{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "hidden-vitamin",
   "metadata": {},
   "source": [
    "# Parametrising a distribution with a neural network\n",
    "\n",
    "Parametrization of a [PyTorch](https://pytorch.org/) distribution with a nueral network, for the purpose of uncertainty quantification.\n",
    "\n",
    "We'll consider the [OLS Regression Challenge](https://data.world/nrippner/ols-regression-challenge), which aims at predicting cancer mortality rates for US counties.\n",
    "\n",
    "## Data Dictionary\n",
    "\n",
    "* **TARGET_deathRate**: Dependent variable. Mean per capita (100,000) cancer mortalities (a)\n",
    "* **avgAnnCount**: Mean number of reported cases of cancer diagnosed annually (a)\n",
    "* **avgDeathsPerYear**: Mean number of reported mortalities due to cancer (a)\n",
    "* **incidenceRate**: Mean per capita (100,000) cancer diagoses (a)\n",
    "* **medianIncome**: Median income per county (b)\n",
    "* **popEst2015**: Population of county (b)\n",
    "* **povertyPercent**: Percent of populace in poverty (b)\n",
    "* **studyPerCap**: Per capita number of cancer-related clinical trials per county (a)\n",
    "* **binnedInc**: Median income per capita binned by decile (b)\n",
    "* **MedianAge**: Median age of county residents (b)\n",
    "* **MedianAgeMale**: Median age of male county residents (b)\n",
    "* **MedianAgeFemale**: Median age of female county residents (b)\n",
    "* **Geography**: County name (b)\n",
    "* **AvgHouseholdSize**: Mean household size of county (b)\n",
    "* **PercentMarried**: Percent of county residents who are married (b)\n",
    "* **PctNoHS18_24**: Percent of county residents ages 18-24 highest education attained: less than high school (b)\n",
    "* **PctHS18_24**: Percent of county residents ages 18-24 highest education attained: high school diploma (b)\n",
    "* **PctSomeCol18_24**: Percent of county residents ages 18-24 highest education attained: some college (b)\n",
    "* **PctBachDeg18_24**: Percent of county residents ages 18-24 highest education attained: bachelor's degree (b)\n",
    "* **PctHS25_Over**: Percent of county residents ages 25 and over highest education attained: high school diploma (b)\n",
    "* **PctBachDeg25_Over**: Percent of county residents ages 25 and over highest education attained: bachelor's degree (b)\n",
    "* **PctEmployed16_Over**: Percent of county residents ages 16 and over employed (b)\n",
    "* **PctUnemployed16_Over**: Percent of county residents ages 16 and over unemployed (b)\n",
    "* **PctPrivateCoverage**: Percent of county residents with private health coverage (b)\n",
    "* **PctPrivateCoverageAlone**: Percent of county residents with private health coverage alone (no public assistance) (b)\n",
    "* **PctEmpPrivCoverage**: Percent of county residents with employee-provided private health coverage (b)\n",
    "* **PctPublicCoverage**: Percent of county residents with government-provided health coverage (b)\n",
    "* **PctPubliceCoverageAlone**: Percent of county residents with government-provided health coverage alone (b)\n",
    "* **PctWhite**: Percent of county residents who identify as White (b)\n",
    "* **PctBlack**: Percent of county residents who identify as Black (b)\n",
    "* **PctAsian**: Percent of county residents who identify as Asian (b)\n",
    "* **PctOtherRace**: Percent of county residents who identify in a category which is not White, Black, or Asian (b)\n",
    "* **PctMarriedHouseholds**: Percent of married households (b)\n",
    "* **BirthRate**: Number of live births relative to number of women in county (b)\n",
    "\n",
    "Notes:\n",
    "* (a): years 2010-2016\n",
    "* (b): 2013 Census Estimates"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "static-green",
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "from os.path import join\n",
    "\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "import torch\n",
    "import torch.nn.functional as F\n",
    "from sklearn.metrics import r2_score\n",
    "from sklearn.model_selection import train_test_split\n",
    "from scipy.stats import binned_statistic\n",
    "\n",
    "cwd = os.getcwd()\n",
    "if cwd.endswith('notebook'):\n",
    "    os.chdir('..')\n",
    "    cwd = os.getcwd()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "beautiful-worker",
   "metadata": {},
   "outputs": [],
   "source": [
    "sns.set(palette='colorblind', font_scale=1.3)\n",
    "palette = sns.color_palette()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "medical-chick",
   "metadata": {},
   "outputs": [],
   "source": [
    "seed = 444\n",
    "np.random.seed(seed);\n",
    "torch.manual_seed(seed);\n",
    "torch.set_default_dtype(torch.float64)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "classified-factory",
   "metadata": {},
   "source": [
    "## Dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "pacific-directory",
   "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>avgAnnCount</th>\n",
       "      <th>avgDeathsPerYear</th>\n",
       "      <th>TARGET_deathRate</th>\n",
       "      <th>incidenceRate</th>\n",
       "      <th>medIncome</th>\n",
       "      <th>popEst2015</th>\n",
       "      <th>povertyPercent</th>\n",
       "      <th>studyPerCap</th>\n",
       "      <th>binnedInc</th>\n",
       "      <th>MedianAge</th>\n",
       "      <th>...</th>\n",
       "      <th>PctPrivateCoverageAlone</th>\n",
       "      <th>PctEmpPrivCoverage</th>\n",
