HCA 203 PUF Description and Aggregation (OLD).ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Data Cleaning Notebook for Combined PUF File\n",
    "\n",
    "DeSYNPuf Exploration & Cleanup"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "%matplotlib inline\n",
    "import random\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import seaborn as sb\n",
    "import matplotlib.pyplot as plt\n",
    "import matplotlib.rcsetup as mrc\n",
    "\n",
    "# Library that supplies Elixhauser scores based on codes\n",
    "from hcuppy.elixhauser import ElixhauserEngine\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This file is 1/3 of a GB in size."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/kylier/anaconda3/lib/python3.8/site-packages/IPython/core/interactiveshell.py:3146: DtypeWarning: Columns (59,69,71,72,74,75,95,96,98,102,104,115) have mixed types.Specify dtype option on import or set low_memory=False.\n",
      "  has_raised = await self.run_ast_nodes(code_ast.body, cell_name,\n"
     ]
    }
   ],
   "source": [
    "desynpuf = pd.read_csv(\"/home/kylier/python/DS/data/PUF/IPANDOP_FIPS_ALL.csv\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Drop the first 2 columns (created when the csv file was written out)\n",
    "\n",
    "Show nulls"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "DESYNPUF_ID               0\n",
       "BENE_BIRTH_DT             0\n",
       "BENE_DEATH_DT        981851\n",
       "BENE_SEX_IDENT_CD         0\n",
       "BENE_RACE_CD              0\n",
       "                      ...  \n",
       "HCPCS_CD_44          981241\n",
       "HCPCS_CD_45          991604\n",
       "CLAIM_TYPE           149316\n",
       "BENE_AGE             149316\n",
       "YEAR                      0\n",
       "Length: 122, dtype: int64"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "desynpuf.drop(columns=desynpuf.columns[0], axis=1, inplace=True)\n",
    "desynpuf.drop(columns=desynpuf.columns[0], axis=1, inplace=True)\n",
    "desynpuf.isnull().sum() "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Almost 1 million rows"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(991604, 122)"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "desynpuf.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "DESYNPUF_ID\n",
      "BENE_BIRTH_DT\n",
      "BENE_DEATH_DT\n",
      "BENE_SEX_IDENT_CD\n",
      "BENE_RACE_CD\n",
      "BENE_ESRD_IND\n",
      "SP_STATE_CODE\n",
      "BENE_COUNTY_CD\n",
      "BENE_HI_CVRAGE_TOT_MONS\n",
      "BENE_SMI_CVRAGE_TOT_MONS\n",
      "BENE_HMO_CVRAGE_TOT_MONS\n",
      "PLAN_CVRG_MOS_NUM\n",
      "SP_ALZHDMTA\n",
      "SP_CHF\n",
      "SP_CHRNKIDN\n",
      "SP_CNCR\n",
      "SP_COPD\n",
      "SP_DEPRESSN\n",
      "SP_DIABETES\n",
      "SP_ISCHMCHT\n",
      "SP_OSTEOPRS\n",
      "SP_RA_OA\n",
      "SP_STRKETIA\n",
      "MEDREIMB_IP\n",
      "BENRES_IP\n",
      "PPPYMT_IP\n",
      "MEDREIMB_OP\n",
      "BENRES_OP\n",
      "PPPYMT_OP\n",
      "MEDREIMB_CAR\n",
      "BENRES_CAR\n",
      "PPPYMT_CAR\n",
      "FIPS_COUNTY_CODE\n",
      "FULL_FIPS_CODE\n",
      "CBSA\n",
      "CBSA_NAME\n",
      "FIPS_STATE_CODE\n",
      "CLM_ID\n",
      "SEGMENT\n",
      "CLM_FROM_DT\n",
      "CLM_THRU_DT\n",
      "PRVDR_NUM\n",
      "CLM_PMT_AMT\n",
      "NCH_PRMRY_PYR_CLM_PD_AMT\n",
      "AT_PHYSN_NPI\n",
      "OP_PHYSN_NPI\n",
      "OT_PHYSN_NPI\n",
