{
 "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 cetaceo.pipeline import Pipeline\n",
    "from cetaceo.models import MLP\n",
    "from cetaceo.data import HDF5Dataset\n",
    "from cetaceo.evaluators import RegressionEvaluatorPlotter\n",
    "from cetaceo.plotting import TrueVsPredPlotter\n",
    "from cetaceo.utils import PathManager\n",
    "from pathlib import Path\n",
    "\n",
    "import torch\n",
    "from sklearn.preprocessing import MinMaxScaler\n",
    "\n",
    "import warnings\n",
    "warnings.filterwarnings(\"ignore\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "DATA_DIR = Path.cwd().parent / \"sample_data\"\n",
    "CASE_DIR = Path.cwd() / \"results\"\n",
    "PathManager.create_directory(CASE_DIR / 'models')\n",
    "PathManager.create_directory(CASE_DIR / 'hyperparameters')\n",
    "PathManager.create_directory(CASE_DIR / 'plots')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Define sklearn scalers if needed\n",
    "\n",
    "Here, we create 2 minmax scalers, one for scaling the inputs, and other for the outputs."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "x_scaler = MinMaxScaler()\n",
    "y_scaler = MinMaxScaler()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Create datasets\n",
    "For this example, we will use the airfoil data from the DLR paper. As the files are processed as .h5, a `HDF5Dataset` is needed. We create one for each dataset split."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "train_dataset = HDF5Dataset(src_file = str(DATA_DIR) + \"/train.h5\", x_scaler=x_scaler, y_scaler=y_scaler)\n",
    "test_dataset = HDF5Dataset(src_file = str(DATA_DIR) + \"/test.h5\" , x_scaler=x_scaler, y_scaler=y_scaler)\n",
    "valid_dataset = HDF5Dataset(src_file = str(DATA_DIR) + \"/val.h5\", x_scaler=x_scaler, y_scaler=y_scaler)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "After creating the datasets, we can scale them because we passed the scalers on the constructors"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\tTrain dataset length:  23283\n",
      "\tTest dataset length:  23283\n",
      "\tValid dataset length:  11940\n",
      "\tX, y train shapes: torch.Size([23283, 4]) torch.Size([23283, 1])\n"
     ]
    }
   ],
   "source": [
    "x, y = train_dataset[:]\n",
    "train_dataset.scale_data()\n",
    "valid_dataset.scale_data()\n",
    "test_dataset.scale_data()\n",
    "print(\"\\tTrain dataset length: \", len(train_dataset))\n",
    "print(\"\\tTest dataset length: \", len(test_dataset))\n",
    "print(\"\\tValid dataset length: \", len(valid_dataset))\n",
    "print(\"\\tX, y train shapes:\", x.shape, y.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Evaluators and Plotters\n",
    "\n",
    "Here we define which evaluator to use. For this case we use a `RegressionEvaluatorPlotter`, which gives metrics related with regression problems. Additionally, this class can take as parameters a list of plotters, which are useful to create plots based on the model's predictions"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "plotters = [TrueVsPredPlotter()]\n",
    "evaluator = RegressionEvaluatorPlotter(plots_path=CASE_DIR / 'plots', plotters=plotters)"
   ]
  },
  {
   "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": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "training_params = {\n",
