1.6 .Visualisation and identifying the most prescribed drug by Speciality.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 1.6 .Visualisation and identifying the most prescribed drug by Speciality\n",
    "\n",
    "##### Feature Selection\n",
    "\n",
    "In this section, I will select specific features for model training. The original dataset contains 265 features, most of which are categorical attributes, dominantly the list of drug names that are approved as pain medications that need special AED licensed prescriber.Here,my main target is to predict the overdoses using the  the list of prescriber specialists with NPI information and the FDA approved drug lists. The data set has only total opiod cliams and total claim counts and i took the standard prescription for opiod drugs is 84 days which is 12 weeks. Therefore, an additional feature was created in the data cleaning, pre processing that shows avg_op_supply which i limit to the standard to be 84 and any ones who prescribes the category of medications under the controlled substance act(CSA). The CSA is used for organizing drugs based on the risk of abuse or harm to users in five and my capestone focuses on the approved by [FDA](https://www.fda.gov/drugs/drugsafety/informationbydrugclass/ucm251735.htm) and [DEA](https://www.deadiversion.usdoj.gov/schedules/) to be prescribed by licensed and certified health professional.  These drug lists that are considered controlled substances under the Controlled Substances Act (CSA) are divided into five schedules.  An updated and complete list of the schedules is published annually in [Title 21 Code of Federal Regulations (C.F.R.) §§ 1308.11 through 1308.15](https://www.deadiversion.usdoj.gov/21cfr/cfr/2108cfrt.htm).\n",
    "\n",
    "Therfore, for analysis and visualization  i only took those physicians who have greater opood cliams from the center for medical services dataset and created a feature average opiod supply  by dividing the total cliam by the opiod cliam and reviewed those specialists who prescribe more than the set limit of 12 weeks and that also become a new feature that measures the length of opiod prescription supply more than 84 days. As been visualized in notebook 1.3, significant amount of prescribers are family physicians, followed by internal medicine,nurse practitioners, Physicain Assistant and physical medicine and rehabilitation. When i group based on speciality and the vsuals can be accessed   [here top 20](https://plot.ly/~kiros/112) and the lists are as follows:-\n",
    "  > $'Cardiology', 'Nephrology', 'Endocrinology', 'Neurology'  'General Practice', 'Internal Medicine', 'Urology'$,   > $'Pulmonary Disease', 'Gastroenterology', 'Family Practice', 'Infectious Disease','Psychiatry'$ \n",
    "  >$'Nurse Practitioner', 'Ophthalmology','Allergy/Immunology', 'Otolaryngology', 'Psychiatry & Neurology'$ , $'Rheumatology', 'Dermatology', 'Obstetrics/Gynecology'$"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Author : Kiros Gebremariam**\n",
    "\n",
    "Cohorts of the Data Science Immersive, General Assembly @ Washington DC campus"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<b>Importing packages and csv files.</b>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "import seaborn as sns\n",
    "import matplotlib.mlab as mlab\n",
    "import re\n",
    "import csv\n",
    "\n",
    "from matplotlib import rcParams\n",
    "rcParams.update({'figure.autolayout':True})\n",
    "\n",
    "# setting visual\n",
    "sns.set(font_scale=1)\n",
    "cmap = sns.diverging_palette(220, 10, as_cmap=True) # one of the many color mappings\n",
    "plt.style.use('fivethirtyeight')\n",
    "sns.set_style('whitegrid')\n",
    "plt.style.use('ggplot')\n",
    "%config InlineBackend.figure_format = 'retina'\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "python 3.6.5 |Anaconda custom (64-bit)| (default, Apr 26 2018, 08:42:37) \n",
      "[GCC 4.2.1 Compatible Clang 4.0.1 (tags/RELEASE_401/final)]\n",
      "\n",
      "pandas 0.23.0\n",
      "numpy 1.14.5\n",
      "matplotlib 2.2.2\n",
      "seaborn 0.8.1\n",
      "sklearn0.19.1\n"
     ]
    }
   ],
   "source": [
    "# Print version info for the sake of reproducibility\n",
    "import sys\n",
    "import matplotlib as mpl\n",
    "import sklearn as skl\n",
    "print(\"python \" + sys.version)\n",
    "print(\"\")\n",
    "print(\"pandas \" + str(pd.__version__))\n",
    "print(\"numpy \" + np.__version__)\n",
    "print(\"matplotlib \" + mpl.__version__)\n",
    "print(\"seaborn \" + sns.__version__)\n",
    "print(\"sklearn\" + skl.__version__)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/kirosgebremariam/anaconda3/envs/dsi/lib/python3.6/site-packages/IPython/core/interactiveshell.py:2785: DtypeWarning: Columns (5,6) have mixed types. Specify dtype option on import or set low_memory=False.\n",
      "  interactivity=interactivity, compiler=compiler, result=result)\n"
     ]
    }
   ],
   "source": [
    "opioids = pd.read_csv('./inputs/list_opioids.csv')\n",
    "prescribers = pd.read_csv('./inputs/cleaned_prescriber_info18.csv')\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<b>Viewing raw data and statistics.</b>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "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>NPI</th>\n",
       "      <th>Gender</th>\n",
       "      <th>State</th>\n",
       "      <th>Credentials</th>\n",
       "      <th>Specialty</th>\n",
       "      <th>NPPES Provider Last Name</th>\n",
       "      <th>NPPES Provider First Name</th>\n",
       "      <th>NPPES Provider ZIP Code</th>\n",
       "      <th>NPPES Provider State</th>\n",
       "      <th>Totalclaimcount</th>\n",
       "      <th>...</th>\n",
       "      <th>VYTORIN</th>\n",
       "      <th>WARFARIN.SODIUM</th>\n",
       "      <th>XARELTO</th>\n",
       "      <th>ZETIA</th>\n",
       "      <th>ZIPRASIDONE.HCL</th>\n",
       "      <th>ZOLPIDEM.TARTRATE</th>\n",
       "      <th>avg_op_supply</th>\n",
       "      <th>op_longer</th>\n",
       "      <th>Opioid_Prescriber</th>\n",
       "      <th>op_prescriber</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1003002320</td>\n",
       "      <td>M</td>\n",
       "      <td>MS</td>\n",
       "      <td>D.M.D. P.A.</td>\n",
       "      <td>Dentist</td>\n",
       "      <td>EKLUND</td>\n",
       "      <td>D.</td>\n",
       "      <td>39208.0</td>\n",
       "      <td>MS</td>\n",
       "      <td>129</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>4.5</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1003004771</td>\n",
       "      <td>F</td>\n",
       "      <td>CO</td>\n",
       "      <td>M.D.</td>\n",
       "      <td>Pulmonary Disease</td>\n",
       "      <td>RIGGLE</td>\n",
       "      <td>ERIN</td>\n",
       "      <td>80120.0</td>\n",
