{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Regression with python and statsmodels\n",
    "\n",
    "A quick illustration of linear regression with `statsmodels` package. It mostly parallels lecture notes on regression on class website"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import statsmodels.formula.api as sm\n",
    "import pandas as pd\n",
    "from plotnine import *"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's read the `mpg` dataset we used in lecture notes. Note we give the type for `origin` so it is read as a categorical variable."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "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>mpg</th>\n",
       "      <th>cylinders</th>\n",
       "      <th>displacement</th>\n",
       "      <th>horsepower</th>\n",
       "      <th>weight</th>\n",
       "      <th>acceleration</th>\n",
       "      <th>year</th>\n",
       "      <th>origin</th>\n",
       "      <th>name</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>18.0</td>\n",
       "      <td>8</td>\n",
       "      <td>307.0</td>\n",
       "      <td>130</td>\n",
       "      <td>3504</td>\n",
       "      <td>12.0</td>\n",
       "      <td>70</td>\n",
       "      <td>1</td>\n",
       "      <td>chevrolet chevelle malibu</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>15.0</td>\n",
       "      <td>8</td>\n",
       "      <td>350.0</td>\n",
       "      <td>165</td>\n",
       "      <td>3693</td>\n",
       "      <td>11.5</td>\n",
       "      <td>70</td>\n",
       "      <td>1</td>\n",
       "      <td>buick skylark 320</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>18.0</td>\n",
       "      <td>8</td>\n",
       "      <td>318.0</td>\n",
       "      <td>150</td>\n",
       "      <td>3436</td>\n",
       "      <td>11.0</td>\n",
       "      <td>70</td>\n",
       "      <td>1</td>\n",
       "      <td>plymouth satellite</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>16.0</td>\n",
       "      <td>8</td>\n",
       "      <td>304.0</td>\n",
       "      <td>150</td>\n",
       "      <td>3433</td>\n",
       "      <td>12.0</td>\n",
       "      <td>70</td>\n",
       "      <td>1</td>\n",
       "      <td>amc rebel sst</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>17.0</td>\n",
       "      <td>8</td>\n",
       "      <td>302.0</td>\n",
       "      <td>140</td>\n",
       "      <td>3449</td>\n",
       "      <td>10.5</td>\n",
       "      <td>70</td>\n",
       "      <td>1</td>\n",
       "      <td>ford torino</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    mpg  cylinders  displacement  horsepower  weight  acceleration  year  \\\n",
       "0  18.0          8         307.0         130    3504          12.0    70   \n",
       "1  15.0          8         350.0         165    3693          11.5    70   \n",
       "2  18.0          8         318.0         150    3436          11.0    70   \n",
       "3  16.0          8         304.0         150    3433          12.0    70   \n",
       "4  17.0          8         302.0         140    3449          10.5    70   \n",
       "\n",
       "  origin                       name  \n",
       "0      1  chevrolet chevelle malibu  \n",
       "1      1          buick skylark 320  \n",
       "2      1         plymouth satellite  \n",
       "3      1              amc rebel sst  \n",
       "4      1                ford torino  "
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mpg = pd.read_csv('data/auto-mpg.csv', dtype={'origin': np.str})\n",
    "mpg.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We will start with simple regression of mpg regressed on weight."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/hcorrada/opt/miniconda3/envs/cmsc320/lib/python3.6/site-packages/pandas/core/generic.py:5191: FutureWarning: Attribute 'is_copy' is deprecated and will be removed in a future version.\n",
      "  object.__getattribute__(self, name)\n",
      "/Users/hcorrada/opt/miniconda3/envs/cmsc320/lib/python3.6/site-packages/pandas/core/generic.py:5192: FutureWarning: Attribute 'is_copy' is deprecated and will be removed in a future version.\n",
      "  return object.__setattr__(self, name, value)\n",