       "      <th>PctPublicCoverage</th>\n",
       "      <th>PctPublicCoverageAlone</th>\n",
       "      <th>PctWhite</th>\n",
       "      <th>PctBlack</th>\n",
       "      <th>PctAsian</th>\n",
       "      <th>PctOtherRace</th>\n",
       "      <th>PctMarriedHouseholds</th>\n",
       "      <th>BirthRate</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1397.0</td>\n",
       "      <td>469</td>\n",
       "      <td>164.9</td>\n",
       "      <td>489.8</td>\n",
       "      <td>61898</td>\n",
       "      <td>260131</td>\n",
       "      <td>11.2</td>\n",
       "      <td>499.748204</td>\n",
       "      <td>(61494.5, 125635]</td>\n",
       "      <td>39.3</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>41.6</td>\n",
       "      <td>32.9</td>\n",
       "      <td>14.0</td>\n",
       "      <td>81.780529</td>\n",
       "      <td>2.594728</td>\n",
       "      <td>4.821857</td>\n",
       "      <td>1.843479</td>\n",
       "      <td>52.856076</td>\n",
       "      <td>6.118831</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>173.0</td>\n",
       "      <td>70</td>\n",
       "      <td>161.3</td>\n",
       "      <td>411.6</td>\n",
       "      <td>48127</td>\n",
       "      <td>43269</td>\n",
       "      <td>18.6</td>\n",
       "      <td>23.111234</td>\n",
       "      <td>(48021.6, 51046.4]</td>\n",
       "      <td>33.0</td>\n",
       "      <td>...</td>\n",
       "      <td>53.8</td>\n",
       "      <td>43.6</td>\n",
       "      <td>31.1</td>\n",
       "      <td>15.3</td>\n",
       "      <td>89.228509</td>\n",
       "      <td>0.969102</td>\n",
       "      <td>2.246233</td>\n",
       "      <td>3.741352</td>\n",
       "      <td>45.372500</td>\n",
       "      <td>4.333096</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>102.0</td>\n",
       "      <td>50</td>\n",
       "      <td>174.7</td>\n",
       "      <td>349.7</td>\n",
       "      <td>49348</td>\n",
       "      <td>21026</td>\n",
       "      <td>14.6</td>\n",
       "      <td>47.560164</td>\n",
       "      <td>(48021.6, 51046.4]</td>\n",
       "      <td>45.0</td>\n",
       "      <td>...</td>\n",
       "      <td>43.5</td>\n",
       "      <td>34.9</td>\n",
       "      <td>42.1</td>\n",
       "      <td>21.1</td>\n",
       "      <td>90.922190</td>\n",
       "      <td>0.739673</td>\n",
       "      <td>0.465898</td>\n",
       "      <td>2.747358</td>\n",
       "      <td>54.444868</td>\n",
       "      <td>3.729488</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>427.0</td>\n",
       "      <td>202</td>\n",
       "      <td>194.8</td>\n",
       "      <td>430.4</td>\n",
       "      <td>44243</td>\n",
       "      <td>75882</td>\n",
       "      <td>17.1</td>\n",
       "      <td>342.637253</td>\n",
       "      <td>(42724.4, 45201]</td>\n",
       "      <td>42.8</td>\n",
       "      <td>...</td>\n",
       "      <td>40.3</td>\n",
       "      <td>35.0</td>\n",
       "      <td>45.3</td>\n",
       "      <td>25.0</td>\n",
       "      <td>91.744686</td>\n",
       "      <td>0.782626</td>\n",
       "      <td>1.161359</td>\n",
       "      <td>1.362643</td>\n",
       "      <td>51.021514</td>\n",
       "      <td>4.603841</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>57.0</td>\n",
       "      <td>26</td>\n",
       "      <td>144.4</td>\n",
       "      <td>350.1</td>\n",
       "      <td>49955</td>\n",
       "      <td>10321</td>\n",
       "      <td>12.5</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>(48021.6, 51046.4]</td>\n",
       "      <td>48.3</td>\n",
       "      <td>...</td>\n",
       "      <td>43.9</td>\n",
       "      <td>35.1</td>\n",
       "      <td>44.0</td>\n",
       "      <td>22.7</td>\n",
       "      <td>94.104024</td>\n",
       "      <td>0.270192</td>\n",
       "      <td>0.665830</td>\n",
       "      <td>0.492135</td>\n",
       "      <td>54.027460</td>\n",
       "      <td>6.796657</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 34 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   avgAnnCount  avgDeathsPerYear  TARGET_deathRate  incidenceRate  medIncome  \\\n",
       "0       1397.0               469             164.9          489.8      61898   \n",
       "1        173.0                70             161.3          411.6      48127   \n",
       "2        102.0                50             174.7          349.7      49348   \n",
       "3        427.0               202             194.8          430.4      44243   \n",
       "4         57.0                26             144.4          350.1      49955   \n",
       "\n",
       "   popEst2015  povertyPercent  studyPerCap           binnedInc  MedianAge  \\\n",
       "0      260131            11.2   499.748204   (61494.5, 125635]       39.3   \n",
       "1       43269            18.6    23.111234  (48021.6, 51046.4]       33.0   \n",
       "2       21026            14.6    47.560164  (48021.6, 51046.4]       45.0   \n",
       "3       75882            17.1   342.637253    (42724.4, 45201]       42.8   \n",
       "4       10321            12.5     0.000000  (48021.6, 51046.4]       48.3   \n",
       "\n",
       "   ...  PctPrivateCoverageAlone  PctEmpPrivCoverage PctPublicCoverage  \\\n",
       "0  ...                      NaN                41.6              32.9   \n",
       "1  ...                     53.8                43.6              31.1   \n",
       "2  ...                     43.5                34.9              42.1   \n",