       "      <td>CO</td>\n",
       "      <td>537</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>16</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>4.5</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1003008475</td>\n",
       "      <td>F</td>\n",
       "      <td>GA</td>\n",
       "      <td>NP</td>\n",
       "      <td>Nurse Practitioner</td>\n",
       "      <td>DAVIS</td>\n",
       "      <td>JENNIFER</td>\n",
       "      <td>31533.0</td>\n",
       "      <td>GA</td>\n",
       "      <td>299</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>4.5</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1003009630</td>\n",
       "      <td>M</td>\n",
       "      <td>NY</td>\n",
       "      <td>MD</td>\n",
       "      <td>Emergency Medicine</td>\n",
       "      <td>SINGLETARY</td>\n",
       "      <td>ROBERT</td>\n",
       "      <td>11215.0</td>\n",
       "      <td>NY</td>\n",
       "      <td>320</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>4.1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1003016270</td>\n",
       "      <td>M</td>\n",
       "      <td>CT</td>\n",
       "      <td>M.D.</td>\n",
       "      <td>Family Practice</td>\n",
       "      <td>MUTHUKRISHNAN</td>\n",
       "      <td>VIJAI</td>\n",
       "      <td>6010.0</td>\n",
       "      <td>CT</td>\n",
       "      <td>4017</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>32</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>36</td>\n",
       "      <td>13.5</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 264 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "          NPI Gender State  Credentials           Specialty  \\\n",
       "0  1003002320      M    MS  D.M.D. P.A.             Dentist   \n",
       "1  1003004771      F    CO         M.D.   Pulmonary Disease   \n",
       "2  1003008475      F    GA           NP  Nurse Practitioner   \n",
       "3  1003009630      M    NY           MD  Emergency Medicine   \n",
       "4  1003016270      M    CT         M.D.     Family Practice   \n",
       "\n",
       "  NPPES Provider Last Name NPPES Provider First Name  NPPES Provider ZIP Code  \\\n",
       "0                   EKLUND                        D.                  39208.0   \n",
       "1                   RIGGLE                      ERIN                  80120.0   \n",
       "2                    DAVIS                  JENNIFER                  31533.0   \n",
       "3               SINGLETARY                    ROBERT                  11215.0   \n",
       "4            MUTHUKRISHNAN                     VIJAI                   6010.0   \n",
       "\n",
       "  NPPES Provider State  Totalclaimcount      ...        VYTORIN  \\\n",
       "0                   MS              129      ...              0   \n",
       "1                   CO              537      ...              0   \n",
       "2                   GA              299      ...              0   \n",
       "3                   NY              320      ...              0   \n",
       "4                   CT             4017      ...              0   \n",
       "\n",
       "   WARFARIN.SODIUM  XARELTO  ZETIA  ZIPRASIDONE.HCL  ZOLPIDEM.TARTRATE  \\\n",
       "0                0        0      0                0                  0   \n",
       "1                0       16      0                0                  0   \n",
       "2                0        0      0                0                  0   \n",
       "3                0        0      0                0                  0   \n",
       "4               32        0      0                0                 36   \n",
       "\n",
       "   avg_op_supply  op_longer  Opioid_Prescriber  op_prescriber  \n",
       "0            4.5        1.0                  1            1.0  \n",
       "1            4.5        0.0                  0            0.0  \n",
       "2            4.5        0.0                  1            1.0  \n",
       "3            4.1        1.0                  1            1.0  \n",
       "4           13.5        1.0                  1            1.0  \n",
       "\n",
       "[5 rows x 264 columns]"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "prescribers.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "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>NPI</th>\n",
       "      <th>NPPES Provider ZIP Code</th>\n",
       "      <th>Totalclaimcount</th>\n",
       "      <th>OpioidClaimCount</th>\n",
       "      <th>ACETAMINOPHEN.CODEINE</th>\n",
       "      <th>ACYCLOVIR</th>\n",
       "      <th>ADVAIR.DISKUS</th>\n",
       "      <th>AGGRENOX</th>\n",
       "      <th>ALENDRONATE.SODIUM</th>\n",
       "      <th>ALLOPURINOL</th>\n",
       "      <th>...</th>\n",
       "      <th>VYTORIN</th>\n",
       "      <th>WARFARIN.SODIUM</th>\n",
       "      <th>XARELTO</th>\n",
       "      <th>ZETIA</th>\n",
       "      <th>ZIPRASIDONE.HCL</th>\n",
       "      <th>ZOLPIDEM.TARTRATE</th>\n",
       "      <th>avg_op_supply</th>\n",
       "      <th>op_longer</th>\n",
       "      <th>Opioid_Prescriber</th>\n",
       "      <th>op_prescriber</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>2.500000e+04</td>\n",
       "      <td>22390.000000</td>\n",
       "      <td>25000.000000</td>\n",
       "      <td>25000.000000</td>\n",
       "      <td>25000.000000</td>\n",
       "      <td>25000.000000</td>\n",
       "      <td>25000.000000</td>\n",
       "      <td>25000.000000</td>\n",
       "      <td>25000.000000</td>\n",
       "      <td>25000.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>25000.000000</td>\n",
       "      <td>25000.000000</td>\n",
       "      <td>25000.00000</td>\n",
       "      <td>25000.000000</td>\n",
       "      <td>25000.000000</td>\n",
       "      <td>25000.000000</td>\n",
       "      <td>22390.000000</td>\n",
       "      <td>22390.000000</td>\n",
       "      <td>25000.000000</td>\n",
       "      <td>22390.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>1.497815e+09</td>\n",
       "      <td>48156.120232</td>\n",
       "      <td>1698.879960</td>\n",
       "      <td>80.216440</td>\n",
       "      <td>2.539120</td>\n",
       "      <td>1.169320</td>\n",
       "      <td>6.938680</td>\n",
       "      <td>1.333360</td>\n",
       "      <td>8.763960</td>\n",
       "      <td>9.957560</td>\n",
       "      <td>...</td>\n",
       "      <td>1.030800</td>\n",
       "      <td>18.253280</td>\n",
       "      <td>4.92088</td>\n",
       "      <td>4.308920</td>\n",
       "      <td>1.428480</td>\n",
       "      <td>11.148480</td>\n",
       "      <td>23.306757</td>\n",
       "      <td>0.595400</td>\n",
       "      <td>1.721560</td>\n",
       "      <td>0.595578</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>2.879339e+08</td>\n",
