{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "# Estimación de la demanda de dinero"
   ]
  },
  {
   "cell_type": "markdown",
   "source": [
    "**Nota** Para ejecutar este cuaderno se requiere el paquete `bccr`. Si no lo tiene, ejecute la siguiente celda"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "outputs": [],
   "source": [
    "try:\n",
    "    import bccr\n",
    "except ImportError:\n",
    "    print('Module bccr missing. Installing it now')\n",
    "    !pip install bccr"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "Collapsed": "false",
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "from bccr import SW\n",
    "import numpy as np\n",
    "from matplotlib import rcParams\n",
    "import matplotlib.pyplot as plt\n",
    "plt.style.use('seaborn')\n",
    "import matplotlib.gridspec as gridspec\n",
    "\n",
    "import statsmodels.api as sm\n",
    "from statsmodels.formula.api import ols\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "Collapsed": "false",
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "plt.style.use('seaborn')\n",
    "\n",
    "# Cambiar tamaño de las fuentes\n",
    "rcParams['axes.titlesize'] = 20\n",
    "rcParams['axes.labelsize'] = 16\n",
    "rcParams['xtick.labelsize'] = 14\n",
    "rcParams['ytick.labelsize'] = 14"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "Collapsed": "false",
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": "                                                                                                                    DESCRIPCION          descripcion               Unidad    Medida  periodo\ncodigo                                                                                                                                                                                      \n1445                              Node('/BCCR/Sector Monetario y Financiero/Medio circulante sistema bancario nacional [1445]')     Medio circulante  Colón Costarricense  Millones  Mensual\n1479                            Node('/BCCR/Sector Monetario y Financiero/Medio circulante sistema financiero nacional [1479]')     Medio circulante  Colón Costarricense  Millones  Mensual\n2936    Node('/BCCR/Sector Monetario y Financiero/Medio circulante sistema financiero nacional [1479]/Otros activos netos [2...  Otros activos netos  Colón Costarricense  Millones  Mensual",
      "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>DESCRIPCION</th>\n      <th>descripcion</th>\n      <th>Unidad</th>\n      <th>Medida</th>\n      <th>periodo</th>\n    </tr>\n    <tr>\n      <th>codigo</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>1445</th>\n      <td>Node('/BCCR/Sector Monetario y Financiero/Medio circulante sistema bancario nacional [1445]')</td>\n      <td>Medio circulante</td>\n      <td>Colón Costarricense</td>\n      <td>Millones</td>\n      <td>Mensual</td>\n    </tr>\n    <tr>\n      <th>1479</th>\n      <td>Node('/BCCR/Sector Monetario y Financiero/Medio circulante sistema financiero nacional [1479]')</td>\n      <td>Medio circulante</td>\n      <td>Colón Costarricense</td>\n      <td>Millones</td>\n      <td>Mensual</td>\n    </tr>\n    <tr>\n      <th>2936</th>\n      <td>Node('/BCCR/Sector Monetario y Financiero/Medio circulante sistema financiero nacional [1479]/Otros activos netos [2...</td>\n      <td>Otros activos netos</td>\n      <td>Colón Costarricense</td>\n      <td>Millones</td>\n      <td>Mensual</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "SW.buscar('medio circulante')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "Collapsed": "false",
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": "                                                                          DESCRIPCION                                               descripcion      Unidad       Medida periodo\ncodigo                                                                                                                                                                          \n423     Node('/BCCR/Tasas de interés/Tasa básica pasiva calculada por el BCCR [423]')  Tasa Básica pasiva bruta calculada por el Banco Central.  Porcentaje  NO DEFINIDO  Diaria",
      "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>DESCRIPCION</th>\n      <th>descripcion</th>\n      <th>Unidad</th>\n      <th>Medida</th>\n      <th>periodo</th>\n    </tr>\n    <tr>\n      <th>codigo</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>423</th>\n      <td>Node('/BCCR/Tasas de interés/Tasa básica pasiva calculada por el BCCR [423]')</td>\n      <td>Tasa Básica pasiva bruta calculada por el Banco Central.</td>\n      <td>Porcentaje</td>\n      <td>NO DEFINIDO</td>\n      <td>Diaria</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "SW.buscar('tasa básica pasiva', frecuencia='D')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "Collapsed": "false",
