{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Regression"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Loading required package: daltoolbox\n",
      "\n",
      "Registered S3 method overwritten by 'quantmod':\n",
      "  method            from\n",
      "  as.zoo.data.frame zoo \n",
      "\n",
      "\n",
      "Attaching package: ‘daltoolbox’\n",
      "\n",
      "\n",
      "The following object is masked from ‘package:base’:\n",
      "\n",
      "    transform\n",
      "\n",
      "\n",
      "Loading required package: MASS\n",
      "\n",
      "Loading required package: plotly\n",
      "\n",
      "Loading required package: ggplot2\n",
      "\n",
      "\n",
      "Attaching package: ‘plotly’\n",
      "\n",
      "\n",
      "The following object is masked from ‘package:ggplot2’:\n",
      "\n",
      "    last_plot\n",
      "\n",
      "\n",
      "The following object is masked from ‘package:MASS’:\n",
      "\n",
      "    select\n",
      "\n",
      "\n",
      "The following object is masked from ‘package:stats’:\n",
      "\n",
      "    filter\n",
      "\n",
      "\n",
      "The following object is masked from ‘package:graphics’:\n",
      "\n",
      "    layout\n",
      "\n",
      "\n",
      "Loading required package: reshape2\n",
      "\n"
     ]
    }
   ],
   "source": [
    "# DAL ToolBox\n",
    "# version 1.0.77\n",
    "\n",
    "source(\"https://raw.githubusercontent.com/cefet-rj-dal/daltoolbox-examples/main/jupyter.R\")\n",
    "\n",
    "load_library(\"daltoolbox\")\n",
    "load_library(\"MASS\")\n",
    "load_library(\"plotly\")\n",
    "load_library(\"reshape2\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Dataset\n",
    "Both independent and dependent variables are numeric. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<table class=\"dataframe\">\n",
       "<caption>A data.frame: 6 × 14</caption>\n",
       "<thead>\n",
       "\t<tr><th></th><th scope=col>crim</th><th scope=col>zn</th><th scope=col>indus</th><th scope=col>chas</th><th scope=col>nox</th><th scope=col>rm</th><th scope=col>age</th><th scope=col>dis</th><th scope=col>rad</th><th scope=col>tax</th><th scope=col>ptratio</th><th scope=col>black</th><th scope=col>lstat</th><th scope=col>medv</th></tr>\n",
       "\t<tr><th></th><th scope=col>&lt;dbl&gt;</th><th scope=col>&lt;dbl&gt;</th><th scope=col>&lt;dbl&gt;</th><th scope=col>&lt;int&gt;</th><th scope=col>&lt;dbl&gt;</th><th scope=col>&lt;dbl&gt;</th><th scope=col>&lt;dbl&gt;</th><th scope=col>&lt;dbl&gt;</th><th scope=col>&lt;int&gt;</th><th scope=col>&lt;dbl&gt;</th><th scope=col>&lt;dbl&gt;</th><th scope=col>&lt;dbl&gt;</th><th scope=col>&lt;dbl&gt;</th><th scope=col>&lt;dbl&gt;</th></tr>\n",
       "</thead>\n",
       "<tbody>\n",
       "\t<tr><th scope=row>1</th><td>0.00632</td><td>18</td><td>2.31</td><td>0</td><td>0.538</td><td>6.575</td><td>65.2</td><td>4.0900</td><td>1</td><td>296</td><td>15.3</td><td>396.90</td><td>4.98</td><td>24.0</td></tr>\n",
       "\t<tr><th scope=row>2</th><td>0.02731</td><td> 0</td><td>7.07</td><td>0</td><td>0.469</td><td>6.421</td><td>78.9</td><td>4.9671</td><td>2</td><td>242</td><td>17.8</td><td>396.90</td><td>9.14</td><td>21.6</td></tr>\n",
       "\t<tr><th scope=row>3</th><td>0.02729</td><td> 0</td><td>7.07</td><td>0</td><td>0.469</td><td>7.185</td><td>61.1</td><td>4.9671</td><td>2</td><td>242</td><td>17.8</td><td>392.83</td><td>4.03</td><td>34.7</td></tr>\n",
       "\t<tr><th scope=row>4</th><td>0.03237</td><td> 0</td><td>2.18</td><td>0</td><td>0.458</td><td>6.998</td><td>45.8</td><td>6.0622</td><td>3</td><td>222</td><td>18.7</td><td>394.63</td><td>2.94</td><td>33.4</td></tr>\n",
       "\t<tr><th scope=row>5</th><td>0.06905</td><td> 0</td><td>2.18</td><td>0</td><td>0.458</td><td>7.147</td><td>54.2</td><td>6.0622</td><td>3</td><td>222</td><td>18.7</td><td>396.90</td><td>5.33</td><td>36.2</td></tr>\n",