       "      <td>30003.420351</td>\n",
       "      <td>3512.928148</td>\n",
       "      <td>264.465556</td>\n",
       "      <td>12.504745</td>\n",
       "      <td>6.805065</td>\n",
       "      <td>25.619397</td>\n",
       "      <td>9.105226</td>\n",
       "      <td>36.012932</td>\n",
       "      <td>30.567146</td>\n",
       "      <td>...</td>\n",
       "      <td>8.167705</td>\n",
       "      <td>81.237655</td>\n",
       "      <td>24.69952</td>\n",
       "      <td>19.147394</td>\n",
       "      <td>11.375485</td>\n",
       "      <td>36.323232</td>\n",
       "      <td>41.877051</td>\n",
       "      <td>0.490825</td>\n",
       "      <td>15.200218</td>\n",
       "      <td>0.490791</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>1.003002e+09</td>\n",
       "      <td>601.000000</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>0.000000</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>0.00000</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>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>1.245430e+09</td>\n",
       "      <td>22031.500000</td>\n",
       "      <td>75.000000</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>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.00000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>11.200000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>1.497834e+09</td>\n",
       "      <td>44720.000000</td>\n",
       "      <td>325.000000</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>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.00000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>18.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>1.740388e+09</td>\n",
       "      <td>76107.000000</td>\n",
       "      <td>1636.250000</td>\n",
       "      <td>57.000000</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>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.00000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>18.300000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>1.992999e+09</td>\n",
       "      <td>99901.000000</td>\n",
       "      <td>58397.000000</td>\n",
       "      <td>14177.000000</td>\n",
       "      <td>644.000000</td>\n",
       "      <td>356.000000</td>\n",
       "      <td>1105.000000</td>\n",
       "      <td>609.000000</td>\n",
       "      <td>2431.000000</td>\n",
       "      <td>790.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>608.000000</td>\n",
       "      <td>6029.000000</td>\n",
       "      <td>826.00000</td>\n",
       "      <td>772.000000</td>\n",
       "      <td>694.000000</td>\n",
       "      <td>1707.000000</td>\n",
       "      <td>2260.400000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1707.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>8 rows × 257 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                NPI  NPPES Provider ZIP Code  Totalclaimcount  \\\n",
       "count  2.500000e+04             22390.000000     25000.000000   \n",
       "mean   1.497815e+09             48156.120232      1698.879960   \n",
       "std    2.879339e+08             30003.420351      3512.928148   \n",
       "min    1.003002e+09               601.000000         0.000000   \n",
       "25%    1.245430e+09             22031.500000        75.000000   \n",
       "50%    1.497834e+09             44720.000000       325.000000   \n",
       "75%    1.740388e+09             76107.000000      1636.250000   \n",
       "max    1.992999e+09             99901.000000     58397.000000   \n",
       "\n",
       "       OpioidClaimCount  ACETAMINOPHEN.CODEINE     ACYCLOVIR  ADVAIR.DISKUS  \\\n",
       "count      25000.000000           25000.000000  25000.000000   25000.000000   \n",
       "mean          80.216440               2.539120      1.169320       6.938680   \n",
       "std          264.465556              12.504745      6.805065      25.619397   \n",
       "min            0.000000               0.000000      0.000000       0.000000   \n",
       "25%            0.000000               0.000000      0.000000       0.000000   \n",
       "50%            0.000000               0.000000      0.000000       0.000000   \n",
       "75%           57.000000               0.000000      0.000000       0.000000   \n",
       "max        14177.000000             644.000000    356.000000    1105.000000   \n",
       "\n",
       "           AGGRENOX  ALENDRONATE.SODIUM   ALLOPURINOL      ...        \\\n",
       "count  25000.000000        25000.000000  25000.000000      ...         \n",
       "mean       1.333360            8.763960      9.957560      ...         \n",
       "std        9.105226           36.012932     30.567146      ...         \n",
       "min        0.000000            0.000000      0.000000      ...         \n",
       "25%        0.000000            0.000000      0.000000      ...         \n",
       "50%        0.000000            0.000000      0.000000      ...         \n",
       "75%        0.000000            0.000000      0.000000      ...         \n",
       "max      609.000000         2431.000000    790.000000      ...         \n",
       "\n",
       "            VYTORIN  WARFARIN.SODIUM      XARELTO         ZETIA  \\\n",
       "count  25000.000000     25000.000000  25000.00000  25000.000000   \n",
       "mean       1.030800        18.253280      4.92088      4.308920   \n",
       "std        8.167705        81.237655     24.69952     19.147394   \n",
       "min        0.000000         0.000000      0.00000      0.000000   \n",
       "25%        0.000000         0.000000      0.00000      0.000000   \n",
       "50%        0.000000         0.000000      0.00000      0.000000   \n",
       "75%        0.000000         0.000000      0.00000      0.000000   \n",
       "max      608.000000      6029.000000    826.00000    772.000000   \n",
       "\n",
       "       ZIPRASIDONE.HCL  ZOLPIDEM.TARTRATE  avg_op_supply     op_longer  \\\n",
       "count     25000.000000       25000.000000   22390.000000  22390.000000   \n",
       "mean          1.428480          11.148480      23.306757      0.595400   \n",
       "std          11.375485          36.323232      41.877051      0.490825   \n",
       "min           0.000000           0.000000       0.000000      0.000000   \n",
       "25%           0.000000           0.000000      11.200000      0.000000   \n",
       "50%           0.000000           0.000000      18.000000      1.000000   \n",
       "75%           0.000000           0.000000      18.300000      1.000000   \n",
       "max         694.000000        1707.000000    2260.400000      1.000000   \n",
       "\n",
       "       Opioid_Prescriber  op_prescriber  \n",
       "count       25000.000000   22390.000000  \n",
       "mean            1.721560       0.595578  \n",