      "CLM_ADMSN_DT\n",
      "ADMTNG_ICD9_DGNS_CD\n",
      "CLM_PASS_THRU_PER_DIEM_AMT\n",
      "NCH_BENE_IP_DDCTBL_AMT\n",
      "NCH_BENE_PTB_DDCTBL_AMT\n",
      "NCH_BENE_PTA_COINSRNC_LBLTY_AM\n",
      "NCH_BENE_PTB_COINSRNC_AMT\n",
      "NCH_BENE_BLOOD_DDCTBL_LBLTY_AM\n",
      "CLM_UTLZTN_DAY_CNT\n",
      "NCH_BENE_DSCHRG_DT\n",
      "CLM_DRG_CD\n",
      "ICD9_DGNS_CD_1\n",
      "ICD9_DGNS_CD_2\n",
      "ICD9_DGNS_CD_3\n",
      "ICD9_DGNS_CD_4\n",
      "ICD9_DGNS_CD_5\n",
      "ICD9_DGNS_CD_6\n",
      "ICD9_DGNS_CD_7\n",
      "ICD9_DGNS_CD_8\n",
      "ICD9_DGNS_CD_9\n",
      "ICD9_DGNS_CD_10\n",
      "ICD9_PRCDR_CD_1\n",
      "ICD9_PRCDR_CD_2\n",
      "ICD9_PRCDR_CD_3\n",
      "ICD9_PRCDR_CD_4\n",
      "ICD9_PRCDR_CD_5\n",
      "ICD9_PRCDR_CD_6\n",
      "HCPCS_CD_1\n",
      "HCPCS_CD_2\n",
      "HCPCS_CD_3\n",
      "HCPCS_CD_4\n",
      "HCPCS_CD_5\n",
      "HCPCS_CD_6\n",
      "HCPCS_CD_7\n",
      "HCPCS_CD_8\n",
      "HCPCS_CD_9\n",
      "HCPCS_CD_10\n",
      "HCPCS_CD_11\n",
      "HCPCS_CD_12\n",
      "HCPCS_CD_13\n",
      "HCPCS_CD_14\n",
      "HCPCS_CD_15\n",
      "HCPCS_CD_16\n",
      "HCPCS_CD_17\n",
      "HCPCS_CD_18\n",
      "HCPCS_CD_19\n",
      "HCPCS_CD_20\n",
      "HCPCS_CD_21\n",
      "HCPCS_CD_22\n",
      "HCPCS_CD_23\n",
      "HCPCS_CD_24\n",
      "HCPCS_CD_25\n",
      "HCPCS_CD_26\n",
      "HCPCS_CD_27\n",
      "HCPCS_CD_28\n",
      "HCPCS_CD_29\n",
      "HCPCS_CD_30\n",
      "HCPCS_CD_31\n",
      "HCPCS_CD_32\n",
      "HCPCS_CD_33\n",
      "HCPCS_CD_34\n",
      "HCPCS_CD_35\n",
      "HCPCS_CD_36\n",
      "HCPCS_CD_37\n",
      "HCPCS_CD_38\n",
      "HCPCS_CD_39\n",
      "HCPCS_CD_40\n",
      "HCPCS_CD_41\n",
      "HCPCS_CD_42\n",
      "HCPCS_CD_43\n",
      "HCPCS_CD_44\n",
      "HCPCS_CD_45\n",
      "CLAIM_TYPE\n",
      "BENE_AGE\n",
      "YEAR\n"
     ]
    }
   ],
   "source": [
    "for c in desynpuf.columns:\n",
    "    print(c)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Age\n",
    "\n",
    "This data is slightly more normally-distributed.  The mean age is 73, the median age is 74. IQR is 15, making anyone under 67 years old in the <25th percentile.  \n",
    "\n",
    "Not surprising - these are Medicare beneficiaries.  Only those who are disabled are eligible at <65 years."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='BENE_AGE', ylabel='Count'>"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1080x360 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sb.set(rc={\"figure.figsize\":(15, 5)})\n",
    "sb.set_theme(style=\"whitegrid\", palette=\"mako\")\n",
    "sb.histplot(x=round(desynpuf.groupby([\"DESYNPUF_ID\",\"YEAR\"])[\"BENE_AGE\"].mean()), binwidth=10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "count    194068.000000\n",
       "mean         73.159626\n",
       "std          12.768693\n",
       "min          24.000000\n",
       "25%          67.666667\n",
       "50%          74.000000\n",
       "75%          81.625000\n",
       "max         102.000000\n",
       "Name: BENE_AGE, dtype: float64"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "desynpuf.groupby([\"DESYNPUF_ID\",\"YEAR\"])[\"BENE_AGE\"].mean().describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Race Codes\n",
    "\n",
    "NaN\tUNKNOWN\n",
    "\n",
    "1\tNON-HISPANIC WHITE\n",
    "\n",
    "2\tBLACK (OR AFRICAN-AMERICAN)\n",
    "\n",