       "\t<tr><th scope=row>6</th><td>0.02985</td><td> 0</td><td>2.18</td><td>0</td><td>0.458</td><td>6.430</td><td>58.7</td><td>6.0622</td><td>3</td><td>222</td><td>18.7</td><td>394.12</td><td>5.21</td><td>28.7</td></tr>\n",
       "</tbody>\n",
       "</table>\n"
      ],
      "text/latex": [
       "A data.frame: 6 × 14\n",
       "\\begin{tabular}{r|llllllllllllll}\n",
       "  & crim & zn & indus & chas & nox & rm & age & dis & rad & tax & ptratio & black & lstat & medv\\\\\n",
       "  & <dbl> & <dbl> & <dbl> & <int> & <dbl> & <dbl> & <dbl> & <dbl> & <int> & <dbl> & <dbl> & <dbl> & <dbl> & <dbl>\\\\\n",
       "\\hline\n",
       "\t1 & 0.00632 & 18 & 2.31 & 0 & 0.538 & 6.575 & 65.2 & 4.0900 & 1 & 296 & 15.3 & 396.90 & 4.98 & 24.0\\\\\n",
       "\t2 & 0.02731 &  0 & 7.07 & 0 & 0.469 & 6.421 & 78.9 & 4.9671 & 2 & 242 & 17.8 & 396.90 & 9.14 & 21.6\\\\\n",
       "\t3 & 0.02729 &  0 & 7.07 & 0 & 0.469 & 7.185 & 61.1 & 4.9671 & 2 & 242 & 17.8 & 392.83 & 4.03 & 34.7\\\\\n",
       "\t4 & 0.03237 &  0 & 2.18 & 0 & 0.458 & 6.998 & 45.8 & 6.0622 & 3 & 222 & 18.7 & 394.63 & 2.94 & 33.4\\\\\n",
       "\t5 & 0.06905 &  0 & 2.18 & 0 & 0.458 & 7.147 & 54.2 & 6.0622 & 3 & 222 & 18.7 & 396.90 & 5.33 & 36.2\\\\\n",
       "\t6 & 0.02985 &  0 & 2.18 & 0 & 0.458 & 6.430 & 58.7 & 6.0622 & 3 & 222 & 18.7 & 394.12 & 5.21 & 28.7\\\\\n",
       "\\end{tabular}\n"
      ],
      "text/markdown": [
       "\n",
       "A data.frame: 6 × 14\n",
       "\n",
       "| <!--/--> | crim &lt;dbl&gt; | zn &lt;dbl&gt; | indus &lt;dbl&gt; | chas &lt;int&gt; | nox &lt;dbl&gt; | rm &lt;dbl&gt; | age &lt;dbl&gt; | dis &lt;dbl&gt; | rad &lt;int&gt; | tax &lt;dbl&gt; | ptratio &lt;dbl&gt; | black &lt;dbl&gt; | lstat &lt;dbl&gt; | medv &lt;dbl&gt; |\n",
       "|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|\n",
       "| 1 | 0.00632 | 18 | 2.31 | 0 | 0.538 | 6.575 | 65.2 | 4.0900 | 1 | 296 | 15.3 | 396.90 | 4.98 | 24.0 |\n",
       "| 2 | 0.02731 |  0 | 7.07 | 0 | 0.469 | 6.421 | 78.9 | 4.9671 | 2 | 242 | 17.8 | 396.90 | 9.14 | 21.6 |\n",
       "| 3 | 0.02729 |  0 | 7.07 | 0 | 0.469 | 7.185 | 61.1 | 4.9671 | 2 | 242 | 17.8 | 392.83 | 4.03 | 34.7 |\n",
       "| 4 | 0.03237 |  0 | 2.18 | 0 | 0.458 | 6.998 | 45.8 | 6.0622 | 3 | 222 | 18.7 | 394.63 | 2.94 | 33.4 |\n",
       "| 5 | 0.06905 |  0 | 2.18 | 0 | 0.458 | 7.147 | 54.2 | 6.0622 | 3 | 222 | 18.7 | 396.90 | 5.33 | 36.2 |\n",
       "| 6 | 0.02985 |  0 | 2.18 | 0 | 0.458 | 6.430 | 58.7 | 6.0622 | 3 | 222 | 18.7 | 394.12 | 5.21 | 28.7 |\n",
       "\n"
      ],
      "text/plain": [
       "  crim    zn indus chas nox   rm    age  dis    rad tax ptratio black  lstat\n",
       "1 0.00632 18 2.31  0    0.538 6.575 65.2 4.0900 1   296 15.3    396.90 4.98 \n",
       "2 0.02731  0 7.07  0    0.469 6.421 78.9 4.9671 2   242 17.8    396.90 9.14 \n",
       "3 0.02729  0 7.07  0    0.469 7.185 61.1 4.9671 2   242 17.8    392.83 4.03 \n",
       "4 0.03237  0 2.18  0    0.458 6.998 45.8 6.0622 3   222 18.7    394.63 2.94 \n",
       "5 0.06905  0 2.18  0    0.458 7.147 54.2 6.0622 3   222 18.7    396.90 5.33 \n",
       "6 0.02985  0 2.18  0    0.458 6.430 58.7 6.0622 3   222 18.7    394.12 5.21 \n",
       "  medv\n",
       "1 24.0\n",
       "2 21.6\n",
       "3 34.7\n",
       "4 33.4\n",
       "5 36.2\n",
       "6 28.7"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "head(Boston)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Fitting a first model\n",
    "Explaining house price using lower status population variable.\n",
    "\n",
    "$lm$ builds the model.\n",
    "\n",
    "$summary$ describes the significance of the built model."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\n",
       "Call:\n",
       "lm(formula = medv ~ lstat, data = Boston)\n",
       "\n",
       "Residuals:\n",
       "    Min      1Q  Median      3Q     Max \n",
       "-15.168  -3.990  -1.318   2.034  24.500 \n",
       "\n",