       "std            15.200218       0.490791  \n",
       "min             0.000000       0.000000  \n",
       "25%             0.000000       0.000000  \n",
       "50%             1.000000       1.000000  \n",
       "75%             1.000000       1.000000  \n",
       "max          1707.000000       1.000000  \n",
       "\n",
       "[8 rows x 257 columns]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "prescribers.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['NPI',\n",
       " 'Gender',\n",
       " 'State',\n",
       " 'Credentials',\n",
       " 'Specialty',\n",
       " 'NPPES Provider Last Name',\n",
       " 'NPPES Provider First Name',\n",
       " 'NPPES Provider ZIP Code',\n",
       " 'NPPES Provider State',\n",
       " 'Totalclaimcount',\n",
       " 'OpioidClaimCount',\n",
       " 'ACETAMINOPHEN.CODEINE',\n",
       " 'ACYCLOVIR',\n",
       " 'ADVAIR.DISKUS',\n",
       " 'AGGRENOX',\n",
       " 'ALENDRONATE.SODIUM',\n",
       " 'ALLOPURINOL',\n",
       " 'ALPRAZOLAM',\n",
       " 'AMIODARONE.HCL',\n",
       " 'AMITRIPTYLINE.HCL',\n",
       " 'AMLODIPINE.BESYLATE',\n",
       " 'AMLODIPINE.BESYLATE.BENAZEPRIL',\n",
       " 'AMOXICILLIN',\n",
       " 'AMOX.TR.POTASSIUM.CLAVULANATE',\n",
       " 'AMPHETAMINE.SALT.COMBO',\n",
       " 'ATENOLOL',\n",
       " 'ATORVASTATIN.CALCIUM',\n",
       " 'AVODART',\n",
       " 'AZITHROMYCIN',\n",
       " 'BACLOFEN',\n",
       " 'BD.ULTRA.FINE.PEN.NEEDLE',\n",
       " 'BENAZEPRIL.HCL',\n",
       " 'BENICAR',\n",
       " 'BENICAR.HCT',\n",
       " 'BENZTROPINE.MESYLATE',\n",
       " 'BISOPROLOL.HYDROCHLOROTHIAZIDE',\n",
       " 'BRIMONIDINE.TARTRATE',\n",
       " 'BUMETANIDE',\n",
       " 'BUPROPION.HCL.SR',\n",
       " 'BUPROPION.XL',\n",
       " 'BUSPIRONE.HCL',\n",
       " 'BYSTOLIC',\n",
       " 'CARBAMAZEPINE',\n",
       " 'CARBIDOPA.LEVODOPA',\n",
       " 'CARISOPRODOL',\n",
       " 'CARTIA.XT',\n",
       " 'CARVEDILOL',\n",
       " 'CEFUROXIME',\n",
       " 'CELEBREX',\n",
       " 'CEPHALEXIN',\n",
       " 'CHLORHEXIDINE.GLUCONATE',\n",
       " 'CHLORTHALIDONE',\n",
       " 'CILOSTAZOL',\n",
       " 'CIPROFLOXACIN.HCL',\n",
       " 'CITALOPRAM.HBR',\n",
       " 'CLINDAMYCIN.HCL',\n",
       " 'CLOBETASOL.PROPIONATE',\n",
       " 'CLONAZEPAM',\n",
       " 'CLONIDINE.HCL',\n",
       " 'CLOPIDOGREL',\n",
       " 'CLOTRIMAZOLE.BETAMETHASONE',\n",
       " 'COLCRYS',\n",
       " 'COMBIVENT.RESPIMAT',\n",
       " 'CRESTOR',\n",
       " 'CYCLOBENZAPRINE.HCL',\n",
       " 'DEXILANT',\n",
       " 'DIAZEPAM',\n",
       " 'DICLOFENAC.SODIUM',\n",
       " 'DICYCLOMINE.HCL',\n",
       " 'DIGOX',\n",
       " 'DIGOXIN',\n",
       " 'DILTIAZEM.24HR.CD',\n",
       " 'DILTIAZEM.24HR.ER',\n",
       " 'DILTIAZEM.ER',\n",
       " 'DILTIAZEM.HCL',\n",
       " 'DIOVAN',\n",
       " 'DIPHENOXYLATE.ATROPINE',\n",
       " 'DIVALPROEX.SODIUM',\n",
       " 'DIVALPROEX.SODIUM.ER',\n",
       " 'DONEPEZIL.HCL',\n",
       " 'DORZOLAMIDE.TIMOLOL',\n",
       " 'DOXAZOSIN.MESYLATE',\n",
       " 'DOXEPIN.HCL',\n",
       " 'DOXYCYCLINE.HYCLATE',\n",
       " 'DULOXETINE.HCL',\n",
       " 'ENALAPRIL.MALEATE',\n",
       " 'ESCITALOPRAM.OXALATE',\n",
       " 'ESTRADIOL',\n",
       " 'EXELON',\n",
       " 'FAMOTIDINE',\n",
       " 'FELODIPINE.ER',\n",
       " 'FENOFIBRATE',\n",
       " 'FENTANYL',\n",
       " 'FINASTERIDE',\n",
       " 'FLOVENT.HFA',\n",
       " 'FLUCONAZOLE',\n",
       " 'FLUOXETINE.HCL',\n",
       " 'FLUTICASONE.PROPIONATE',\n",
       " 'FUROSEMIDE',\n",
       " 'GABAPENTIN',\n",
       " 'GEMFIBROZIL',\n",
       " 'GLIMEPIRIDE',\n",
       " 'GLIPIZIDE',\n",
       " 'GLIPIZIDE.ER',\n",
       " 'GLIPIZIDE.XL',\n",
       " 'GLYBURIDE',\n",
       " 'HALOPERIDOL',\n",
       " 'HUMALOG',\n",
       " 'HYDRALAZINE.HCL',\n",
       " 'HYDROCHLOROTHIAZIDE',\n",
       " 'HYDROCODONE.ACETAMINOPHEN',\n",
       " 'HYDROCORTISONE',\n",
       " 'HYDROMORPHONE.HCL',\n",
       " 'HYDROXYZINE.HCL',\n",
       " 'IBANDRONATE.SODIUM',\n",
       " 'IBUPROFEN',\n",
       " 'INSULIN.SYRINGE',\n",
       " 'IPRATROPIUM.BROMIDE',\n",
       " 'IRBESARTAN',\n",
       " 'ISOSORBIDE.MONONITRATE.ER',\n",
       " 'JANTOVEN',\n",
       " 'JANUMET',\n",
       " 'JANUVIA',\n",
       " 'KETOCONAZOLE',\n",
       " 'KLOR.CON.10',\n",
       " 'KLOR.CON.M10',\n",
       " 'KLOR.CON.M20',\n",
       " 'LABETALOL.HCL',\n",
       " 'LACTULOSE',\n",
       " 'LAMOTRIGINE',\n",
       " 'LANSOPRAZOLE',\n",
       " 'LANTUS',\n",
       " 'LANTUS.SOLOSTAR',\n",
       " 'LATANOPROST',\n",
       " 'LEVEMIR',\n",
       " 'LEVEMIR.FLEXPEN',\n",
       " 'LEVETIRACETAM',\n",
       " 'LEVOFLOXACIN',\n",
       " 'LEVOTHYROXINE.SODIUM',\n",
       " 'LIDOCAINE',\n",
       " 'LISINOPRIL',\n",
       " 'LISINOPRIL.HYDROCHLOROTHIAZIDE',\n",
       " 'LITHIUM.CARBONATE',\n",
       " 'LORAZEPAM',\n",
       " 'LOSARTAN.HYDROCHLOROTHIAZIDE',\n",
       " 'LOSARTAN.POTASSIUM',\n",
       " 'LOVASTATIN',\n",
       " 'LOVAZA',\n",
       " 'LUMIGAN',\n",
       " 'LYRICA',\n",
       " 'MECLIZINE.HCL',\n",
       " 'MELOXICAM',\n",
       " 'METFORMIN.HCL',\n",
       " 'METFORMIN.HCL.ER',\n",
       " 'METHADONE.HCL',\n",
       " 'METHOCARBAMOL',\n",
       " 'METHOTREXATE',\n",
       " 'METHYLPREDNISOLONE',\n",
       " 'METOCLOPRAMIDE.HCL',\n",
       " 'METOLAZONE',\n",
       " 'METOPROLOL.SUCCINATE',\n",
       " 'METOPROLOL.TARTRATE',\n",
       " 'METRONIDAZOLE',\n",
       " 'MIRTAZAPINE',\n",
       " 'MONTELUKAST.SODIUM',\n",
       " 'MORPHINE.SULFATE',\n",
       " 'MORPHINE.SULFATE.ER',\n",
       " 'MUPIROCIN',\n",
       " 'NABUMETONE',\n",
       " 'NAMENDA',\n",
       " 'NAMENDA.XR',\n",
       " 'NAPROXEN',\n",
       " 'NASONEX',\n",
       " 'NEXIUM',\n",
       " 'NIACIN.ER',\n",
       " 'NIFEDICAL.XL',\n",
       " 'NIFEDIPINE.ER',\n",
       " 'NITROFURANTOIN.MONO.MACRO',\n",
       " 'NITROSTAT',\n",
       " 'NORTRIPTYLINE.HCL',\n",
       " 'NOVOLOG',\n",
       " 'NOVOLOG.FLEXPEN',\n",
       " 'NYSTATIN',\n",
       " 'OLANZAPINE',\n",
       " 'OMEPRAZOLE',\n",
       " 'ONDANSETRON.HCL',\n",
       " 'ONDANSETRON.ODT',\n",
       " 'ONGLYZA',\n",
       " 'OXCARBAZEPINE',\n",
       " 'OXYBUTYNIN.CHLORIDE',\n",
       " 'OXYBUTYNIN.CHLORIDE.ER',\n",
       " 'OXYCODONE.ACETAMINOPHEN',\n",
       " 'OXYCODONE.HCL',\n",
       " 'OXYCONTIN',\n",
       " 'PANTOPRAZOLE.SODIUM',\n",
       " 'PAROXETINE.HCL',\n",
       " 'PHENOBARBITAL',\n",
       " 'PHENYTOIN.SODIUM.EXTENDED',\n",
       " 'PIOGLITAZONE.HCL',\n",
       " 'POLYETHYLENE.GLYCOL.3350',\n",
       " 'POTASSIUM.CHLORIDE',\n",
       " 'PRADAXA',\n",
       " 'PRAMIPEXOLE.DIHYDROCHLORIDE',\n",
       " 'PRAVASTATIN.SODIUM',\n",
       " 'PREDNISONE',\n",
       " 'PREMARIN',\n",
       " 'PRIMIDONE',\n",
       " 'PROAIR.HFA',\n",