       "3  ...                     40.3                35.0              45.3   \n",
       "4  ...                     43.9                35.1              44.0   \n",
       "\n",
       "   PctPublicCoverageAlone   PctWhite  PctBlack  PctAsian  PctOtherRace  \\\n",
       "0                    14.0  81.780529  2.594728  4.821857      1.843479   \n",
       "1                    15.3  89.228509  0.969102  2.246233      3.741352   \n",
       "2                    21.1  90.922190  0.739673  0.465898      2.747358   \n",
       "3                    25.0  91.744686  0.782626  1.161359      1.362643   \n",
       "4                    22.7  94.104024  0.270192  0.665830      0.492135   \n",
       "\n",
       "   PctMarriedHouseholds  BirthRate  \n",
       "0             52.856076   6.118831  \n",
       "1             45.372500   4.333096  \n",
       "2             54.444868   3.729488  \n",
       "3             51.021514   4.603841  \n",
       "4             54.027460   6.796657  \n",
       "\n",
       "[5 rows x 34 columns]"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.read_csv(join(cwd, 'data/cancer_reg.csv'))\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "underlying-jenny",
   "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>avgAnnCount</th>\n",
       "      <th>avgDeathsPerYear</th>\n",
       "      <th>TARGET_deathRate</th>\n",
       "      <th>incidenceRate</th>\n",
       "      <th>medIncome</th>\n",
       "      <th>popEst2015</th>\n",
       "      <th>povertyPercent</th>\n",
       "      <th>studyPerCap</th>\n",
       "      <th>MedianAge</th>\n",
       "      <th>MedianAgeMale</th>\n",
       "      <th>...</th>\n",
       "      <th>PctPrivateCoverageAlone</th>\n",
       "      <th>PctEmpPrivCoverage</th>\n",
       "      <th>PctPublicCoverage</th>\n",
       "      <th>PctPublicCoverageAlone</th>\n",
       "      <th>PctWhite</th>\n",
       "      <th>PctBlack</th>\n",
       "      <th>PctAsian</th>\n",
       "      <th>PctOtherRace</th>\n",
       "      <th>PctMarriedHouseholds</th>\n",
       "      <th>BirthRate</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>3047.000000</td>\n",
       "      <td>3047.000000</td>\n",
       "      <td>3047.000000</td>\n",
       "      <td>3047.000000</td>\n",
       "      <td>3047.000000</td>\n",
       "      <td>3.047000e+03</td>\n",
       "      <td>3047.000000</td>\n",
       "      <td>3047.000000</td>\n",
       "      <td>3047.000000</td>\n",
       "      <td>3047.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>2438.000000</td>\n",
       "      <td>3047.000000</td>\n",
       "      <td>3047.000000</td>\n",
       "      <td>3047.000000</td>\n",
       "      <td>3047.000000</td>\n",
       "      <td>3047.000000</td>\n",
       "      <td>3047.000000</td>\n",
       "      <td>3047.000000</td>\n",
       "      <td>3047.000000</td>\n",
       "      <td>3047.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>606.338544</td>\n",
       "      <td>185.965868</td>\n",
       "      <td>178.664063</td>\n",
       "      <td>448.268586</td>\n",
       "      <td>47063.281917</td>\n",
       "      <td>1.026374e+05</td>\n",
       "      <td>16.878175</td>\n",
       "      <td>155.399415</td>\n",
       "      <td>45.272333</td>\n",
       "      <td>39.570725</td>\n",
       "      <td>...</td>\n",
       "      <td>48.453774</td>\n",
       "      <td>41.196324</td>\n",
       "      <td>36.252642</td>\n",
       "      <td>19.240072</td>\n",
       "      <td>83.645286</td>\n",
       "      <td>9.107978</td>\n",
       "      <td>1.253965</td>\n",
       "      <td>1.983523</td>\n",
       "      <td>51.243872</td>\n",
       "      <td>5.640306</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>1416.356223</td>\n",
       "      <td>504.134286</td>\n",
       "      <td>27.751511</td>\n",
       "      <td>54.560733</td>\n",
       "      <td>12040.090836</td>\n",
       "      <td>3.290592e+05</td>\n",
       "      <td>6.409087</td>\n",
       "      <td>529.628366</td>\n",
       "      <td>45.304480</td>\n",
       "      <td>5.226017</td>\n",
       "      <td>...</td>\n",
       "      <td>10.083006</td>\n",
       "      <td>9.447687</td>\n",
       "      <td>7.841741</td>\n",
       "      <td>6.113041</td>\n",
       "      <td>16.380025</td>\n",
       "      <td>14.534538</td>\n",
       "      <td>2.610276</td>\n",
       "      <td>3.517710</td>\n",
       "      <td>6.572814</td>\n",
       "      <td>1.985816</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>6.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>59.700000</td>\n",
       "      <td>201.300000</td>\n",
       "      <td>22640.000000</td>\n",
       "      <td>8.270000e+02</td>\n",
       "      <td>3.200000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>22.300000</td>\n",
       "      <td>22.400000</td>\n",
       "      <td>...</td>\n",
       "      <td>15.700000</td>\n",
       "      <td>13.500000</td>\n",
       "      <td>11.200000</td>\n",
       "      <td>2.600000</td>\n",
       "      <td>10.199155</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>22.992490</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>76.000000</td>\n",
       "      <td>28.000000</td>\n",
       "      <td>161.200000</td>\n",
       "      <td>420.300000</td>\n",
       "      <td>38882.500000</td>\n",
       "      <td>1.168400e+04</td>\n",
       "      <td>12.150000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>37.700000</td>\n",
