Machine Learning Medicare Fraud 2017_mod - KNN.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "from tqdm import tqdm_notebook, tqdm"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The data has a size of (904999, 32)\n"
     ]
    }
   ],
   "source": [
    "new_main_2017 = pd.read_csv('data/ml_2017.csv', low_memory=False)\n",
    "print(\"The data has a size of {}\".format(new_main_2017.shape))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "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>Unnamed: 0</th>\n",
       "      <th>npi</th>\n",
       "      <th>specialty_description</th>\n",
       "      <th>nppes_provider_state</th>\n",
       "      <th>t_cost_per_claim_excluded</th>\n",
       "      <th>t_claim_count_schedule2</th>\n",
       "      <th>t_claim_per_bene</th>\n",
       "      <th>%b2bg_claim_count</th>\n",
       "      <th>%b2bg_drug_cost</th>\n",
       "      <th>%b2t_claim_count</th>\n",
       "      <th>...</th>\n",
       "      <th>antipsych_cost_per_claim_ge65</th>\n",
       "      <th>antipsych_claim_per_bene_ge65</th>\n",
       "      <th>total_30_day_fill_count</th>\n",
       "      <th>total_day_supply</th>\n",
       "      <th>total_30_day_fill_count_ge65</th>\n",
       "      <th>total_day_supply_ge65</th>\n",
       "      <th>opioid_day_supply</th>\n",
       "      <th>opioid_prescriber_rate</th>\n",
       "      <th>is_excluded</th>\n",
       "      <th>year</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>1023417649</td>\n",
       "      <td>Internal Medicine</td>\n",
       "      <td>PA</td>\n",
       "      <td>512.29</td>\n",
       "      <td>14</td>\n",
       "      <td>2.7</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>605.0</td>\n",
       "      <td>13547</td>\n",
       "      <td>533.9</td>\n",
       "      <td>12009.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>2017-2018</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1 rows × 32 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   Unnamed: 0         npi specialty_description nppes_provider_state  \\\n",
       "0           0  1023417649     Internal Medicine                   PA   \n",
       "\n",
       "   t_cost_per_claim_excluded  t_claim_count_schedule2  t_claim_per_bene  \\\n",
       "0                     512.29                       14               2.7   \n",
       "\n",
       "   %b2bg_claim_count  %b2bg_drug_cost  %b2t_claim_count  ...  \\\n",
       "0                0.0              0.0               0.0  ...   \n",
       "\n",
       "   antipsych_cost_per_claim_ge65  antipsych_claim_per_bene_ge65  \\\n",
       "0                            0.0                            0.0   \n",
       "\n",
       "   total_30_day_fill_count  total_day_supply  total_30_day_fill_count_ge65  \\\n",
       "0                    605.0             13547                         533.9   \n",
       "\n",
       "   total_day_supply_ge65  opioid_day_supply  opioid_prescriber_rate  \\\n",
       "0                12009.0                0.0                     0.0   \n",
       "\n",
       "   is_excluded       year  \n",
       "0            0  2017-2018  \n",
       "\n",
       "[1 rows x 32 columns]"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "new_main_2017.head(1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "new_main_2017.drop(['Unnamed: 0'], axis=1, inplace = True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "new_main_2017.drop(['npi', 'specialty_description','nppes_provider_state','year'], axis=1, inplace = True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "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>t_cost_per_claim_excluded</th>\n",
       "      <th>t_claim_count_schedule2</th>\n",
       "      <th>t_claim_per_bene</th>\n",
       "      <th>%b2bg_claim_count</th>\n",
       "      <th>%b2bg_drug_cost</th>\n",
       "      <th>%b2t_claim_count</th>\n",
       "      <th>%b2t_drug_cost</th>\n",
       "      <th>t_cost_per_claim</th>\n",
       "      <th>t_cost_per_claim_ge65</th>\n",
       "      <th>t_claim_per_bene_ge65</th>\n",
       "      <th>...</th>\n",
       "      <th>antibiotic_claim_per_bene</th>\n",
       "      <th>antipsych_cost_per_claim_ge65</th>\n",
       "      <th>antipsych_claim_per_bene_ge65</th>\n",
       "      <th>total_30_day_fill_count</th>\n",
       "      <th>total_day_supply</th>\n",
       "      <th>total_30_day_fill_count_ge65</th>\n",
       "      <th>total_day_supply_ge65</th>\n",
       "      <th>opioid_day_supply</th>\n",
       "      <th>opioid_prescriber_rate</th>\n",
       "      <th>is_excluded</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>512.29</td>\n",
       "      <td>14</td>\n",
       "      <td>2.7</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>6966.0</td>\n",
       "      <td>5285.0</td>\n",
       "      <td>269.0</td>\n",
       "      <td>...</td>\n",
       "      <td>116.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>605.0</td>\n",
       "      <td>13547</td>\n",
       "      <td>533.9</td>\n",
       "      <td>12009.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1 rows × 27 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   t_cost_per_claim_excluded  t_claim_count_schedule2  t_claim_per_bene  \\\n",
       "0                     512.29                       14               2.7   \n",
       "\n",
       "   %b2bg_claim_count  %b2bg_drug_cost  %b2t_claim_count  %b2t_drug_cost  \\\n",
       "0                0.0              0.0               0.0             0.0   \n",
       "\n",
       "   t_cost_per_claim  t_cost_per_claim_ge65  t_claim_per_bene_ge65  ...  \\\n",
       "0            6966.0                 5285.0                  269.0  ...   \n",
       "\n",
       "   antibiotic_claim_per_bene  antipsych_cost_per_claim_ge65  \\\n",
       "0                      116.0                            0.0   \n",
       "\n",
       "   antipsych_claim_per_bene_ge65  total_30_day_fill_count  total_day_supply  \\\n",
       "0                            0.0                    605.0             13547   \n",
       "\n",
       "   total_30_day_fill_count_ge65  total_day_supply_ge65  opioid_day_supply  \\\n",
       "0                         533.9                12009.0                0.0   \n",
       "\n",
       "   opioid_prescriber_rate  is_excluded  \n",
       "0                     0.0            0  \n",
       "\n",
       "[1 rows x 27 columns]"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "new_main_2017.head(1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "101"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(new_main_2017[new_main_2017['is_excluded'] == 1])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "dropIndex = new_main_2017[new_main_2017['is_excluded'] == 1].index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "904898"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(new_main_2017[new_main_2017['is_excluded'] == 0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "only_excluded = new_main_2017[new_main_2017['is_excluded'] == 1]\n",
    "new_main_2017.drop(dropIndex, inplace = True)\n",
    "new_main_2017 = new_main_2017.sample(frac=1)\n",
    "random_sample = new_main_2017.iloc[0:180899]\n",
    "new_df = pd.concat([only_excluded, random_sample])\n",
    "new_main_2017 = new_main_2017.drop(new_main_2017.iloc[0:180899].index, axis = 0)\n",
    "new_df = new_df.sample(frac=1)\n",
    "#part_d_df.iloc[0:85000].index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "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>t_cost_per_claim_excluded</th>\n",
       "      <th>t_claim_count_schedule2</th>\n",
       "      <th>t_claim_per_bene</th>\n",
       "      <th>%b2bg_claim_count</th>\n",
       "      <th>%b2bg_drug_cost</th>\n",
       "      <th>%b2t_claim_count</th>\n",
       "      <th>%b2t_drug_cost</th>\n",
       "      <th>t_cost_per_claim</th>\n",
       "      <th>t_cost_per_claim_ge65</th>\n",
       "      <th>t_claim_per_bene_ge65</th>\n",
       "      <th>...</th>\n",
       "      <th>antibiotic_claim_per_bene</th>\n",
       "      <th>antipsych_cost_per_claim_ge65</th>\n",
       "      <th>antipsych_claim_per_bene_ge65</th>\n",
       "      <th>total_30_day_fill_count</th>\n",
       "      <th>total_day_supply</th>\n",
       "      <th>total_30_day_fill_count_ge65</th>\n",
       "      <th>total_day_supply_ge65</th>\n",
       "      <th>opioid_day_supply</th>\n",
       "      <th>opioid_prescriber_rate</th>\n",
       "      <th>is_excluded</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>640617</th>\n",
       "      <td>1943.33</td>\n",
       "      <td>13</td>\n",
       "      <td>4.1</td>\n",
       "      <td>10.0</td>\n",
       "      <td>63.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>63.0</td>\n",
       "      <td>8379.0</td>\n",
       "      <td>7896.0</td>\n",
       "      <td>360.0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>635.5</td>\n",
       "      <td>17957</td>\n",
       "      <td>377.2</td>\n",
       "      <td>10549.0</td>\n",
       "      <td>10307.0</td>\n",
       "      <td>59.67</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>750391</th>\n",
       "      <td>1573.63</td>\n",
       "      <td>5</td>\n",
       "      <td>2.9</td>\n",
       "      <td>20.0</td>\n",
       "      <td>44.0</td>\n",
       "      <td>20.0</td>\n",
       "      <td>44.0</td>\n",
       "      <td>7508.0</td>\n",
       "      <td>9285.0</td>\n",
       "      <td>329.0</td>\n",
       "      <td>...</td>\n",
       "      <td>133.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>260.9</td>\n",
       "      <td>6834</td>\n",
       "      <td>158.9</td>\n",
       "      <td>4192.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>768194</th>\n",
       "      <td>1278.57</td>\n",
       "      <td>20</td>\n",
       "      <td>17.3</td>\n",
       "      <td>20.0</td>\n",
       "      <td>64.0</td>\n",
       "      <td>20.0</td>\n",
       "      <td>64.0</td>\n",
       "      <td>10612.0</td>\n",
       "      <td>11221.0</td>\n",
       "      <td>2105.0</td>\n",
       "      <td>...</td>\n",
       "      <td>244.0</td>\n",
       "      <td>59451.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1012.5</td>\n",
       "      <td>28409</td>\n",
       "      <td>417.8</td>\n",
       "      <td>11915.0</td>\n",
       "      <td>2850.0</td>\n",
       "      <td>9.96</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>596409</th>\n",
       "      <td>280.36</td>\n",
       "      <td>11</td>\n",
       "      <td>1.7</td>\n",
       "      <td>10.0</td>\n",
       "      <td>36.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>36.0</td>\n",
       "      <td>1506.0</td>\n",
       "      <td>1582.0</td>\n",
       "      <td>160.0</td>\n",
       "      <td>...</td>\n",
       "      <td>105.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>383.1</td>\n",
       "      <td>4122</td>\n",
       "      <td>217.0</td>\n",
       "      <td>2194.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>689207</th>\n",
       "      <td>87.83</td>\n",
       "      <td>1</td>\n",
       "      <td>1.6</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>520.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>129.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>33.0</td>\n",
       "      <td>261</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 27 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        t_cost_per_claim_excluded  t_claim_count_schedule2  t_claim_per_bene  \\\n",
       "640617                    1943.33                       13               4.1   \n",
       "750391                    1573.63                        5               2.9   \n",
       "768194                    1278.57                       20              17.3   \n",
       "596409                     280.36                       11               1.7   \n",
       "689207                      87.83                        1               1.6   \n",