       "Coefficients:\n",
       "            Estimate Std. Error t value Pr(>|t|)    \n",
       "(Intercept) 34.55384    0.56263   61.41   <2e-16 ***\n",
       "lstat       -0.95005    0.03873  -24.53   <2e-16 ***\n",
       "---\n",
       "Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1\n",
       "\n",
       "Residual standard error: 6.216 on 504 degrees of freedom\n",
       "Multiple R-squared:  0.5441,\tAdjusted R-squared:  0.5432 \n",
       "F-statistic: 601.6 on 1 and 504 DF,  p-value: < 2.2e-16\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "lm.fit = lm(medv ~ lstat, data = Boston)\n",
    "\n",
    "summary(lm.fit)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## prediction\n",
    "The $predict$ function makes predictions from the adjusted model.\n",
    "\n",
    "The predictions can be presented with either $confidence$ and $prediction$ intervals. \n",
    "\n",
    "These intervals can be analyzed at https://statisticsbyjim.com/hypothesis-testing/confidence-prediction-tolerance-intervals/\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<table class=\"dataframe\">\n",
       "<caption>A matrix: 3 × 3 of type dbl</caption>\n",
       "<thead>\n",
       "\t<tr><th></th><th scope=col>fit</th><th scope=col>lwr</th><th scope=col>upr</th></tr>\n",
       "</thead>\n",
       "<tbody>\n",
       "\t<tr><th scope=row>1</th><td>29.80359</td><td>29.00741</td><td>30.59978</td></tr>\n",
       "\t<tr><th scope=row>2</th><td>25.05335</td><td>24.47413</td><td>25.63256</td></tr>\n",
       "\t<tr><th scope=row>3</th><td>20.30310</td><td>19.73159</td><td>20.87461</td></tr>\n",
       "</tbody>\n",
       "</table>\n"
      ],
      "text/latex": [
       "A matrix: 3 × 3 of type dbl\n",
       "\\begin{tabular}{r|lll}\n",
       "  & fit & lwr & upr\\\\\n",
       "\\hline\n",
       "\t1 & 29.80359 & 29.00741 & 30.59978\\\\\n",
       "\t2 & 25.05335 & 24.47413 & 25.63256\\\\\n",
       "\t3 & 20.30310 & 19.73159 & 20.87461\\\\\n",
       "\\end{tabular}\n"
      ],
      "text/markdown": [
       "\n",
       "A matrix: 3 × 3 of type dbl\n",
       "\n",
       "| <!--/--> | fit | lwr | upr |\n",
       "|---|---|---|---|\n",
       "| 1 | 29.80359 | 29.00741 | 30.59978 |\n",
       "| 2 | 25.05335 | 24.47413 | 25.63256 |\n",
       "| 3 | 20.30310 | 19.73159 | 20.87461 |\n",
       "\n"
      ],
      "text/plain": [
       "  fit      lwr      upr     \n",
       "1 29.80359 29.00741 30.59978\n",
       "2 25.05335 24.47413 25.63256\n",
       "3 20.30310 19.73159 20.87461"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<table class=\"dataframe\">\n",
       "<caption>A matrix: 3 × 3 of type dbl</caption>\n",
       "<thead>\n",
       "\t<tr><th></th><th scope=col>fit</th><th scope=col>lwr</th><th scope=col>upr</th></tr>\n",
       "</thead>\n",
       "<tbody>\n",
       "\t<tr><th scope=row>1</th><td>29.80359</td><td>17.565675</td><td>42.04151</td></tr>\n",
       "\t<tr><th scope=row>2</th><td>25.05335</td><td>12.827626</td><td>37.27907</td></tr>\n",
       "\t<tr><th scope=row>3</th><td>20.30310</td><td> 8.077742</td><td>32.52846</td></tr>\n",
       "</tbody>\n",
       "</table>\n"
      ],
      "text/latex": [
       "A matrix: 3 × 3 of type dbl\n",
       "\\begin{tabular}{r|lll}\n",
       "  & fit & lwr & upr\\\\\n",
       "\\hline\n",
       "\t1 & 29.80359 & 17.565675 & 42.04151\\\\\n",
       "\t2 & 25.05335 & 12.827626 & 37.27907\\\\\n",
       "\t3 & 20.30310 &  8.077742 & 32.52846\\\\\n",
       "\\end{tabular}\n"
      ],
      "text/markdown": [
       "\n",
       "A matrix: 3 × 3 of type dbl\n",
       "\n",
       "| <!--/--> | fit | lwr | upr |\n",
       "|---|---|---|---|\n",
       "| 1 | 29.80359 | 17.565675 | 42.04151 |\n",
       "| 2 | 25.05335 | 12.827626 | 37.27907 |\n",
       "| 3 | 20.30310 |  8.077742 | 32.52846 |\n",
       "\n"
      ],
      "text/plain": [