    "3\tOTHER\n",
    "\n",
    "4\tASIAN/PACIFIC ISLANDER\n",
    "\n",
    "5\tHISPANIC\n",
    "\n",
    "6\tAMERICAN INDIAN / ALASKA NATIVE"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='BENE_RACE_CD', ylabel='count'>"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1080x360 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sb.set(rc={\"figure.figsize\":(15, 5)})\n",
    "sb.set_theme(style=\"whitegrid\", palette=\"mako\")\n",
    "sb.countplot(x=round(desynpuf.groupby([\"DESYNPUF_ID\",\"YEAR\"])[\"BENE_RACE_CD\"].mean()))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "For this data set, the beneficiary population is 84% white, 11% Black or African American, 2.3% Hispanic, and 4% Other.  \n",
    "\n",
    "Asians / Pacific Islanders and American Indians / AK Natives are not represented."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1    0.826797\n",
       "2    0.107737\n",
       "3    0.042233\n",
       "5    0.023233\n",
       "Name: BENE_RACE_CD, dtype: float64"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "desynpuf.groupby([\"DESYNPUF_ID\",\"YEAR\"])[\"BENE_RACE_CD\"].mean().value_counts(normalize=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Sex\n",
    "\n",
    "1 MALE, 2 FEMALE recoded to 1 MALE, 0 FEMALE"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='B_SEX', ylabel='count'>"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1080x360 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "desynpuf[\"B_SEX\"] = desynpuf[\"BENE_SEX_IDENT_CD\"].replace(2, 0)\n",
    "\n",
    "sb.set_theme(style=\"whitegrid\", palette=\"mako\")\n",
    "sb.countplot(x=desynpuf.groupby([\"DESYNPUF_ID\",\"YEAR\"])[\"B_SEX\"].mean())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    0.556415\n",
       "1    0.443585\n",
       "Name: B_SEX, dtype: float64"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "desynpuf.groupby([\"DESYNPUF_ID\",\"YEAR\"])[\"B_SEX\"].mean().value_counts(normalize=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Chronic Conditions\n",
    "\n",
    "Alzheimer's & Related SP_ALZHDMTA 1=Yes, 2=No\n",
    "\n",
    "Congestive Heart Failure SP_CHF 1=Yes, 2=No\n",
    "\n",
    "Cancer SP_CNCR 1=Yes, 2=No\n",
    "\n",
    "Depression SP_DEPRESSN 1=Yes, 2=No\n",
    "\n",
    "Diabetes SP_DIABETES 1=Yes, 2=No\n",
    "\n",
    "Ischemic Heart Disease SP_ISCHMCHT 1=Yes, 2=No\n",
    "\n",
    "Osteoporosis SP_OSTEOPRS 1=Yes, 2=No\n",
    "\n",
    "COPD SP_COPD 1=Yes, 2=No\n",
    "\n",
    "Chronic Kidney Disease SP_CHRNKIDN 1=Yes, 2=No\n",
    "\n",
    "Rheumatoid or Osteoarthritis SP_RA_OA 1=Yes, 2=No\n",
    "\n",
    "Stroke or TIA SP_STRKETIA 1=Yes, 2=No\n",
    "\n",
    "ESRD Y=Yes, 0=No, recoded to 1=Yes, 2=No"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "desynpuf[\"SP_ESRD\"] = desynpuf[\"BENE_ESRD_IND\"].replace(\"Y\", 1).astype(int)\n",
    "desynpuf[\"SP_ESRD\"] = desynpuf[\"SP_ESRD\"].replace(0, 2).astype(int)\n",
    "desynpuf[\"CLM_ADMSN_DT\"] = pd.to_datetime(desynpuf[\"CLM_ADMSN_DT\"], format=\"%Y%m%d\")\n",
    "desynpuf[\"NCH_BENE_DSCHRG_DT\"] = pd.to_datetime(desynpuf[\"NCH_BENE_DSCHRG_DT\"], format=\"%Y%m%d\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x720 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "conditions = desynpuf[[\"SP_ALZHDMTA\", \"SP_CHF\", \"SP_CNCR\", \"SP_DEPRESSN\", \"SP_DIABETES\", \"SP_ISCHMCHT\", \n",