       "\n",
       "        %b2bg_claim_count  %b2bg_drug_cost  %b2t_claim_count  %b2t_drug_cost  \\\n",
       "640617               10.0             63.0              10.0            63.0   \n",
       "750391               20.0             44.0              20.0            44.0   \n",
       "768194               20.0             64.0              20.0            64.0   \n",
       "596409               10.0             36.0              10.0            36.0   \n",
       "689207                0.0              0.0               0.0             0.0   \n",
       "\n",
       "        t_cost_per_claim  t_cost_per_claim_ge65  t_claim_per_bene_ge65  ...  \\\n",
       "640617            8379.0                 7896.0                  360.0  ...   \n",
       "750391            7508.0                 9285.0                  329.0  ...   \n",
       "768194           10612.0                11221.0                 2105.0  ...   \n",
       "596409            1506.0                 1582.0                  160.0  ...   \n",
       "689207             520.0                    0.0                    0.0  ...   \n",
       "\n",
       "        antibiotic_claim_per_bene  antipsych_cost_per_claim_ge65  \\\n",
       "640617                        0.0                            0.0   \n",
       "750391                      133.0                            0.0   \n",
       "768194                      244.0                        59451.0   \n",
       "596409                      105.0                            0.0   \n",
       "689207                      129.0                            0.0   \n",
       "\n",
       "        antipsych_claim_per_bene_ge65  total_30_day_fill_count  \\\n",
       "640617                            0.0                    635.5   \n",
       "750391                            0.0                    260.9   \n",
       "768194                            0.0                   1012.5   \n",
       "596409                            0.0                    383.1   \n",
       "689207                            0.0                     33.0   \n",
       "\n",
       "        total_day_supply  total_30_day_fill_count_ge65  total_day_supply_ge65  \\\n",
       "640617             17957                         377.2                10549.0   \n",
       "750391              6834                         158.9                 4192.0   \n",
       "768194             28409                         417.8                11915.0   \n",
       "596409              4122                         217.0                 2194.0   \n",
       "689207               261                           0.0                    0.0   \n",
       "\n",
       "        opioid_day_supply  opioid_prescriber_rate  is_excluded  \n",
       "640617            10307.0                   59.67            0  \n",
       "750391                0.0                    0.00            0  \n",
       "768194             2850.0                    9.96            0  \n",
       "596409                0.0                    0.00            0  \n",
       "689207                0.0                    0.00            0  \n",
       "\n",
       "[5 rows x 27 columns]"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#new_df.drop(['Unnamed: 0'], axis=1, inplace = True)\n",
    "new_df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "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>t_cost_per_claim_excluded</th>\n",
       "      <th>t_claim_count_schedule2</th>\n",
       "      <th>t_claim_per_bene</th>\n",
       "      <th>%b2bg_claim_count</th>\n",
       "      <th>%b2bg_drug_cost</th>\n",
       "      <th>%b2t_claim_count</th>\n",
       "      <th>%b2t_drug_cost</th>\n",
       "      <th>t_cost_per_claim</th>\n",
       "      <th>t_cost_per_claim_ge65</th>\n",
       "      <th>t_claim_per_bene_ge65</th>\n",
       "      <th>...</th>\n",
       "      <th>antibiotic_claim_per_bene</th>\n",
       "      <th>antipsych_cost_per_claim_ge65</th>\n",
       "      <th>antipsych_claim_per_bene_ge65</th>\n",
       "      <th>total_30_day_fill_count</th>\n",
       "      <th>total_day_supply</th>\n",
       "      <th>total_30_day_fill_count_ge65</th>\n",
       "      <th>total_day_supply_ge65</th>\n",
       "      <th>opioid_day_supply</th>\n",
       "      <th>opioid_prescriber_rate</th>\n",
       "      <th>is_excluded</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>7.239990e+05</td>\n",
       "      <td>723999.000000</td>\n",
       "      <td>723999.000000</td>\n",
       "      <td>723999.000000</td>\n",
       "      <td>723999.000000</td>\n",
       "      <td>723999.000000</td>\n",
       "      <td>723999.000000</td>\n",
       "      <td>7.239990e+05</td>\n",
       "      <td>7.239990e+05</td>\n",
       "      <td>723999.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>723999.000000</td>\n",
       "      <td>723999.000000</td>\n",
       "      <td>723999.000000</td>\n",
       "      <td>723999.000000</td>\n",
       "      <td>7.239990e+05</td>\n",
       "      <td>723999.000000</td>\n",
       "      <td>7.239990e+05</td>\n",
       "      <td>723999.000000</td>\n",
       "      <td>723999.000000</td>\n",
       "      <td>723999.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>2.211595e+03</td>\n",
       "      <td>25.530519</td>\n",
       "      <td>6.389761</td>\n",
       "      <td>12.569051</td>\n",
       "      <td>38.906029</td>\n",
       "      <td>12.347517</td>\n",
       "      <td>38.846846</td>\n",
       "      <td>1.253042e+04</td>\n",
       "      <td>1.026093e+04</td>\n",
       "      <td>478.928703</td>\n",
       "      <td>...</td>\n",
       "      <td>92.371187</td>\n",
       "      <td>1382.985420</td>\n",
       "      <td>28.341136</td>\n",
       "      <td>2507.240687</td>\n",
       "      <td>6.969298e+04</td>\n",
       "      <td>2032.622450</td>\n",
       "      <td>5.681541e+04</td>\n",
       "      <td>1840.436407</td>\n",
       "      <td>8.735216</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>5.780364e+03</td>\n",
       "      <td>40.552056</td>\n",
       "      <td>7.114598</td>\n",
       "      <td>16.528388</td>\n",
       "      <td>37.132151</td>\n",
       "      <td>15.887904</td>\n",
       "      <td>36.907153</td>\n",
       "      <td>5.398670e+04</td>\n",
       "      <td>3.652764e+04</td>\n",
       "      <td>686.064979</td>\n",
       "      <td>...</td>\n",
       "      <td>82.630107</td>\n",
       "      <td>6956.817534</td>\n",
       "      <td>144.814574</td>\n",
       "      <td>5137.089381</td>\n",
       "      <td>1.438730e+05</td>\n",
       "      <td>4460.559101</td>\n",
       "      <td>1.252993e+05</td>\n",
       "      <td>8366.798245</td>\n",
       "      <td>18.344355</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>11.000000</td>\n",
       "      <td>1.100000e+01</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>1.670100e+02</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>1.900000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>2.355000e+03</td>\n",
       "      <td>1.397000e+03</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>141.000000</td>\n",
       "      <td>2.168000e+03</td>\n",
       "      <td>72.000000</td>\n",
       "      <td>9.720000e+02</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>6.741900e+02</td>\n",
       "      <td>7.000000</td>\n",
       "      <td>3.600000</td>\n",
       "      <td>10.000000</td>\n",
       "      <td>42.000000</td>\n",
       "      <td>10.000000</td>\n",
       "      <td>43.000000</td>\n",
       "      <td>5.505000e+03</td>\n",
       "      <td>4.658000e+03</td>\n",
       "      <td>222.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>113.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>444.900000</td>\n",
       "      <td>1.027400e+04</td>\n",
       "      <td>298.000000</td>\n",
       "      <td>6.691000e+03</td>\n",
       "      <td>46.000000</td>\n",
       "      <td>0.810000</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>2.370290e+03</td>\n",
       "      <td>29.000000</td>\n",
       "      <td>8.300000</td>\n",
       "      <td>20.000000</td>\n",
       "      <td>73.000000</td>\n",
       "      <td>20.000000</td>\n",
       "      <td>73.000000</td>\n",
       "      <td>9.334000e+03</td>\n",
       "      <td>7.992000e+03</td>\n",
       "      <td>652.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>143.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>2266.000000</td>\n",
       "      <td>6.273600e+04</td>\n",
       "      <td>1609.700000</td>\n",
       "      <td>4.438300e+04</td>\n",
       "      <td>630.000000</td>\n",
       "      <td>8.420000</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>1.713038e+06</td>\n",
       "      <td>393.000000</td>\n",
       "      <td>307.100000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>1.712797e+07</td>\n",
       "      <td>7.622389e+06</td>\n",
       "      <td>27000.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>3422.000000</td>\n",
       "      <td>479253.000000</td>\n",
       "      <td>6007.000000</td>\n",
       "      <td>447960.500000</td>\n",
       "      <td>5.634058e+06</td>\n",
       "      <td>379751.000000</td>\n",
       "      <td>4.737252e+06</td>\n",
       "      <td>615456.000000</td>\n",
       "      <td>909.000000</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>8 rows × 27 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       t_cost_per_claim_excluded  t_claim_count_schedule2  t_claim_per_bene  \\\n",
       "count               7.239990e+05            723999.000000     723999.000000   \n",
       "mean                2.211595e+03                25.530519          6.389761   \n",
       "std                 5.780364e+03                40.552056          7.114598   \n",
       "min                 0.000000e+00                 0.000000          0.000000   \n",
       "25%                 1.670100e+02                 2.000000          1.900000   \n",
       "50%                 6.741900e+02                 7.000000          3.600000   \n",
       "75%                 2.370290e+03                29.000000          8.300000   \n",
       "max                 1.713038e+06               393.000000        307.100000   \n",
       "\n",
       "       %b2bg_claim_count  %b2bg_drug_cost  %b2t_claim_count  %b2t_drug_cost  \\\n",
       "count      723999.000000    723999.000000     723999.000000   723999.000000   \n",
       "mean           12.569051        38.906029         12.347517       38.846846   \n",
       "std            16.528388        37.132151         15.887904       36.907153   \n",
       "min             0.000000         0.000000          0.000000        0.000000   \n",
       "25%             0.000000         0.000000          0.000000        0.000000   \n",
       "50%            10.000000        42.000000         10.000000       43.000000   \n",
       "75%            20.000000        73.000000         20.000000       73.000000   \n",
       "max           100.000000       100.000000        100.000000      100.000000   \n",
       "\n",
       "       t_cost_per_claim  t_cost_per_claim_ge65  t_claim_per_bene_ge65  ...  \\\n",
       "count      7.239990e+05           7.239990e+05          723999.000000  ...   \n",
       "mean       1.253042e+04           1.026093e+04             478.928703  ...   \n",
       "std        5.398670e+04           3.652764e+04             686.064979  ...   \n",
       "min        0.000000e+00           0.000000e+00               0.000000  ...   \n",
       "25%        2.355000e+03           1.397000e+03               0.000000  ...   \n",
       "50%        5.505000e+03           4.658000e+03             222.000000  ...   \n",
       "75%        9.334000e+03           7.992000e+03             652.000000  ...   \n",
       "max        1.712797e+07           7.622389e+06           27000.000000  ...   \n",
       "\n",