       "  fit      lwr       upr     \n",
       "1 29.80359 17.565675 42.04151\n",
       "2 25.05335 12.827626 37.27907\n",
       "3 20.30310  8.077742 32.52846"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "predict(lm.fit, data.frame(lstat =(c(5, 10, 15))), interval = \"confidence\")\n",
    "predict(lm.fit, data.frame(lstat =(c(5, 10, 15))), interval = \"prediction\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Plotting the regression model\n",
    "\n",
    "It is a good practice to plot the regression model. It enables us to have a feeling of its quality."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAA0gAAANICAIAAAByhViMAAAACXBIWXMAABJ0AAASdAHeZh94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\nMZ0CUuT41AAAAABJRU5ErkJggg==",
      "text/plain": [
       "plot without title"
      ]
     },
     "metadata": {
      "image/png": {
       "height": 420,
       "width": 420
      }
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "axis_x <- seq(min(Boston$lstat), max(Boston$lstat), by = 0.5)\n",
    "axis_y <- predict(lm.fit, data.frame(lstat=axis_x))\n",
    "\n",
    "data_adj = data.frame(lstat=axis_x, medv=axis_y)\n",
    "\n",
    "ggplot(Boston) + geom_point(aes(x = lstat, y = medv)) + geom_line(data=data_adj,aes(x=lstat,y=medv), color=\"Blue\") + theme_bw(base_size = 10) "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Polynomial regression\n",
    "\n",
    "It is possible to introduce polynomial dimensions of independent data. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\n",
       "Call:\n",
       "lm(formula = medv ~ lstat + I(lstat^2), data = Boston)\n",
       "\n",
       "Residuals:\n",
       "     Min       1Q   Median       3Q      Max \n",
       "-15.2834  -3.8313  -0.5295   2.3095  25.4148 \n",
       "\n",
       "Coefficients:\n",
       "             Estimate Std. Error t value Pr(>|t|)    \n",
       "(Intercept) 42.862007   0.872084   49.15   <2e-16 ***\n",
       "lstat       -2.332821   0.123803  -18.84   <2e-16 ***\n",
       "I(lstat^2)   0.043547   0.003745   11.63   <2e-16 ***\n",
       "---\n",
       "Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1\n",
       "\n",
       "Residual standard error: 5.524 on 503 degrees of freedom\n",
       "Multiple R-squared:  0.6407,\tAdjusted R-squared:  0.6393 \n",
       "F-statistic: 448.5 on 2 and 503 DF,  p-value: < 2.2e-16\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "lm.fit_p =lm(medv~lstat+I(lstat^2), data=Boston)\n",
    "summary (lm.fit_p)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Plotting the polynomial regression model\n",
    "\n",
    "It seems to be better adjusted with the data. Is it significant?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAA0gAAANICAIAAAByhViMAAAACXBIWXMAABJ0AAASdAHeZh94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",
      "text/plain": [
       "plot without title"
      ]
     },
     "metadata": {
      "image/png": {
       "height": 420,
       "width": 420
      }
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "axis_x <- seq(min(Boston$lstat), max(Boston$lstat), by = 0.5)\n",
    "axis_x2 <- axis_x^2\n",
    "axis_y <- predict(lm.fit_p, data.frame(lstat=axis_x, `I(lstat^2)`=axis_x2))\n",
    "\n",
    "\n",
    "data_adj = data.frame(lstat=axis_x, medv=axis_y)\n",
    "ggplot(Boston) + geom_point(aes(x = lstat, y = medv)) + geom_line(data=data_adj,aes(x=lstat,y=medv), color=\"Blue\") + theme_bw(base_size = 10) "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## ANOVA test\n",
    "\n",
    "It is possible to check if a built model is significantly better than another model using the ANOVA test. \n",
    "\n",
    "The null hypothesis is that both models are not different ($\\operatorname{p-value} > 5\\%$). The alternative hypothesis says that they are different ($\\operatorname{p-value} < 5\\%$). "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<table class=\"dataframe\">\n",