      "/Users/hcorrada/opt/miniconda3/envs/cmsc320/lib/python3.6/site-packages/numpy/core/fromnumeric.py:2542: FutureWarning: Method .ptp is deprecated and will be removed in a future version. Use numpy.ptp instead.\n",
      "  return ptp(axis=axis, out=out, **kwargs)\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAjIAAAGxCAYAAAB4AFyyAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "<ggplot: (317328581)>"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "(ggplot(mpg, aes(x='weight', y='mpg'))\n",
    "     + geom_point()\n",
    "     + geom_smooth(method='lm'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<table class=\"simpletable\">\n",
       "<caption>OLS Regression Results</caption>\n",
       "<tr>\n",
       "  <th>Dep. Variable:</th>           <td>mpg</td>       <th>  R-squared:         </th> <td>   0.693</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Model:</th>                   <td>OLS</td>       <th>  Adj. R-squared:    </th> <td>   0.692</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Method:</th>             <td>Least Squares</td>  <th>  F-statistic:       </th> <td>   878.8</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Date:</th>             <td>Sun, 12 Apr 2020</td> <th>  Prob (F-statistic):</th> <td>6.02e-102</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Time:</th>                 <td>20:00:49</td>     <th>  Log-Likelihood:    </th> <td> -1130.0</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>No. Observations:</th>      <td>   392</td>      <th>  AIC:               </th> <td>   2264.</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Df Residuals:</th>          <td>   390</td>      <th>  BIC:               </th> <td>   2272.</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Df Model:</th>              <td>     1</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>   46.2165</td> <td>    0.799</td> <td>   57.867</td> <td> 0.000</td> <td>   44.646</td> <td>   47.787</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>weight</th>    <td>   -0.0076</td> <td>    0.000</td> <td>  -29.645</td> <td> 0.000</td> <td>   -0.008</td> <td>   -0.007</td>\n",
       "</tr>\n",
       "</table>\n",
       "<table class=\"simpletable\">\n",
       "<tr>\n",
       "  <th>Omnibus:</th>       <td>41.682</td> <th>  Durbin-Watson:     </th> <td>   0.808</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Prob(Omnibus):</th> <td> 0.000</td> <th>  Jarque-Bera (JB):  </th> <td>  60.039</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Skew:</th>          <td> 0.727</td> <th>  Prob(JB):          </th> <td>9.18e-14</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Kurtosis:</th>      <td> 4.251</td> <th>  Cond. No.          </th> <td>1.13e+04</td>\n",
       "</tr>\n",
       "</table><br/><br/>Warnings:<br/>[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.<br/>[2] The condition number is large, 1.13e+04. This might indicate that there are<br/>strong multicollinearity or other numerical problems."
      ],
      "text/plain": [
       "<class 'statsmodels.iolib.summary.Summary'>\n",
       "\"\"\"\n",
       "                            OLS Regression Results                            \n",
       "==============================================================================\n",
       "Dep. Variable:                    mpg   R-squared:                       0.693\n",
       "Model:                            OLS   Adj. R-squared:                  0.692\n",
       "Method:                 Least Squares   F-statistic:                     878.8\n",
       "Date:                Sun, 12 Apr 2020   Prob (F-statistic):          6.02e-102\n",
       "Time:                        20:00:49   Log-Likelihood:                -1130.0\n",
       "No. Observations:                 392   AIC:                             2264.\n",
       "Df Residuals:                     390   BIC:                             2272.\n",
       "Df Model:                           1                                         \n",
       "Covariance Type:            nonrobust                                         \n",
       "==============================================================================\n",
       "                 coef    std err          t      P>|t|      [0.025      0.975]\n",
       "------------------------------------------------------------------------------\n",
       "Intercept     46.2165      0.799     57.867      0.000      44.646      47.787\n",