       " 'PROMETHAZINE.HCL',\n",
       " 'PROPRANOLOL.HCL',\n",
       " 'PROPRANOLOL.HCL.ER',\n",
       " 'QUETIAPINE.FUMARATE',\n",
       " 'QUINAPRIL.HCL',\n",
       " 'RALOXIFENE.HCL',\n",
       " 'RAMIPRIL',\n",
       " 'RANEXA',\n",
       " 'RANITIDINE.HCL',\n",
       " 'RESTASIS',\n",
       " 'RISPERIDONE',\n",
       " 'ROPINIROLE.HCL',\n",
       " 'SEROQUEL.XR',\n",
       " 'SERTRALINE.HCL',\n",
       " 'SIMVASTATIN',\n",
       " 'SOTALOL',\n",
       " 'SPIRIVA',\n",
       " 'SPIRONOLACTONE',\n",
       " 'SUCRALFATE',\n",
       " 'SULFAMETHOXAZOLE.TRIMETHOPRIM',\n",
       " 'SUMATRIPTAN.SUCCINATE',\n",
       " 'SYMBICORT',\n",
       " 'SYNTHROID',\n",
       " 'TAMSULOSIN.HCL',\n",
       " 'TEMAZEPAM',\n",
       " 'TERAZOSIN.HCL',\n",
       " 'TIMOLOL.MALEATE',\n",
       " 'TIZANIDINE.HCL',\n",
       " 'TOLTERODINE.TARTRATE.ER',\n",
       " 'TOPIRAMATE',\n",
       " 'TOPROL.XL',\n",
       " 'TORSEMIDE',\n",
       " 'TRAMADOL.HCL',\n",
       " 'TRAVATAN.Z',\n",
       " 'TRAZODONE.HCL',\n",
       " 'TRIAMCINOLONE.ACETONIDE',\n",
       " 'TRIAMTERENE.HYDROCHLOROTHIAZID',\n",
       " 'VALACYCLOVIR',\n",
       " 'VALSARTAN',\n",
       " 'VALSARTAN.HYDROCHLOROTHIAZIDE',\n",
       " 'VENLAFAXINE.HCL',\n",
       " 'VENLAFAXINE.HCL.ER',\n",
       " 'VENTOLIN.HFA',\n",
       " 'VERAPAMIL.ER',\n",
       " 'VESICARE',\n",
       " 'VOLTAREN',\n",
       " 'VYTORIN',\n",
       " 'WARFARIN.SODIUM',\n",
       " 'XARELTO',\n",
       " 'ZETIA',\n",
       " 'ZIPRASIDONE.HCL',\n",
       " 'ZOLPIDEM.TARTRATE',\n",
       " 'avg_op_supply',\n",
       " 'op_longer',\n",
       " 'Opioid_Prescriber',\n",
       " 'op_prescriber']"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "list(prescribers)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<b> Opiates are not defined in 'prescriber-info.csv'\n",
    "    opioids.csv has different names often with extra “.” etc. \n",
    "    Using re.sub to only get columns in opioids.csv</b> "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1 HYDROMORPHONE.HCL\n",
      "2 ACETAMINOPHEN.CODEINE\n",
      "3 OXYCONTIN\n",
      "4 FENTANYL\n",
      "5 MORPHINE.SULFATE.ER\n",
      "6 HYDROCODONE.ACETAMINOPHEN\n",
      "7 OXYCODONE.ACETAMINOPHEN\n",
      "8 METHADONE.HCL\n",
      "9 OXYCODONE.HCL\n",
      "10 TRAMADOL.HCL\n",
      "11 MORPHINE.SULFATE\n"
     ]
    }
   ],
   "source": [
    "ops = list(re.sub(r'[-\\s]','.',x) for x in opioids.values[:,0])\n",
    "prescribed_ops = list(set(ops) & set(prescribers.columns))\n",
    "\n",
    "for i,drug in enumerate(prescribed_ops):\n",
    "    print (i+1,drug)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<b>These 11 are opioids.</b>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<b> Finding the specialty which prescribes opiates more than others. Present information by state.\n",
    "   \n",
    "   I will use the Column Opioid.Prescriber.</b>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "stateCount_PrescribedOpiods = pd.DataFrame(prescribers.loc[prescribers['Opioid_Prescriber']>0])\n",
    "df = pd.DataFrame(stateCount_PrescribedOpiods[['State','Specialty','Opioid_Prescriber']])\n",
    "\n",
    "SpecGrp = df.groupby(['Specialty',])[['Opioid_Prescriber']].sum()\n",
    "SpecGrpResult = SpecGrp.sort_values(by='Opioid_Prescriber', ascending=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<b>First, lets look at specialty.</b>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "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>Opioid_Prescriber</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Specialty</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Family Practice</th>\n",
       "      <td>12686</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Internal Medicine</th>\n",
       "      <td>11737</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Psychiatry</th>\n",
       "      <td>3962</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Nurse Practitioner</th>\n",
       "      <td>2517</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Physician Assistant</th>\n",
       "      <td>2292</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                     Opioid_Prescriber\n",
       "Specialty                             \n",
       "Family Practice                  12686\n",
       "Internal Medicine                11737\n",
       "Psychiatry                        3962\n",
       "Nurse Practitioner                2517\n",
       "Physician Assistant               2292"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "SpecGrpResult.head(5)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<b>Next, I will group by specialty and state. I'll sort by the top opioid prescriber.</b> "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "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></th>\n",
       "      <th>Opioid_Prescriber</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Specialty</th>\n",
       "      <th>State</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Internal Medicine</th>\n",
       "      <th>CA</th>\n",
       "      <td>1796</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Psychiatry</th>\n",
       "      <th>MA</th>\n",
       "      <td>1787</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Family Practice</th>\n",
       "      <th>FL</th>\n",
       "      <td>1285</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"3\" valign=\"top\">Internal Medicine</th>\n",
       "      <th>FL</th>\n",
       "      <td>1052</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>PA</th>\n",
       "      <td>1025</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>NY</th>\n",
       "      <td>1011</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"5\" valign=\"top\">Family Practice</th>\n",
       "      <th>NC</th>\n",
       "      <td>914</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>OH</th>\n",
       "      <td>827</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>CA</th>\n",
       "      <td>790</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>TX</th>\n",
       "      <td>751</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>TN</th>\n",
       "      <td>697</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Internal Medicine</th>\n",
       "      <th>NJ</th>\n",
       "      <td>651</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">Family Practice</th>\n",
       "      <th>PA</th>\n",
       "      <td>615</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>GA</th>\n",
       "      <td>573</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">Internal Medicine</th>\n",
       "      <th>NC</th>\n",
       "      <td>508</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>AL</th>\n",