       "       antibiotic_claim_per_bene  antipsych_cost_per_claim_ge65  \\\n",
       "count              723999.000000                  723999.000000   \n",
       "mean                   92.371187                    1382.985420   \n",
       "std                    82.630107                    6956.817534   \n",
       "min                     0.000000                       0.000000   \n",
       "25%                     0.000000                       0.000000   \n",
       "50%                   113.000000                       0.000000   \n",
       "75%                   143.000000                       0.000000   \n",
       "max                  3422.000000                  479253.000000   \n",
       "\n",
       "       antipsych_claim_per_bene_ge65  total_30_day_fill_count  \\\n",
       "count                  723999.000000            723999.000000   \n",
       "mean                       28.341136              2507.240687   \n",
       "std                       144.814574              5137.089381   \n",
       "min                         0.000000                11.000000   \n",
       "25%                         0.000000               141.000000   \n",
       "50%                         0.000000               444.900000   \n",
       "75%                         0.000000              2266.000000   \n",
       "max                      6007.000000            447960.500000   \n",
       "\n",
       "       total_day_supply  total_30_day_fill_count_ge65  total_day_supply_ge65  \\\n",
       "count      7.239990e+05                 723999.000000           7.239990e+05   \n",
       "mean       6.969298e+04                   2032.622450           5.681541e+04   \n",
       "std        1.438730e+05                   4460.559101           1.252993e+05   \n",
       "min        1.100000e+01                      0.000000           0.000000e+00   \n",
       "25%        2.168000e+03                     72.000000           9.720000e+02   \n",
       "50%        1.027400e+04                    298.000000           6.691000e+03   \n",
       "75%        6.273600e+04                   1609.700000           4.438300e+04   \n",
       "max        5.634058e+06                 379751.000000           4.737252e+06   \n",
       "\n",
       "       opioid_day_supply  opioid_prescriber_rate  is_excluded  \n",
       "count      723999.000000           723999.000000     723999.0  \n",
       "mean         1840.436407                8.735216          0.0  \n",
       "std          8366.798245               18.344355          0.0  \n",
       "min             0.000000                0.000000          0.0  \n",
       "25%             0.000000                0.000000          0.0  \n",
       "50%            46.000000                0.810000          0.0  \n",
       "75%           630.000000                8.420000          0.0  \n",
       "max        615456.000000              909.000000          0.0  \n",
       "\n",
       "[8 rows x 27 columns]"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "new_main_2017.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "import math"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn import decomposition\n",
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.metrics import confusion_matrix, roc_curve, roc_auc_score, auc\n",
    "from sklearn.utils import resample\n",
    "from sklearn.preprocessing import label_binarize\n",
    "from sklearn.svm import SVC\n",
    "from scipy.stats import pointbiserialr"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>t_cost_per_claim_excluded</th>\n",
       "      <th>t_claim_count_schedule2</th>\n",
       "      <th>t_claim_per_bene</th>\n",
       "      <th>%b2bg_claim_count</th>\n",
       "      <th>%b2bg_drug_cost</th>\n",
       "      <th>%b2t_claim_count</th>\n",
       "      <th>%b2t_drug_cost</th>\n",
       "      <th>t_cost_per_claim</th>\n",
       "      <th>t_cost_per_claim_ge65</th>\n",
       "      <th>t_claim_per_bene_ge65</th>\n",
       "      <th>...</th>\n",
       "      <th>antibiotic_claim_per_bene</th>\n",
       "      <th>antipsych_cost_per_claim_ge65</th>\n",
       "      <th>antipsych_claim_per_bene_ge65</th>\n",
       "      <th>total_30_day_fill_count</th>\n",
       "      <th>total_day_supply</th>\n",
       "      <th>total_30_day_fill_count_ge65</th>\n",
       "      <th>total_day_supply_ge65</th>\n",
       "      <th>opioid_day_supply</th>\n",
       "      <th>opioid_prescriber_rate</th>\n",
       "      <th>is_excluded</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>1000000.000000</td>\n",
       "      <td>1000000.000000</td>\n",
       "      <td>1000000.000000</td>\n",
       "      <td>1000000.000000</td>\n",
       "      <td>1000000.000000</td>\n",
       "      <td>1000000.000000</td>\n",
       "      <td>1000000.000000</td>\n",
       "      <td>1000000.000000</td>\n",
       "      <td>1000000.000000</td>\n",
       "      <td>1000000.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>1000000.000000</td>\n",
       "      <td>1000000.000000</td>\n",
       "      <td>1000000.000000</td>\n",
       "      <td>1000000.000000</td>\n",
       "      <td>1000000.000000</td>\n",
       "      <td>1000000.000000</td>\n",
       "      <td>1000000.000000</td>\n",
       "      <td>1000000.000000</td>\n",
       "      <td>1000000.000000</td>\n",
       "      <td>1000000.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>5194.967630</td>\n",
       "      <td>38.609067</td>\n",
       "      <td>9.485671</td>\n",
       "      <td>11.374050</td>\n",
       "      <td>36.234950</td>\n",
       "      <td>10.876360</td>\n",
       "      <td>36.026284</td>\n",
       "      <td>10551.133795</td>\n",
       "      <td>8908.213605</td>\n",
       "      <td>751.031469</td>\n",
       "      <td>...</td>\n",
       "      <td>77.438471</td>\n",
       "      <td>2743.050558</td>\n",
       "      <td>43.789287</td>\n",
       "      <td>3131.733322</td>\n",
       "      <td>88423.346199</td>\n",
       "      <td>2090.284659</td>\n",
       "      <td>59364.759391</td>\n",
       "      <td>5985.222628</td>\n",
       "      <td>8.280612</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>28249.745002</td>\n",
       "      <td>55.813583</td>\n",
       "      <td>9.620971</td>\n",
       "      <td>14.980311</td>\n",
       "      <td>36.168503</td>\n",
       "      <td>12.989995</td>\n",
       "      <td>35.937057</td>\n",
       "      <td>17528.724650</td>\n",
       "      <td>16454.262782</td>\n",
       "      <td>932.513383</td>\n",
       "      <td>...</td>\n",
       "      <td>88.433065</td>\n",
       "      <td>8561.702769</td>\n",
       "      <td>158.750327</td>\n",
       "      <td>5513.810033</td>\n",
       "      <td>156739.468845</td>\n",
       "      <td>4178.857341</td>\n",
       "      <td>118866.398677</td>\n",
       "      <td>22597.822680</td>\n",
       "      <td>14.853448</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>40.990000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>294.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>13.000000</td>\n",
       "      <td>221.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>293.230000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>2.200000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>4406.000000</td>\n",
       "      <td>2876.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>109.000000</td>\n",
       "      <td>2955.000000</td>\n",
       "      <td>62.000000</td>\n",
       "      <td>1280.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>1206.820000</td>\n",
       "      <td>11.000000</td>\n",
       "      <td>5.800000</td>\n",
       "      <td>10.000000</td>\n",
       "      <td>43.000000</td>\n",
       "      <td>10.000000</td>\n",
       "      <td>43.000000</td>\n",
       "      <td>7223.000000</td>\n",
       "      <td>5345.000000</td>\n",
       "      <td>378.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>632.600000</td>\n",
       "      <td>18369.000000</td>\n",
       "      <td>368.400000</td>\n",
       "      <td>10843.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>3338.240000</td>\n",
       "      <td>54.000000</td>\n",
       "      <td>13.800000</td>\n",
       "      <td>20.000000</td>\n",
       "      <td>71.000000</td>\n",
       "      <td>20.000000</td>\n",
       "      <td>70.000000</td>\n",
       "      <td>10419.000000</td>\n",
       "      <td>7982.000000</td>\n",
       "      <td>1163.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>157.000000</td>\n",
       "      <td>633.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>3164.200000</td>\n",
       "      <td>90194.000000</td>\n",
       "      <td>1882.600000</td>\n",
       "      <td>52000.000000</td>\n",
       "      <td>3107.000000</td>\n",
       "      <td>7.590000</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>286886.380000</td>\n",
       "      <td>299.000000</td>\n",
       "      <td>46.100000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>60.000000</td>\n",
       "      <td>98.000000</td>\n",
       "      <td>141957.000000</td>\n",
       "      <td>125896.000000</td>\n",
       "      <td>4355.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>322.000000</td>\n",
       "      <td>50758.000000</td>\n",
       "      <td>803.000000</td>\n",
       "      <td>33073.000000</td>\n",
       "      <td>934916.000000</td>\n",
       "      <td>22770.800000</td>\n",
       "      <td>647623.000000</td>\n",
       "      <td>213611.000000</td>\n",
       "      <td>68.220000</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>8 rows × 27 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       t_cost_per_claim_excluded  t_claim_count_schedule2  t_claim_per_bene  \\\n",
       "count             1000000.000000           1000000.000000    1000000.000000   \n",
       "mean                 5194.967630                38.609067          9.485671   \n",
       "std                 28249.745002                55.813583          9.620971   \n",
       "min                    40.990000                 1.000000          0.000000   \n",
       "25%                   293.230000                 3.000000          2.200000   \n",
       "50%                  1206.820000                11.000000          5.800000   \n",
       "75%                  3338.240000                54.000000         13.800000   \n",
       "max                286886.380000               299.000000         46.100000   \n",
       "\n",
       "       %b2bg_claim_count  %b2bg_drug_cost  %b2t_claim_count  %b2t_drug_cost  \\\n",
       "count     1000000.000000   1000000.000000    1000000.000000  1000000.000000   \n",
       "mean           11.374050        36.234950         10.876360       36.026284   \n",
       "std            14.980311        36.168503         12.989995       35.937057   \n",
       "min             0.000000         0.000000          0.000000        0.000000   \n",
       "25%             0.000000         0.000000          0.000000        0.000000   \n",
       "50%            10.000000        43.000000         10.000000       43.000000   \n",
       "75%            20.000000        71.000000         20.000000       70.000000   \n",
       "max           100.000000       100.000000         60.000000       98.000000   \n",
       "\n",
       "       t_cost_per_claim  t_cost_per_claim_ge65  t_claim_per_bene_ge65  ...  \\\n",
       "count    1000000.000000         1000000.000000         1000000.000000  ...   \n",
       "mean       10551.133795            8908.213605             751.031469  ...   \n",
       "std        17528.724650           16454.262782             932.513383  ...   \n",
       "min          294.000000               0.000000               0.000000  ...   \n",
       "25%         4406.000000            2876.000000               0.000000  ...   \n",
       "50%         7223.000000            5345.000000             378.000000  ...   \n",
       "75%        10419.000000            7982.000000            1163.000000  ...   \n",