       "<caption>A anova: 2 × 6</caption>\n",
       "<thead>\n",
       "\t<tr><th></th><th scope=col>Res.Df</th><th scope=col>RSS</th><th scope=col>Df</th><th scope=col>Sum of Sq</th><th scope=col>F</th><th scope=col>Pr(&gt;F)</th></tr>\n",
       "\t<tr><th></th><th scope=col>&lt;dbl&gt;</th><th scope=col>&lt;dbl&gt;</th><th scope=col>&lt;dbl&gt;</th><th scope=col>&lt;dbl&gt;</th><th scope=col>&lt;dbl&gt;</th><th scope=col>&lt;dbl&gt;</th></tr>\n",
       "</thead>\n",
       "<tbody>\n",
       "\t<tr><th scope=row>1</th><td>504</td><td>19472.38</td><td>NA</td><td>      NA</td><td>      NA</td><td>          NA</td></tr>\n",
       "\t<tr><th scope=row>2</th><td>503</td><td>15347.24</td><td> 1</td><td>4125.138</td><td>135.1998</td><td>7.630116e-28</td></tr>\n",
       "</tbody>\n",
       "</table>\n"
      ],
      "text/latex": [
       "A anova: 2 × 6\n",
       "\\begin{tabular}{r|llllll}\n",
       "  & Res.Df & RSS & Df & Sum of Sq & F & Pr(>F)\\\\\n",
       "  & <dbl> & <dbl> & <dbl> & <dbl> & <dbl> & <dbl>\\\\\n",
       "\\hline\n",
       "\t1 & 504 & 19472.38 & NA &       NA &       NA &           NA\\\\\n",
       "\t2 & 503 & 15347.24 &  1 & 4125.138 & 135.1998 & 7.630116e-28\\\\\n",
       "\\end{tabular}\n"
      ],
      "text/markdown": [
       "\n",
       "A anova: 2 × 6\n",
       "\n",
       "| <!--/--> | Res.Df &lt;dbl&gt; | RSS &lt;dbl&gt; | Df &lt;dbl&gt; | Sum of Sq &lt;dbl&gt; | F &lt;dbl&gt; | Pr(&gt;F) &lt;dbl&gt; |\n",
       "|---|---|---|---|---|---|---|\n",
       "| 1 | 504 | 19472.38 | NA |       NA |       NA |           NA |\n",
       "| 2 | 503 | 15347.24 |  1 | 4125.138 | 135.1998 | 7.630116e-28 |\n",
       "\n"
      ],
      "text/plain": [
       "  Res.Df RSS      Df Sum of Sq F        Pr(>F)      \n",
       "1 504    19472.38 NA       NA        NA           NA\n",
       "2 503    15347.24  1 4125.138  135.1998 7.630116e-28"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "anova(lm.fit, lm.fit_p)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Multiple regression\n",
    "\n",
    "It is possible to use more than one dimension as independent data for the regression model. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\n",
       "Call:\n",
       "lm(formula = medv ~ lstat + age, data = Boston)\n",
       "\n",
       "Residuals:\n",
       "    Min      1Q  Median      3Q     Max \n",
       "-15.981  -3.978  -1.283   1.968  23.158 \n",
       "\n",
       "Coefficients:\n",
       "            Estimate Std. Error t value Pr(>|t|)    \n",
       "(Intercept) 33.22276    0.73085  45.458  < 2e-16 ***\n",
       "lstat       -1.03207    0.04819 -21.416  < 2e-16 ***\n",
       "age          0.03454    0.01223   2.826  0.00491 ** \n",
       "---\n",
       "Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1\n",
       "\n",
       "Residual standard error: 6.173 on 503 degrees of freedom\n",
       "Multiple R-squared:  0.5513,\tAdjusted R-squared:  0.5495 \n",
       "F-statistic:   309 on 2 and 503 DF,  p-value: < 2.2e-16\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "lm.fit2 =lm(medv~lstat+age, data=Boston)\n",
    "summary (lm.fit2)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Checking the significance of the model\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<table class=\"dataframe\">\n",
       "<caption>A anova: 2 × 6</caption>\n",
       "<thead>\n",
       "\t<tr><th></th><th scope=col>Res.Df</th><th scope=col>RSS</th><th scope=col>Df</th><th scope=col>Sum of Sq</th><th scope=col>F</th><th scope=col>Pr(&gt;F)</th></tr>\n",
       "\t<tr><th></th><th scope=col>&lt;dbl&gt;</th><th scope=col>&lt;dbl&gt;</th><th scope=col>&lt;dbl&gt;</th><th scope=col>&lt;dbl&gt;</th><th scope=col>&lt;dbl&gt;</th><th scope=col>&lt;dbl&gt;</th></tr>\n",
       "</thead>\n",
       "<tbody>\n",
