{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "142d241f-2ce8-424e-8828-9505488d2b39",
   "metadata": {},
   "source": [
    "# Forecasting time series with Ngboost regressor (Python version)\n",
    "\n",
    "This notebook provides some examples of how the functions in the `ngboost_models.py` module can be used. The functions in this module allow the application of the ngboost regressor model. There are separate methods to train and evaluate (separate the data in train and test datasets), train with all the data available, and make forecasts."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "c2fe963b",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "from epigraphhub.analysis.forecast_models.plots import * \n",
    "from epigraphhub.analysis.preprocessing import * \n",
    "from epigraphhub.analysis.forecast_models.ngboost_models import * \n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a9c88faf-38eb-4824-bf41-0e713f0722d4",
   "metadata": {},
   "source": [
    "In this tutorial, we will use the data saved in the path: `./data/data_GE.csv`. This table represents the number of tests, cases, and hospitalizations (your values by day and differences in first and second order) for some cantons in Switzerland. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "23fd777a",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>test_FR</th>\n",
       "      <th>diff_test_FR</th>\n",
       "      <th>diff_2_test_FR</th>\n",
       "      <th>test_NE</th>\n",
       "      <th>diff_test_NE</th>\n",
       "      <th>diff_2_test_NE</th>\n",
       "      <th>test_TI</th>\n",
       "      <th>diff_test_TI</th>\n",
       "      <th>diff_2_test_TI</th>\n",
       "      <th>test_VD</th>\n",
       "      <th>...</th>\n",
       "      <th>hosp_NE</th>\n",
       "      <th>diff_hosp_NE</th>\n",
       "      <th>diff_2_hosp_NE</th>\n",
       "      <th>hosp_FR</th>\n",
       "      <th>diff_hosp_FR</th>\n",
       "      <th>diff_2_hosp_FR</th>\n",
       "      <th>hosp_GE</th>\n",
       "      <th>diff_hosp_GE</th>\n",
       "      <th>diff_2_hosp_GE</th>\n",
       "      <th>vac_all</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>datum</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2020-03-01</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.142857</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.428571</td>\n",
       "      <td>0.142857</td>\n",
       "      <td>0.285714</td>\n",
       "      <td>0.428571</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2020-03-02</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.285714</td>\n",
       "      <td>0.142857</td>\n",
       "      <td>0.142857</td>\n",
       "      <td>0.857143</td>\n",
       "      <td>0.428571</td>\n",
       "      <td>0.571429</td>\n",
       "      <td>0.428571</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.142857</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2020-03-03</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.428571</td>\n",
       "      <td>0.142857</td>\n",
       "      <td>0.285714</td>\n",
       "      <td>0.857143</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.428571</td>\n",
       "      <td>0.428571</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2020-03-04</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.285714</td>\n",
       "      <td>-0.142857</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.714286</td>\n",
       "      <td>-0.142857</td>\n",
       "      <td>-0.142857</td>\n",
       "      <td>0.571429</td>\n",
       "      <td>0.142857</td>\n",
       "      <td>0.142857</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2020-03-05</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.428571</td>\n",
       "      <td>0.142857</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.285714</td>\n",
       "      <td>0.142857</td>\n",
       "      <td>0.857143</td>\n",
       "      <td>0.285714</td>\n",
       "      <td>0.428571</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2022-08-26</th>\n",
       "      <td>165.857143</td>\n",
       "      <td>-0.714286</td>\n",
       "      <td>-9.000000</td>\n",
       "      <td>137.142857</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>3.857143</td>\n",
       "      <td>406.428571</td>\n",
       "      <td>-7.714286</td>\n",
       "      <td>-13.714286</td>\n",
       "      <td>650.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.142857</td>\n",
       "      <td>-0.428571</td>\n",
       "      <td>-0.428571</td>\n",
       "      <td>2.571429</td>\n",
       "      <td>-0.142857</td>\n",