       "max       141957.000000          125896.000000            4355.000000  ...   \n",
       "\n",
       "       antibiotic_claim_per_bene  antipsych_cost_per_claim_ge65  \\\n",
       "count             1000000.000000                 1000000.000000   \n",
       "mean                   77.438471                    2743.050558   \n",
       "std                    88.433065                    8561.702769   \n",
       "min                     0.000000                       0.000000   \n",
       "25%                     0.000000                       0.000000   \n",
       "50%                     0.000000                       0.000000   \n",
       "75%                   157.000000                     633.000000   \n",
       "max                   322.000000                   50758.000000   \n",
       "\n",
       "       antipsych_claim_per_bene_ge65  total_30_day_fill_count  \\\n",
       "count                 1000000.000000           1000000.000000   \n",
       "mean                       43.789287              3131.733322   \n",
       "std                       158.750327              5513.810033   \n",
       "min                         0.000000                13.000000   \n",
       "25%                         0.000000               109.000000   \n",
       "50%                         0.000000               632.600000   \n",
       "75%                         0.000000              3164.200000   \n",
       "max                       803.000000             33073.000000   \n",
       "\n",
       "       total_day_supply  total_30_day_fill_count_ge65  total_day_supply_ge65  \\\n",
       "count    1000000.000000                1000000.000000         1000000.000000   \n",
       "mean       88423.346199                   2090.284659           59364.759391   \n",
       "std       156739.468845                   4178.857341          118866.398677   \n",
       "min          221.000000                      0.000000               0.000000   \n",
       "25%         2955.000000                     62.000000            1280.000000   \n",
       "50%        18369.000000                    368.400000           10843.000000   \n",
       "75%        90194.000000                   1882.600000           52000.000000   \n",
       "max       934916.000000                  22770.800000          647623.000000   \n",
       "\n",
       "       opioid_day_supply  opioid_prescriber_rate  is_excluded  \n",
       "count     1000000.000000          1000000.000000    1000000.0  \n",
       "mean         5985.222628                8.280612          1.0  \n",
       "std         22597.822680               14.853448          0.0  \n",
       "min             0.000000                0.000000          1.0  \n",
       "25%             0.000000                0.000000          1.0  \n",
       "50%             0.000000                0.000000          1.0  \n",
       "75%          3107.000000                7.590000          1.0  \n",
       "max        213611.000000               68.220000          1.0  \n",
       "\n",
       "[8 rows x 27 columns]"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#part_d_excluded = new_df[new_df[\"is_excluded\"]==1]\n",
    "\n",
    "fudge = resample(only_excluded, replace=True, n_samples=1000000, random_state = 0)\n",
    "#fudge.drop(['Unnamed: 0'], axis=1, inplace = True)\n",
    "fudge.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "std = fudge.describe().loc[\"std\"]\n",
    "std = std[0:26]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "rtstd = std.map(lambda x : math.sqrt(x)/2) #use half of square root of standard deviation as the range for gaussian normal\n",
    "rtstd = rtstd.to_dict()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\ipykernel_launcher.py:3: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
      "Try using .loc[row_indexer,col_indexer] = value instead\n",
      "\n",
      "See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
      "  This is separate from the ipykernel package so we can avoid doing imports until\n"
     ]
    }
   ],
   "source": [
    "for key in rtstd:\n",
    "    #fudge[key] = fudge[key].map(lambda x: (np.random.normal(x, rtstd[key])))\n",
    "    fudge[key] = fudge[key].map(lambda x: (np.random.normal(x, 2)))\n",
    "fudge = fudge[fudge>=0]\n",
    "fudge.dropna(inplace = True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'t_cost_per_claim_excluded': 84.03830228283725,\n",
       " 't_claim_count_schedule2': 3.735424432090368,\n",
       " 't_claim_per_bene': 1.5508844893809823,\n",
       " '%b2bg_claim_count': 1.9352203219559672,\n",
       " '%b2bg_drug_cost': 3.007012758064355,\n",
       " '%b2t_claim_count': 1.802081760350314,\n",
       " '%b2t_drug_cost': 2.99737621069871,\n",
       " 't_cost_per_claim': 66.19804500548426,\n",
       " 't_cost_per_claim_ge65': 64.13708518052151,\n",
       " 't_claim_per_bene_ge65': 15.268541048298102,\n",
       " 'mapd_cost_per_claim': 64.61408506431768,\n",
       " 'pdp_cost_per_claim': 67.25735816485223,\n",
       " 'lis_cost_per_claim': 68.22596052313033,\n",
       " 'nonlis_cost_per_claim': 62.07153722436618,\n",
       " 'opioid_cost_per_claim': 46.504668620058595,\n",
       " 'opioid_claim_per_bene': 8.847407251096762,\n",
       " 'antibiotic_cost_per_claim': 29.817508674809556,\n",
       " 'antibiotic_claim_per_bene': 4.701942818546453,\n",
       " 'antipsych_cost_per_claim_ge65': 46.26473486591827,\n",
       " 'antipsych_claim_per_bene_ge65': 6.299808071086247,\n",
       " 'total_30_day_fill_count': 37.12751686106159,\n",
       " 'total_day_supply': 197.95167898077315,\n",
       " 'total_30_day_fill_count_ge65': 32.32204101305794,\n",
       " 'total_day_supply_ge65': 172.3850331940279,\n",
       " 'opioid_day_supply': 75.1628609755071,\n",
       " 'opioid_prescriber_rate': 1.9270085656978702}"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rtstd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "scrolled": false
   },
   "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>t_cost_per_claim_excluded</th>\n",
       "      <th>t_claim_count_schedule2</th>\n",
       "      <th>t_claim_per_bene</th>\n",
       "      <th>%b2bg_claim_count</th>\n",
       "      <th>%b2bg_drug_cost</th>\n",
       "      <th>%b2t_claim_count</th>\n",
       "      <th>%b2t_drug_cost</th>\n",
       "      <th>t_cost_per_claim</th>\n",
       "      <th>t_cost_per_claim_ge65</th>\n",
       "      <th>t_claim_per_bene_ge65</th>\n",
       "      <th>...</th>\n",
       "      <th>antibiotic_claim_per_bene</th>\n",
       "      <th>antipsych_cost_per_claim_ge65</th>\n",
       "      <th>antipsych_claim_per_bene_ge65</th>\n",
       "      <th>total_30_day_fill_count</th>\n",
       "      <th>total_day_supply</th>\n",
       "      <th>total_30_day_fill_count_ge65</th>\n",
       "      <th>total_day_supply_ge65</th>\n",
       "      <th>opioid_day_supply</th>\n",
       "      <th>opioid_prescriber_rate</th>\n",
       "      <th>is_excluded</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>115020.000000</td>\n",
       "      <td>115020.000000</td>\n",
       "      <td>115020.000000</td>\n",
       "      <td>115020.000000</td>\n",
       "      <td>115020.000000</td>\n",
       "      <td>115020.000000</td>\n",
       "      <td>115020.000000</td>\n",
       "      <td>115020.000000</td>\n",
       "      <td>115020.000000</td>\n",
       "      <td>115020.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>115020.000000</td>\n",
       "      <td>115020.000000</td>\n",
       "      <td>115020.000000</td>\n",
       "      <td>115020.000000</td>\n",
       "      <td>115020.000000</td>\n",
       "      <td>115020.000000</td>\n",
       "      <td>115020.000000</td>\n",
       "      <td>115020.000000</td>\n",
       "      <td>115020.000000</td>\n",
       "      <td>115020.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>3620.440014</td>\n",
       "      <td>121.796508</td>\n",
       "      <td>21.059942</td>\n",
       "      <td>17.642962</td>\n",
       "      <td>66.652208</td>\n",
       "      <td>17.643202</td>\n",
       "      <td>66.167208</td>\n",
       "      <td>8202.252845</td>\n",
       "      <td>7535.053842</td>\n",
       "      <td>2019.749603</td>\n",
       "      <td>...</td>\n",
       "      <td>168.453609</td>\n",
       "      <td>8510.089217</td>\n",
       "      <td>247.844387</td>\n",
       "      <td>10443.221261</td>\n",
       "      <td>294409.215004</td>\n",
       "      <td>7264.580999</td>\n",
       "      <td>205487.963975</td>\n",
       "      <td>12149.091988</td>\n",
       "      <td>8.544059</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>3351.937990</td>\n",
       "      <td>76.062795</td>\n",
       "      <td>10.511540</td>\n",
       "      <td>6.744974</td>\n",
       "      <td>12.650744</td>\n",
       "      <td>6.751661</td>\n",
       "      <td>12.649563</td>\n",
       "      <td>5412.909876</td>\n",
       "      <td>4741.734793</td>\n",
       "      <td>1058.971552</td>\n",
       "      <td>...</td>\n",
       "      <td>51.586517</td>\n",
       "      <td>14300.084406</td>\n",
       "      <td>307.834687</td>\n",
       "      <td>8896.147327</td>\n",
       "      <td>252005.648105</td>\n",
       "      <td>6937.908084</td>\n",
       "      <td>196614.246996</td>\n",
       "      <td>14317.659075</td>\n",
       "      <td>9.924202</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>41.434751</td>\n",
       "      <td>0.007947</td>\n",
       "      <td>0.008382</td>\n",
       "      <td>0.001331</td>\n",
       "      <td>0.001250</td>\n",
       "      <td>0.000528</td>\n",
       "      <td>0.002098</td>\n",
       "      <td>366.877688</td>\n",
       "      <td>1.212781</td>\n",
       "      <td>0.000925</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000164</td>\n",
       "      <td>0.000140</td>\n",
       "      <td>0.000116</td>\n",
       "      <td>35.825144</td>\n",
       "      <td>231.667649</td>\n",
       "      <td>0.651231</td>\n",
       "      <td>2.332491</td>\n",
       "      <td>0.001827</td>\n",
       "      <td>0.000023</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>1819.191869</td>\n",
       "      <td>62.424880</td>\n",
       "      <td>13.996954</td>\n",
       "      <td>11.498131</td>\n",
       "      <td>63.835498</td>\n",
       "      <td>11.487487</td>\n",
       "      <td>63.456317</td>\n",
       "      <td>5312.957350</td>\n",
       "      <td>4754.084023</td>\n",
       "      <td>1418.601093</td>\n",
       "      <td>...</td>\n",
       "      <td>157.500934</td>\n",
       "      <td>754.146670</td>\n",
       "      <td>1.157015</td>\n",
       "      <td>3233.028388</td>\n",
       "      <td>91532.068940</td>\n",
       "      <td>2205.988371</td>\n",
       "      <td>63403.745682</td>\n",
       "      <td>4623.530829</td>\n",
       "      <td>3.493263</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>3002.566527</td>\n",
       "      <td>117.601585</td>\n",
       "      <td>19.608105</td>\n",
       "      <td>18.982799</td>\n",
       "      <td>68.939246</td>\n",
       "      <td>18.984291</td>\n",
       "      <td>68.693956</td>\n",
       "      <td>5957.502048</td>\n",
       "      <td>5688.139523</td>\n",
       "      <td>1768.442371</td>\n",
       "      <td>...</td>\n",
       "      <td>172.391331</td>\n",
       "      <td>3287.697825</td>\n",
       "      <td>3.053487</td>\n",
       "      <td>9283.952234</td>\n",
       "      <td>268680.588902</td>\n",
       "      <td>5177.180204</td>\n",
       "      <td>147270.675733</td>\n",
       "      <td>10182.785706</td>\n",
       "      <td>6.255574</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>4191.784871</td>\n",
       "      <td>152.179567</td>\n",
       "      <td>24.847275</td>\n",
       "      <td>21.215446</td>\n",
       "      <td>73.466242</td>\n",
       "      <td>21.231879</td>\n",
       "      <td>72.921545</td>\n",