       "      <td>36.350000</td>\n",
       "      <td>...</td>\n",
       "      <td>41.000000</td>\n",
       "      <td>34.500000</td>\n",
       "      <td>30.900000</td>\n",
       "      <td>14.850000</td>\n",
       "      <td>77.296180</td>\n",
       "      <td>0.620675</td>\n",
       "      <td>0.254199</td>\n",
       "      <td>0.295172</td>\n",
       "      <td>47.763063</td>\n",
       "      <td>4.521419</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>171.000000</td>\n",
       "      <td>61.000000</td>\n",
       "      <td>178.100000</td>\n",
       "      <td>453.549422</td>\n",
       "      <td>45207.000000</td>\n",
       "      <td>2.664300e+04</td>\n",
       "      <td>15.900000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>41.000000</td>\n",
       "      <td>39.600000</td>\n",
       "      <td>...</td>\n",
       "      <td>48.700000</td>\n",
       "      <td>41.100000</td>\n",
       "      <td>36.300000</td>\n",
       "      <td>18.800000</td>\n",
       "      <td>90.059774</td>\n",
       "      <td>2.247576</td>\n",
       "      <td>0.549812</td>\n",
       "      <td>0.826185</td>\n",
       "      <td>51.669941</td>\n",
       "      <td>5.381478</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>518.000000</td>\n",
       "      <td>149.000000</td>\n",
       "      <td>195.200000</td>\n",
       "      <td>480.850000</td>\n",
       "      <td>52492.000000</td>\n",
       "      <td>6.867100e+04</td>\n",
       "      <td>20.400000</td>\n",
       "      <td>83.650776</td>\n",
       "      <td>44.000000</td>\n",
       "      <td>42.500000</td>\n",
       "      <td>...</td>\n",
       "      <td>55.600000</td>\n",
       "      <td>47.700000</td>\n",
       "      <td>41.550000</td>\n",
       "      <td>23.100000</td>\n",
       "      <td>95.451693</td>\n",
       "      <td>10.509732</td>\n",
       "      <td>1.221037</td>\n",
       "      <td>2.177960</td>\n",
       "      <td>55.395132</td>\n",
       "      <td>6.493677</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>38150.000000</td>\n",
       "      <td>14010.000000</td>\n",
       "      <td>362.800000</td>\n",
       "      <td>1206.900000</td>\n",
       "      <td>125635.000000</td>\n",
       "      <td>1.017029e+07</td>\n",
       "      <td>47.400000</td>\n",
       "      <td>9762.308998</td>\n",
       "      <td>624.000000</td>\n",
       "      <td>64.700000</td>\n",
       "      <td>...</td>\n",
       "      <td>78.900000</td>\n",
       "      <td>70.700000</td>\n",
       "      <td>65.100000</td>\n",
       "      <td>46.600000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>85.947799</td>\n",
       "      <td>42.619425</td>\n",
       "      <td>41.930251</td>\n",
       "      <td>78.075397</td>\n",
       "      <td>21.326165</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>8 rows × 32 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        avgAnnCount  avgDeathsPerYear  TARGET_deathRate  incidenceRate  \\\n",
       "count   3047.000000       3047.000000       3047.000000    3047.000000   \n",
       "mean     606.338544        185.965868        178.664063     448.268586   \n",
       "std     1416.356223        504.134286         27.751511      54.560733   \n",
       "min        6.000000          3.000000         59.700000     201.300000   \n",
       "25%       76.000000         28.000000        161.200000     420.300000   \n",
       "50%      171.000000         61.000000        178.100000     453.549422   \n",
       "75%      518.000000        149.000000        195.200000     480.850000   \n",
       "max    38150.000000      14010.000000        362.800000    1206.900000   \n",
       "\n",
       "           medIncome    popEst2015  povertyPercent  studyPerCap    MedianAge  \\\n",
       "count    3047.000000  3.047000e+03     3047.000000  3047.000000  3047.000000   \n",
       "mean    47063.281917  1.026374e+05       16.878175   155.399415    45.272333   \n",
       "std     12040.090836  3.290592e+05        6.409087   529.628366    45.304480   \n",
       "min     22640.000000  8.270000e+02        3.200000     0.000000    22.300000   \n",
       "25%     38882.500000  1.168400e+04       12.150000     0.000000    37.700000   \n",
       "50%     45207.000000  2.664300e+04       15.900000     0.000000    41.000000   \n",
       "75%     52492.000000  6.867100e+04       20.400000    83.650776    44.000000   \n",
       "max    125635.000000  1.017029e+07       47.400000  9762.308998   624.000000   \n",
       "\n",
       "       MedianAgeMale  ...  PctPrivateCoverageAlone  PctEmpPrivCoverage  \\\n",
       "count    3047.000000  ...              2438.000000         3047.000000   \n",
       "mean       39.570725  ...                48.453774           41.196324   \n",
       "std         5.226017  ...                10.083006            9.447687   \n",
       "min        22.400000  ...                15.700000           13.500000   \n",
       "25%        36.350000  ...                41.000000           34.500000   \n",
       "50%        39.600000  ...                48.700000           41.100000   \n",
       "75%        42.500000  ...                55.600000           47.700000   \n",
       "max        64.700000  ...                78.900000           70.700000   \n",
       "\n",
       "       PctPublicCoverage  PctPublicCoverageAlone     PctWhite     PctBlack  \\\n",