       "      <td>0.142857</td>\n",
       "      <td>182.8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2022-08-27</th>\n",
       "      <td>165.142857</td>\n",
       "      <td>-0.714286</td>\n",
       "      <td>-1.428571</td>\n",
       "      <td>137.285714</td>\n",
       "      <td>0.142857</td>\n",
       "      <td>1.142857</td>\n",
       "      <td>405.285714</td>\n",
       "      <td>-1.142857</td>\n",
       "      <td>-8.857143</td>\n",
       "      <td>650.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.142857</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>-0.428571</td>\n",
       "      <td>2.571429</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>-0.142857</td>\n",
       "      <td>182.8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2022-08-28</th>\n",
       "      <td>159.000000</td>\n",
       "      <td>-6.142857</td>\n",
       "      <td>-6.857143</td>\n",
       "      <td>135.428571</td>\n",
       "      <td>-1.857143</td>\n",
       "      <td>-1.714286</td>\n",
       "      <td>407.571429</td>\n",
       "      <td>2.285714</td>\n",
       "      <td>1.142857</td>\n",
       "      <td>645.142857</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.142857</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>2.142857</td>\n",
       "      <td>-0.428571</td>\n",
       "      <td>-0.428571</td>\n",
       "      <td>182.8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2022-08-29</th>\n",
       "      <td>151.857143</td>\n",
       "      <td>-7.142857</td>\n",
       "      <td>-13.285714</td>\n",
       "      <td>130.142857</td>\n",
       "      <td>-5.285714</td>\n",
       "      <td>-7.142857</td>\n",
       "      <td>360.714286</td>\n",
       "      <td>-46.857143</td>\n",
       "      <td>-44.571429</td>\n",
       "      <td>615.714286</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.142857</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.857143</td>\n",
       "      <td>-0.285714</td>\n",
       "      <td>-0.714286</td>\n",
       "      <td>182.8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2022-08-30</th>\n",
       "      <td>123.857143</td>\n",
       "      <td>-6.714286</td>\n",
       "      <td>-28.142857</td>\n",
       "      <td>107.142857</td>\n",
       "      <td>-6.285714</td>\n",
       "      <td>-22.857143</td>\n",
       "      <td>293.571429</td>\n",
       "      <td>-41.714286</td>\n",
       "      <td>-82.285714</td>\n",
       "      <td>505.714286</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.142857</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.428571</td>\n",
       "      <td>-0.428571</td>\n",
       "      <td>-0.714286</td>\n",
       "      <td>182.8</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>913 rows × 64 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "               test_FR  diff_test_FR  diff_2_test_FR     test_NE  \\\n",
       "datum                                                              \n",
       "2020-03-01    0.000000      0.000000        0.000000    0.000000   \n",
       "2020-03-02    0.000000      0.000000        0.000000    0.000000   \n",
       "2020-03-03    0.000000      0.000000        0.000000    0.000000   \n",
       "2020-03-04    0.000000      0.000000        0.000000    0.000000   \n",
       "2020-03-05    0.000000      0.000000        0.000000    0.000000   \n",
       "...                ...           ...             ...         ...   \n",
       "2022-08-26  165.857143     -0.714286       -9.000000  137.142857   \n",
       "2022-08-27  165.142857     -0.714286       -1.428571  137.285714   \n",
       "2022-08-28  159.000000     -6.142857       -6.857143  135.428571   \n",
       "2022-08-29  151.857143     -7.142857      -13.285714  130.142857   \n",
       "2022-08-30  123.857143     -6.714286      -28.142857  107.142857   \n",
       "\n",
       "            diff_test_NE  diff_2_test_NE     test_TI  diff_test_TI  \\\n",
       "datum                                                                \n",
       "2020-03-01      0.000000        0.000000    0.000000      0.000000   \n",
       "2020-03-02      0.000000        0.000000    0.000000      0.000000   \n",
       "2020-03-03      0.000000        0.000000    0.000000      0.000000   \n",
       "2020-03-04      0.000000        0.000000    0.000000      0.000000   \n",
       "2020-03-05      0.000000        0.000000    0.000000      0.000000   \n",
       "...                  ...             ...         ...           ...   \n",