       "      <td>10246.472842</td>\n",
       "      <td>9553.972714</td>\n",
       "      <td>2606.703935</td>\n",
       "      <td>...</td>\n",
       "      <td>209.919668</td>\n",
       "      <td>4982.195986</td>\n",
       "      <td>623.065456</td>\n",
       "      <td>13861.983980</td>\n",
       "      <td>390052.589368</td>\n",
       "      <td>9289.277173</td>\n",
       "      <td>270397.723430</td>\n",
       "      <td>19232.136073</td>\n",
       "      <td>9.576230</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>286887.504557</td>\n",
       "      <td>305.889940</td>\n",
       "      <td>53.288143</td>\n",
       "      <td>64.086000</td>\n",
       "      <td>104.757918</td>\n",
       "      <td>66.724604</td>\n",
       "      <td>104.553769</td>\n",
       "      <td>141958.472729</td>\n",
       "      <td>125898.700115</td>\n",
       "      <td>4362.475358</td>\n",
       "      <td>...</td>\n",
       "      <td>328.291117</td>\n",
       "      <td>50760.552899</td>\n",
       "      <td>810.327031</td>\n",
       "      <td>33080.252020</td>\n",
       "      <td>934922.722389</td>\n",
       "      <td>22779.937200</td>\n",
       "      <td>647632.013643</td>\n",
       "      <td>213616.711914</td>\n",
       "      <td>73.282953</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>8 rows × 27 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       t_cost_per_claim_excluded  t_claim_count_schedule2  t_claim_per_bene  \\\n",
       "count              115020.000000            115020.000000     115020.000000   \n",
       "mean                 3620.440014               121.796508         21.059942   \n",
       "std                  3351.937990                76.062795         10.511540   \n",
       "min                    41.434751                 0.007947          0.008382   \n",
       "25%                  1819.191869                62.424880         13.996954   \n",
       "50%                  3002.566527               117.601585         19.608105   \n",
       "75%                  4191.784871               152.179567         24.847275   \n",
       "max                286887.504557               305.889940         53.288143   \n",
       "\n",
       "       %b2bg_claim_count  %b2bg_drug_cost  %b2t_claim_count  %b2t_drug_cost  \\\n",
       "count      115020.000000    115020.000000     115020.000000   115020.000000   \n",
       "mean           17.642962        66.652208         17.643202       66.167208   \n",
       "std             6.744974        12.650744          6.751661       12.649563   \n",
       "min             0.001331         0.001250          0.000528        0.002098   \n",
       "25%            11.498131        63.835498         11.487487       63.456317   \n",
       "50%            18.982799        68.939246         18.984291       68.693956   \n",
       "75%            21.215446        73.466242         21.231879       72.921545   \n",
       "max            64.086000       104.757918         66.724604      104.553769   \n",
       "\n",
       "       t_cost_per_claim  t_cost_per_claim_ge65  t_claim_per_bene_ge65  ...  \\\n",
       "count     115020.000000          115020.000000          115020.000000  ...   \n",
       "mean        8202.252845            7535.053842            2019.749603  ...   \n",
       "std         5412.909876            4741.734793            1058.971552  ...   \n",
       "min          366.877688               1.212781               0.000925  ...   \n",
       "25%         5312.957350            4754.084023            1418.601093  ...   \n",
       "50%         5957.502048            5688.139523            1768.442371  ...   \n",
       "75%        10246.472842            9553.972714            2606.703935  ...   \n",
       "max       141958.472729          125898.700115            4362.475358  ...   \n",
       "\n",
       "       antibiotic_claim_per_bene  antipsych_cost_per_claim_ge65  \\\n",
       "count              115020.000000                  115020.000000   \n",
       "mean                  168.453609                    8510.089217   \n",
       "std                    51.586517                   14300.084406   \n",
       "min                     0.000164                       0.000140   \n",
       "25%                   157.500934                     754.146670   \n",
       "50%                   172.391331                    3287.697825   \n",
       "75%                   209.919668                    4982.195986   \n",
       "max                   328.291117                   50760.552899   \n",
       "\n",
       "       antipsych_claim_per_bene_ge65  total_30_day_fill_count  \\\n",
       "count                  115020.000000            115020.000000   \n",
       "mean                      247.844387             10443.221261   \n",
       "std                       307.834687              8896.147327   \n",
       "min                         0.000116                35.825144   \n",
       "25%                         1.157015              3233.028388   \n",
       "50%                         3.053487              9283.952234   \n",
       "75%                       623.065456             13861.983980   \n",
       "max                       810.327031             33080.252020   \n",
       "\n",
       "       total_day_supply  total_30_day_fill_count_ge65  total_day_supply_ge65  \\\n",
       "count     115020.000000                 115020.000000          115020.000000   \n",
       "mean      294409.215004                   7264.580999          205487.963975   \n",
       "std       252005.648105                   6937.908084          196614.246996   \n",
       "min          231.667649                      0.651231               2.332491   \n",
       "25%        91532.068940                   2205.988371           63403.745682   \n",
       "50%       268680.588902                   5177.180204          147270.675733   \n",
       "75%       390052.589368                   9289.277173          270397.723430   \n",
       "max       934922.722389                  22779.937200          647632.013643   \n",
       "\n",
       "       opioid_day_supply  opioid_prescriber_rate  is_excluded  \n",
       "count      115020.000000           115020.000000     115020.0  \n",
       "mean        12149.091988                8.544059          1.0  \n",
       "std         14317.659075                9.924202          0.0  \n",
       "min             0.001827                0.000023          1.0  \n",
       "25%          4623.530829                3.493263          1.0  \n",
       "50%         10182.785706                6.255574          1.0  \n",
       "75%         19232.136073                9.576230          1.0  \n",
       "max        213616.711914               73.282953          1.0  \n",
       "\n",
       "[8 rows x 27 columns]"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fudge.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "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>t_cost_per_claim_excluded</th>\n",
       "      <th>t_claim_count_schedule2</th>\n",
       "      <th>t_claim_per_bene</th>\n",
       "      <th>%b2bg_claim_count</th>\n",
       "      <th>%b2bg_drug_cost</th>\n",
       "      <th>%b2t_claim_count</th>\n",
       "      <th>%b2t_drug_cost</th>\n",
       "      <th>t_cost_per_claim</th>\n",
       "      <th>t_cost_per_claim_ge65</th>\n",
       "      <th>t_claim_per_bene_ge65</th>\n",
       "      <th>...</th>\n",
       "      <th>antibiotic_claim_per_bene</th>\n",
       "      <th>antipsych_cost_per_claim_ge65</th>\n",
       "      <th>antipsych_claim_per_bene_ge65</th>\n",
       "      <th>total_30_day_fill_count</th>\n",
       "      <th>total_day_supply</th>\n",
       "      <th>total_30_day_fill_count_ge65</th>\n",
       "      <th>total_day_supply_ge65</th>\n",
       "      <th>opioid_day_supply</th>\n",
       "      <th>opioid_prescriber_rate</th>\n",
       "      <th>is_excluded</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>101.000000</td>\n",
       "      <td>101.000000</td>\n",
       "      <td>101.000000</td>\n",
       "      <td>101.000000</td>\n",
       "      <td>101.000000</td>\n",
       "      <td>101.000000</td>\n",
       "      <td>101.000000</td>\n",
       "      <td>101.000000</td>\n",
       "      <td>101.000000</td>\n",
       "      <td>101.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>101.000000</td>\n",
       "      <td>101.000000</td>\n",
       "      <td>101.000000</td>\n",
       "      <td>101.000000</td>\n",
       "      <td>101.000000</td>\n",
       "      <td>101.000000</td>\n",
       "      <td>101.000000</td>\n",
       "      <td>101.000000</td>\n",
       "      <td>101.000000</td>\n",
       "      <td>101.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>5221.393465</td>\n",
       "      <td>38.673267</td>\n",
       "      <td>9.499010</td>\n",
       "      <td>11.386139</td>\n",
       "      <td>36.306931</td>\n",
       "      <td>10.891089</td>\n",
       "      <td>36.099010</td>\n",
       "      <td>10562.524752</td>\n",
       "      <td>8919.534653</td>\n",
       "      <td>751.980198</td>\n",
       "      <td>...</td>\n",
       "      <td>77.495050</td>\n",
       "      <td>2757.247525</td>\n",
       "      <td>44.079208</td>\n",
       "      <td>3136.292079</td>\n",
       "      <td>88552.960396</td>\n",
       "      <td>2093.873267</td>\n",
       "      <td>59466.841584</td>\n",
       "      <td>5972.128713</td>\n",
       "      <td>8.322871</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>28518.834547</td>\n",
       "      <td>56.116684</td>\n",
       "      <td>9.667021</td>\n",
       "      <td>15.035272</td>\n",
       "      <td>36.333935</td>\n",
       "      <td>13.045996</td>\n",
       "      <td>36.102771</td>\n",
       "      <td>17653.641240</td>\n",
       "      <td>16564.118105</td>\n",
       "      <td>937.517232</td>\n",
       "      <td>...</td>\n",
       "      <td>88.851182</td>\n",
       "      <td>8633.955942</td>\n",
       "      <td>159.991417</td>\n",
       "      <td>5542.441612</td>\n",
       "      <td>157554.695894</td>\n",
       "      <td>4202.779267</td>\n",
       "      <td>119551.162208</td>\n",
       "      <td>22570.729549</td>\n",
       "      <td>14.976968</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>40.990000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>294.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>13.000000</td>\n",
       "      <td>221.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>293.230000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>2.200000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>4406.000000</td>\n",
       "      <td>2876.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>109.000000</td>\n",
       "      <td>2955.000000</td>\n",
       "      <td>62.000000</td>\n",
       "      <td>1280.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>1206.820000</td>\n",
       "      <td>11.000000</td>\n",
       "      <td>5.800000</td>\n",
       "      <td>10.000000</td>\n",
       "      <td>43.000000</td>\n",
       "      <td>10.000000</td>\n",
       "      <td>43.000000</td>\n",
       "      <td>7223.000000</td>\n",
       "      <td>5345.000000</td>\n",
       "      <td>378.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>632.600000</td>\n",
       "      <td>18369.000000</td>\n",
       "      <td>368.400000</td>\n",
       "      <td>10843.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>3338.240000</td>\n",
       "      <td>54.000000</td>\n",
       "      <td>13.800000</td>\n",
       "      <td>20.000000</td>\n",
       "      <td>71.000000</td>\n",
       "      <td>20.000000</td>\n",
       "      <td>70.000000</td>\n",
       "      <td>10419.000000</td>\n",
       "      <td>7982.000000</td>\n",
       "      <td>1163.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>157.000000</td>\n",