    "    \"epochs\": 100,\n",
    "    \"lr\": 0.00126,\n",
    "    'lr_gamma': 0.966,\n",
    "    'lr_scheduler_step': 1,\n",
    "    'batch_size': 512,\n",
    "    \"optimizer_class\": torch.optim.Adam,\n",
    "    \"print_rate\": 1,\n",
    "}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "model = MLP(\n",
    "        input_size=x.shape[1],\n",
    "        output_size=y.shape[1],\n",
    "        hidden_size=512,\n",
    "        n_layers=3,\n",
    "        p_dropouts=0.15\n",
    "    )"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Run the pipeline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/100 | Train loss (x1e5) 3968.2092 | Test loss (x1e5) 640.3254\n",
      "Epoch 2/100 | Train loss (x1e5) 531.2284 | Test loss (x1e5) 268.4059\n",
      "Epoch 3/100 | Train loss (x1e5) 363.7133 | Test loss (x1e5) 193.8889\n",
      "Epoch 4/100 | Train loss (x1e5) 281.3932 | Test loss (x1e5) 117.6769\n",
      "Epoch 5/100 | Train loss (x1e5) 219.3242 | Test loss (x1e5) 94.8438\n",
      "Epoch 6/100 | Train loss (x1e5) 188.3426 | Test loss (x1e5) 66.5134\n",
      "Epoch 7/100 | Train loss (x1e5) 162.8639 | Test loss (x1e5) 52.9106\n",
      "Epoch 8/100 | Train loss (x1e5) 147.2162 | Test loss (x1e5) 43.3563\n",
      "Epoch 9/100 | Train loss (x1e5) 133.1248 | Test loss (x1e5) 69.3100\n",
      "Epoch 10/100 | Train loss (x1e5) 129.9856 | Test loss (x1e5) 40.7987\n",
      "Epoch 11/100 | Train loss (x1e5) 116.6901 | Test loss (x1e5) 34.9828\n",
      "Epoch 12/100 | Train loss (x1e5) 111.6007 | Test loss (x1e5) 30.6759\n",
      "Epoch 13/100 | Train loss (x1e5) 107.0436 | Test loss (x1e5) 37.7164\n",
      "Epoch 14/100 | Train loss (x1e5) 100.2151 | Test loss (x1e5) 31.0014\n",
      "Epoch 15/100 | Train loss (x1e5) 97.2787 | Test loss (x1e5) 31.0849\n",
      "Epoch 16/100 | Train loss (x1e5) 94.6964 | Test loss (x1e5) 43.5958\n",
      "Epoch 17/100 | Train loss (x1e5) 91.4782 | Test loss (x1e5) 29.6458\n",
      "Epoch 18/100 | Train loss (x1e5) 90.4933 | Test loss (x1e5) 33.6109\n",
      "Epoch 19/100 | Train loss (x1e5) 86.9575 | Test loss (x1e5) 30.7852\n",
      "Epoch 20/100 | Train loss (x1e5) 88.1818 | Test loss (x1e5) 29.2189\n",
      "Epoch 21/100 | Train loss (x1e5) 84.4978 | Test loss (x1e5) 22.2148\n",
      "Epoch 22/100 | Train loss (x1e5) 84.4161 | Test loss (x1e5) 35.0264\n",
      "Epoch 23/100 | Train loss (x1e5) 80.5170 | Test loss (x1e5) 22.3276\n",
      "Epoch 24/100 | Train loss (x1e5) 80.5800 | Test loss (x1e5) 29.2161\n",
      "Epoch 25/100 | Train loss (x1e5) 77.0368 | Test loss (x1e5) 22.5613\n",
      "Epoch 26/100 | Train loss (x1e5) 77.6624 | Test loss (x1e5) 28.3152\n",
      "Epoch 27/100 | Train loss (x1e5) 75.9246 | Test loss (x1e5) 27.3747\n",
      "Epoch 28/100 | Train loss (x1e5) 75.1129 | Test loss (x1e5) 22.1203\n",
      "Epoch 29/100 | Train loss (x1e5) 73.9176 | Test loss (x1e5) 21.3708\n",
      "Epoch 30/100 | Train loss (x1e5) 73.8303 | Test loss (x1e5) 19.4375\n",
      "Epoch 31/100 | Train loss (x1e5) 71.4301 | Test loss (x1e5) 17.4285\n",
      "Epoch 32/100 | Train loss (x1e5) 71.6028 | Test loss (x1e5) 30.2202\n",
      "Epoch 33/100 | Train loss (x1e5) 70.7754 | Test loss (x1e5) 27.7524\n",
      "Epoch 34/100 | Train loss (x1e5) 70.7107 | Test loss (x1e5) 21.8441\n",