       "      <td>505</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Family Practice</th>\n",
       "      <th>IN</th>\n",
       "      <td>488</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Psychiatry</th>\n",
       "      <th>WV</th>\n",
       "      <td>457</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">Internal Medicine</th>\n",
       "      <th>MA</th>\n",
       "      <td>455</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>IL</th>\n",
       "      <td>434</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                         Opioid_Prescriber\n",
       "Specialty         State                   \n",
       "Internal Medicine CA                  1796\n",
       "Psychiatry        MA                  1787\n",
       "Family Practice   FL                  1285\n",
       "Internal Medicine FL                  1052\n",
       "                  PA                  1025\n",
       "                  NY                  1011\n",
       "Family Practice   NC                   914\n",
       "                  OH                   827\n",
       "                  CA                   790\n",
       "                  TX                   751\n",
       "                  TN                   697\n",
       "Internal Medicine NJ                   651\n",
       "Family Practice   PA                   615\n",
       "                  GA                   573\n",
       "Internal Medicine NC                   508\n",
       "                  AL                   505\n",
       "Family Practice   IN                   488\n",
       "Psychiatry        WV                   457\n",
       "Internal Medicine MA                   455\n",
       "                  IL                   434"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "Grp = df.groupby(['Specialty','State'])[['Opioid_Prescriber']].sum()\n",
    "Result = Grp.sort_values(by='Opioid_Prescriber', ascending=False)\n",
    "Result.head(n=20)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<seaborn.axisgrid.PairGrid at 0x10dc29278>"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/kirosgebremariam/anaconda3/envs/dsi/lib/python3.6/site-packages/matplotlib/figure.py:2267: UserWarning: This figure includes Axes that are not compatible with tight_layout, so results might be incorrect.\n",
      "  warnings.warn(\"This figure includes Axes that are not compatible \"\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 180x180 with 2 Axes>"
      ]
     },
     "metadata": {
      "image/png": {
       "height": 172,
       "width": 172
      }
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.pairplot(Result)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Here i am going to check the most “popular” opiate in the nation and to try to understand the distributionby states and specialties for the purpose of visualization in tableau. manipulating the data sometimes was not helpful to get the results needed and using the skills of applying different tools, i found it very helpful, specifically galancing and cleaning the data to visualize it in tableau needs more work in excel than in python."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "popOpiate = prescribers[['Specialty','State','METHADONE.HCL',\n",
    " 'OXYCODONE.ACETAMINOPHEN',\n",
    " 'HYDROCODONE.ACETAMINOPHEN',\n",
    " 'ACETAMINOPHEN.CODEINE',\n",
    " 'FENTANYL',\n",
    " 'TRAMADOL.HCL',\n",
    " 'MORPHINE.SULFATE.ER',\n",
    " 'OXYCODONE.HCL',\n",
    " 'MORPHINE.SULFATE',\n",
    " 'OXYCONTIN',\n",
    " 'HYDROMORPHONE.HCL']]\n",
    "psum = popOpiate.sum(numeric_only=True)\n",
    "psum = psum.sort_values(ascending=False)\n",
    "psum\n",
    "popOpiate.to_csv(\"./inputs/popular.csv\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    " The most popular opiate was found to be based on my data HYDROCODONE.ACETAMINOPHEN in most of the states and please enjoy the visuals below."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "** The below link is the visual of stacked display of the drugs, grouped  by speciality and displayed by state also**\n",
    "https://public.tableau.com/profile/kirosdsi.com#!/vizhome/CapstoneUSAOpiodscrisisByStateandSpeciality2018/ByStateAndSpecialty"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**This link is easy work of drugs by state in map  and both of them use the same data as above its only by color of map**\n",
    "\n",
    "https://public.tableau.com/profile/kirosdsi.com#!/vizhome/CapstoneUSAOpiodscrisisByStateandSpeciality2018/ByState\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    " To get the most popular drugs sometimes are not classified as opiats though they are prescribed as opiate and have some level of synthetic morphine and codene in the chemical combination\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "nonops = list(set(prescribers.columns)-set(ops))\n",
    "nonopsdf = list(set(nonops)& set (prescribers.columns))\n",
    "nonopsdf.append('Opioid_Prescriber')\n",
    "\n",
    "nonpopOpiate = prescribers[nonopsdf]\n",
    "\n",
    "nonpopOpiate.to_csv(\"./inputs/test.csv\")\n",
    "\n",
    "# drugsnotop = pd.read_csv('drugsnotops.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/kirosgebremariam/anaconda3/envs/dsi/lib/python3.6/site-packages/IPython/core/interactiveshell.py:2785: DtypeWarning: Columns (23,101) have mixed types. Specify dtype option on import or set low_memory=False.\n",
      "  interactivity=interactivity, compiler=compiler, result=result)\n"
     ]
    },
    {
     "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>METOPROLOL.SUCCINATE</th>\n",
       "      <th>NIACIN.ER</th>\n",
       "      <th>VALSARTAN.HYDROCHLOROTHIAZIDE</th>\n",
       "      <th>OXYBUTYNIN.CHLORIDE.ER</th>\n",
       "      <th>CARISOPRODOL</th>\n",
       "      <th>JANUVIA</th>\n",
       "      <th>DICYCLOMINE.HCL</th>\n",
       "      <th>TOLTERODINE.TARTRATE.ER</th>\n",
       "      <th>AMLODIPINE.BESYLATE.BENAZEPRIL</th>\n",
       "      <th>...</th>\n",
       "      <th>VOLTAREN</th>\n",
       "      <th>DILTIAZEM.24HR.ER</th>\n",
       "      <th>WARFARIN.SODIUM</th>\n",
       "      <th>DOXYCYCLINE.HYCLATE</th>\n",
       "      <th>PRIMIDONE</th>\n",
       "      <th>CLOBETASOL.PROPIONATE</th>\n",
       "      <th>NIFEDICAL.XL</th>\n",
       "      <th>NABUMETONE</th>\n",
       "      <th>avg_op_supply</th>\n",
       "      <th>Opioid_Prescriber.1</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>4.5</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>4.5</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>4.5</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>4.1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>4</td>\n",
       "      <td>22</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>12</td>\n",