    "                        \"SP_OSTEOPRS\", \"SP_COPD\", \"SP_CHRNKIDN\", \"SP_RA_OA\", \"SP_STRKETIA\", \"SP_ESRD\"]]\n",
    "conditions_corr = conditions.corr(method=\"pearson\")\n",
    "lower_corr = conditions_corr.where(np.tril(np.ones(conditions_corr.shape)).astype(np.bool))\n",
    "\n",
    "plt.rcParams[\"figure.figsize\"] = (10.0, 10.0)\n",
    "conditions_hmap=sb.heatmap(lower_corr, annot=True, cmap=\"mako\", fmt=\".2f\")\n",
    "fig = conditions_hmap.get_figure()\n",
    "fig.savefig(\"desynpuf_cc_heatmap.png\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Note the clinically understood correlations between diabetes, ischemic heart disease, CHF and CKD.\n",
    "\n",
    "They are known to be causally connected on the basis of their pathophysiology.\n",
    "\n",
    "Obviously, so are ESRD and CKD, which are two points on the same disease continuum.\n",
    "\n",
    "There are also moderate correlations between depression, dementia, COPD and the DM/CHF/Heart Disease/CKD group.\n",
    "\n",
    "Strangly, there appears to be a weaker correlation between stroke / TIA and these diseases.\n",
    "\n",
    "While RA & OA produce similar disability in advanced stages, they have almost nothing in common in terms of pathophysiology or disease course."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Re-code the conditions indicators as dummy variables\n",
    "# \"SP_ALZHDMTA\", \"SP_CHF\", \"SP_CNCR\", \"SP_DEPRESSN\", \"SP_DIABETES\", \"SP_ISCHMCHT\", SP_OSTEOPRS\"\n",
    "# \"SP_COPD\", \"SP_CHRNKIDN\", \"SP_RA_OA\" and \"SP_STRKETIA\"  \n",
    "\n",
    "desynpuf[\"B_ALZHDMTA\"] = desynpuf[\"SP_ALZHDMTA\"].replace(2, 0).astype(int)\n",
    "desynpuf[\"B_CHF\"] = desynpuf[\"SP_CHF\"].replace(2, 0).astype(int)\n",
    "desynpuf[\"B_CNCR\"] = desynpuf[\"SP_CNCR\"].replace(2, 0).astype(int)\n",
    "desynpuf[\"B_COPD\"] = desynpuf[\"SP_COPD\"].replace(2, 0).astype(int)\n",
    "desynpuf[\"B_DEPRESSN\"] = desynpuf[\"SP_DEPRESSN\"].replace(2, 0).astype(int)\n",
    "desynpuf[\"B_DIABETES\"] = desynpuf[\"SP_DIABETES\"].replace(2, 0).astype(int)\n",
    "desynpuf[\"B_ISCHMCHT\"] = desynpuf[\"SP_ISCHMCHT\"].replace(2, 0).astype(int)\n",
    "desynpuf[\"B_OSTEOPRS\"] = desynpuf[\"SP_OSTEOPRS\"].replace(2, 0).astype(int)\n",
    "desynpuf[\"B_CHRNKIDN\"] = desynpuf[\"SP_CHRNKIDN\"].replace(2, 0).astype(int)\n",
    "desynpuf[\"B_RA_OA\"] = desynpuf[\"SP_RA_OA\"].replace(2, 0).astype(int)\n",
    "desynpuf[\"B_STRKETIA\"] = desynpuf[\"SP_STRKETIA\"].replace(2, 0).astype(int)\n",
    "desynpuf[\"B_ESRD\"] = desynpuf[\"SP_ESRD\"].replace(2, 0).astype(int)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Elixhauser Scores\n",
    "\n",
    "NOTE: Abandoning this for now.  \n",
    "\n",
    "Found a library that would do this with python but it only accepts **ICD10** codes.\n",
    "\n",
    "I believe I can do this in R, but will leave that for later, if necessary."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "#ICD9Fields = [\"ADMTNG_ICD9_DGNS_CD\", \"ICD9_DGNS_CD_1\", \"ICD9_DGNS_CD_2\", \"ICD9_DGNS_CD_3\", \"ICD9_DGNS_CD_4\",\n",
    "#             \"ICD9_DGNS_CD_5\", \"ICD9_DGNS_CD_6\", \"ICD9_DGNS_CD_7\", \"ICD9_DGNS_CD_8\", \"ICD9_DGNS_CD_9\",\n",
    "#             \"ICD9_DGNS_CD_10\"]\n",
    "\n",
    "#for f in ICD9Fields:\n",
    "#    desynpuf[f] = desynpuf[f].astype(\"string\")\n",
