691937620992 | Validation metrics: 0.00018925534095615149\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.0001932962638641682 | Validation metrics: 0.00018944878221108493\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.00019348263895905863 | Validation metrics: 0.0001896435922279841\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.0001936646764526111 | Validation metrics: 0.00018983859053784698\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.0001938426132237464 | Validation metrics: 0.0001900335359316545\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.0001940166648523415 | Validation metrics: 0.0001902282593720075\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.00019418697554459397 | Validation metrics: 0.00019042269853555193\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.0001943536764136247 | Validation metrics: 0.00019061647801227265\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.0001945166474334863 | Validation metrics: 0.00019080918490994872\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.00019467664621554474 | Validation metrics: 0.00019100128488986744\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.00019483347800484436 | Validation metrics: 0.0001911921157663914\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.00019498736173659097 | Validation metrics: 0.00019138162168368434\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.00019513892474786184 | Validation metrics: 0.00019157000651554853\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.0001952891890645228 | Validation metrics: 0.00019175704272294587\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.0001954367701393111 | Validation metrics: 0.00019194193538913333\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.0001955836751518122 | Validation metrics: 0.0001921254490041221\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.000195729663320712 | Validation metrics: 0.0001923078607892467\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.00019587413757983456 | Validation metrics: 0.0001924875013899491\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.00019601683387938972 | Validation metrics: 0.00019266448913240862\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.00019615714257071844 | Validation metrics: 0.00019283766691888108\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.00019629587053746116 | Validation metrics: 0.00019300719496742304\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.00019643246294681992 | Validation metrics: 0.00019317320306935922\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.00019656654031839884 | Validation metrics: 0.00019333419090753064\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.00019669870715845086 | Validation metrics: 0.00019349076466474945\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.00019682804640454887 | Validation metrics: 0.00019364244148201037\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.00019695512518020614 | Validation metrics: 0.00019378923370639295\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.00019707915746317454 | Validation metrics: 0.00019393008139991023\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.00019720067317658256 | Validation metrics: 0.00019406545786727973\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.00019731925779143653 | Validation metrics: 0.0001941950563423693\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.00019743469339371763 | Validation metrics: 0.00019431903057571764\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.00019754638185959198 | Validation metrics: 0.00019443675601088227\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.00019765476766071588 | Validation metrics: 0.00019454812328801538\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.00019775922043292193 | Validation metrics: 0.0001946530058495512\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.00019786054290216044 | Validation metrics: 0.00019475173383287972\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.00019795821853014722 | Validation metrics: 0.00019484443585341326\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.00019805156964987263 | Validation metrics: 0.00019493055379375665\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.0001981408930620538 | Validation metrics: 0.00019501017878711637\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.00019822696209704284 | Validation metrics: 0.00019508422495834906\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.00019830909037126933 | Validation metrics: 0.00019515213639489517\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.0001983861180715599 | Validation metrics: 0.0001952140149601613\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.00019845934582548566 | Validation metrics: 0.00019526948274531863\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.00019852842508002948 | Validation metrics: 0.00019531981532127981\n",
      "10-14 20:48:54 - INFO - Train metrics: 0.00019859355358076622 | Validation metrics: 0.00019536461581762956\n"
     ]
    }
   ],
   "source": [
    "narx_net.fit(train_dl, valid_dl)\n",
    "yhat = narx_net.predict(x_valid, y_valid)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.00020776957378755621\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\Users\\wilso\\Desktop\\projects\\GitHub\\sysidentpy\\sysidentpy\\utils\\deprecation.py:27: FutureWarning: Function residuals has been deprecated since v0.1.7.\n",
      " Use from sysidentpy.residues_correlation import compute_cross_correlation, compute_residues_autocorrelation instead.This module was deprecated in favor of from sysidentpy.residues_correlation import compute_cross_correlation, compute_residues_autocorrelation module into which all the refactored classes and functions are moved.\n",
      " This feature will be removed in version v0.2.0.\n",
      "  warnings.warn(message, FutureWarning)\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 720x576 with 3 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "print(mean_squared_error(y_valid, yhat))\n",
    "\n",
    "ee, ex, extras, lam = narx_net.residuals(x_valid, y_valid, yhat)\n",
    "narx_net.plot_result(y_valid, yhat, ee, ex)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Note\n",
    "\n",
    "If you built the net configuration before calling the NARXNN, you can just pass the model to the NARXNN as follows:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "tags": [
     "outputPrepend"
    ]