       "count        3047.000000             3047.000000  3047.000000  3047.000000   \n",
       "mean           36.252642               19.240072    83.645286     9.107978   \n",
       "std             7.841741                6.113041    16.380025    14.534538   \n",
       "min            11.200000                2.600000    10.199155     0.000000   \n",
       "25%            30.900000               14.850000    77.296180     0.620675   \n",
       "50%            36.300000               18.800000    90.059774     2.247576   \n",
       "75%            41.550000               23.100000    95.451693    10.509732   \n",
       "max            65.100000               46.600000   100.000000    85.947799   \n",
       "\n",
       "          PctAsian  PctOtherRace  PctMarriedHouseholds    BirthRate  \n",
       "count  3047.000000   3047.000000           3047.000000  3047.000000  \n",
       "mean      1.253965      1.983523             51.243872     5.640306  \n",
       "std       2.610276      3.517710              6.572814     1.985816  \n",
       "min       0.000000      0.000000             22.992490     0.000000  \n",
       "25%       0.254199      0.295172             47.763063     4.521419  \n",
       "50%       0.549812      0.826185             51.669941     5.381478  \n",
       "75%       1.221037      2.177960             55.395132     6.493677  \n",
       "max      42.619425     41.930251             78.075397    21.326165  \n",
       "\n",
       "[8 rows x 32 columns]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "dried-speaking",
   "metadata": {},
   "source": [
    "### Plot distribution of target variable"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "classical-large",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x360 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "_, ax = plt.subplots(1, 1, figsize=(10, 5))\n",
    "df['TARGET_deathRate'].hist(bins=50, ax=ax);\n",
    "ax.set_title('Distribution of cancer death rate per 100,000 people');\n",
    "ax.set_xlabel('Cancer death rate in county (per 100,000 people)');\n",
    "ax.set_ylabel('Count');"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ceramic-credits",
   "metadata": {},
   "source": [
    "### Define feature & target variables"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "terminal-front",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "28 features\n"
     ]
    }
   ],
   "source": [
    "target = 'TARGET_deathRate'\n",
    "features = [\n",
    "    col for col in df.columns\n",
    "    if col not in [\n",
    "        target, \n",
    "        'Geography',                # Label describing the county - each row has a different one\n",
    "        'binnedInc',                # Redundant with median income?\n",
    "        'PctSomeCol18_24',          # contains null values - ignoring for now\n",
    "        'PctEmployed16_Over',       # contains null values - ignoring for now\n",
    "        'PctPrivateCoverageAlone',  # contains null values - ignoring for now\n",
    "    ]\n",
    "]\n",
    "print(len(features), 'features')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "fantastic-transfer",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(3047, 28) (3047, 1)\n"
     ]
    }
   ],
   "source": [
    "x = df[features].values\n",
    "y = df[[target]].values\n",
    "print(x.shape, y.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "stone-addiction",
   "metadata": {},
   "source": [
    "## Define model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "elementary-parts",
   "metadata": {},
   "outputs": [],
   "source": [
    "class DeepNormalModel(torch.nn.Module):\n",
    "    def __init__(\n",
    "        self, \n",
    "        n_inputs,\n",
    "        n_hidden,\n",
    "        x_scaler, \n",
    "        y_scaler,\n",
    "    ):\n",
    "        super().__init__()\n",
    "        \n",
    "        self.x_scaler = x_scaler\n",
    "        self.y_scaler = y_scaler\n",
    "        self.jitter = 1e-6\n",
    "        \n",
    "        self.shared = torch.nn.Linear(n_inputs, n_hidden)\n",
    "        \n",
    "        self.mean_hidden = torch.nn.Linear(n_hidden, n_hidden)\n",
    "        self.mean_linear = torch.nn.Linear(n_hidden, 1)\n",
    "        \n",
    "        self.std_hidden = torch.nn.Linear(n_hidden, n_hidden)\n",
    "        self.std_linear = torch.nn.Linear(n_hidden, 1)\n",
    "        \n",
    "        self.dropout = torch.nn.Dropout()\n",
    "        \n",
    "    def forward(self, x):\n",
    "        # Normalization\n",
    "        shared = self.x_scaler(x)\n",
    "        \n",
    "        # Shared layer\n",
    "        shared = self.shared(shared)\n",
    "        shared = F.relu(shared)\n",
    "        shared = self.dropout(shared)\n",
    "        \n",
    "        # Parametrization of the mean\n",
    "        mean_hidden = self.mean_hidden(shared)\n",
    "        mean_hidden = F.relu(mean_hidden)\n",
    "        mean_hidden = self.dropout(mean_hidden)\n",
    "        mean = self.mean_linear(mean_hidden)\n",
    "        \n",
    "        # Parametrization fo the standard deviation\n",
    "        std_hidden = self.std_hidden(shared)\n",
    "        std_hidden = F.relu(std_hidden)\n",
    "        std_hidden = self.dropout(std_hidden)\n",
    "        std = F.softplus(self.mean_linear(std_hidden)) + self.jitter\n",
    "        \n",
    "        return torch.distributions.Normal(mean, std)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "generous-lightweight",