      "Epoch 35/100 | Train loss (x1e5) 67.9373 | Test loss (x1e5) 18.7597\n",
      "Epoch 36/100 | Train loss (x1e5) 66.5284 | Test loss (x1e5) 21.3425\n",
      "Epoch 37/100 | Train loss (x1e5) 69.2680 | Test loss (x1e5) 18.1248\n",
      "Epoch 38/100 | Train loss (x1e5) 66.0457 | Test loss (x1e5) 18.3276\n",
      "Epoch 39/100 | Train loss (x1e5) 66.4341 | Test loss (x1e5) 18.3668\n",
      "Epoch 40/100 | Train loss (x1e5) 64.8588 | Test loss (x1e5) 14.3345\n",
      "Epoch 41/100 | Train loss (x1e5) 65.0324 | Test loss (x1e5) 22.2836\n",
      "Epoch 42/100 | Train loss (x1e5) 64.2346 | Test loss (x1e5) 20.3639\n",
      "Epoch 43/100 | Train loss (x1e5) 63.5873 | Test loss (x1e5) 23.6401\n",
      "Epoch 44/100 | Train loss (x1e5) 63.5231 | Test loss (x1e5) 16.7890\n",
      "Epoch 45/100 | Train loss (x1e5) 62.1668 | Test loss (x1e5) 14.9163\n",
      "Epoch 46/100 | Train loss (x1e5) 60.7827 | Test loss (x1e5) 17.4896\n",
      "Epoch 47/100 | Train loss (x1e5) 62.4567 | Test loss (x1e5) 13.8604\n",
      "Epoch 48/100 | Train loss (x1e5) 61.4397 | Test loss (x1e5) 17.9461\n",
      "Epoch 49/100 | Train loss (x1e5) 60.8647 | Test loss (x1e5) 19.6511\n",
      "Epoch 50/100 | Train loss (x1e5) 60.5594 | Test loss (x1e5) 13.8324\n",
      "Epoch 51/100 | Train loss (x1e5) 59.3509 | Test loss (x1e5) 12.3390\n",
      "Epoch 52/100 | Train loss (x1e5) 60.1447 | Test loss (x1e5) 14.2438\n",
      "Epoch 53/100 | Train loss (x1e5) 59.2692 | Test loss (x1e5) 19.0007\n",
      "Epoch 54/100 | Train loss (x1e5) 59.7058 | Test loss (x1e5) 13.2120\n",
      "Epoch 55/100 | Train loss (x1e5) 59.4506 | Test loss (x1e5) 21.6260\n",
      "Epoch 56/100 | Train loss (x1e5) 59.7846 | Test loss (x1e5) 14.1505\n",
      "Epoch 57/100 | Train loss (x1e5) 59.1430 | Test loss (x1e5) 11.9013\n",
      "Epoch 58/100 | Train loss (x1e5) 57.7920 | Test loss (x1e5) 18.3841\n",
      "Epoch 59/100 | Train loss (x1e5) 58.3397 | Test loss (x1e5) 12.8296\n",
      "Epoch 60/100 | Train loss (x1e5) 56.5668 | Test loss (x1e5) 15.5571\n",
      "Epoch 61/100 | Train loss (x1e5) 57.3597 | Test loss (x1e5) 18.4371\n",
      "Epoch 62/100 | Train loss (x1e5) 58.0973 | Test loss (x1e5) 12.8372\n",
      "Epoch 63/100 | Train loss (x1e5) 56.9284 | Test loss (x1e5) 12.7845\n",
      "Epoch 64/100 | Train loss (x1e5) 55.6151 | Test loss (x1e5) 15.2220\n",
      "Epoch 65/100 | Train loss (x1e5) 56.3089 | Test loss (x1e5) 12.8679\n",
      "Epoch 66/100 | Train loss (x1e5) 57.0098 | Test loss (x1e5) 11.3940\n",
      "Epoch 67/100 | Train loss (x1e5) 55.8330 | Test loss (x1e5) 16.7325\n",
      "Epoch 68/100 | Train loss (x1e5) 55.6434 | Test loss (x1e5) 13.6628\n",
      "Epoch 69/100 | Train loss (x1e5) 55.7484 | Test loss (x1e5) 13.5055\n",
      "Epoch 70/100 | Train loss (x1e5) 54.4978 | Test loss (x1e5) 12.0881\n",
      "Epoch 71/100 | Train loss (x1e5) 55.6273 | Test loss (x1e5) 15.7260\n",
      "Epoch 72/100 | Train loss (x1e5) 55.3004 | Test loss (x1e5) 13.6676\n",
      "Epoch 73/100 | Train loss (x1e5) 53.8224 | Test loss (x1e5) 11.3997\n",
      "Epoch 74/100 | Train loss (x1e5) 54.8473 | Test loss (x1e5) 11.9121\n",
      "Epoch 75/100 | Train loss (x1e5) 54.4477 | Test loss (x1e5) 13.0294\n",
      "Epoch 76/100 | Train loss (x1e5) 54.2868 | Test loss (x1e5) 11.7455\n",
      "Epoch 77/100 | Train loss (x1e5) 53.2922 | Test loss (x1e5) 11.6593\n",