    "#    desynpuf[f] = desynpuf[f].str.strip()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "#s = desynpuf[\"ADMTNG_ICD9_DGNS_CD\"].copy()\n",
    "#SeriesArray = [desynpuf[\"ICD9_DGNS_CD_1\"], desynpuf[\"ICD9_DGNS_CD_2\"], \n",
    "#               desynpuf[\"ICD9_DGNS_CD_3\"], desynpuf[\"ICD9_DGNS_CD_4\"], desynpuf[\"ICD9_DGNS_CD_5\"], \n",
    "#               desynpuf[\"ICD9_DGNS_CD_6\"], desynpuf[\"ICD9_DGNS_CD_7\"], desynpuf[\"ICD9_DGNS_CD_8\"], \n",
    "#               desynpuf[\"ICD9_DGNS_CD_9\"], desynpuf[\"ICD9_DGNS_CD_10\"]]\n",
    "\n",
    "#desynpuf[\"ALL_ICD9_CDS\"] = s.str.cat(SeriesArray, sep=\",\")\n",
    "#codes_df = desynpuf[\"ALL_ICD9_CDS\"][~desynpuf[\"ALL_ICD9_CDS\"].isnull()]\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "#codesDict = {}\n",
    "#for i, v in desynpuf[\"ALL_ICD9_CDS\"].items():\n",
    "#    if not pd.isna(v):\n",
    "#        l = v.split(\",\")\n",
    "#        lambda: [code.strip() for code in l]\n",
    "#        codesDict[i] = l\n",
    "#"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Create Summaries\n",
    "\n",
    "For each year;\n",
    "For all 3 years\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "cc_summary = desynpuf.groupby([\"DESYNPUF_ID\", \"YEAR\"]).aggregate({\"BENE_AGE\":\"mean\",\n",
    "                                                                                  \"B_SEX\":\"mean\",\n",
    "                                                                                  \"BENE_RACE_CD\":\"mean\",\n",
    "                                                                                  \"B_ALZHDMTA\":\"sum\",\n",
    "                                                                                  \"B_CHF\":\"sum\",\n",
    "                                                                                  \"B_CNCR\":\"sum\",\n",
    "                                                                                  \"B_COPD\":\"sum\",\n",
    "                                                                                  \"B_DEPRESSN\":\"sum\",\n",
    "                                                                                  \"B_DIABETES\":\"sum\",\n",
    "                                                                                  \"B_ISCHMCHT\":\"sum\",\n",
    "                                                                                  \"B_OSTEOPRS\":\"sum\",\n",
    "                                                                                  \"B_CHRNKIDN\":\"sum\",\n",
    "                                                                                  \"B_RA_OA\":\"sum\",\n",
    "                                                                                  \"B_STRKETIA\":\"sum\",\n",
    "                                                                                  \"B_ESRD\":\"sum\",\n",
    "                                                                                  \"BENE_HI_CVRAGE_TOT_MONS\":\"mean\",\n",
    "                                                                                  \"BENE_SMI_CVRAGE_TOT_MONS\":\"mean\",\n",
    "                                                                                  \"BENE_HMO_CVRAGE_TOT_MONS\":\"mean\",\n",
    "                                                                                  \"PLAN_CVRG_MOS_NUM\":\"mean\",\n",
    "                                                                                  \"CLAIM_TYPE\":\"count\",\n",