       "      <td>32</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>11</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>13.5</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 255 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   Unnamed: 0  METOPROLOL.SUCCINATE  NIACIN.ER  VALSARTAN.HYDROCHLOROTHIAZIDE  \\\n",
       "0           0                     0          0                              0   \n",
       "1           1                     0          0                              0   \n",
       "2           2                     0          0                              0   \n",
       "3           3                     0          0                              0   \n",
       "4           4                    22          0                              0   \n",
       "\n",
       "   OXYBUTYNIN.CHLORIDE.ER  CARISOPRODOL  JANUVIA  DICYCLOMINE.HCL  \\\n",
       "0                       0             0        0                0   \n",
       "1                       0             0        0                0   \n",
       "2                       0             0        0                0   \n",
       "3                       0             0        0                0   \n",
       "4                       0             0        0                0   \n",
       "\n",
       "   TOLTERODINE.TARTRATE.ER  AMLODIPINE.BESYLATE.BENAZEPRIL  \\\n",
       "0                        0                               0   \n",
       "1                        0                               0   \n",
       "2                        0                               0   \n",
       "3                        0                               0   \n",
       "4                        0                               0   \n",
       "\n",
       "          ...           VOLTAREN  DILTIAZEM.24HR.ER  WARFARIN.SODIUM  \\\n",
       "0         ...                  0                  0                0   \n",
       "1         ...                  0                  0                0   \n",
       "2         ...                  0                  0                0   \n",
       "3         ...                  0                  0                0   \n",
       "4         ...                  0                 12               32   \n",
       "\n",
       "   DOXYCYCLINE.HYCLATE  PRIMIDONE  CLOBETASOL.PROPIONATE  NIFEDICAL.XL  \\\n",
       "0                    0          0                      0             0   \n",
       "1                    0          0                      0             0   \n",
       "2                    0          0                      0             0   \n",
       "3                    0          0                      0             0   \n",
       "4                    0          0                     11             0   \n",
       "\n",
       "   NABUMETONE avg_op_supply  Opioid_Prescriber.1  \n",
       "0           0           4.5                    1  \n",
       "1           0           4.5                    0  \n",
       "2           0           4.5                    1  \n",
       "3           0           4.1                    1  \n",
       "4           0          13.5                    1  \n",
       "\n",
       "[5 rows x 255 columns]"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "drugsnotop =pd.read_csv(\"./inputs/test.csv\")\n",
    "drugsnotop.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['Unnamed: 0',\n",
       " 'METOPROLOL.SUCCINATE',\n",
       " 'NIACIN.ER',\n",
       " 'VALSARTAN.HYDROCHLOROTHIAZIDE',\n",
       " 'OXYBUTYNIN.CHLORIDE.ER',\n",
       " 'CARISOPRODOL',\n",
       " 'JANUVIA',\n",
       " 'DICYCLOMINE.HCL',\n",
       " 'TOLTERODINE.TARTRATE.ER',\n",
       " 'AMLODIPINE.BESYLATE.BENAZEPRIL',\n",
       " 'NAPROXEN',\n",
       " 'VENLAFAXINE.HCL',\n",
       " 'BUPROPION.HCL.SR',\n",
       " 'DOXAZOSIN.MESYLATE',\n",
       " 'KETOCONAZOLE',\n",
       " 'BYSTOLIC',\n",
       " 'GEMFIBROZIL',\n",
       " 'TIZANIDINE.HCL',\n",
       " 'Credentials',\n",
       " 'BRIMONIDINE.TARTRATE',\n",
       " 'SUCRALFATE',\n",
       " 'METOLAZONE',\n",
       " 'Specialty',\n",
       " 'NPPES Provider First Name',\n",
       " 'DIGOX',\n",
       " 'ENALAPRIL.MALEATE',\n",
       " 'ONDANSETRON.ODT',\n",
       " 'LUMIGAN',\n",
       " 'LATANOPROST',\n",
       " 'CARBAMAZEPINE',\n",
       " 'ALENDRONATE.SODIUM',\n",
       " 'NEXIUM',\n",
       " 'OLANZAPINE',\n",
       " 'PREMARIN',\n",
       " 'CYCLOBENZAPRINE.HCL',\n",
       " 'DIVALPROEX.SODIUM',\n",
       " 'PRAMIPEXOLE.DIHYDROCHLORIDE',\n",
       " 'DIVALPROEX.SODIUM.ER',\n",
       " 'SPIRONOLACTONE',\n",
       " 'HYDROCHLOROTHIAZIDE',\n",
       " 'VESICARE',\n",
       " 'AMOX.TR.POTASSIUM.CLAVULANATE',\n",
       " 'ADVAIR.DISKUS',\n",
       " 'LITHIUM.CARBONATE',\n",
       " 'PROPRANOLOL.HCL.ER',\n",
       " 'DILTIAZEM.HCL',\n",
       " 'LANTUS',\n",
       " 'SUMATRIPTAN.SUCCINATE',\n",
       " 'LEVOFLOXACIN',\n",
       " 'AZITHROMYCIN',\n",
       " 'CLONIDINE.HCL',\n",
       " 'PANTOPRAZOLE.SODIUM',\n",
       " 'METOPROLOL.TARTRATE',\n",
       " 'FENOFIBRATE',\n",
       " 'AMOXICILLIN',\n",
       " 'PHENYTOIN.SODIUM.EXTENDED',\n",
       " 'NPPES Provider State',\n",
       " 'SOTALOL',\n",
       " 'IRBESARTAN',\n",
       " 'AGGRENOX',\n",
       " 'METFORMIN.HCL.ER',\n",
       " 'GLYBURIDE',\n",
       " 'op_prescriber',\n",
       " 'NAMENDA',\n",
       " 'DIPHENOXYLATE.ATROPINE',\n",
       " 'CLINDAMYCIN.HCL',\n",
       " 'LYRICA',\n",
       " 'METOCLOPRAMIDE.HCL',\n",
       " 'SIMVASTATIN',\n",
       " 'ONGLYZA',\n",
       " 'POTASSIUM.CHLORIDE',\n",
       " 'PROPRANOLOL.HCL',\n",
       " 'POLYETHYLENE.GLYCOL.3350',\n",
       " 'VYTORIN',\n",
       " 'LACTULOSE',\n",
       " 'NASONEX',\n",
       " 'NORTRIPTYLINE.HCL',\n",
       " 'IPRATROPIUM.BROMIDE',\n",
       " 'LISINOPRIL',\n",
       " 'ESCITALOPRAM.OXALATE',\n",
       " 'PROMETHAZINE.HCL',\n",
       " 'GLIPIZIDE.XL',\n",
       " 'CLONAZEPAM',\n",
       " 'DICLOFENAC.SODIUM',\n",
       " 'JANTOVEN',\n",
       " 'NOVOLOG.FLEXPEN',\n",
       " 'DOXEPIN.HCL',\n",
       " 'RESTASIS',\n",
       " 'CARTIA.XT',\n",
       " 'KLOR.CON.M10',\n",
       " 'Gender',\n",
       " 'NYSTATIN',\n",
       " 'VENTOLIN.HFA',\n",
       " 'CILOSTAZOL',\n",
       " 'TAMSULOSIN.HCL',\n",
       " 'CARBIDOPA.LEVODOPA',\n",
       " 'FAMOTIDINE',\n",
       " 'CHLORTHALIDONE',\n",
       " 'METHOTREXATE',\n",
       " 'TRIAMCINOLONE.ACETONIDE',\n",
       " 'ZOLPIDEM.TARTRATE',\n",
       " 'NPPES Provider Last Name',\n",
       " 'DULOXETINE.HCL',\n",
       " 'AVODART',\n",
       " 'PREDNISONE',\n",
       " 'CLOTRIMAZOLE.BETAMETHASONE',\n",
       " 'NPPES Provider ZIP Code',\n",
       " 'EXELON',\n",
       " 'FUROSEMIDE',\n",
       " 'ROPINIROLE.HCL',\n",
       " 'OpioidClaimCount',\n",
       " 'Totalclaimcount',\n",
       " 'COMBIVENT.RESPIMAT',\n",
       " 'RAMIPRIL',\n",