       "      <td>633.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>3164.200000</td>\n",
       "      <td>90194.000000</td>\n",
       "      <td>1882.600000</td>\n",
       "      <td>52000.000000</td>\n",
       "      <td>3107.000000</td>\n",
       "      <td>7.590000</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>286886.380000</td>\n",
       "      <td>299.000000</td>\n",
       "      <td>46.100000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>60.000000</td>\n",
       "      <td>98.000000</td>\n",
       "      <td>141957.000000</td>\n",
       "      <td>125896.000000</td>\n",
       "      <td>4355.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>322.000000</td>\n",
       "      <td>50758.000000</td>\n",
       "      <td>803.000000</td>\n",
       "      <td>33073.000000</td>\n",
       "      <td>934916.000000</td>\n",
       "      <td>22770.800000</td>\n",
       "      <td>647623.000000</td>\n",
       "      <td>213611.000000</td>\n",
       "      <td>68.220000</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>8 rows × 27 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       t_cost_per_claim_excluded  t_claim_count_schedule2  t_claim_per_bene  \\\n",
       "count                 101.000000               101.000000        101.000000   \n",
       "mean                 5221.393465                38.673267          9.499010   \n",
       "std                 28518.834547                56.116684          9.667021   \n",
       "min                    40.990000                 1.000000          0.000000   \n",
       "25%                   293.230000                 3.000000          2.200000   \n",
       "50%                  1206.820000                11.000000          5.800000   \n",
       "75%                  3338.240000                54.000000         13.800000   \n",
       "max                286886.380000               299.000000         46.100000   \n",
       "\n",
       "       %b2bg_claim_count  %b2bg_drug_cost  %b2t_claim_count  %b2t_drug_cost  \\\n",
       "count         101.000000       101.000000        101.000000      101.000000   \n",
       "mean           11.386139        36.306931         10.891089       36.099010   \n",
       "std            15.035272        36.333935         13.045996       36.102771   \n",
       "min             0.000000         0.000000          0.000000        0.000000   \n",
       "25%             0.000000         0.000000          0.000000        0.000000   \n",
       "50%            10.000000        43.000000         10.000000       43.000000   \n",
       "75%            20.000000        71.000000         20.000000       70.000000   \n",
       "max           100.000000       100.000000         60.000000       98.000000   \n",
       "\n",
       "       t_cost_per_claim  t_cost_per_claim_ge65  t_claim_per_bene_ge65  ...  \\\n",
       "count        101.000000             101.000000             101.000000  ...   \n",
       "mean       10562.524752            8919.534653             751.980198  ...   \n",
       "std        17653.641240           16564.118105             937.517232  ...   \n",
       "min          294.000000               0.000000               0.000000  ...   \n",
       "25%         4406.000000            2876.000000               0.000000  ...   \n",
       "50%         7223.000000            5345.000000             378.000000  ...   \n",
       "75%        10419.000000            7982.000000            1163.000000  ...   \n",
       "max       141957.000000          125896.000000            4355.000000  ...   \n",
       "\n",
       "       antibiotic_claim_per_bene  antipsych_cost_per_claim_ge65  \\\n",
       "count                 101.000000                     101.000000   \n",
       "mean                   77.495050                    2757.247525   \n",
       "std                    88.851182                    8633.955942   \n",
       "min                     0.000000                       0.000000   \n",
       "25%                     0.000000                       0.000000   \n",
       "50%                     0.000000                       0.000000   \n",
       "75%                   157.000000                     633.000000   \n",
       "max                   322.000000                   50758.000000   \n",
       "\n",
       "       antipsych_claim_per_bene_ge65  total_30_day_fill_count  \\\n",
       "count                     101.000000               101.000000   \n",
       "mean                       44.079208              3136.292079   \n",
       "std                       159.991417              5542.441612   \n",
       "min                         0.000000                13.000000   \n",
       "25%                         0.000000               109.000000   \n",
       "50%                         0.000000               632.600000   \n",
       "75%                         0.000000              3164.200000   \n",
       "max                       803.000000             33073.000000   \n",
       "\n",
       "       total_day_supply  total_30_day_fill_count_ge65  total_day_supply_ge65  \\\n",
       "count        101.000000                    101.000000             101.000000   \n",
       "mean       88552.960396                   2093.873267           59466.841584   \n",
       "std       157554.695894                   4202.779267          119551.162208   \n",
       "min          221.000000                      0.000000               0.000000   \n",
       "25%         2955.000000                     62.000000            1280.000000   \n",
       "50%        18369.000000                    368.400000           10843.000000   \n",
       "75%        90194.000000                   1882.600000           52000.000000   \n",
       "max       934916.000000                  22770.800000          647623.000000   \n",
       "\n",
       "       opioid_day_supply  opioid_prescriber_rate  is_excluded  \n",
       "count         101.000000              101.000000        101.0  \n",
       "mean         5972.128713                8.322871          1.0  \n",
       "std         22570.729549               14.976968          0.0  \n",
       "min             0.000000                0.000000          1.0  \n",
       "25%             0.000000                0.000000          1.0  \n",
       "50%             0.000000                0.000000          1.0  \n",
       "75%          3107.000000                7.590000          1.0  \n",
       "max        213611.000000               68.220000          1.0  \n",
       "\n",
       "[8 rows x 27 columns]"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "only_excluded.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(115020, 27)"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fudge.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "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>t_cost_per_claim_excluded</th>\n",
       "      <th>t_claim_count_schedule2</th>\n",
       "      <th>t_claim_per_bene</th>\n",
       "      <th>%b2bg_claim_count</th>\n",
       "      <th>%b2bg_drug_cost</th>\n",
       "      <th>%b2t_claim_count</th>\n",
       "      <th>%b2t_drug_cost</th>\n",
       "      <th>t_cost_per_claim</th>\n",
       "      <th>t_cost_per_claim_ge65</th>\n",
       "      <th>t_claim_per_bene_ge65</th>\n",
       "      <th>...</th>\n",
       "      <th>antibiotic_claim_per_bene</th>\n",
       "      <th>antipsych_cost_per_claim_ge65</th>\n",
       "      <th>antipsych_claim_per_bene_ge65</th>\n",
       "      <th>total_30_day_fill_count</th>\n",
       "      <th>total_day_supply</th>\n",
       "      <th>total_30_day_fill_count_ge65</th>\n",
       "      <th>total_day_supply_ge65</th>\n",
       "      <th>opioid_day_supply</th>\n",
       "      <th>opioid_prescriber_rate</th>\n",
       "      <th>is_excluded</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>394626</th>\n",
       "      <td>1323.329265</td>\n",
       "      <td>117.960642</td>\n",
       "      <td>16.464682</td>\n",
       "      <td>9.837992</td>\n",
       "      <td>70.346432</td>\n",
       "      <td>8.351582</td>\n",
       "      <td>67.363500</td>\n",
       "      <td>5544.216032</td>\n",
       "      <td>5165.236987</td>\n",
       "      <td>1418.593027</td>\n",
       "      <td>...</td>\n",
       "      <td>172.946116</td>\n",
       "      <td>758.364345</td>\n",
       "      <td>1.487764</td>\n",
       "      <td>7731.162156</td>\n",
       "      <td>219194.751741</td>\n",
       "      <td>5177.729582</td>\n",
       "      <td>147273.750216</td>\n",
       "      <td>15821.462328</td>\n",
       "      <td>14.086673</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15936</th>\n",
       "      <td>3561.291022</td>\n",
       "      <td>137.947148</td>\n",
       "      <td>31.843531</td>\n",
       "      <td>19.538723</td>\n",
       "      <td>76.957262</td>\n",
       "      <td>20.084003</td>\n",
       "      <td>79.614832</td>\n",
       "      <td>7989.761622</td>\n",
       "      <td>7771.028694</td>\n",
       "      <td>3902.728009</td>\n",
       "      <td>...</td>\n",
       "      <td>171.163517</td>\n",
       "      <td>32837.827028</td>\n",
       "      <td>3.411723</td>\n",
       "      <td>10495.749012</td>\n",
       "      <td>302809.913750</td>\n",
       "      <td>7308.775344</td>\n",
       "      <td>211947.297951</td>\n",
       "      <td>11385.897766</td>\n",
       "      <td>5.671517</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>250232</th>\n",
       "      <td>2055.281024</td>\n",
       "      <td>134.330214</td>\n",
       "      <td>22.985749</td>\n",
       "      <td>20.879553</td>\n",
       "      <td>69.376491</td>\n",
       "      <td>19.953949</td>\n",
       "      <td>69.090820</td>\n",
       "      <td>5318.587272</td>\n",
       "      <td>4757.997034</td>\n",
       "      <td>2070.333504</td>\n",
       "      <td>...</td>\n",
       "      <td>155.020715</td>\n",
       "      <td>4457.316968</td>\n",
       "      <td>460.975632</td>\n",
       "      <td>9670.868369</td>\n",
       "      <td>268678.018926</td>\n",
       "      <td>7809.690992</td>\n",
       "      <td>219079.777835</td>\n",
       "      <td>10879.099277</td>\n",
       "      <td>5.862675</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>250232</th>\n",
       "      <td>2055.190318</td>\n",
       "      <td>132.749968</td>\n",
       "      <td>20.829365</td>\n",
       "      <td>17.620837</td>\n",
       "      <td>65.455473</td>\n",
       "      <td>20.019689</td>\n",
       "      <td>71.674797</td>\n",
       "      <td>5318.625497</td>\n",
       "      <td>4755.367022</td>\n",
       "      <td>2068.797384</td>\n",
       "      <td>...</td>\n",
       "      <td>153.661973</td>\n",
       "      <td>4454.701063</td>\n",
       "      <td>460.973392</td>\n",
       "      <td>9667.486234</td>\n",
       "      <td>268676.155425</td>\n",
       "      <td>7810.655306</td>\n",
       "      <td>219082.046845</td>\n",
       "      <td>10878.199591</td>\n",
       "      <td>3.976740</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15591</th>\n",
       "      <td>5737.192401</td>\n",
       "      <td>176.507527</td>\n",
       "      <td>18.419334</td>\n",
       "      <td>21.442674</td>\n",
       "      <td>77.075079</td>\n",
       "      <td>17.329945</td>\n",
       "      <td>77.804503</td>\n",
       "      <td>10250.591760</td>\n",
       "      <td>9559.121916</td>\n",
       "      <td>1860.035355</td>\n",
       "      <td>...</td>\n",
       "      <td>193.655422</td>\n",
       "      <td>1922.713762</td>\n",
       "      <td>2.859027</td>\n",
       "      <td>19479.821606</td>\n",
       "      <td>551912.308973</td>\n",
       "      <td>17043.344787</td>\n",
       "      <td>484195.717507</td>\n",
       "      <td>5479.418904</td>\n",
       "      <td>1.729178</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 27 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        t_cost_per_claim_excluded  t_claim_count_schedule2  t_claim_per_bene  \\\n",