       "weight        -0.0076      0.000    -29.645      0.000      -0.008      -0.007\n",
       "==============================================================================\n",
       "Omnibus:                       41.682   Durbin-Watson:                   0.808\n",
       "Prob(Omnibus):                  0.000   Jarque-Bera (JB):               60.039\n",
       "Skew:                           0.727   Prob(JB):                     9.18e-14\n",
       "Kurtosis:                       4.251   Cond. No.                     1.13e+04\n",
       "==============================================================================\n",
       "\n",
       "Warnings:\n",
       "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
       "[2] The condition number is large, 1.13e+04. This might indicate that there are\n",
       "strong multicollinearity or other numerical problems.\n",
       "\"\"\""
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "simple_res = sm.ols('mpg~weight', data=mpg).fit()\n",
    "simple_res.summary()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We can extract fit information from result object. Here is a list of its contents"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['HC0_se',\n",
       " 'HC1_se',\n",
       " 'HC2_se',\n",
       " 'HC3_se',\n",
       " '_HCCM',\n",
       " '__class__',\n",
       " '__delattr__',\n",
       " '__dict__',\n",
       " '__dir__',\n",
       " '__doc__',\n",
       " '__eq__',\n",
       " '__format__',\n",
       " '__ge__',\n",
       " '__getattribute__',\n",
       " '__gt__',\n",
       " '__hash__',\n",
       " '__init__',\n",
       " '__init_subclass__',\n",
       " '__le__',\n",
       " '__lt__',\n",
       " '__module__',\n",
       " '__ne__',\n",
       " '__new__',\n",
       " '__reduce__',\n",
       " '__reduce_ex__',\n",
       " '__repr__',\n",
       " '__setattr__',\n",
       " '__sizeof__',\n",
       " '__str__',\n",
       " '__subclasshook__',\n",
       " '__weakref__',\n",
       " '_cache',\n",
       " '_data_attr',\n",
       " '_get_robustcov_results',\n",
       " '_is_nested',\n",
       " '_wexog_singular_values',\n",
       " 'aic',\n",
       " 'bic',\n",
       " 'bse',\n",
       " 'centered_tss',\n",
       " 'compare_f_test',\n",
       " 'compare_lm_test',\n",
       " 'compare_lr_test',\n",
       " 'condition_number',\n",
       " 'conf_int',\n",
       " 'conf_int_el',\n",
       " 'cov_HC0',\n",
       " 'cov_HC1',\n",
       " 'cov_HC2',\n",
       " 'cov_HC3',\n",
       " 'cov_kwds',\n",
       " 'cov_params',\n",
       " 'cov_type',\n",
       " 'df_model',\n",
       " 'df_resid',\n",
       " 'diagn',\n",
       " 'eigenvals',\n",
       " 'el_test',\n",
       " 'ess',\n",
       " 'f_pvalue',\n",
       " 'f_test',\n",
       " 'fittedvalues',\n",
       " 'fvalue',\n",
       " 'get_influence',\n",
       " 'get_prediction',\n",
       " 'get_robustcov_results',\n",
       " 'initialize',\n",
       " 'k_constant',\n",
       " 'llf',\n",
       " 'load',\n",
       " 'model',\n",
       " 'mse_model',\n",
       " 'mse_resid',\n",
       " 'mse_total',\n",
       " 'nobs',\n",
       " 'normalized_cov_params',\n",
       " 'outlier_test',\n",
       " 'params',\n",
       " 'predict',\n",
       " 'pvalues',\n",
       " 'remove_data',\n",
       " 'resid',\n",
       " 'resid_pearson',\n",
       " 'rsquared',\n",
       " 'rsquared_adj',\n",
       " 'save',\n",
       " 'scale',\n",
       " 'ssr',\n",
       " 'summary',\n",
       " 'summary2',\n",
       " 't_test',\n",
       " 't_test_pairwise',\n",
       " 'tvalues',\n",
       " 'uncentered_tss',\n",
       " 'use_t',\n",
       " 'wald_test',\n",
       " 'wald_test_terms',\n",
       " 'wresid']"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dir(simple_res)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "For example, we can access estimated parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Intercept    46.216525\n",
       "weight       -0.007647\n",
       "dtype: float64"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "simple_res.params"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "To make a residuals vs. fitted plot, we can add that information to our original data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [],
   "source": [