   "metadata": {},
   "outputs": [],
   "source": [
    "def compute_loss(model, x, y, kl_reg=0.1):\n",
    "    y_scaled = model.y_scaler(y)\n",
    "    y_hat = model(x)\n",
    "    neg_log_likelihood = -y_hat.log_prob(y_scaled)\n",
    "    return torch.mean(neg_log_likelihood)\n",
    "\n",
    "\n",
    "def compute_rmse(model, x_test, y_test):\n",
    "    model.eval()\n",
    "    y_hat = model(x_test)\n",
    "    pred = model.y_scaler.inverse_transform(y_hat.mean)\n",
    "    return torch.sqrt(torch.mean((pred - y_test)**2))\n",
    "\n",
    "\n",
    "def train_one_step(model, optimizer, x_batch, y_batch):\n",
    "    model.train()\n",
    "    optimizer.zero_grad()\n",
    "    loss = compute_loss(model, x_batch, y_batch)\n",
    "    loss.backward()\n",
    "    optimizer.step()\n",
    "    return loss"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "binary-dylan",
   "metadata": {},
   "outputs": [],
   "source": [
    "def train(model, optimizer, x_train, x_val, y_train, y_val, n_epochs, batch_size, scheduler=None, print_every=10):\n",
    "    train_losses, val_losses = [], []\n",
    "    for epoch in range(n_epochs):\n",
    "        batch_indices = sample_batch_indices(x_train, y_train, batch_size)\n",
    "        \n",
    "        batch_losses_t, batch_losses_v, batch_rmse_v = [], [], []\n",
    "        for batch_ix in batch_indices:\n",
    "            b_train_loss = train_one_step(model, optimizer, x_train[batch_ix], y_train[batch_ix])\n",
    "\n",
    "            model.eval()\n",
    "            b_val_loss = compute_loss(model, x_val, y_val)\n",
    "            b_val_rmse = compute_rmse(model, x_val, y_val)\n",
    "\n",
    "            batch_losses_t.append(b_train_loss.detach().numpy())\n",
    "            batch_losses_v.append(b_val_loss.detach().numpy())\n",
    "            batch_rmse_v.append(b_val_rmse.detach().numpy())\n",
    "            \n",
    "        if scheduler is not None:\n",
    "            scheduler.step()\n",
    "            \n",
    "        train_loss = np.mean(batch_losses_t)\n",
    "        val_loss = np.mean(batch_losses_v)\n",
    "        val_rmse = np.mean(batch_rmse_v)\n",
    "        \n",
    "        train_losses.append(train_loss)\n",
    "        val_losses.append(val_loss)\n",
    "\n",
    "        if epoch == 0 or (epoch + 1) % print_every == 0:\n",
    "            print(f'Epoch {epoch+1} | Validation loss = {val_loss:.4f} | Validation RMSE = {val_rmse:.4f}')\n",
    "        \n",
    "    _, ax = plt.subplots(1, 1, figsize=(12, 6))\n",
    "    ax.plot(range(1, n_epochs + 1), train_losses, label='Train loss')\n",
    "    ax.plot(range(1, n_epochs + 1), val_losses, label='Validation loss')\n",
    "    ax.set_xlabel('Epoch')\n",
    "    ax.set_ylabel('Loss')\n",
    "    ax.set_title('Training Overview')\n",
    "    ax.legend()\n",
    "    \n",
    "    return train_losses, val_losses\n",
    "\n",
    "\n",
    "def sample_batch_indices(x, y, batch_size, rs=None):\n",
    "    if rs is None:\n",
    "        rs = np.random.RandomState()\n",
    "    \n",
    "    train_ix = np.arange(len(x))\n",
    "    rs.shuffle(train_ix)\n",
    "    \n",
    "    n_batches = int(np.ceil(len(x) / batch_size))\n",
    "    \n",
    "    batch_indices = []\n",
    "    for i in range(n_batches):\n",
    "        start = i + batch_size\n",
    "        end = start + batch_size\n",
    "        batch_indices.append(\n",
    "            train_ix[start:end].tolist()\n",
    "        )\n",
    "\n",
    "    return batch_indices"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "collectible-limitation",
   "metadata": {},
   "outputs": [],
   "source": [
    "class StandardScaler(object):\n",
    "    \"\"\"\n",
    "    Standardize data by removing the mean and scaling to unit variance.\n",
    "    \"\"\"\n",
    "    def __init__(self):\n",
    "        self.mean = None\n",
    "        self.scale = None\n",
    "\n",
    "    def fit(self, sample):\n",
    "        self.mean = sample.mean(0, keepdim=True)\n",
    "        self.scale = sample.std(0, unbiased=False, keepdim=True)\n",
    "        return self\n",
    "\n",
    "    def __call__(self, sample):\n",
    "        return self.transform(sample)\n",
    "    \n",
    "    def transform(self, sample):\n",
    "        return (sample - self.mean) / self.scale\n",
    "\n",
    "    def inverse_transform(self, sample):\n",
    "        return sample * self.scale + self.mean"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "structural-truck",
   "metadata": {},
   "source": [
    "## Split between training and validation sets"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "naughty-neighborhood",
   "metadata": {},
   "outputs": [],
   "source": [
    "def compute_train_test_split(x, y, test_size):\n",
    "    x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=test_size)\n",
    "    return (\n",
    "        torch.from_numpy(x_train),\n",
    "        torch.from_numpy(x_test),\n",
    "        torch.from_numpy(y_train),\n",
    "        torch.from_numpy(y_test),\n",
    "    )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "welsh-fraud",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "torch.Size([2437, 28]) torch.Size([2437, 1])\n",
      "torch.Size([610, 28]) torch.Size([610, 1])\n"
     ]
    }
   ],
   "source": [
    "x_train, x_val, y_train, y_val = compute_train_test_split(x, y, test_size=0.2)\n",
    "\n",
    "print(x_train.shape, y_train.shape)\n",