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "10-14 20:49:00 - INFO - Train metrics: 0.13531316816806793 | Validation metrics: 0.13191769166727257\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.018423788828359808 | Validation metrics: 0.02039402553981001\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.017191101547171895 | Validation metrics: 0.018505071637907412\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.004398609300314409 | Validation metrics: 0.004448795477116499\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.005147629867968404 | Validation metrics: 0.0053938134347624855\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.0015457770559600646 | Validation metrics: 0.0018605957868405515\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.00198836172761671 | Validation metrics: 0.0024948635049201924\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.0012973400054879971 | Validation metrics: 0.001802109771013034\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.0012088184395774657 | Validation metrics: 0.0014578327865838402\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.0011429692711039238 | Validation metrics: 0.0013947886475973359\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.0010430012830477068 | Validation metrics: 0.0013793609410787772\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.0009956922944352722 | Validation metrics: 0.0012592470239274054\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.0009594122970530432 | Validation metrics: 0.0011785748235956586\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\Users\\wilso\\Desktop\\projects\\GitHub\\sysidentpy\\sysidentpy\\utils\\deprecation.py:27: FutureWarning: Function __init__ has been deprecated since v0.1.7.\n",
      " Use NARXNN(ylag=2, xlag=2, basis_function='Some basis function') instead.This module was deprecated in favor of NARXNN(ylag=2, xlag=2, basis_function='Some basis function') module into which all the refactored classes and functions are moved.\n",
      " This feature will be removed in version v0.2.0.\n",
      "  warnings.warn(message, FutureWarning)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "10-14 20:49:00 - INFO - Train metrics: 0.0009113025726379364 | Validation metrics: 0.001130729026485686\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.0008734577102878395 | Validation metrics: 0.0010684542469633273\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.0008441428745802688 | Validation metrics: 0.0010228202410155172\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.0008112886174521257 | Validation metrics: 0.0009746597615315231\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.0007797167214849745 | Validation metrics: 0.0009258962189308321\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.0007527490781928252 | Validation metrics: 0.0008886476309565508\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.0007271181716452958 | Validation metrics: 0.0008498650312310818\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.000702367844596916 | Validation metrics: 0.0008135927162565893\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.0006788028630236617 | Validation metrics: 0.0007808110018194925\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.0006567008202816161 | Validation metrics: 0.0007491584689676235\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.0006362167744311437 | Validation metrics: 0.000720306477777547\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.0006169979408019243 | Validation metrics: 0.0006932156255134767\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.0005989898568635484 | Validation metrics: 0.0006680542522585113\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.0005822524024706969 | Validation metrics: 0.0006446120005237371\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.0005668453403333095 | Validation metrics: 0.000622952548314281\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.0005528424292590404 | Validation metrics: 0.0006031149097558375\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.0005402695637063257 | Validation metrics: 0.0005849934106038864\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.0005291596922018614 | Validation metrics: 0.0005686509656964453\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.0005195055061100485 | Validation metrics: 0.0005540039482634665\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.0005112541277098112 | Validation metrics: 0.0005410077791740986\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.0005042796164843251 | Validation metrics: 0.0005295233009618265\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.0004983296430258916 | Validation metrics: 0.0005193327908107841\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.0004930145685347428 | Validation metrics: 0.0005100852876873405\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.0004877685314659403 | Validation metrics: 0.0005012895800808275\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.0004818696145144499 | Validation metrics: 0.0004923125353260813\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.0004745072722090712 | Validation metrics: 0.00048244652024357384\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.0004649095228210297 | Validation metrics: 0.000471018614292126\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.00045252913804047913 | Validation metrics: 0.0004575622951226177\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.0004372503008882522 | Validation metrics: 0.0004420039050558563\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.0004195359246373494 | Validation metrics: 0.0004247950111878001\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.00040044133394739515 | Validation metrics: 0.0004069155292006943\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.0003814170152219689 | Validation metrics: 0.00038967920952909295\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.0003639527933962671 | Validation metrics: 0.00037438559788044055\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.00034914312363114384 | Validation metrics: 0.00036190650743347675\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.00033738851621058447 | Validation metrics: 0.00035241308164632305\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.00032837413071087543 | Validation metrics: 0.0003453836067241024\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.0003213310142439839 | Validation metrics: 0.0003398962183961306\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.0003154298106358996 | Validation metrics: 0.00033504968612558313\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.00031007275135282023 | Validation metrics: 0.00033026573164717795\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.00030496460976450236 | Validation metrics: 0.00032534777284411696\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.00030001814681091313 | Validation metrics: 0.0003203442592157352\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.00029522858942738665 | Validation metrics: 0.0003153746137736516\n",