    "mpg_copy = mpg.copy()\n",
    "mpg_copy['fitted'] = simple_res.fittedvalues\n",
    "mpg_copy['resid'] = simple_res.resid"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now we can make our plot"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/hcorrada/opt/miniconda3/envs/cmsc320/lib/python3.6/site-packages/pandas/core/generic.py:5191: FutureWarning: Attribute 'is_copy' is deprecated and will be removed in a future version.\n",
      "  object.__getattribute__(self, name)\n",
      "/Users/hcorrada/opt/miniconda3/envs/cmsc320/lib/python3.6/site-packages/pandas/core/generic.py:5192: FutureWarning: Attribute 'is_copy' is deprecated and will be removed in a future version.\n",
      "  return object.__setattr__(self, name, value)\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAj0AAAGxCAYAAACJCwc/AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nEP4fagZT9anSqnAAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "<ggplot: (317328981)>"
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "(ggplot(mpg_copy, aes(x='fitted', y='resid'))\n",
    "   + geom_point())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We can expand formula to fit multiple linear regression model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<table class=\"simpletable\">\n",
       "<caption>OLS Regression Results</caption>\n",
       "<tr>\n",
       "  <th>Dep. Variable:</th>           <td>mpg</td>       <th>  R-squared:         </th> <td>   0.809</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Model:</th>                   <td>OLS</td>       <th>  Adj. R-squared:    </th> <td>   0.806</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Method:</th>             <td>Least Squares</td>  <th>  F-statistic:       </th> <td>   326.8</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Date:</th>             <td>Sun, 12 Apr 2020</td> <th>  Prob (F-statistic):</th> <td>2.82e-136</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Time:</th>                 <td>20:01:01</td>     <th>  Log-Likelihood:    </th> <td> -1036.8</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>No. Observations:</th>      <td>   392</td>      <th>  AIC:               </th> <td>   2086.</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Df Residuals:</th>          <td>   386</td>      <th>  BIC:               </th> <td>   2109.</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Df Model:</th>              <td>     5</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>  -12.7795</td> <td>    4.274</td> <td>   -2.990</td> <td> 0.003</td> <td>  -21.183</td> <td>   -4.376</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>weight</th>       <td>   -0.0065</td> <td>    0.001</td> <td>  -11.122</td> <td> 0.000</td> <td>   -0.008</td> <td>   -0.005</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>cylinders</th>    <td>   -0.3437</td> <td>    0.332</td> <td>   -1.037</td> <td> 0.301</td> <td>   -0.996</td> <td>    0.308</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>horsepower</th>   <td>   -0.0077</td> <td>    0.011</td> <td>   -0.721</td> <td> 0.471</td> <td>   -0.029</td> <td>    0.013</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>displacement</th> <td>    0.0070</td> <td>    0.007</td> <td>    0.957</td> <td> 0.339</td> <td>   -0.007</td> <td>    0.021</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>year</th>         <td>    0.7499</td> <td>    0.052</td> <td>   14.302</td> <td> 0.000</td> <td>    0.647</td> <td>    0.853</td>\n",
       "</tr>\n",
       "</table>\n",
       "<table class=\"simpletable\">\n",
       "<tr>\n",
       "  <th>Omnibus:</th>       <td>42.042</td> <th>  Durbin-Watson:     </th> <td>   1.236</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Prob(Omnibus):</th> <td> 0.000</td> <th>  Jarque-Bera (JB):  </th> <td>  70.268</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Skew:</th>          <td> 0.669</td> <th>  Prob(JB):          </th> <td>5.51e-16</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Kurtosis:</th>      <td> 4.585</td> <th>  Cond. No.          </th> <td>7.66e+04</td>\n",
       "</tr>\n",
       "</table><br/><br/>Warnings:<br/>[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.<br/>[2] The condition number is large, 7.66e+04. This might indicate that there are<br/>strong multicollinearity or other numerical problems."