    "print(x_val.shape, y_val.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "floppy-drove",
   "metadata": {},
   "source": [
    "## Train model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "powerful-horror",
   "metadata": {},
   "outputs": [],
   "source": [
    "x_scaler = StandardScaler().fit(torch.from_numpy(x))\n",
    "y_scaler = StandardScaler().fit(torch.from_numpy(y))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "herbal-insider",
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "23,302 trainable parameters\n",
      "\n",
      "Epoch 1 | Validation loss = 1.4055 | Validation RMSE = 27.4095\n",
      "Epoch 50 | Validation loss = 0.9461 | Validation RMSE = 18.4691\n",
      "Epoch 100 | Validation loss = 0.9660 | Validation RMSE = 18.9607\n",
      "Epoch 150 | Validation loss = 0.9224 | Validation RMSE = 18.2273\n",
      "Epoch 200 | Validation loss = 0.9014 | Validation RMSE = 17.9393\n",
      "Epoch 250 | Validation loss = 0.8869 | Validation RMSE = 17.9120\n",
      "Epoch 300 | Validation loss = 0.9030 | Validation RMSE = 18.2160\n",
      "CPU times: user 54.8 s, sys: 6.85 s, total: 1min 1s\n",
      "Wall time: 55.7 s\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 864x432 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "%%time\n",
    "\n",
    "learning_rate = 1e-3\n",
    "momentum = 0.9\n",
    "weight_decay = 1e-5\n",
    "\n",
    "n_epochs = 300\n",
    "batch_size = 64\n",
    "print_every = 50\n",
    "\n",
    "n_hidden = 100\n",
    "\n",
    "model = DeepNormalModel(\n",
    "    n_inputs=x.shape[1],\n",
    "    n_hidden=n_hidden,\n",
    "    x_scaler=x_scaler, \n",
    "    y_scaler=y_scaler,\n",
    ")\n",
    "\n",
    "pytorch_total_params = sum(p.numel() for p in model.parameters() if p.requires_grad)\n",
    "print(f'{pytorch_total_params:,} trainable parameters')\n",
    "print()\n",
    "\n",
    "optimizer = torch.optim.SGD(\n",
    "    model.parameters(), \n",
    "    lr=learning_rate, \n",
    "    momentum=momentum, \n",
    "    nesterov=True,\n",
    "    weight_decay=weight_decay,\n",
    ")\n",
    "scheduler = None\n",
    "\n",
    "train_losses, val_losses = train(\n",
    "    model, \n",
    "    optimizer, \n",
    "    x_train, \n",
    "    x_val, \n",
    "    y_train, \n",
    "    y_val, \n",
    "    n_epochs=n_epochs, \n",
    "    batch_size=batch_size, \n",
    "    scheduler=scheduler, \n",
    "    print_every=print_every,\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "laden-headquarters",
   "metadata": {},
   "source": [
    "### Validation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "intermediate-identifier",
   "metadata": {},
   "outputs": [],
   "source": [
    "y_dist = model(x_val)\n",
    "y_hat = model.y_scaler.inverse_transform(y_dist.mean)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "ahead-parliament",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Validation RMSE = 18.47\n"
     ]
    }
   ],
   "source": [
    "val_rmse = float(compute_rmse(model, x_val, y_val).detach().numpy())\n",
    "print(f'Validation RMSE = {val_rmse:.2f}')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "accomplished-donor",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Validation $R^2$ = 0.56\n"
     ]
    }
   ],
   "source": [
    "val_r2 = r2_score(\n",
    "    y_val.detach().numpy().flatten(),\n",
    "    y_hat.detach().numpy().flatten(),\n",
    ")\n",
    "print(f'Validation $R^2$ = {val_r2:.2f}')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "substantial-airline",
   "metadata": {},
   "outputs": [],
   "source": [
    "def plot_results(y_true, y_pred):\n",
    "    _, ax = plt.subplots(1, 1, figsize=(7, 7))\n",
    "    palette = sns.color_palette()\n",
    "    \n",
    "    min_value = min(np.amin(y_true), np.amin(y_pred))\n",
    "    max_value = max(np.amax(y_true), np.amax(y_pred))\n",
    "    y_mid = np.linspace(min_value, max_value)\n",
    "    \n",
    "    ax.plot(y_mid, y_mid, '--', color=palette[1])\n",
    "    ax.scatter(y_true, y_pred, color=palette[0], alpha=0.5);\n",
    "    \n",
    "    return ax"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "related-concentrate",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 504x504 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "ax = plot_results(\n",
    "    y_val.detach().numpy().flatten(),\n",
    "    y_hat.detach().numpy().flatten(),\n",
    ");\n",
    "\n",
    "ax.text(270, 120, f'$R^2 = {val_r2:.2f}$')\n",
    "ax.text(270, 100, f'$RMSE = {val_rmse:.2f}$')\n",
    "    \n",
    "ax.set_xlabel('Actuals');\n",
    "ax.set_ylabel('Predictions');\n",
    "ax.set_title('Regression results on validation set');"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "caroline-nurse",
   "metadata": {},
   "source": [
    "## Uncertainty"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "proof-cigarette",
   "metadata": {},
   "outputs": [],
   "source": [
    "def make_predictions(model, x):\n",
    "    dist = model(x)\n",
    "    \n",
    "    inv_tr = model.y_scaler.inverse_transform\n",
    "    y_hat = inv_tr(dist.mean)\n",
    "    \n",
    "    # Recover standard deviation's original scale\n",
    "    std = inv_tr(dist.mean + dist.stddev) - y_hat\n",
    "    \n",
    "    return y_hat, std"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "guided-corrections",
   "metadata": {},
   "outputs": [],
   "source": [