       "\t<tr><th scope=row>1</th><td>504</td><td>19472.38</td><td>NA</td><td>      NA</td><td>      NA</td><td>         NA</td></tr>\n",
       "\t<tr><th scope=row>2</th><td>503</td><td>19168.13</td><td> 1</td><td>304.2528</td><td>7.984043</td><td>0.004906776</td></tr>\n",
       "</tbody>\n",
       "</table>\n"
      ],
      "text/latex": [
       "A anova: 2 × 6\n",
       "\\begin{tabular}{r|llllll}\n",
       "  & Res.Df & RSS & Df & Sum of Sq & F & Pr(>F)\\\\\n",
       "  & <dbl> & <dbl> & <dbl> & <dbl> & <dbl> & <dbl>\\\\\n",
       "\\hline\n",
       "\t1 & 504 & 19472.38 & NA &       NA &       NA &          NA\\\\\n",
       "\t2 & 503 & 19168.13 &  1 & 304.2528 & 7.984043 & 0.004906776\\\\\n",
       "\\end{tabular}\n"
      ],
      "text/markdown": [
       "\n",
       "A anova: 2 × 6\n",
       "\n",
       "| <!--/--> | Res.Df &lt;dbl&gt; | RSS &lt;dbl&gt; | Df &lt;dbl&gt; | Sum of Sq &lt;dbl&gt; | F &lt;dbl&gt; | Pr(&gt;F) &lt;dbl&gt; |\n",
       "|---|---|---|---|---|---|---|\n",
       "| 1 | 504 | 19472.38 | NA |       NA |       NA |          NA |\n",
       "| 2 | 503 | 19168.13 |  1 | 304.2528 | 7.984043 | 0.004906776 |\n",
       "\n"
      ],
      "text/plain": [
       "  Res.Df RSS      Df Sum of Sq F        Pr(>F)     \n",
       "1 504    19472.38 NA       NA        NA          NA\n",
       "2 503    19168.13  1 304.2528  7.984043 0.004906776"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "anova(lm.fit ,lm.fit2)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Logistic Regression\n",
    "In this example the predicted dependent variable is categorical."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<table class=\"dataframe\">\n",
       "<caption>A data.frame: 6 × 5</caption>\n",
       "<thead>\n",
       "\t<tr><th></th><th scope=col>Sepal.Length</th><th scope=col>Sepal.Width</th><th scope=col>Petal.Length</th><th scope=col>Petal.Width</th><th scope=col>Species</th></tr>\n",
       "\t<tr><th></th><th scope=col>&lt;dbl&gt;</th><th scope=col>&lt;dbl&gt;</th><th scope=col>&lt;dbl&gt;</th><th scope=col>&lt;dbl&gt;</th><th scope=col>&lt;fct&gt;</th></tr>\n",
       "</thead>\n",
       "<tbody>\n",
       "\t<tr><th scope=row>1</th><td>5.1</td><td>3.5</td><td>1.4</td><td>0.2</td><td>setosa</td></tr>\n",
       "\t<tr><th scope=row>2</th><td>4.9</td><td>3.0</td><td>1.4</td><td>0.2</td><td>setosa</td></tr>\n",
       "\t<tr><th scope=row>3</th><td>4.7</td><td>3.2</td><td>1.3</td><td>0.2</td><td>setosa</td></tr>\n",
       "\t<tr><th scope=row>4</th><td>4.6</td><td>3.1</td><td>1.5</td><td>0.2</td><td>setosa</td></tr>\n",
       "\t<tr><th scope=row>5</th><td>5.0</td><td>3.6</td><td>1.4</td><td>0.2</td><td>setosa</td></tr>\n",
       "\t<tr><th scope=row>6</th><td>5.4</td><td>3.9</td><td>1.7</td><td>0.4</td><td>setosa</td></tr>\n",
       "</tbody>\n",
       "</table>\n"
      ],
      "text/latex": [
       "A data.frame: 6 × 5\n",
       "\\begin{tabular}{r|lllll}\n",
       "  & Sepal.Length & Sepal.Width & Petal.Length & Petal.Width & Species\\\\\n",
       "  & <dbl> & <dbl> & <dbl> & <dbl> & <fct>\\\\\n",
       "\\hline\n",
       "\t1 & 5.1 & 3.5 & 1.4 & 0.2 & setosa\\\\\n",
       "\t2 & 4.9 & 3.0 & 1.4 & 0.2 & setosa\\\\\n",
       "\t3 & 4.7 & 3.2 & 1.3 & 0.2 & setosa\\\\\n",
       "\t4 & 4.6 & 3.1 & 1.5 & 0.2 & setosa\\\\\n",
       "\t5 & 5.0 & 3.6 & 1.4 & 0.2 & setosa\\\\\n",
       "\t6 & 5.4 & 3.9 & 1.7 & 0.4 & setosa\\\\\n",
       "\\end{tabular}\n"
      ],
      "text/markdown": [
       "\n",
       "A data.frame: 6 × 5\n",
       "\n",
       "| <!--/--> | Sepal.Length &lt;dbl&gt; | Sepal.Width &lt;dbl&gt; | Petal.Length &lt;dbl&gt; | Petal.Width &lt;dbl&gt; | Species &lt;fct&gt; |\n",
       "|---|---|---|---|---|---|\n",
       "| 1 | 5.1 | 3.5 | 1.4 | 0.2 | setosa |\n",
       "| 2 | 4.9 | 3.0 | 1.4 | 0.2 | setosa |\n",
       "| 3 | 4.7 | 3.2 | 1.3 | 0.2 | setosa |\n",
       "| 4 | 4.6 | 3.1 | 1.5 | 0.2 | setosa |\n",