      ],
      "text/plain": [
       "<class 'statsmodels.iolib.summary.Summary'>\n",
       "\"\"\"\n",
       "                            OLS Regression Results                            \n",
       "==============================================================================\n",
       "Dep. Variable:                    mpg   R-squared:                       0.809\n",
       "Model:                            OLS   Adj. R-squared:                  0.806\n",
       "Method:                 Least Squares   F-statistic:                     326.8\n",
       "Date:                Sun, 12 Apr 2020   Prob (F-statistic):          2.82e-136\n",
       "Time:                        20:01:01   Log-Likelihood:                -1036.8\n",
       "No. Observations:                 392   AIC:                             2086.\n",
       "Df Residuals:                     386   BIC:                             2109.\n",
       "Df Model:                           5                                         \n",
       "Covariance Type:            nonrobust                                         \n",
       "================================================================================\n",
       "                   coef    std err          t      P>|t|      [0.025      0.975]\n",
       "--------------------------------------------------------------------------------\n",
       "Intercept      -12.7795      4.274     -2.990      0.003     -21.183      -4.376\n",
       "weight          -0.0065      0.001    -11.122      0.000      -0.008      -0.005\n",
       "cylinders       -0.3437      0.332     -1.037      0.301      -0.996       0.308\n",
       "horsepower      -0.0077      0.011     -0.721      0.471      -0.029       0.013\n",
       "displacement     0.0070      0.007      0.957      0.339      -0.007       0.021\n",
       "year             0.7499      0.052     14.302      0.000       0.647       0.853\n",
       "==============================================================================\n",
       "Omnibus:                       42.042   Durbin-Watson:                   1.236\n",
       "Prob(Omnibus):                  0.000   Jarque-Bera (JB):               70.268\n",
       "Skew:                           0.669   Prob(JB):                     5.51e-16\n",
       "Kurtosis:                       4.585   Cond. No.                     7.66e+04\n",
       "==============================================================================\n",
       "\n",
       "Warnings:\n",
       "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
       "[2] The condition number is large, 7.66e+04. This might indicate that there are\n",
       "strong multicollinearity or other numerical problems.\n",
       "\"\"\""
      ]
     },
     "execution_count": 40,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "multi_res = sm.ols('mpg~1+weight+cylinders+horsepower+displacement+year', data=mpg).fit()\n",
    "multi_res.summary()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now a model with interactionsm."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<table class=\"simpletable\">\n",
       "<caption>OLS Regression Results</caption>\n",
       "<tr>\n",
       "  <th>Dep. Variable:</th>           <td>mpg</td>       <th>  R-squared:         </th> <td>   0.707</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Model:</th>                   <td>OLS</td>       <th>  Adj. R-squared:    </th> <td>   0.703</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Method:</th>             <td>Least Squares</td>  <th>  F-statistic:       </th> <td>   186.1</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Date:</th>             <td>Sun, 12 Apr 2020</td> <th>  Prob (F-statistic):</th> <td>1.72e-100</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Time:</th>                 <td>20:01:11</td>     <th>  Log-Likelihood:    </th> <td> -1120.7</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>No. Observations:</th>      <td>   392</td>      <th>  AIC:               </th> <td>   2253.</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Df Residuals:</th>          <td>   386</td>      <th>  BIC:               </th> <td>   2277.</td> \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Df Model:</th>              <td>     5</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>   43.1485</td> <td>    1.186</td> <td>   36.378</td> <td> 0.000</td> <td>   40.816</td> <td>   45.481</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>origin[T.2]</th>        <td>    1.1247</td> <td>    2.878</td> <td>    0.391</td> <td> 0.696</td> <td>   -4.534</td> <td>    6.783</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>origin[T.3]</th>        <td>   11.1117</td> <td>    3.574</td> <td>    3.109</td> <td> 0.002</td> <td>    4.084</td> <td>   18.139</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>weight</th>             <td>   -0.0069</td> <td>    0.000</td> <td>  -20.020</td> <td> 0.000</td> <td>   -0.008</td> <td>   -0.006</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>weight:origin[T.2]</th> <td> 3.575e-06</td> <td>    0.001</td> <td>    0.003</td> <td> 0.997</td> <td>   -0.002</td> <td>    0.002</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>weight:origin[T.3]</th> <td>   -0.0039</td> <td>    0.002</td> <td>   -2.508</td> <td> 0.013</td> <td>   -0.007</td> <td>   -0.001</td>\n",
       "</tr>\n",
       "</table>\n",
       "<table class=\"simpletable\">\n",
       "<tr>\n",
       "  <th>Omnibus:</th>       <td>45.388</td> <th>  Durbin-Watson:     </th> <td>   0.837</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Prob(Omnibus):</th> <td> 0.000</td> <th>  Jarque-Bera (JB):  </th> <td>  70.270</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Skew:</th>          <td> 0.746</td> <th>  Prob(JB):          </th> <td>5.51e-16</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Kurtosis:</th>      <td> 4.440</td> <th>  Cond. No.          </th> <td>5.35e+04</td>\n",
       "</tr>\n",
       "</table><br/><br/>Warnings:<br/>[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.<br/>[2] The condition number is large, 5.35e+04. This might indicate that there are<br/>strong multicollinearity or other numerical problems."