       "2022-08-26      1.000000        3.857143  406.428571     -7.714286   \n",
       "2022-08-27      0.142857        1.142857  405.285714     -1.142857   \n",
       "2022-08-28     -1.857143       -1.714286  407.571429      2.285714   \n",
       "2022-08-29     -5.285714       -7.142857  360.714286    -46.857143   \n",
       "2022-08-30     -6.285714      -22.857143  293.571429    -41.714286   \n",
       "\n",
       "            diff_2_test_TI     test_VD  ...   hosp_NE  diff_hosp_NE  \\\n",
       "datum                                   ...                           \n",
       "2020-03-01        0.000000    0.000000  ...  0.142857      0.000000   \n",
       "2020-03-02        0.000000    0.000000  ...  0.285714      0.142857   \n",
       "2020-03-03        0.000000    0.000000  ...  0.428571      0.142857   \n",
       "2020-03-04        0.000000    0.000000  ...  0.285714     -0.142857   \n",
       "2020-03-05        0.000000    0.000000  ...  0.428571      0.142857   \n",
       "...                    ...         ...  ...       ...           ...   \n",
       "2022-08-26      -13.714286  650.000000  ...  0.000000      0.000000   \n",
       "2022-08-27       -8.857143  650.000000  ...  0.000000      0.000000   \n",
       "2022-08-28        1.142857  645.142857  ...  0.000000      0.000000   \n",
       "2022-08-29      -44.571429  615.714286  ...  0.000000      0.000000   \n",
       "2022-08-30      -82.285714  505.714286  ...  0.000000      0.000000   \n",
       "\n",
       "            diff_2_hosp_NE   hosp_FR  diff_hosp_FR  diff_2_hosp_FR   hosp_GE  \\\n",
       "datum                                                                          \n",
       "2020-03-01        0.000000  0.428571      0.142857        0.285714  0.428571   \n",
       "2020-03-02        0.142857  0.857143      0.428571        0.571429  0.428571   \n",
       "2020-03-03        0.285714  0.857143      0.000000        0.428571  0.428571   \n",
       "2020-03-04        0.000000  0.714286     -0.142857       -0.142857  0.571429   \n",
       "2020-03-05        0.000000  1.000000      0.285714        0.142857  0.857143   \n",
       "...                    ...       ...           ...             ...       ...   \n",
       "2022-08-26        0.000000  0.142857     -0.428571       -0.428571  2.571429   \n",
       "2022-08-27        0.000000  0.142857      0.000000       -0.428571  2.571429   \n",
       "2022-08-28        0.000000  0.142857      0.000000        0.000000  2.142857   \n",
       "2022-08-29        0.000000  0.142857      0.000000        0.000000  1.857143   \n",
       "2022-08-30        0.000000  0.142857      0.000000        0.000000  1.428571   \n",
       "\n",
       "            diff_hosp_GE  diff_2_hosp_GE  vac_all  \n",
       "datum                                              \n",
       "2020-03-01      0.000000        0.000000      0.0  \n",
       "2020-03-02      0.000000        0.142857      0.0  \n",
       "2020-03-03      0.000000        0.000000      0.0  \n",
       "2020-03-04      0.142857        0.142857      0.0  \n",
       "2020-03-05      0.285714        0.428571      0.0  \n",
       "...                  ...             ...      ...  \n",
       "2022-08-26     -0.142857        0.142857    182.8  \n",
       "2022-08-27      0.000000       -0.142857    182.8  \n",
       "2022-08-28     -0.428571       -0.428571    182.8  \n",
       "2022-08-29     -0.285714       -0.714286    182.8  \n",
       "2022-08-30     -0.428571       -0.714286    182.8  \n",
       "\n",
       "[913 rows x 64 columns]"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.read_csv('./data/data_GE.csv')\n",
    "df.set_index('datum', inplace = True)\n",
    "df.index = pd.to_datetime(df.index)\n",
    "\n",
    "df"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "92659335",
   "metadata": {},
   "source": [
    "### Class NGBModel()\n",
    "\n",
    "This class instantiates a ngboost regressor model. This class takes as input the parameters accepted by a Ngboost model (defined in their documentation), a parameter to define the number of last observations that the model will use as input, a parameter to define the number of days that it will be predicted by the model, the percentage of the train data that will be used as validation, and a parameter to define the early stop of the training. The methods in this class allows the user to train and evaluate the model, to train and save the model and make the forecast using saved  models.\n",
    "\n",
    "This class allows the training of multiple ngboost models, each one specialized in the forecast for a single day. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "6304bb85",