    "                                                                                  \"CLM_ID\":\"count\",\n",
    "                                                                                  \"PRVDR_NUM\":\"nunique\",\n",
    "                                                                                  \"CLM_PMT_AMT\":[\"sum\",\"mean\"],\n",
    "                                                                                  \"NCH_PRMRY_PYR_CLM_PD_AMT\":\"sum\",\n",
    "                                                                                  \"AT_PHYSN_NPI\":\"nunique\",\n",
    "                                                                                  \"OP_PHYSN_NPI\":\"nunique\",\n",
    "                                                                                  \"OT_PHYSN_NPI\":\"nunique\",\n",
    "                                                                                  \"ADMTNG_ICD9_DGNS_CD\":[\"nunique\", \"count\"],\n",
    "                                                                                  \"CLM_UTLZTN_DAY_CNT\":[\"sum\",\"mean\",\"min\",\"max\"],\n",
    "                                                                                  \"CLM_DRG_CD\":[\"nunique\", \"count\"],\n",
    "                                                                                  \"MEDREIMB_IP\":[\"sum\",\"mean\"],\n",
    "                                                                                  \"BENRES_IP\":[\"sum\",\"mean\"],\n",
    "                                                                                  \"PPPYMT_IP\":[\"sum\",\"mean\"],\n",
    "                                                                                  \"MEDREIMB_OP\":[\"sum\",\"mean\"],\n",
    "                                                                                  \"BENRES_OP\":[\"sum\",\"mean\"],\n",
    "                                                                                  \"PPPYMT_OP\":[\"sum\",\"mean\"],\n",
    "                                                                                  \"CBSA\":\"mean\",\n",
    "                                                                                  \"FIPS_STATE_CODE\":\"mean\",\n",
    "                                                                                  \"FIPS_COUNTY_CODE\":\"mean\"})\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "cc_summary.columns = [\"MEAN_AGE\", \"B_SEX\", \"BENE_RACE_CD\", \"B_ALZHDMTA\", \"B_CHF\", \"B_CNCR\", \"B_COPD\",\n",
    "                      \"B_DEPRESSN\", \"B_DIABETES\", \"B_ISCHMCHT\", \"B_OSTEOPRS\", \"B_CHRNKIDN\", \"B_RA_OA\",\n",
    "                      \"B_STRKETIA\", \"B_ESRD\", \"MEAN_HI_CVRAGE_TOT_MONS\", \"MEAN_SMI_CVRAGE_TOT_MONS\",\n",
    "                      \"MEAN_HMO_CVRAGE_TOT_MONS\", \"MEAN_CVRG_MOS_NUM\", \"TOTAL_VISITS\",\"TOTAL_CLAIMS\",\n",
    "                      \"NUM_PRVDRS\", \"TOT_CLM_PMT_AMT\", \"MEAN_CLM_PMT_AMT\", \"TOT_NCH_PRMRY_PYR_CLM_PD_AMT\",\n",
    "                      \"NUM_AT_PHYSNS\", \"NUM_OP_PHYSNS\",\"NUM_OT_PHYSNS\",\"UNQ_ADMTNG_ICD9_CDS\", \n",
    "                      \"TOT_ADMTNG_ICD9_CDS\", \"TOTAL_INP_DAYS\", \"MEAN_INP_STAY\", \"MIN_INP_STAY\", \n",
    "                      \"MAX_INP_STAY\",\"UNQ_CLM_DRG_CDS\", \"TOT_CLM_DRG_CDS\", \"TOT_MEDREIMB_IP\", \n",