       " 'ONDANSETRON.HCL',\n",
       " 'op_longer',\n",
       " 'BENICAR',\n",
       " 'State',\n",
       " 'CHLORHEXIDINE.GLUCONATE',\n",
       " 'METHYLPREDNISOLONE',\n",
       " 'AMIODARONE.HCL',\n",
       " 'LOVASTATIN',\n",
       " 'MUPIROCIN',\n",
       " 'SPIRIVA',\n",
       " 'LIDOCAINE',\n",
       " 'ATORVASTATIN.CALCIUM',\n",
       " 'LISINOPRIL.HYDROCHLOROTHIAZIDE',\n",
       " 'DORZOLAMIDE.TIMOLOL',\n",
       " 'CARVEDILOL',\n",
       " 'PIOGLITAZONE.HCL',\n",
       " 'BUPROPION.XL',\n",
       " 'OXCARBAZEPINE',\n",
       " 'NAMENDA.XR',\n",
       " 'OXYBUTYNIN.CHLORIDE',\n",
       " 'DILTIAZEM.24HR.CD',\n",
       " 'LABETALOL.HCL',\n",
       " 'LEVEMIR.FLEXPEN',\n",
       " 'TERAZOSIN.HCL',\n",
       " 'FLUCONAZOLE',\n",
       " 'LANSOPRAZOLE',\n",
       " 'NITROFURANTOIN.MONO.MACRO',\n",
       " 'LAMOTRIGINE',\n",
       " 'DIGOXIN',\n",
       " 'ZIPRASIDONE.HCL',\n",
       " 'BACLOFEN',\n",
       " 'GLIPIZIDE',\n",
       " 'CRESTOR',\n",
       " 'CELEBREX',\n",
       " 'LEVEMIR',\n",
       " 'OMEPRAZOLE',\n",
       " 'TEMAZEPAM',\n",
       " 'LOVAZA',\n",
       " 'AMITRIPTYLINE.HCL',\n",
       " 'LEVETIRACETAM',\n",
       " 'CEPHALEXIN',\n",
       " 'METHOCARBAMOL',\n",
       " 'METRONIDAZOLE',\n",
       " 'MELOXICAM',\n",
       " 'NITROSTAT',\n",
       " 'PHENOBARBITAL',\n",
       " 'SERTRALINE.HCL',\n",
       " 'TOPIRAMATE',\n",
       " 'GLIMEPIRIDE',\n",
       " 'LANTUS.SOLOSTAR',\n",
       " 'TRAVATAN.Z',\n",
       " 'TRIAMTERENE.HYDROCHLOROTHIAZID',\n",
       " 'VENLAFAXINE.HCL.ER',\n",
       " 'BISOPROLOL.HYDROCHLOROTHIAZIDE',\n",
       " 'COLCRYS',\n",
       " 'METFORMIN.HCL',\n",
       " 'QUINAPRIL.HCL',\n",
       " 'ALLOPURINOL',\n",
       " 'NIFEDIPINE.ER',\n",
       " 'VERAPAMIL.ER',\n",
       " 'RISPERIDONE',\n",
       " 'LEVOTHYROXINE.SODIUM',\n",
       " 'PRAVASTATIN.SODIUM',\n",
       " 'ISOSORBIDE.MONONITRATE.ER',\n",
       " 'NOVOLOG',\n",
       " 'LOSARTAN.HYDROCHLOROTHIAZIDE',\n",
       " 'SYNTHROID',\n",
       " 'PROAIR.HFA',\n",
       " 'RANITIDINE.HCL',\n",
       " 'ZETIA',\n",
       " 'ALPRAZOLAM',\n",
       " 'GLIPIZIDE.ER',\n",
       " 'CEFUROXIME',\n",
       " 'CITALOPRAM.HBR',\n",
       " 'KLOR.CON.M20',\n",
       " 'DIAZEPAM',\n",
       " 'SYMBICORT',\n",
       " 'HYDROXYZINE.HCL',\n",
       " 'BUSPIRONE.HCL',\n",
       " 'HALOPERIDOL',\n",
       " 'Opioid_Prescriber',\n",
       " 'SEROQUEL.XR',\n",
       " 'FINASTERIDE',\n",
       " 'MONTELUKAST.SODIUM',\n",
       " 'JANUMET',\n",
       " 'ATENOLOL',\n",
       " 'ESTRADIOL',\n",
       " 'FELODIPINE.ER',\n",
       " 'DILTIAZEM.ER',\n",
       " 'RANEXA',\n",
       " 'TRAZODONE.HCL',\n",
       " 'DONEPEZIL.HCL',\n",
       " 'MECLIZINE.HCL',\n",
       " 'SULFAMETHOXAZOLE.TRIMETHOPRIM',\n",
       " 'BENZTROPINE.MESYLATE',\n",
       " 'DEXILANT',\n",
       " 'FLOVENT.HFA',\n",
       " 'BD.ULTRA.FINE.PEN.NEEDLE',\n",
       " 'RALOXIFENE.HCL',\n",
       " 'AMLODIPINE.BESYLATE',\n",
       " 'BENICAR.HCT',\n",
       " 'BENAZEPRIL.HCL',\n",
       " 'VALACYCLOVIR',\n",
       " 'LOSARTAN.POTASSIUM',\n",
       " 'XARELTO',\n",
       " 'KLOR.CON.10',\n",
       " 'TOPROL.XL',\n",
       " 'AMPHETAMINE.SALT.COMBO',\n",
       " 'IBUPROFEN',\n",
       " 'QUETIAPINE.FUMARATE',\n",
       " 'PRADAXA',\n",
       " 'ACYCLOVIR',\n",
       " 'IBANDRONATE.SODIUM',\n",
       " 'FLUOXETINE.HCL',\n",
       " 'MIRTAZAPINE',\n",
       " 'HUMALOG',\n",
       " 'HYDROCORTISONE',\n",
       " 'CLOPIDOGREL',\n",
       " 'INSULIN.SYRINGE',\n",
       " 'LORAZEPAM',\n",
       " 'TIMOLOL.MALEATE',\n",
       " 'NPI',\n",
       " 'PAROXETINE.HCL',\n",
       " 'TORSEMIDE',\n",
       " 'DIOVAN',\n",
       " 'FLUTICASONE.PROPIONATE',\n",
       " 'GABAPENTIN',\n",
       " 'BUMETANIDE',\n",
       " 'HYDRALAZINE.HCL',\n",
       " 'CIPROFLOXACIN.HCL',\n",
       " 'VALSARTAN',\n",
       " 'VOLTAREN',\n",
       " 'DILTIAZEM.24HR.ER',\n",
       " 'WARFARIN.SODIUM',\n",
       " 'DOXYCYCLINE.HYCLATE',\n",
       " 'PRIMIDONE',\n",
       " 'CLOBETASOL.PROPIONATE',\n",
       " 'NIFEDICAL.XL',\n",
       " 'NABUMETONE',\n",
       " 'avg_op_supply',\n",
       " 'Opioid_Prescriber.1']"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "list(drugsnotop)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "drugsnotop.drop(['Unnamed: 0','NPI','Gender','NPPES Provider ZIP Code','Opioid_Prescriber.1','op_longer','avg_op_supply',\n",
    "                 'Specialty','Totalclaimcount','OpioidClaimCount'],axis =1,inplace =True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "LISINOPRIL              1148009.0\n",
       "LEVOTHYROXINE.SODIUM    1121317.0\n",
       "AMLODIPINE.BESYLATE     1090182.0\n",
       "SIMVASTATIN             1043740.0\n",
       "ATORVASTATIN.CALCIUM    1004584.0\n",
       "OMEPRAZOLE               991368.0\n",
       "FUROSEMIDE               829156.0\n",
       "METFORMIN.HCL            720012.0\n",
       "GABAPENTIN               692210.0\n",
       "METOPROLOL.TARTRATE      688762.0\n",
       "dtype: float64"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dsum = drugsnotop.sum(numeric_only=True)\n",
    "dsum = dsum.sort_values(ascending=False)\n",
    "dsum.head(10)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<b> LISINOPRIL Is the most popular drug that is not opiate itself that is prescribed with opiates. its ACE inhibitor.It can treat high blood pressure and heart failure. It can also reduce the risk of death after a heart attack.</b>\n",
    "\n",
    "<b> LEVOTHYROXINE.SODIUM Is the most popular drug that is not opiate itself that is prescribed with opiates.</b>\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "import seaborn as sns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/kirosgebremariam/anaconda3/envs/dsi/lib/python3.6/site-packages/matplotlib/axes/_axes.py:6462: UserWarning: The 'normed' kwarg is deprecated, and has been replaced by the 'density' kwarg.\n",
      "  warnings.warn(\"The 'normed' kwarg is deprecated, and has been \"\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x1a215092b0>"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/kirosgebremariam/anaconda3/envs/dsi/lib/python3.6/site-packages/matplotlib/figure.py:2267: UserWarning: This figure includes Axes that are not compatible with tight_layout, so results might be incorrect.\n",
      "  warnings.warn(\"This figure includes Axes that are not compatible \"\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "image/png": {
       "height": 280,
       "width": 424
      }
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.distplot(dsum)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python [conda env:dsi]",
   "language": "python",
   "name": "conda-env-dsi-py"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}