       "394626                1323.329265               117.960642         16.464682   \n",
       "15936                 3561.291022               137.947148         31.843531   \n",
       "250232                2055.281024               134.330214         22.985749   \n",
       "250232                2055.190318               132.749968         20.829365   \n",
       "15591                 5737.192401               176.507527         18.419334   \n",
       "\n",
       "        %b2bg_claim_count  %b2bg_drug_cost  %b2t_claim_count  %b2t_drug_cost  \\\n",
       "394626           9.837992        70.346432          8.351582       67.363500   \n",
       "15936           19.538723        76.957262         20.084003       79.614832   \n",
       "250232          20.879553        69.376491         19.953949       69.090820   \n",
       "250232          17.620837        65.455473         20.019689       71.674797   \n",
       "15591           21.442674        77.075079         17.329945       77.804503   \n",
       "\n",
       "        t_cost_per_claim  t_cost_per_claim_ge65  t_claim_per_bene_ge65  ...  \\\n",
       "394626       5544.216032            5165.236987            1418.593027  ...   \n",
       "15936        7989.761622            7771.028694            3902.728009  ...   \n",
       "250232       5318.587272            4757.997034            2070.333504  ...   \n",
       "250232       5318.625497            4755.367022            2068.797384  ...   \n",
       "15591       10250.591760            9559.121916            1860.035355  ...   \n",
       "\n",
       "        antibiotic_claim_per_bene  antipsych_cost_per_claim_ge65  \\\n",
       "394626                 172.946116                     758.364345   \n",
       "15936                  171.163517                   32837.827028   \n",
       "250232                 155.020715                    4457.316968   \n",
       "250232                 153.661973                    4454.701063   \n",
       "15591                  193.655422                    1922.713762   \n",
       "\n",
       "        antipsych_claim_per_bene_ge65  total_30_day_fill_count  \\\n",
       "394626                       1.487764              7731.162156   \n",
       "15936                        3.411723             10495.749012   \n",
       "250232                     460.975632              9670.868369   \n",
       "250232                     460.973392              9667.486234   \n",
       "15591                        2.859027             19479.821606   \n",
       "\n",
       "        total_day_supply  total_30_day_fill_count_ge65  total_day_supply_ge65  \\\n",
       "394626     219194.751741                   5177.729582          147273.750216   \n",
       "15936      302809.913750                   7308.775344          211947.297951   \n",
       "250232     268678.018926                   7809.690992          219079.777835   \n",
       "250232     268676.155425                   7810.655306          219082.046845   \n",
       "15591      551912.308973                  17043.344787          484195.717507   \n",
       "\n",
       "        opioid_day_supply  opioid_prescriber_rate  is_excluded  \n",
       "394626       15821.462328               14.086673            1  \n",
       "15936        11385.897766                5.671517            1  \n",
       "250232       10879.099277                5.862675            1  \n",
       "250232       10878.199591                3.976740            1  \n",
       "15591         5479.418904                1.729178            1  \n",
       "\n",
       "[5 rows x 27 columns]"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fudge=fudge.sample(n=10000)\n",
    "fudge.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {
    "scrolled": false
   },
   "outputs": [],
   "source": [
    "ag_2017 = pd.concat([new_main_2017, fudge])\n",
    "ag_2017.dropna(inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(10000, 27)"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ag_2017[ag_2017[\"is_excluded\"]==1].shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(733999, 27)"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ag_2017.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#Applying PCA, 2 components and 3 components for variance visualization\n",
    "\n",
    "pca = decomposition.PCA(n_components='mle')\n",
    "pca.fit(part_d_df)\n",
    "npi_drug_df_transformed = pca.transform(part_d_df)\n",
    "plt.plot(np.cumsum(pca.explained_variance_ratio_), color='r')\n",
    "\n",
    "pca = decomposition.PCA(n_components='mle')\n",
    "pca.fit(part_d_df)\n",
    "npi_drug_cross_df_transformed = pca.transform(part_d_df)\n",
    "plt.plot(np.cumsum(pca.explained_variance_ratio_))\n",
    "plt.xlabel('number of components')\n",
    "plt.ylabel('cumulative explained variance')\n",
    "\n",
    "plt.vlines(1, color='grey', ymax=0.1, ymin=0, linestyle=':')\n",
    "plt.vlines(2, color='grey', ymax=0.1, ymin=0, linestyle=':')\n",
    "\n",
    "plt.annotate('1 components', xy=(0.6, 0.05), xytext=(0.9, 0.05), fontsize=15, rotation=90)\n",
    "plt.annotate('2 components', xy=(1.6, 0.05), xytext=(1.9, 0.05), fontsize=15, rotation=90)\n",
    "\n",
    "plt.savefig('VarExp.jpeg', dpi=1000)\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Training without Upsampling or Downsampling\n",
    "#fudged data (ag_2017) only for train, regular data (new_df) only for test\n",
    "\n",
    "X_train = ag_2017.drop(['is_excluded'], axis=1)\n",
    "y_train = ag_2017['is_excluded']\n",
    "X_test = new_df.drop(['is_excluded'], axis =1)\n",
    "y_test = new_df[\"is_excluded\"]\n",
    "#X = new_main_2017.drop(['is_excluded'], axis=1)\n",
    "#y = new_main_2017['is_excluded']\n",
    "#X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33, random_state=42)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [],
   "source": [
    "pca = decomposition.PCA(n_components='mle')\n",
    "X_train = pca.fit_transform(X_train)\n",
    "X_test = pca.fit_transform(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[7.13700535e-01 2.00719035e-01 3.17619178e-02 1.73367337e-02\n",
      " 1.44752287e-02 7.28680091e-03 5.22912319e-03 5.04097367e-03\n",
      " 1.81973459e-03 9.79282418e-04 8.22399523e-04 4.64093694e-04\n",
      " 3.48778557e-04 1.05592297e-05 4.03529308e-06 3.34100413e-07\n",
      " 2.27012538e-07 1.03203708e-07 4.80720203e-08 4.52092520e-08\n",
      " 5.18160730e-09 2.81574566e-09 2.49100454e-09 2.24581498e-10\n",
      " 1.48346426e-10]\n"
     ]
    }
   ],
   "source": [
    "print(pca.explained_variance_ratio_)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "Labels = ag_2017.drop([\"is_excluded\"],axis = 1).columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['total_day_supply',\n",
       " 'lis_cost_per_claim',\n",
       " 'mapd_cost_per_claim',\n",
       " 'pdp_cost_per_claim',\n",
       " 'mapd_cost_per_claim',\n",
       " 't_cost_per_claim',\n",
       " 'total_day_supply_ge65',\n",
       " 't_cost_per_claim_ge65',\n",
       " 'antibiotic_cost_per_claim',\n",
       " 'antipsych_cost_per_claim_ge65',\n",
       " 'antipsych_cost_per_claim_ge65',\n",
       " 't_cost_per_claim_excluded',\n",
       " 'opioid_cost_per_claim',\n",
       " 'total_30_day_fill_count',\n",
       " 't_claim_per_bene_ge65',\n",
       " 'opioid_claim_per_bene',\n",
       " 'antipsych_claim_per_bene_ge65',\n",
       " 'antibiotic_claim_per_bene',\n",
       " 'total_30_day_fill_count_ge65',\n",
       " 'total_30_day_fill_count_ge65',\n",
       " 'opioid_prescriber_rate',\n",
       " '%b2bg_claim_count',\n",
       " 't_claim_count_schedule2',\n",
       " 't_claim_per_bene',\n",
       " '%b2t_drug_cost']"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#new Labels after PCA\n",
    "most_important = [np.abs(pca.components_[i]).argmax() for i in range(len(pca.components_))]\n",
    "most_important_names = [Labels[most_important[i]] for i in range(len(pca.components_))]\n",
    "dic = {'PC{}'.format(i+1): most_important_names[i] for i in range(len(pca.components_))}\n",
    "newLabels = list(dic.values())\n",
    "newLabels"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "KNeighborsClassifier(algorithm='auto', leaf_size=30, metric='minkowski',\n",
       "           metric_params=None, n_jobs=None, n_neighbors=5, p=2,\n",
       "           weights='uniform')"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "clf = KNeighborsClassifier(n_neighbors=5)\n",
    "clf.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "101\n"
     ]
    }
   ],
   "source": [
    "#excluded samples in test data\n",
    "count = 0\n",
    "for x in y_test:\n",
    "    if int(x)== 1:\n",
    "        count +=1\n",
    "print(count)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "10000\n"
     ]
    }
   ],
   "source": [
    "#excluded samples in train data\n",
    "count2 = 0\n",
    "for x in y_train:\n",
    "    if int(x)== 1:\n",
    "        count2 +=1\n",
    "print(count2)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "coef_df = pd.DataFrame(clf.feature_importances_, Labels, columns = [\"Importances\"])\n",
    "coef_df.sort_values(\"Importances\", ascending = False)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "check for contamination by not dropping the npis and seeing if any of them overlap between training and testing\n",
    "train_nps = set(X_train['npi'])\n",
    "test_nps = set(X_test['npi'])\n",
    "print(len(train_nps.intersection(test_nps))) # should be zero"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[1. 0.]\n",
      " [1. 0.]\n",
      " [1. 0.]\n",
      " ...\n",
      " [0. 1.]\n",
      " [0. 1.]\n",
      " [0. 1.]]\n",
      "0.9999993587698325\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "array([[723897,    102],\n",
       "       [    25,   9975]], dtype=int64)"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_pred = clf.predict(X_train)\n",
    "y_pred_prob = clf.predict_proba(X_train)\n",
    "print(y_pred_prob)\n",
    "print(roc_auc_score(y_train, y_pred_prob[:,1]))\n",
    "confusion_matrix(y_train, y_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[1. 0.]\n",
      " [1. 0.]\n",
      " [1. 0.]\n",
      " ...\n",
      " [1. 0.]\n",
      " [1. 0.]\n",
      " [1. 0.]]\n",
      "0.6037749088039335\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "array([[180869,     30],\n",
       "       [    84,     17]], dtype=int64)"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_pred = clf.predict(X_test)\n",
    "y_pred_prob = clf.predict_proba(X_test)\n",
    "print(y_pred_prob)\n",
    "print(roc_auc_score(y_test, y_pred_prob[:,1]))\n",
    "confusion_matrix(y_test, y_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    723999\n",
       "1    100000\n",
       "Name: is_excluded, dtype: int64"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Upsampling only\n",
    "\n",
    "ag_2017_majority = ag_2017[ag_2017['is_excluded'] == 0]\n",
    "ag_2017_minority = ag_2017[ag_2017['is_excluded'] > 0]\n",
    "\n",
    "# Increase by 10 times\n",
    "ag_2017_minority_upsampled = resample(ag_2017_minority, replace=True, n_samples=100000, random_state=42) \n",
    "ag_2017_upsampled = pd.concat([ag_2017_majority, ag_2017_minority_upsampled])  \n",
    "ag_2017_upsampled['is_excluded'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "#fudged data (ag_2017) only for train, regular data (new_df) only for test\n",
    "X_train = ag_2017_upsampled.drop(['is_excluded'], axis=1)\n",
    "y_train = ag_2017_upsampled['is_excluded']\n",
    "X_test = new_df.drop(['is_excluded'], axis =1)\n",
    "y_test = new_df[\"is_excluded\"]\n",
    "\n",
    "#X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33, random_state=42)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [],
   "source": [
    "pca = decomposition.PCA(n_components='mle')\n",
    "X_train = pca.fit_transform(X_train)\n",