      "Epoch 78/100 | Train loss (x1e5) 52.6854 | Test loss (x1e5) 14.3897\n",
      "Epoch 79/100 | Train loss (x1e5) 52.8497 | Test loss (x1e5) 13.3810\n",
      "Epoch 80/100 | Train loss (x1e5) 53.2287 | Test loss (x1e5) 11.8646\n",
      "Epoch 81/100 | Train loss (x1e5) 54.0476 | Test loss (x1e5) 14.3325\n",
      "Epoch 82/100 | Train loss (x1e5) 53.6350 | Test loss (x1e5) 13.7774\n",
      "Epoch 83/100 | Train loss (x1e5) 53.7555 | Test loss (x1e5) 11.0659\n",
      "Epoch 84/100 | Train loss (x1e5) 53.1362 | Test loss (x1e5) 13.7008\n",
      "Epoch 85/100 | Train loss (x1e5) 52.4187 | Test loss (x1e5) 16.8150\n",
      "Epoch 86/100 | Train loss (x1e5) 52.6289 | Test loss (x1e5) 13.3272\n",
      "Epoch 87/100 | Train loss (x1e5) 51.3318 | Test loss (x1e5) 13.8505\n",
      "Epoch 88/100 | Train loss (x1e5) 53.0107 | Test loss (x1e5) 12.2213\n",
      "Epoch 89/100 | Train loss (x1e5) 51.8942 | Test loss (x1e5) 13.0393\n",
      "Epoch 90/100 | Train loss (x1e5) 51.7824 | Test loss (x1e5) 12.1874\n",
      "Epoch 91/100 | Train loss (x1e5) 51.4040 | Test loss (x1e5) 12.8719\n",
      "Epoch 92/100 | Train loss (x1e5) 50.7001 | Test loss (x1e5) 10.9069\n",
      "Epoch 93/100 | Train loss (x1e5) 51.5473 | Test loss (x1e5) 12.0467\n",
      "Epoch 94/100 | Train loss (x1e5) 50.8814 | Test loss (x1e5) 13.0899\n",
      "Epoch 95/100 | Train loss (x1e5) 51.5298 | Test loss (x1e5) 13.6348\n",
      "Epoch 96/100 | Train loss (x1e5) 51.8971 | Test loss (x1e5) 14.7821\n",
      "Epoch 97/100 | Train loss (x1e5) 51.7207 | Test loss (x1e5) 11.0060\n",
      "Epoch 98/100 | Train loss (x1e5) 51.4634 | Test loss (x1e5) 10.5973\n",
      "Epoch 99/100 | Train loss (x1e5) 51.1898 | Test loss (x1e5) 11.7234\n",
      "Epoch 100/100 | Train loss (x1e5) 50.5890 | Test loss (x1e5) 10.9737\n",
      "\n",
      "--------------------------------------------------\n",
      "Metrics on train data:\n",
      "--------------------------------------------------\n",
      "Rescale output: True\n",
      "\n",
      "Regression evaluator metrics:\n",
      "mse: 0.0015\n",
      "mae: 0.0246\n",
      "mre: 15.6336%\n",
      "ae_95: 0.0813\n",
      "ae_99: 0.1536\n",
      "r2: 0.9936\n",
      "l2_error: 0.0668\n",
      "--------------------------------------------------\n",
      "Metrics on test data:\n",
      "--------------------------------------------------\n",
      "Rescale output: True\n",
      "\n",
      "Regression evaluator metrics:\n",
      "mse: 0.0028\n",
      "mae: 0.0286\n",
      "mre: 17.6299%\n",
      "ae_95: 0.0993\n",
      "ae_99: 0.2377\n",
      "r2: 0.9885\n",
      "l2_error: 0.0895\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x500 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x500 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "pipeline = Pipeline(\n",
    "        train_dataset=train_dataset,\n",
    "        test_dataset=test_dataset,\n",
    "        model=model,\n",
    "        training_params=training_params,\n",
    "        evaluators=[evaluator],\n",
    "    )\n",
    "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\"))"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "cetaceo",
   "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": "3.11.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}