   "metadata": {},
   "outputs": [],
   "source": [
    "m = NGBModel(look_back = 14,\n",
    "            predict_n = 14, \n",
    "            validation_split = 0.15, \n",
    "            early_stop = 10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "e409f6ef",
   "metadata": {},
   "outputs": [],
   "source": [
    "def remove_zeros(tgt):\n",
    "    \n",
    "    tgt[tgt == 0] = 0.01\n",
    "    \n",
    "    return tgt\n",
    "    "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e1cb7d49",
   "metadata": {},
   "source": [
    "### Method `train_eval()`\n",
    "\n",
    "This method takes the class `NGBModel()` and trains and evaluates this model. This function split the data in train and test dataset and returns the predictions made using the test dataset."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "7367de31",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>target</th>\n",
       "      <th>lower</th>\n",
       "      <th>median</th>\n",
       "      <th>upper</th>\n",
       "      <th>train_size</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>date</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2020-05-02</th>\n",
       "      <td>0.285714</td>\n",
       "      <td>0.171583</td>\n",
       "      <td>0.300695</td>\n",
       "      <td>0.526959</td>\n",
       "      <td>584</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2020-05-03</th>\n",
       "      <td>0.285714</td>\n",
       "      <td>0.188583</td>\n",
       "      <td>0.363243</td>\n",
       "      <td>0.699668</td>\n",
       "      <td>584</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2020-05-04</th>\n",
       "      <td>0.142857</td>\n",
       "      <td>0.077129</td>\n",
       "      <td>0.199622</td>\n",
       "      <td>0.516653</td>\n",
       "      <td>584</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2020-05-05</th>\n",
       "      <td>0.142857</td>\n",
       "      <td>0.074032</td>\n",
       "      <td>0.222506</td>\n",
       "      <td>0.668752</td>\n",
       "      <td>584</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2020-05-06</th>\n",
       "      <td>0.142857</td>\n",
       "      <td>0.083643</td>\n",
       "      <td>0.205801</td>\n",
       "      <td>0.506366</td>\n",
       "      <td>584</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2022-04-26</th>\n",
       "      <td>7.714286</td>\n",
       "      <td>1.810433</td>\n",
       "      <td>3.324867</td>\n",
       "      <td>6.106128</td>\n",
       "      <td>584</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2022-04-27</th>\n",
       "      <td>6.857143</td>\n",
       "      <td>2.234695</td>\n",
       "      <td>3.160372</td>\n",
       "      <td>4.469492</td>\n",
       "      <td>584</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2022-04-28</th>\n",
       "      <td>5.714286</td>\n",
       "      <td>2.208807</td>\n",
       "      <td>3.287218</td>\n",
       "      <td>4.892146</td>\n",
       "      <td>584</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2022-04-29</th>\n",
       "      <td>5.000000</td>\n",
       "      <td>1.947474</td>\n",
       "      <td>3.324971</td>\n",
       "      <td>5.676806</td>\n",
       "      <td>584</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2022-04-30</th>\n",
       "      <td>5.714286</td>\n",
       "      <td>3.261146</td>\n",
       "      <td>5.104967</td>\n",
       "      <td>7.991267</td>\n",
       "      <td>584</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>729 rows × 5 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "              target     lower    median     upper  train_size\n",
       "date                                                          \n",
       "2020-05-02  0.285714  0.171583  0.300695  0.526959         584\n",
       "2020-05-03  0.285714  0.188583  0.363243  0.699668         584\n",
       "2020-05-04  0.142857  0.077129  0.199622  0.516653         584\n",
       "2020-05-05  0.142857  0.074032  0.222506  0.668752         584\n",
       "2020-05-06  0.142857  0.083643  0.205801  0.506366         584\n",
       "...              ...       ...       ...       ...         ...\n",
       "2022-04-26  7.714286  1.810433  3.324867  6.106128         584\n",
       "2022-04-27  6.857143  2.234695  3.160372  4.469492         584\n",
       "2022-04-28  5.714286  2.208807  3.287218  4.892146         584\n",
       "2022-04-29  5.000000  1.947474  3.324971  5.676806         584\n",
       "2022-04-30  5.714286  3.261146  5.104967  7.991267         584\n",
