{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# How to train an MLP using the Pipeline"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Import classes and define paths"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from pyLOM import NN\n",
    "from pathlib import Path\n",
    "\n",
    "import torch\n",
    "\n",
    "import warnings\n",
    "warnings.filterwarnings(\"ignore\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Folder already exists: /home/david/Desktop/pyLowOrder/docs/source/notebook_examples/NN/results/models\n",
      "Folder already exists: /home/david/Desktop/pyLowOrder/docs/source/notebook_examples/NN/results/hyperparameters\n",
      "Folder already exists: /home/david/Desktop/pyLowOrder/docs/source/notebook_examples/NN/results/plots\n"
     ]
    }
   ],
   "source": [
    "DATA_DIR = Path.cwd().parent.parent.parent.parent / \"Testsuite/DATA\"\n",
    "CASE_DIR = Path.cwd() / \"results\"\n",
    "\n",
    "NN.create_results_folder(CASE_DIR / 'models')\n",
    "NN.create_results_folder(CASE_DIR / 'hyperparameters')\n",
    "NN.create_results_folder(CASE_DIR / 'plots')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Define scalers if needed\n",
    "\n",
    "Here, we create 2 minmax scalers, one for scaling the inputs, and other for the outputs. They will be passed to the dataset and the data will be automatically scaled"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "input_scaler = NN.MinMaxScaler()\n",
    "output_scaler = NN.MinMaxScaler()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Create datasets\n",
    "For this example, a dataset of airfoils generated with XFoil is used. As inputs, the model will receive the x and y coordinates of a point of the airfoil, the Reynolds number and the angle of attack; and the output will be the cp on that point"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "dataset = NN.Dataset.load(\n",
    "    DATA_DIR / 'AIRFOIL.h5',\n",
    "    field_names=[\"cp\"],\n",
    "    add_mesh_coordinates=True,\n",
    "    variables_names=[\"AoA\", \"Re\"],\n",
    "    inputs_scaler=input_scaler,\n",
    "    outputs_scaler=output_scaler,\n",
    ")\n",
    "train_dataset, test_dataset = dataset.get_splits_by_parameters([0.8, 0.2])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "After creating the datasets, we can see the shape of the tensors"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\tTrain dataset length:  27720\n",
      "\tTest dataset length:  6831\n",
      "\tX, y train shapes: torch.Size([27720, 4]) torch.Size([27720, 1])\n"
     ]
    }
   ],
   "source": [
    "x, y = train_dataset[:]\n",
    "print(\"\\tTrain dataset length: \", len(train_dataset))\n",
    "print(\"\\tTest dataset length: \", len(test_dataset))\n",
    "print(\"\\tX, y train shapes:\", x.shape, y.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Model creation\n",
    "\n",
    "Now, the only thing left is creating the model. For this example we are using an `MLP`"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "training_params = {\n",
    "    \"epochs\": 250,\n",
    "    \"lr\": 0.00015,\n",
    "    \"lr_gamma\": 0.98,\n",
    "    \"lr_scheduler_step\": 15,\n",
    "    \"batch_size\": 512,\n",
    "    \"loss_fn\": torch.nn.MSELoss(),\n",
    "    \"optimizer_class\": torch.optim.Adam,\n",
    "    \"print_rate_epoch\": 10,\n",
    "}"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We can train the model on a GPU to speed up the training. pyLOM can detect if a GPU is available with ´NN.DEVICE´, that will select the fist GPU.\n",
    "If many GPUs are available, the device can be define with `device = cuda:i` where `i` is the index of the GPU"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "device = NN.DEVICE"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "model = NN.MLP(\n",
    "    input_size=x.shape[1],\n",
    "    output_size=y.shape[1],\n",
    "    hidden_size=128,\n",
    "    n_layers=3,\n",
    "    p_dropouts=0.1,\n",
    "    device=device\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Run the pipeline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 10/250 | Train loss (x1e5) 1298.3891  | Test loss (x1e5) 703.0160\n",
      "Epoch 20/250 | Train loss (x1e5) 797.9615  | Test loss (x1e5) 349.2481\n",
      "Epoch 30/250 | Train loss (x1e5) 579.6663  | Test loss (x1e5) 227.8643\n",
      "Epoch 40/250 | Train loss (x1e5) 444.7827  | Test loss (x1e5) 153.3643\n",
      "Epoch 50/250 | Train loss (x1e5) 372.1323  | Test loss (x1e5) 118.2516\n",
      "Epoch 60/250 | Train loss (x1e5) 322.1863  | Test loss (x1e5) 83.2253\n",
      "Epoch 70/250 | Train loss (x1e5) 275.1737  | Test loss (x1e5) 62.4014\n",
      "Epoch 80/250 | Train loss (x1e5) 255.4608  | Test loss (x1e5) 44.5339\n",