    "y_hat, std = make_predictions(model, x_val)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "pressed-simple",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.hist(y_hat.detach().numpy().flatten(), bins=50);"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "humanitarian-quantum",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.hist(std.detach().numpy().flatten(), bins=50);"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "developmental-consent",
   "metadata": {},
   "source": [
    "### Plot absolute error against uncertainty"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "id": "opponent-canvas",
   "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>error</th>\n",
       "      <th>uncertainty</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>error</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.290894</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>uncertainty</th>\n",
       "      <td>0.290894</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                error  uncertainty\n",
       "error        1.000000     0.290894\n",
       "uncertainty  0.290894     1.000000"
      ]
     },
     "execution_count": 53,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "absolute_errors = torch.abs(y_hat - y_val).detach().numpy().flatten()\n",
    "stds = std.detach().numpy().flatten()\n",
    "\n",
    "df = pd.DataFrame.from_dict({\n",
    "    'error': absolute_errors,\n",
    "    'uncertainty': 2 * stds\n",
    "})\n",
    "df.corr()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "id": "underlying-contrast",
   "metadata": {},
   "outputs": [],
   "source": [
    "def plot_absolute_error_vs_uncertainty(y_val, y_hat, std, binned):\n",
    "    absolute_errors = torch.abs(y_hat - y_val).detach().numpy().flatten()\n",
    "    stds = std.detach().numpy().flatten()\n",
    "    \n",
    "    \n",
    "    if binned:\n",
    "        ret = binned_statistic(absolute_errors, stds, bins=100)\n",
    "        a = ret.bin_edges[1:]\n",
    "        b = ret.statistic\n",
    "        alpha = 1.0\n",
    "    else:\n",
    "        a = absolute_errors\n",
    "        b = stds\n",
    "        alpha = 0.3\n",
    "    \n",
    "    _, ax = plt.subplots(1, 1, figsize=(8, 8))\n",
    "    ax.scatter(a, b, alpha=alpha)\n",
    "    \n",
    "    return ax"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "id": "decreased-cheese",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x576 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "ax = plot_absolute_error_vs_uncertainty(y_val, y_hat, std, binned=True)\n",
    "\n",
    "ax.set_title('Absolute error vs uncertainty (binned & averaged)');\n",
    "ax.set_xlabel('Absolute error (binned)');\n",
    "ax.set_ylabel('Uncertainty (average within bin)');"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "id": "finished-prison",
   "metadata": {},
   "outputs": [],
   "source": [
    "def plot_results_with_uncertainty(y_true, y_pred, y_pred_std, subset):\n",
    "    _, ax = plt.subplots(1, 1, figsize=(7, 7))\n",
    "    palette = sns.color_palette()\n",
    "    \n",
    "    min_value = min(np.amin(y_true), np.amin(y_pred))\n",
    "    max_value = max(np.amax(y_true), np.amax(y_pred))\n",
    "    y_mid = np.linspace(min_value, max_value)\n",
    "    \n",
    "    ax.plot(y_mid, y_mid, '--', color=palette[1])\n",
    "    \n",
    "    ax.scatter(y_true, y_pred, color=palette[0], alpha=0.1);\n",
    "    \n",
    "    ax.errorbar(y_true[subset], y_pred[subset], yerr=y_pred_std[subset], color=palette[0], fmt='o')\n",
    "    \n",
    "    return ax"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "id": "cognitive-offset",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 504x504 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "ix = [i for i, v in enumerate(stds) if v > stds.mean() + 3 * stds.std()]\n",
    "\n",
    "plot_results_with_uncertainty(\n",
    "    y_val.detach().numpy().flatten(),\n",
    "    y_hat.detach().numpy().flatten(),\n",
    "    std.detach().numpy().flatten(),\n",
    "    subset=ix,\n",
    ");"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "destroyed-humor",
   "metadata": {},
   "source": [
    "### Uncertainty on an input not yet seen & very different from the rest of the dataset\n",
    "\n",
    "We'll consider an input composed of the maximum of all features."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "id": "exclusive-location",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "torch.Size([1, 28])"
      ]
     },
     "execution_count": 67,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "random_input_np = np.zeros((1, x_val.shape[1]))\n",
    "for i in range(x_val.shape[1]):\n",
    "    fn = torch.amax\n",
    "    random_input_np[0, i] = fn(x_val[:, i]) * 2\n",
    "    \n",
    "random_input = torch.from_numpy(random_input_np)\n",
    "random_input.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "id": "billion-harmony",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Uncertainty on made up input: 115.93\n"
     ]
    }
   ],
   "source": [
    "_, std = make_predictions(model, random_input)\n",
    "uncertainty = float(std.detach().numpy())\n",
    "print(f'Uncertainty on made up input: {uncertainty:.2f}')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "descending-falls",
   "metadata": {},
   "source": [
    "Uncertainty is high, which is what we want!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "incorporate-rehabilitation",
   "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": "3.7.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}