      "10-14 20:49:00 - INFO - Train metrics: 0.00029060119909775866 | Validation metrics: 0.00031051764513408256\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.0002861265971308999 | Validation metrics: 0.00030578593394220476\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.0002817844275127219 | Validation metrics: 0.00030115208893689805\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.00027755779134842537 | Validation metrics: 0.0002965971988019054\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.00027344449600356544 | Validation metrics: 0.00029212680972778626\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.0002694469766445075 | Validation metrics: 0.00028775509748480874\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.00026556262271601314 | Validation metrics: 0.0002834851107727078\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.00026178397083617656 | Validation metrics: 0.00027930413386337646\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.000258103554304234 | Validation metrics: 0.0002752069345348505\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.00025451991570393383 | Validation metrics: 0.00027119803225922616\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.0002510322725142406 | Validation metrics: 0.00026728187962858516\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.0002476362266649555 | Validation metrics: 0.00026345500343883727\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.00024432840670708726 | Validation metrics: 0.0002597147749379428\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.00024110634246214357 | Validation metrics: 0.0002560617296069842\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.0002379676141909774 | Validation metrics: 0.0002524960151699494\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.00023490984176191033 | Validation metrics: 0.0002490135800208652\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.00023192963694930682 | Validation metrics: 0.0002456133803905392\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.0002290257920536159 | Validation metrics: 0.0002422944462982787\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.000226195404970701 | Validation metrics: 0.0002390547362132694\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.00022343660488591662 | Validation metrics: 0.00023589221345533552\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.00022074739833276036 | Validation metrics: 0.00023280597345390818\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.00021812597956078915 | Validation metrics: 0.00022979383856631965\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.00021557028792398213 | Validation metrics: 0.000226853788869145\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.0002130789485034115 | Validation metrics: 0.00022398560505473253\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.00021064965994468422 | Validation metrics: 0.00022118560710540888\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.000208281600411064 | Validation metrics: 0.00021845398654789672\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.0002059724548350749 | Validation metrics: 0.00021578702838113062\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.00020372163745654013 | Validation metrics: 0.00021318578798643718\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.00020152692299950074 | Validation metrics: 0.00021064683728536234\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.00019938740829696742 | Validation metrics: 0.0002081689621484133\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.00019730181970988356 | Validation metrics: 0.00020575144909077672\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.00019526854062623306 | Validation metrics: 0.0002033919828880409\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.0001932873265446633 | Validation metrics: 0.00020109061131164468\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.0001913557497753568 | Validation metrics: 0.0001988438219114235\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.00018947383643152485 | Validation metrics: 0.0001966522840754778\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.00018763999214844036 | Validation metrics: 0.0001945141059078389\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.0001858533775103617 | Validation metrics: 0.00019242803829562182\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.0001841125391493143 | Validation metrics: 0.0001903925437334398\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.0001824171626855757 | Validation metrics: 0.0001884072147676665\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.00018076664036697707 | Validation metrics: 0.00018647131042653751\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.00017915849442906527 | Validation metrics: 0.00018458206246541153\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.0001775935217624362 | Validation metrics: 0.0001827390685752787\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.00017607014744138732 | Validation metrics: 0.00018094385773616118\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.00017458741570779713 | Validation metrics: 0.0001791905302488518\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.0001731454397675425 | Validation metrics: 0.0001774838467944658\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.00017174205153113823 | Validation metrics: 0.00017581785225892683\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.00017037789441935746 | Validation metrics: 0.00017419536089444666\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.00016905081117459173 | Validation metrics: 0.0001726130667704656\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.00016776170208262405 | Validation metrics: 0.00017107188445280748\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.0001665085400871928 | Validation metrics: 0.0001695697502153126\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.00016529148952646838 | Validation metrics: 0.0001681064810566228\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.00016410937720243317 | Validation metrics: 0.00016668173552119182\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.00016296157851333222 | Validation metrics: 0.0001652933925571334\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.0001618480322608855 | Validation metrics: 0.00016394231410819397\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.00016076781966853048 | Validation metrics: 0.0001626272738447902\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.00015971983085184553 | Validation metrics: 0.00016134710188113116\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.00015870413510566506 | Validation metrics: 0.00016010143103858813\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.00015772021063988593 | Validation metrics: 0.00015889019252628915\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.0001567669327628745 | Validation metrics: 0.00015771198818445995\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.00015584403935780183 | Validation metrics: 0.00015656636837361887\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.0001549512335510089 | Validation metrics: 0.0001554533203057192\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.0001540877720277481 | Validation metrics: 0.00015437208581127866\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.00015325311695069149 | Validation metrics: 0.00015332156585322486\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.00015244697760977317 | Validation metrics: 0.00015230141780009926\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.00015166879410273104 | Validation metrics: 0.00015131170147644223\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.0001509183712369578 | Validation metrics: 0.00015035238733745622\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.00015019462184944334 | Validation metrics: 0.00014942163258151273\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.00014949730373650584 | Validation metrics: 0.00014851984010557786\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.00014882651558857795 | Validation metrics: 0.00014764675444269533\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.0001481816162460864 | Validation metrics: 0.00014680227137763393\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.0001475621527761109 | Validation metrics: 0.0001459854387153749\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.00014696758354834297 | Validation metrics: 0.00014519611615487703\n",
      "10-14 20:49:01 - INFO - Train metrics: 0.00014639779677927343 | Validation metrics: 0.00014443450316027127\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00014585256685950982 | Validation metrics: 0.00014370046942577123\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.0001453310186682353 | Validation metrics: 0.00014299300182940005\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00014483334823688936 | Validation metrics: 0.00014231324673870182\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00014435891571885353 | Validation metrics: 0.00014166017993402696\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00014390740122728954 | Validation metrics: 0.0001410334911950008\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.0001434789197551516 | Validation metrics: 0.00014043463747701466\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00014307246072845707 | Validation metrics: 0.00013986251107064274\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00014268799960224615 | Validation metrics: 0.00013931688465733044\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00014232528337743133 | Validation metrics: 0.0001387992099008636\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00014198390197447667 | Validation metrics: 0.00013830834513734743\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00014166341081231292 | Validation metrics: 0.00013784446337288529\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.0001413628263054719 | Validation metrics: 0.00013740792590654407\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00014108228901305462 | Validation metrics: 0.0001369980526200232\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00014082126904840355 | Validation metrics: 0.00013661527514664663\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.0001405790965857666 | Validation metrics: 0.00013625920609679223\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00014035509523461785 | Validation metrics: 0.00013592953569105252\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.0001401485111401008 | Validation metrics: 0.00013562518216356768\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00013995870314264218 | Validation metrics: 0.00013534532884321637\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00013978466810833634 | Validation metrics: 0.00013509015718797185\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00013962581028396213 | Validation metrics: 0.00013485785555788268\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00013948133299774947 | Validation metrics: 0.00013464667493032968\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00013934973390121713 | Validation metrics: 0.00013445552758639678\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00013923031114710538 | Validation metrics: 0.0001342824354945362\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00013912157285410006 | Validation metrics: 0.00013412532985746634\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00013902253405083633 | Validation metrics: 0.0001339821716431867\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00013893176598724137 | Validation metrics: 0.00013385084465044936\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.000138847635201713 | Validation metrics: 0.00013372834868590356\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.0001387695099806581 | Validation metrics: 0.0001336128669649814\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.0001386964931747967 | Validation metrics: 0.00013350301308703204\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00013862728444832543 | Validation metrics: 0.00013339693168286384\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00013856121660140168 | Validation metrics: 0.00013329284661037924\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00013849781955975135 | Validation metrics: 0.00013319011008886697\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00013843633078842804 | Validation metrics: 0.00013308765674174548\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00013837714607034925 | Validation metrics: 0.00013298456656459643\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00013832009286137722 | Validation metrics: 0.0001328818584119694\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00013826566027363011 | Validation metrics: 0.00013277972219370758\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00013821373955068882 | Validation metrics: 0.0001326781953920168\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.0001381649550025405 | Validation metrics: 0.0001325779985471845\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00013811998323853686 | Validation metrics: 0.00013248037687688596\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.0001380785522582173 | Validation metrics: 0.0001323855352103522\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00013804159090413074 | Validation metrics: 0.0001322945684689624\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.0001380093881357368 | Validation metrics: 0.0001322083417567274\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00013798214614806805 | Validation metrics: 0.0001321274366357947\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00013795992088758556 | Validation metrics: 0.00013205281933863656\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00013794276552895704 | Validation metrics: 0.000131984082044154\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00013793098770477634 | Validation metrics: 0.00013192224713463356\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00013792446738909603 | Validation metrics: 0.00013186744094715745\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.0001379228663866532 | Validation metrics: 0.0001318201249538253\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.0001379263724864491 | Validation metrics: 0.00013177975926388318\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.0001379348263833065 | Validation metrics: 0.00013174696865425717\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00013794785548984202 | Validation metrics: 0.00013172124983446503\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00013796576685511406 | Validation metrics: 0.00013170284269062445\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00013798796027644368 | Validation metrics: 0.00013169131999908278\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00013801457065993215 | Validation metrics: 0.00013168667698269617\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00013804563578949974 | Validation metrics: 0.00013168967996883874\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00013808048839236196 | Validation metrics: 0.0001316992682110838\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00013811940440784364 | Validation metrics: 0.0001317152027052479\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00013816204341595296 | Validation metrics: 0.00013173722070841722\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00013820848455868502 | Validation metrics: 0.00013176598617009762\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.0001382587219277434 | Validation metrics: 0.00013180100219383026\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00013831282146263373 | Validation metrics: 0.00013184226157715204\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.0001383703628719497 | Validation metrics: 0.00013188919811827046\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00013843167027316166 | Validation metrics: 0.0001319422465372793\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00013849636801532505 | Validation metrics: 0.000132001234489526\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00013856457313376813 | Validation metrics: 0.00013206617880525594\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00013863588645377366 | Validation metrics: 0.000132136652334311\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00013871144017999417 | Validation metrics: 0.00013221292656545312\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00013879008073579136 | Validation metrics: 0.00013229501950483996\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00013887199448779888 | Validation metrics: 0.00013238203481328909\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00013895774837717516 | Validation metrics: 0.00013247588474475167\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00013904730213997433 | Validation metrics: 0.00013257540632192178\n",
      "10-14 20:49:02 - INFO - Train metrics: 0.00013914033038224232 | Validation metrics: 0.00013268082495249638\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\Users\\wilso\\Desktop\\projects\\GitHub\\sysidentpy\\sysidentpy\\utils\\deprecation.py:27: FutureWarning: Function residuals has been deprecated since v0.1.7.\n",
      " Use from sysidentpy.residues_correlation import compute_cross_correlation, compute_residues_autocorrelation instead.This module was deprecated in favor of from sysidentpy.residues_correlation import compute_cross_correlation, compute_residues_autocorrelation module into which all the refactored classes and functions are moved.\n",
      " This feature will be removed in version v0.2.0.\n",
      "  warnings.warn(message, FutureWarning)\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 720x576 with 3 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "class NARX(nn.Module):\n",
    "    def __init__(self):\n",
    "        super().__init__()\n",
    "        self.lin = nn.Linear(4, 10)\n",
    "        self.lin2 = nn.Linear(10, 10)\n",
    "        self.lin3 = nn.Linear(10, 1)\n",
    "        self.tanh = nn.Tanh()\n",
    "\n",
    "    def forward(self, xb):\n",
    "        z = self.lin(xb)\n",
    "        z = self.tanh(z)\n",
    "        z = self.lin2(z)\n",
    "        z = self.tanh(z)\n",
    "        z = self.lin3(z)\n",
    "        return z\n",
    "\n",
    "narx_net2 = NARXNN(net=NARX(),\n",
    "                   ylag=2,\n",
    "                   xlag=2,\n",
    "                   loss_func='mse_loss',\n",
    "                   optimizer='Adam',\n",
    "                   epochs=200,\n",
    "                   verbose=True,\n",
    "                   optim_params={'betas': (0.9, 0.999), 'eps': 1e-05} # optional parameters of the optimizer\n",
    ")\n",
    "\n",
    "narx_net2.fit(train_dl, valid_dl)\n",
    "yhat = narx_net2.predict(x_valid, y_valid)\n",
    "\n",
    "ee, ex, extras, lam = narx_net2.residuals(x_valid, y_valid, yhat)\n",
    "narx_net2.plot_result(y_valid, yhat, ee, ex)"
   ]
  }
 ],
 "metadata": {
  "interpreter": {
   "hash": "0e65fe37feb8ff9f7778552a28949e943d61f86c936833305e2c18cda5b438ac"
  },
  "kernelspec": {
   "display_name": "Python 3.8.11 64-bit ('rd': conda)",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.11"
  },
  "orig_nbformat": 2
 },
 "nbformat": 4,
 "nbformat_minor": 2
}