       "\n",
       "[729 rows x 5 columns]"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['hosp_GE'] = remove_zeros(df['hosp_GE'].values)\n",
    "\n",
    "df_p = m.train_eval(target_name = 'hosp_GE',\n",
    "                    data = df,\n",
    "                    ini_date = '2020-05-01',\n",
    "                    end_date = '2022-04-30',\n",
    "                    ratio = 0.8, save = False)\n",
    "\n",
    "df_p"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "333aa996",
   "metadata": {},
   "source": [
    "### Function `plot_val()`\n",
    "\n",
    "This function is saved in the `plots.py` module and, given the output of the `train_eval()` method plot the model's behavior in train and test sample. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "5187b8aa",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 900x600 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plot_val(df_p, title = 'Hosp in GE')\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "88e26602",
   "metadata": {},
   "source": [
    "### Method `train()`\n",
    "\n",
    "This method trains multiple ngboost models with all the data available and will save the model that will be used to make forecasts.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "b9e9dd15",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CPU times: user 3min 37s, sys: 653 ms, total: 3min 37s\n",
      "Wall time: 3min 38s\n"
     ]
    }
   ],
   "source": [
    "%%time\n",
    "models = m.train(target_name='hosp_GE',\n",
    "                 data=df,ini_date = '2020-05-01',\n",
    "                 end_date = '2022-04-30',\n",
    "                 save = True,\n",
    "                 path = './saved_models',\n",
    "                 name='hosp_GE')\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4ae43b49",
   "metadata": {},
   "source": [
    "### Method `forecast()`\n",
    "\n",
    "This method uses the models trained in the `train` method and applies them on the last date available (last value in df, or in the data of the date in end_date) and make the forecast making the forecast."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "38415411",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>lower</th>\n",
       "      <th>median</th>\n",
       "      <th>upper</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>date</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2022-05-01</th>\n",
       "      <td>3.659357</td>\n",
       "      <td>4.477327</td>\n",
       "      <td>5.478137</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2022-05-02</th>\n",
       "      <td>3.678122</td>\n",
       "      <td>4.535233</td>\n",
       "      <td>5.592075</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2022-05-03</th>\n",
       "      <td>3.674208</td>\n",
       "      <td>4.571385</td>\n",
       "      <td>5.687637</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2022-05-04</th>\n",
       "      <td>3.513954</td>\n",
       "      <td>4.615518</td>\n",
       "      <td>6.062404</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2022-05-05</th>\n",
       "      <td>3.800476</td>\n",
       "      <td>4.725615</td>\n",
       "      <td>5.875958</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               lower    median     upper\n",
       "date                                    \n",
       "2022-05-01  3.659357  4.477327  5.478137\n",
       "2022-05-02  3.678122  4.535233  5.592075\n",
       "2022-05-03  3.674208  4.571385  5.687637\n",
       "2022-05-04  3.513954  4.615518  6.062404\n",
       "2022-05-05  3.800476  4.725615  5.875958"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_f = m.forecast(df, end_date = '2022-04-30',  path = './saved_models', name='hosp_GE')\n",
    "\n",
    "df_f.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ec93c9b1",
   "metadata": {},
   "source": [
    "### Function `plot_forecast()`\n",
    "\n",
    "This function use the data to train the model and the output of the `forecast()` method to plot the forecast."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "38499e64",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plot_forecast(\n",
    "    df.loc[:'2022-04-30']['hosp_GE'][-90:],\n",
    "    df_f,\n",
    "    title = 'Forecast of hosp in GE',\n",
    "    xlabel=\"Date\",\n",
    "    ylabel=\"Incidence\", \n",
    "    save=False\n",
    "    )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "6cd8f8eb",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.9.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}