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": "               IMAE         IPC            M1    Tbasica\nfecha                                                   \n1991-01   51.108817    8.064069  6.158123e+04  34.000000\n1991-02   42.665858    8.301969  6.024168e+04  35.000000\n1991-03   40.391637    8.407419  5.942290e+04  33.193548\n1991-04   40.185649    8.644489  6.078601e+04  33.000000\n1991-05   40.276545    8.794029  6.185368e+04  32.500000\n...             ...         ...           ...        ...\n2020-07  110.987099  106.127077  5.166828e+06   3.708065\n2020-08  110.584336  106.122788  5.206881e+06   3.635484\n2020-09  113.705524  106.411930  5.206211e+06   3.498333\n2020-10  118.613059  106.496597  5.061595e+06   3.293548\n2020-11  120.969090  106.498184  4.913216e+06   3.346667\n\n[359 rows x 4 columns]",
      "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>IMAE</th>\n      <th>IPC</th>\n      <th>M1</th>\n      <th>Tbasica</th>\n    </tr>\n    <tr>\n      <th>fecha</th>\n      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>1991-01</th>\n      <td>51.108817</td>\n      <td>8.064069</td>\n      <td>6.158123e+04</td>\n      <td>34.000000</td>\n    </tr>\n    <tr>\n      <th>1991-02</th>\n      <td>42.665858</td>\n      <td>8.301969</td>\n      <td>6.024168e+04</td>\n      <td>35.000000</td>\n    </tr>\n    <tr>\n      <th>1991-03</th>\n      <td>40.391637</td>\n      <td>8.407419</td>\n      <td>5.942290e+04</td>\n      <td>33.193548</td>\n    </tr>\n    <tr>\n      <th>1991-04</th>\n      <td>40.185649</td>\n      <td>8.644489</td>\n      <td>6.078601e+04</td>\n      <td>33.000000</td>\n    </tr>\n    <tr>\n      <th>1991-05</th>\n      <td>40.276545</td>\n      <td>8.794029</td>\n      <td>6.185368e+04</td>\n      <td>32.500000</td>\n    </tr>\n    <tr>\n      <th>...</th>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n    </tr>\n    <tr>\n      <th>2020-07</th>\n      <td>110.987099</td>\n      <td>106.127077</td>\n      <td>5.166828e+06</td>\n      <td>3.708065</td>\n    </tr>\n    <tr>\n      <th>2020-08</th>\n      <td>110.584336</td>\n      <td>106.122788</td>\n      <td>5.206881e+06</td>\n      <td>3.635484</td>\n    </tr>\n    <tr>\n      <th>2020-09</th>\n      <td>113.705524</td>\n      <td>106.411930</td>\n      <td>5.206211e+06</td>\n      <td>3.498333</td>\n    </tr>\n    <tr>\n      <th>2020-10</th>\n      <td>118.613059</td>\n      <td>106.496597</td>\n      <td>5.061595e+06</td>\n      <td>3.293548</td>\n    </tr>\n    <tr>\n      <th>2020-11</th>\n      <td>120.969090</td>\n      <td>106.498184</td>\n      <td>4.913216e+06</td>\n      <td>3.346667</td>\n    </tr>\n  </tbody>\n</table>\n<p>359 rows × 4 columns</p>\n</div>"
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "variables = dict(IMAE=35449,IPC=25482,M1=1445,Tbasica=423)\n",
    "datos = SW(**variables, func='mean', FechaInicio='1991m01', FechaFinal='2020m11').dropna()\n",
    "datos"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "Collapsed": "false",
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "res = ols('M1 ~ IMAE + IPC + Tbasica', data=np.log(datos)).fit()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "Collapsed": "false",
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": "<Figure size 720x360 with 3 Axes>",
      "image/png": "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\n"
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig = plt.figure(figsize=[10,5], tight_layout=True)\n",
    "gs = gridspec.GridSpec(2, 2)\n",
    "ax = fig.add_subplot(gs[0, :])\n",
    "axs0 = fig.add_subplot(gs[1,0])\n",
    "axs1 = fig.add_subplot(gs[1,1], sharey=axs0)\n",
    "\n",
    "res.resid.plot(title='Residuos de la regresión', ax=ax)\n",
    "\n",
    "OPCIONES = dict(lags=48, alpha=0.05, )\n",
    "sm.graphics.tsa.plot_acf(res.resid, ax=axs0, title='Autocorrelación',**OPCIONES);\n",
    "sm.graphics.tsa.plot_pacf(res.resid, ax=axs1, title='Autocorrelación parcial', **OPCIONES);\n",
    "axs0.set_xticks([0,12,24,36,48])\n",
    "axs1.set_xticks([0,12,24,36,48])\n",
    "\n",
    "fig.savefig('residuos-demanda-dinero.pdf', bbox_inches='tight')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "Collapsed": "false",
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": "<class 'statsmodels.iolib.summary.Summary'>\n\"\"\"\n                            OLS Regression Results                            \n==============================================================================\nDep. Variable:                     M1   R-squared:                       0.994\nModel:                            OLS   Adj. R-squared:                  0.994\nMethod:                 Least Squares   F-statistic:                 1.944e+04\nDate:                Sat, 23 Apr 2022   Prob (F-statistic):               0.00\nTime:                        11:40:55   Log-Likelihood:                 335.36\nNo. Observations:                 359   AIC:                            -662.7\nDf Residuals:                     355   BIC:                            -647.2\nDf