      "Epoch 90/250 | Train loss (x1e5) 230.0541  | Test loss (x1e5) 37.5939\n",
      "Epoch 100/250 | Train loss (x1e5) 211.6728  | Test loss (x1e5) 34.3095\n",
      "Epoch 110/250 | Train loss (x1e5) 201.9902  | Test loss (x1e5) 33.0887\n",
      "Epoch 120/250 | Train loss (x1e5) 186.0425  | Test loss (x1e5) 26.0977\n",
      "Epoch 130/250 | Train loss (x1e5) 173.7337  | Test loss (x1e5) 26.0191\n",
      "Epoch 140/250 | Train loss (x1e5) 161.6373  | Test loss (x1e5) 27.8452\n",
      "Epoch 150/250 | Train loss (x1e5) 155.1712  | Test loss (x1e5) 23.0178\n",
      "Epoch 160/250 | Train loss (x1e5) 142.3610  | Test loss (x1e5) 20.6776\n",
      "Epoch 170/250 | Train loss (x1e5) 132.5751  | Test loss (x1e5) 18.9251\n",
      "Epoch 180/250 | Train loss (x1e5) 124.3999  | Test loss (x1e5) 19.8462\n",
      "Epoch 190/250 | Train loss (x1e5) 118.0378  | Test loss (x1e5) 17.9491\n",
      "Epoch 200/250 | Train loss (x1e5) 108.6139  | Test loss (x1e5) 18.7399\n",
      "Epoch 210/250 | Train loss (x1e5) 99.7270  | Test loss (x1e5) 16.9778\n",
      "Epoch 220/250 | Train loss (x1e5) 93.6449  | Test loss (x1e5) 16.5442\n",
      "Epoch 230/250 | Train loss (x1e5) 89.8119  | Test loss (x1e5) 15.5588\n",
      "Epoch 240/250 | Train loss (x1e5) 83.1366  | Test loss (x1e5) 14.7850\n",
      "Epoch 250/250 | Train loss (x1e5) 78.1027  | Test loss (x1e5) 13.3011\n"
     ]
    }
   ],
   "source": [
    "pipeline = NN.Pipeline(\n",
    "    train_dataset=train_dataset,\n",
    "    test_dataset=test_dataset,\n",
    "    model=model,\n",
    "    training_params=training_params,\n",
    ")\n",
    "training_logs = pipeline.run()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "To save the model:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "model.save(path=str(CASE_DIR / \"models\"))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Show plots"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "\n",
    "def true_vs_pred_plot(y_true, y_pred):\n",
    "    \"\"\"\n",
    "    Auxiliary function to plot the true vs predicted values\n",
    "    \"\"\"\n",
    "    num_plots = y_true.shape[1]\n",
    "    plt.figure(figsize=(10, 5 * num_plots))\n",
    "    for j in range(num_plots):\n",
    "        plt.subplot(num_plots, 1, j + 1)\n",
    "        plt.scatter(y_true[:, j], y_pred[:, j], s=1, c=\"b\", alpha=0.5)\n",
    "        plt.xlabel(\"True values\")\n",
    "        plt.ylabel(\"Predicted values\")\n",
    "        plt.title(f\"Scatterplot for Component {j+1}\")\n",
    "        plt.grid(True)\n",
    "\n",
    "    plt.tight_layout()\n",
    "    plt.show()\n",
    "\n",
    "def plot_train_test_loss(train_loss, test_loss):\n",
    "    \"\"\"\n",
    "    Auxiliary function to plot the training and test loss\n",
    "    \"\"\"\n",
    "    plt.figure()\n",
    "    plt.plot(range(1, len(train_loss) + 1), train_loss, label=\"Training Loss\")\n",
    "    total_epochs = len(test_loss) # test loss is calculated at the end of each epoch\n",
    "    total_iters = len(train_loss) # train loss is calculated at the end of each iteration/batch\n",
    "    iters_per_epoch = total_iters // total_epochs\n",
    "    plt.plot(np.arange(iters_per_epoch, total_iters+1, step=iters_per_epoch), test_loss, label=\"Test Loss\")\n",
    "    plt.xlabel(\"Iterations\")\n",
    "    plt.ylabel(\"Loss\")\n",
    "    plt.title(\"Training Loss vs Epoch\")\n",
    "    plt.yscale(\"log\")\n",
    "    plt.legend()\n",
    "    plt.grid()\n",
    "    plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plot_train_test_loss(training_logs['train_loss'], training_logs['test_loss'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x500 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "preds = model.predict(train_dataset, batch_size=250)\n",
    "\n",
    "scaled_preds = output_scaler.inverse_transform([preds])[0]\n",
    "scaled_y = output_scaler.inverse_transform([train_dataset[:][1]])[0]\n",
    "true_vs_pred_plot(scaled_y, scaled_preds)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Evaluate the model with some metrics"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "Regression evaluator metrics:\n",
      "mse: 0.0152\n",
      "rmse: 0.1233\n",
      "mae: 0.0645\n",
      "mre: 89.3139%\n",
      "ae_95: 0.2164\n",
      "ae_99: 0.4968\n",
      "r2: 0.9919\n",
      "l2_error: 0.0838\n"
     ]
    }
   ],
   "source": [
    "evaluator = NN.RegressionEvaluator()\n",
    "evaluator(scaled_y, scaled_preds)\n",
    "evaluator.print_metrics()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "pruebasphinx",
   "language": "python",
   "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": "3.11.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}