       "| 5 | 5.0 | 3.6 | 1.4 | 0.2 | setosa |\n",
       "| 6 | 5.4 | 3.9 | 1.7 | 0.4 | setosa |\n",
       "\n"
      ],
      "text/plain": [
       "  Sepal.Length Sepal.Width Petal.Length Petal.Width Species\n",
       "1 5.1          3.5         1.4          0.2         setosa \n",
       "2 4.9          3.0         1.4          0.2         setosa \n",
       "3 4.7          3.2         1.3          0.2         setosa \n",
       "4 4.6          3.1         1.5          0.2         setosa \n",
       "5 5.0          3.6         1.4          0.2         setosa \n",
       "6 5.4          3.9         1.7          0.4         setosa "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "head(iris)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "To make the problem simpler, let us assume that we intend to predict if a species is $versicolor$ or if it is $other$ species. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "data <- iris\n",
    "data$versicolor <- as.integer(data$Species==\"versicolor\")\n",
    "data$Species <- c('other', 'versicolor')[data$versicolor+1]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Using preprocessing functions, we separate both training and test data. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<table class=\"dataframe\">\n",
       "<caption>A data.frame: 6 × 6</caption>\n",
       "<thead>\n",
       "\t<tr><th></th><th scope=col>Sepal.Length</th><th scope=col>Sepal.Width</th><th scope=col>Petal.Length</th><th scope=col>Petal.Width</th><th scope=col>Species</th><th scope=col>versicolor</th></tr>\n",
       "\t<tr><th></th><th scope=col>&lt;dbl&gt;</th><th scope=col>&lt;dbl&gt;</th><th scope=col>&lt;dbl&gt;</th><th scope=col>&lt;dbl&gt;</th><th scope=col>&lt;chr&gt;</th><th scope=col>&lt;int&gt;</th></tr>\n",
       "</thead>\n",
       "<tbody>\n",
       "\t<tr><th scope=row>116</th><td>6.4</td><td>3.2</td><td>5.3</td><td>2.3</td><td>other     </td><td>0</td></tr>\n",
       "\t<tr><th scope=row>32</th><td>5.4</td><td>3.4</td><td>1.5</td><td>0.4</td><td>other     </td><td>0</td></tr>\n",
       "\t<tr><th scope=row>139</th><td>6.0</td><td>3.0</td><td>4.8</td><td>1.8</td><td>other     </td><td>0</td></tr>\n",
       "\t<tr><th scope=row>71</th><td>5.9</td><td>3.2</td><td>4.8</td><td>1.8</td><td>versicolor</td><td>1</td></tr>\n",
       "\t<tr><th scope=row>8</th><td>5.0</td><td>3.4</td><td>1.5</td><td>0.2</td><td>other     </td><td>0</td></tr>\n",
       "\t<tr><th scope=row>6</th><td>5.4</td><td>3.9</td><td>1.7</td><td>0.4</td><td>other     </td><td>0</td></tr>\n",
       "</tbody>\n",
       "</table>\n"
      ],
      "text/latex": [
       "A data.frame: 6 × 6\n",
       "\\begin{tabular}{r|llllll}\n",
       "  & Sepal.Length & Sepal.Width & Petal.Length & Petal.Width & Species & versicolor\\\\\n",
       "  & <dbl> & <dbl> & <dbl> & <dbl> & <chr> & <int>\\\\\n",
       "\\hline\n",
       "\t116 & 6.4 & 3.2 & 5.3 & 2.3 & other      & 0\\\\\n",
       "\t32 & 5.4 & 3.4 & 1.5 & 0.4 & other      & 0\\\\\n",
       "\t139 & 6.0 & 3.0 & 4.8 & 1.8 & other      & 0\\\\\n",
       "\t71 & 5.9 & 3.2 & 4.8 & 1.8 & versicolor & 1\\\\\n",
       "\t8 & 5.0 & 3.4 & 1.5 & 0.2 & other      & 0\\\\\n",
       "\t6 & 5.4 & 3.9 & 1.7 & 0.4 & other      & 0\\\\\n",
       "\\end{tabular}\n"
      ],
      "text/markdown": [
       "\n",
       "A data.frame: 6 × 6\n",
       "\n",
       "| <!--/--> | Sepal.Length &lt;dbl&gt; | Sepal.Width &lt;dbl&gt; | Petal.Length &lt;dbl&gt; | Petal.Width &lt;dbl&gt; | Species &lt;chr&gt; | versicolor &lt;int&gt; |\n",
       "|---|---|---|---|---|---|---|\n",
       "| 116 | 6.4 | 3.2 | 5.3 | 2.3 | other      | 0 |\n",
       "| 32 | 5.4 | 3.4 | 1.5 | 0.4 | other      | 0 |\n",
       "| 139 | 6.0 | 3.0 | 4.8 | 1.8 | other      | 0 |\n",
       "| 71 | 5.9 | 3.2 | 4.8 | 1.8 | versicolor | 1 |\n",
       "| 8 | 5.0 | 3.4 | 1.5 | 0.2 | other      | 0 |\n",