    "X_test = pca.fit_transform(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "KNeighborsClassifier(algorithm='auto', leaf_size=30, metric='minkowski',\n",
       "           metric_params=None, n_jobs=None, n_neighbors=5, p=2,\n",
       "           weights='uniform')"
      ]
     },
     "execution_count": 40,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "clf = KNeighborsClassifier(n_neighbors=5)\n",
    "clf.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.9999999956906017\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "array([[723872,    127],\n",
       "       [     2,  99998]], dtype=int64)"
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_pred = clf.predict(X_train)\n",
    "y_pred_prob = clf.predict_proba(X_train)\n",
    "print(roc_auc_score(y_train, y_pred_prob[:,1]))\n",
    "confusion_matrix(y_train, y_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.49969043499411275\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "array([[180829,     70],\n",
       "       [   101,      0]], dtype=int64)"
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_pred = clf.predict(X_test)\n",
    "y_pred_prob = clf.predict_proba(X_test)\n",
    "print(roc_auc_score(y_test, y_pred_prob[:,1]))\n",
    "confusion_matrix(y_test, y_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    81980\n",
       "1    10000\n",
       "Name: is_excluded, dtype: int64"
      ]
     },
     "execution_count": 43,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Training on downsampled only and testing on regular\n",
    "\n",
    "ag_2017_majority = ag_2017[ag_2017['is_excluded'] == 0]\n",
    "ag_2017_minority = ag_2017[ag_2017['is_excluded'] > 0]\n",
    "\n",
    "# Reduce by 10 times\n",
    "ag_2017_majority_downsampled = resample(ag_2017_majority, replace=True, n_samples=81980, random_state=42) \n",
    "ag_2017_downsampled = pd.concat([ag_2017_majority_downsampled, ag_2017_minority]) \n",
    "ag_2017_downsampled['is_excluded'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [],
   "source": [
    "#fudged data (ag_2017) only for train, regular data (new_df) only for test\n",
    "X_train = ag_2017_downsampled.drop(['is_excluded'], axis=1)\n",
    "y_train = ag_2017_downsampled['is_excluded']\n",
    "X_test = new_df.drop(['is_excluded'], axis =1)\n",
    "y_test = new_df[\"is_excluded\"]\n",
    "\n",
    "#X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33, random_state=42)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [],
   "source": [
    "pca = decomposition.PCA(n_components='mle')\n",
    "X_train = pca.fit_transform(X_train)\n",
    "X_test = pca.fit_transform(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "KNeighborsClassifier(algorithm='auto', leaf_size=30, metric='minkowski',\n",
       "           metric_params=None, n_jobs=None, n_neighbors=5, p=2,\n",
       "           weights='uniform')"
      ]
     },
     "execution_count": 46,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "clf = KNeighborsClassifier(n_neighbors=5)\n",
    "clf.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.9999943101976092\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "array([[81891,    89],\n",
       "       [   25,  9975]], dtype=int64)"
      ]
     },
     "execution_count": 47,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_pred = clf.predict(X_train)\n",
    "y_pred_prob = clf.predict_proba(X_train)\n",
    "print(roc_auc_score(y_train, y_pred_prob[:,1]))\n",
    "confusion_matrix(y_train, y_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.5021904351309431\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "array([[180607,    292],\n",
       "       [   101,      0]], dtype=int64)"
      ]
     },
     "execution_count": 48,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_pred = clf.predict(X_test)\n",
    "y_pred_prob = clf.predict_proba(X_test)\n",
    "print(roc_auc_score(y_test, y_pred_prob[:,1]))\n",
    "confusion_matrix(y_test, y_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1    100000\n",
       "0     81980\n",
       "Name: is_excluded, dtype: int64"
      ]
     },
     "execution_count": 49,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Upsampling/downsampling on training and testing on regular\n",
    "\n",
    "ag_2017_majority = ag_2017[ag_2017['is_excluded'] == 0]\n",
    "ag_2017_minority = ag_2017[ag_2017['is_excluded'] > 0]\n",
    "\n",
    "ag_2017_updownsampled = pd.concat([ag_2017_majority_downsampled, ag_2017_minority_upsampled]) \n",
    "ag_2017_updownsampled['is_excluded'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [],
   "source": [
    "#fudged data (ag_2017) only for train, regular data (new_df) only for test\n",
    "\n",
    "X_train = ag_2017_updownsampled.drop(['is_excluded'], axis=1)\n",
    "y_train = ag_2017_updownsampled['is_excluded']\n",
    "X_test = new_df.drop(['is_excluded'], axis =1)\n",
    "y_test = new_df[\"is_excluded\"]\n",
    "#X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=42)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {},
   "outputs": [],
   "source": [
    "pca = decomposition.PCA(n_components='mle')\n",
    "X_train = pca.fit_transform(X_train)\n",
    "X_test = pca.fit_transform(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "KNeighborsClassifier(algorithm='auto', leaf_size=30, metric='minkowski',\n",
       "           metric_params=None, n_jobs=None, n_neighbors=5, p=2,\n",
       "           weights='uniform')"
      ]
     },
     "execution_count": 52,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "clf = KNeighborsClassifier(n_neighbors=5)\n",
    "clf.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.9999999597462796\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "array([[81856,   124],\n",
       "       [    2, 99998]], dtype=int64)"
      ]
     },
     "execution_count": 53,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_pred = clf.predict(X_train)\n",
    "y_pred_prob = clf.predict_proba(X_train)\n",
    "print(roc_auc_score(y_train, y_pred_prob[:,1]))\n",
    "confusion_matrix(y_train, y_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.49917633596647853\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "array([[180719,    180],\n",
       "       [   101,      0]], dtype=int64)"
      ]
     },
     "execution_count": 54,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_pred = clf.predict(X_test)\n",
    "y_pred_prob = clf.predict_proba(X_test)\n",
    "print(roc_auc_score(y_test, y_pred_prob[:,1]))\n",
    "confusion_matrix(y_test, y_pred)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "In conclusion, results from downsampling is the best."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Classification Model Comparisons\n",
    "\n",
    "def warn(*args, **kwargs):\n",
    "    pass\n",
    "\n",
    "import warnings\n",
    "warnings.warn = warn\n",
    "\n",
    "from scipy import interp\n",
    "import matplotlib.pyplot as plt\n",
    "from itertools import cycle\n",
    "\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.neural_network import MLPClassifier\n",
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "from sklearn.svm import SVC\n",
    "from sklearn.gaussian_process import GaussianProcessClassifier\n",
    "from sklearn.gaussian_process.kernels import RBF\n",
    "from sklearn.tree import DecisionTreeClassifier\n",
    "from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier, GradientBoostingClassifier, ExtraTreesClassifier\n",
    "from sklearn.naive_bayes import GaussianNB\n",
    "from sklearn.discriminant_analysis import QuadraticDiscriminantAnalysis\n",
    "from sklearn.model_selection import cross_validate, GridSearchCV, StratifiedKFold\n",
    "from sklearn.metrics import roc_curve, roc_auc_score, confusion_matrix, auc, recall_score, precision_score, accuracy_score, f1_score\n",
    "\n",
    "seed = 42"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#Identifying the best model algorithm\n",
    "colors = [\"#08306b\", \"#08519c\", \"#1361a9\", \"#4292c6\", \"#6baed6\", 'rgb(76,000,153)', 'rgb(153,000,153)']\n",
    "\n",
    "scoring = {'AUC': 'roc_auc', 'Accuracy': 'accuracy', 'F1': 'f1'}\n",
    "\n",
    "names = [\"Naive Bayes\", \"Nearest Neighbors\", \"RBF SVM\", \n",
    "         \"AdaBoost\", \"GradientBoost\", \"ExtraTrees\", \"Random Forest\"]\n",
    "\n",
    "classifiers = [\n",
    "            GaussianNB(),\n",
    "            KNeighborsClassifier(n_neighbors=5),\n",
    "            SVC(kernel=\"rbf\", C=1, probability=True),\n",
    "            AdaBoostClassifier(n_estimators=25, random_state=seed),\n",
    "            GradientBoostingClassifier(n_estimators=1000, random_state=seed),\n",
    "            ExtraTreesClassifier(n_estimators=25, random_state=seed),\n",
    "            RandomForestClassifier(n_estimators=25, random_state=seed),]\n",
    "\n",
    "trace_dict = {'x_vals':[], 'y_vals':[], 'y_error':[], 'colors':[], 'names':[]}\n",
    "                                                                                         \n",
    "#iterate over classifiers\n",
    "counter = 0\n",
    "for color, name, clf in tqdm_notebook(zip(colors, names, classifiers), total=len(names)):\n",
    "    cv_results = cross_validate(clf, X, y, scoring=scoring, cv=5, return_train_score=True)\n",
    "    print('########################### \\nFor {}'.format(name))\n",
    "    for score in scoring:\n",
    "        print('{0:s}: Mean-{1:.4f}  STD-{2:.4f}'.format(score, cv_results['test_'+score].mean(),\\\n",
    "                                                        cv_results['test_'+score].std()))\n",
    "    \n",
    "    trace_dict['x_vals'].append(counter)\n",
    "    counter += 1\n",
    "    trace_dict['y_vals'].append(cv_results['test_F1'].mean())\n",
    "    trace_dict['y_error'].append()\n",
    "    trace_dict['colors'].append(color)\n",
    "    trace_dict['names'].append(name)\n",
    "    trace_dict['y_error'].append(np.std(cv_results['test_F1']))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Identifying the best model algorithm\n",
    "#colors = [\"#08306b\", \"#08519c\", \"#1361a9\", \"#4292c6\", \"#6baed6\", 'rgb(76,000,153)', 'rgb(153,000,153)']\n",
    "\n",
    "#names = [\"GradientBoost\", \"ExtraTrees\", \"Random Forest\", \"Naive Bayes\", \"Nearest Neighbors\", \"AdaBoost\"]\n",
    "\n",
    "colors = [\"rgb(76,000,153)\"]\n",
    "\n",
    "names = [\"Nearest Neighbors\"]\n",
    "\n",
    "classifiers = [KNeighborsClassifier(n_neighbors=1)]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "5f6e88b3deae420482ad0edab3395e33",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "HBox(children=(IntProgress(value=0, max=1), HTML(value='')))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "########################### \n",
      "For Nearest Neighbors\n",
      "0.8365756199277328\n",
      "\n"
     ]
    }
   ],
   "source": [
    "trace_dict = {'x_vals':[], 'y_vals':[], 'colors':[], 'names':[]}\n",
    "                                                                                         \n",
    "# iterate over classifiers\n",
    "counter = 0\n",
    "for color, name, clf in tqdm_notebook(zip(colors, names, classifiers), total=len(names)):\n",
    "    X_train = ag_2017.drop(['is_excluded'], axis=1)\n",
    "    y_train = ag_2017['is_excluded']\n",
    "    X_test = new_df.drop(['is_excluded'], axis =1)\n",
    "    y_test = new_df[\"is_excluded\"]\n",
    "    clf.fit(X_train, y_train)\n",
    "    y_pred_prob = clf.predict_proba(X_test)\n",
    "    cv_results = roc_auc_score(y_test, y_pred_prob[:,1])\n",
    "    print('########################### \\nFor {}'.format(name))\n",
    "              \n",
    "    trace_dict['x_vals'].append(counter)\n",
    "    counter += 1\n",
    "    print(cv_results)\n",
    "    trace_dict['y_vals'].append(cv_results.mean())\n",
    "    trace_dict['colors'].append(color)\n",
    "    trace_dict['names'].append(name)"
   ]
  },
  {
   "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": "3.7.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}