      ],
      "text/plain": [
       "<class 'statsmodels.iolib.summary.Summary'>\n",
       "\"\"\"\n",
       "                            OLS Regression Results                            \n",
       "==============================================================================\n",
       "Dep. Variable:                    mpg   R-squared:                       0.707\n",
       "Model:                            OLS   Adj. R-squared:                  0.703\n",
       "Method:                 Least Squares   F-statistic:                     186.1\n",
       "Date:                Sun, 12 Apr 2020   Prob (F-statistic):          1.72e-100\n",
       "Time:                        20:01:11   Log-Likelihood:                -1120.7\n",
       "No. Observations:                 392   AIC:                             2253.\n",
       "Df Residuals:                     386   BIC:                             2277.\n",
       "Df Model:                           5                                         \n",
       "Covariance Type:            nonrobust                                         \n",
       "======================================================================================\n",
       "                         coef    std err          t      P>|t|      [0.025      0.975]\n",
       "--------------------------------------------------------------------------------------\n",
       "Intercept             43.1485      1.186     36.378      0.000      40.816      45.481\n",
       "origin[T.2]            1.1247      2.878      0.391      0.696      -4.534       6.783\n",
       "origin[T.3]           11.1117      3.574      3.109      0.002       4.084      18.139\n",
       "weight                -0.0069      0.000    -20.020      0.000      -0.008      -0.006\n",
       "weight:origin[T.2]  3.575e-06      0.001      0.003      0.997      -0.002       0.002\n",
       "weight:origin[T.3]    -0.0039      0.002     -2.508      0.013      -0.007      -0.001\n",
       "==============================================================================\n",
       "Omnibus:                       45.388   Durbin-Watson:                   0.837\n",
       "Prob(Omnibus):                  0.000   Jarque-Bera (JB):               70.270\n",
       "Skew:                           0.746   Prob(JB):                     5.51e-16\n",
       "Kurtosis:                       4.440   Cond. No.                     5.35e+04\n",
       "==============================================================================\n",
       "\n",
       "Warnings:\n",
       "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
       "[2] The condition number is large, 5.35e+04. This might indicate that there are\n",
       "strong multicollinearity or other numerical problems.\n",
       "\"\"\""
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "interact_res = sm.ols('mpg~weight*origin', data=mpg).fit()\n",
    "interact_res.summary()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "And to replicate the plot in lecture notes illustrating different intercept and slopes of the interaction model:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/hcorrada/opt/miniconda3/envs/cmsc320/lib/python3.6/site-packages/plotnine/utils.py:284: FutureWarning: Method .as_matrix will be removed in a future version. Use .values instead.\n",
      "  ndistinct = ids.apply(len_unique, axis=0).as_matrix()\n",
      "/Users/hcorrada/opt/miniconda3/envs/cmsc320/lib/python3.6/site-packages/pandas/core/generic.py:5191: FutureWarning: Attribute 'is_copy' is deprecated and will be removed in a future version.\n",
      "  object.__getattribute__(self, name)\n",
      "/Users/hcorrada/opt/miniconda3/envs/cmsc320/lib/python3.6/site-packages/pandas/core/generic.py:5192: FutureWarning: Attribute 'is_copy' is deprecated and will be removed in a future version.\n",
      "  return object.__setattr__(self, name, value)\n",
      "/Users/hcorrada/opt/miniconda3/envs/cmsc320/lib/python3.6/site-packages/numpy/core/fromnumeric.py:2542: FutureWarning: Method .ptp is deprecated and will be removed in a future version. Use numpy.ptp instead.\n",
      "  return ptp(axis=axis, out=out, **kwargs)\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAocAAAGxCAYAAAAQ3xzPAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "<ggplot: (317784559)>"
      ]
     },
     "execution_count": 43,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "(ggplot(mpg, aes(x='weight', y='mpg', color='origin'))\n",
    "         + geom_point()\n",
    "         + geom_smooth(method='lm'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.6.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}