       "| 6 | 5.4 | 3.9 | 1.7 | 0.4 | other      | 0 |\n",
       "\n"
      ],
      "text/plain": [
       "    Sepal.Length Sepal.Width Petal.Length Petal.Width Species    versicolor\n",
       "116 6.4          3.2         5.3          2.3         other      0         \n",
       "32  5.4          3.4         1.5          0.4         other      0         \n",
       "139 6.0          3.0         4.8          1.8         other      0         \n",
       "71  5.9          3.2         4.8          1.8         versicolor 1         \n",
       "8   5.0          3.4         1.5          0.2         other      0         \n",
       "6   5.4          3.9         1.7          0.4         other      0         "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "tt <- daltoolbox::train_test(daltoolbox::sample_random(), data)\n",
    "train <- tt$train\n",
    "test <- tt$test\n",
    "head(train)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This dataset is unbalanced using this perspective. If the prediction for $versicolor$ is higher than its probability, it can be classified as $versicolor$. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[1] 0.35\n"
     ]
    }
   ],
   "source": [
    "t <- mean(train$versicolor)\n",
    "print(t)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The creation of the logistic regression model using all independent variables uses $glm$ function."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "pred <- glm(versicolor ~ .-Species, data=train, family = binomial)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The quality of adjustment using training data is measured using the confusion table. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "   \n",
       "res  0  1\n",
       "  0 58 11\n",
       "  1 20 31"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "res <- predict(pred, train, type=\"response\")\n",
    "res <- as.integer(res >= t)\n",
    "table(res, train$versicolor)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The quality of prediction using the test data is measured using the confusion table. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "       \n",
       "res      0  1\n",
       "  FALSE 15  1\n",
       "  TRUE   7  7"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "res <- predict(pred, test, type=\"response\")\n",
    "res <- res >= t\n",
    "table(res, test$versicolor)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Creation of the logistic regression model using the independent variables with lower entropy during binning transformation.  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "pred <- glm(versicolor ~ Petal.Length + Petal.Width, data=train, family = binomial)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The quality of adjustment using training data is measured using the confusion table. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "   \n",
       "res  0  1\n",
       "  0 63  8\n",
       "  1 15 34"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "res <- predict(pred, train, type=\"response\")\n",
    "res <- as.integer(res >= t)\n",
    "table(res, train$versicolor)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The quality of prediction using the test data is measured using the confusion table. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "   \n",
       "res  0  1\n",
       "  0 15  0\n",
       "  1  7  8"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "res <- predict(pred, test, type=\"response\")\n",
    "res <- as.integer(res >= t)\n",
    "table(res, test$versicolor)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "R",
   "language": "R",
   "name": "ir"
  },
  "language_info": {
   "codemirror_mode": "r",
   "file_extension": ".r",
   "mimetype": "text/x-r-source",
   "name": "R",
   "pygments_lexer": "r",
   "version": "4.3.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}