Model:                           3                                         \nCovariance Type:            nonrobust                                         \n==============================================================================\n                 coef    std err          t      P>|t|      [0.025      0.975]\n------------------------------------------------------------------------------\nIntercept      6.3294      0.298     21.263      0.000       5.744       6.915\nIMAE           1.0242      0.079     13.044      0.000       0.870       1.179\nIPC            0.9268      0.028     33.508      0.000       0.872       0.981\nTbasica       -0.3519      0.022    -15.919      0.000      -0.395      -0.308\n==============================================================================\nOmnibus:                      115.244   Durbin-Watson:                   0.450\nProb(Omnibus):                  0.000   Jarque-Bera (JB):              463.868\nSkew:                           1.349   Prob(JB):                    1.87e-101\nKurtosis:                       7.872   Cond. No.                         390.\n==============================================================================\n\nNotes:\n[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n\"\"\"",
      "text/html": "<table class=\"simpletable\">\n<caption>OLS Regression Results</caption>\n<tr>\n  <th>Dep. Variable:</th>           <td>M1</td>        <th>  R-squared:         </th> <td>   0.994</td> \n</tr>\n<tr>\n  <th>Model:</th>                   <td>OLS</td>       <th>  Adj. R-squared:    </th> <td>   0.994</td> \n</tr>\n<tr>\n  <th>Method:</th>             <td>Least Squares</td>  <th>  F-statistic:       </th> <td>1.944e+04</td>\n</tr>\n<tr>\n  <th>Date:</th>             <td>Sat, 23 Apr 2022</td> <th>  Prob (F-statistic):</th>  <td>  0.00</td>  \n</tr>\n<tr>\n  <th>Time:</th>                 <td>11:40:55</td>     <th>  Log-Likelihood:    </th> <td>  335.36</td> \n</tr>\n<tr>\n  <th>No. Observations:</th>      <td>   359</td>      <th>  AIC:               </th> <td>  -662.7</td> \n</tr>\n<tr>\n  <th>Df Residuals:</th>          <td>   355</td>      <th>  BIC:               </th> <td>  -647.2</td> \n</tr>\n<tr>\n  <th>Df Model:</th>              <td>     3</td>      <th>                     </th>     <td> </td>    \n</tr>\n<tr>\n  <th>Covariance Type:</th>      <td>nonrobust</td>    <th>                     </th>     <td> </td>    \n</tr>\n</table>\n<table class=\"simpletable\">\n<tr>\n      <td></td>         <th>coef</th>     <th>std err</th>      <th>t</th>      <th>P>|t|</th>  <th>[0.025</th>    <th>0.975]</th>  \n</tr>\n<tr>\n  <th>Intercept</th> <td>    6.3294</td> <td>    0.298</td> <td>   21.263</td> <td> 0.000</td> <td>    5.744</td> <td>    6.915</td>\n</tr>\n<tr>\n  <th>IMAE</th>      <td>    1.0242</td> <td>    0.079</td> <td>   13.044</td> <td> 0.000</td> <td>    0.870</td> <td>    1.179</td>\n</tr>\n<tr>\n  <th>IPC</th>       <td>    0.9268</td> <td>    0.028</td> <td>   33.508</td> <td> 0.000</td> <td>    0.872</td> <td>    0.981</td>\n</tr>\n<tr>\n  <th>Tbasica</th>   <td>   -0.3519</td> <td>    0.022</td> <td>  -15.919</td> <td> 0.000</td> <td>   -0.395</td> <td>   -0.308</td>\n</tr>\n</table>\n<table class=\"simpletable\">\n<tr>\n  <th>Omnibus:</th>       <td>115.244</td> <th>  Durbin-Watson:     </th> <td>   0.450</td> \n</tr>\n<tr>\n  <th>Prob(Omnibus):</th> <td> 0.000</td>  <th>  Jarque-Bera (JB):  </th> <td> 463.868</td> \n</tr>\n<tr>\n  <th>Skew:</th>          <td> 1.349</td>  <th>  Prob(JB):          </th> <td>1.87e-101</td>\n</tr>\n<tr>\n  <th>Kurtosis:</th>      <td> 7.872</td>  <th>  Cond. No.          </th> <td>    390.</td> \n</tr>\n</table><br/><br/>Notes:<br/>[1] Standard Errors assume that the covariance matrix of the errors is correctly specified."
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sss = res.summary()\n",
    "sss"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": "<class 'statsmodels.iolib.table.SimpleTable'>",
      "text/html": "<table class=\"simpletable\">\n<tr>\n  <th>Omnibus:</th>       <td>115.244</td> <th>  Durbin-Watson:     </th> <td>   0.450</td> \n</tr>\n<tr>\n  <th>Prob(Omnibus):</th> <td> 0.000</td>  <th>  Jarque-Bera (JB):  </th> <td> 463.868</td> \n</tr>\n<tr>\n  <th>Skew:</th>          <td> 1.349</td>  <th>  Prob(JB):          </th> <td>1.87e-101</td>\n</tr>\n<tr>\n  <th>Kurtosis:</th>      <td> 7.872</td>  <th>  Cond. No.          </th> <td>    390.</td> \n</tr>\n</table>"
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sss.tables[2]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "Collapsed": "false",
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "sss = res.summary()\n",
    "\n",
    "with open('regresion-M1.tex','w') as file:\n",
    "    file.write(sss.tables[1].as_latex_tabular())\n",
    "    file.write(sss.tables[2].as_latex_tabular())"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.8.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}