    "                      \"MEAN_MEDREIMB_IP\", \"TOT_BENRES_IP\", \"MEAN_BENRES_IP\", \"TOT_PPPYMT_IP\", \n",
    "                      \"MEAN_PPPYMT_IP\", \"TOT_MEDREIMB_OP\",\"MEAN_MEDREIMB_OP\",\"TOT_BENRES_OP\",\n",
    "                      \"MEAN_BENRES_OP\",\"TOT_PPPYMT_OP\",\"MEAN_PPPYMT_OP\",\"CBSA\", \n",
    "                      \"FIPS_STATE_CODE\",\"FIPS_COUNTY_CODE\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "cc_summary.loc[cc_summary[\"B_ALZHDMTA\"]>1, \"B_ALZHDMTA\"] = 1\n",
    "cc_summary.loc[cc_summary[\"B_CHF\"]>1, \"B_CHF\"] = 1\n",
    "cc_summary.loc[cc_summary[\"B_CNCR\"]>1, \"B_CNCR\"] = 1\n",
    "cc_summary.loc[cc_summary[\"B_COPD\"]>1, \"B_COPD\"] = 1\n",
    "cc_summary.loc[cc_summary[\"B_DEPRESSN\"]>1, \"B_DEPRESSN\"] = 1\n",
    "cc_summary.loc[cc_summary[\"B_DIABETES\"]>1, \"B_DIABETES\"] = 1\n",
    "cc_summary.loc[cc_summary[\"B_ISCHMCHT\"]>1, \"B_ISCHMCHT\"] = 1\n",
    "cc_summary.loc[cc_summary[\"B_OSTEOPRS\"]>1, \"B_OSTEOPRS\"] = 1\n",
    "cc_summary.loc[cc_summary[\"B_CHRNKIDN\"]>1, \"B_CHRNKIDN\"] = 1\n",
    "cc_summary.loc[cc_summary[\"B_RA_OA\"]>1, \"B_RA_OA\"] = 1\n",
    "cc_summary.loc[cc_summary[\"B_STRKETIA\"]>1, \"B_STRKETIA\"] = 1\n",
    "cc_summary.loc[cc_summary[\"B_ESRD\"]>1, \"B_ESRD\"] = 1\n",
    "\n",
    "cc_summary[\"TOTCHRONIC\"] = cc_summary[\"B_ALZHDMTA\"] + cc_summary[\"B_CHF\"] + cc_summary[\"B_CNCR\"] + cc_summary[\"B_COPD\"] + cc_summary[\"B_DEPRESSN\"] + cc_summary[\"B_DIABETES\"] + cc_summary[\"B_ISCHMCHT\"] + cc_summary[\"B_OSTEOPRS\"] + cc_summary[\"B_CHRNKIDN\"] + cc_summary[\"B_RA_OA\"] + cc_summary[\"B_STRKETIA\"]\n",
    "cc_summary[\"TOTIPCOST\"] = cc_summary[\"TOT_MEDREIMB_IP\"] + cc_summary[\"TOT_BENRES_IP\"] + cc_summary[\"TOT_PPPYMT_IP\"]\n",
    "cc_summary[\"MEANIPCOST\"] = (cc_summary[\"MEAN_MEDREIMB_IP\"] + cc_summary[\"MEAN_BENRES_IP\"] + cc_summary[\"MEAN_PPPYMT_IP\"])/3\n",
    "cc_summary[\"TOTOPCOST\"] = cc_summary[\"TOT_MEDREIMB_OP\"] + cc_summary[\"TOT_BENRES_OP\"] + cc_summary[\"TOT_PPPYMT_OP\"]\n",
    "cc_summary[\"MEANOPCOST\"] = (cc_summary[\"MEAN_MEDREIMB_OP\"] + cc_summary[\"MEAN_BENRES_OP\"] + cc_summary[\"MEAN_PPPYMT_OP\"])/3\n",
    "cc_summary[\"ALLCOSTS\"] = cc_summary[\"TOTIPCOST\"] + cc_summary[\"TOTOPCOST\"]\n",
    "cc_summary[\"MEANCOSTS\"] = (cc_summary[\"MEANIPCOST\"] + cc_summary[\"MEANOPCOST\"])/2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "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></th>\n",
       "      <th>MEAN_AGE</th>\n",
       "      <th>B_SEX</th>\n",
       "      <th>BENE_RACE_CD</th>\n",
       "      <th>B_ALZHDMTA</th>\n",
       "      <th>B_CHF</th>\n",
       "      <th>B_CNCR</th>\n",
       "      <th>B_COPD</th>\n",
       "      <th>B_DEPRESSN</th>\n",
       "      <th>B_DIABETES</th>\n",
       "      <th>B_ISCHMCHT</th>\n",
       "      <th>...</th>\n",
       "      <th>CBSA</th>\n",
       "      <th>FIPS_STATE_CODE</th>\n",
       "      <th>FIPS_COUNTY_CODE</th>\n",
       "      <th>TOTCHRONIC</th>\n",
       "      <th>TOTIPCOST</th>\n",
       "      <th>MEANIPCOST</th>\n",
       "      <th>TOTOPCOST</th>\n",
       "      <th>MEANOPCOST</th>\n",
       "      <th>ALLCOSTS</th>\n",
       "      <th>MEANCOSTS</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>DESYNPUF_ID</th>\n",
       "      <th>YEAR</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"3\" valign=\"top\">0000438E79D01BEA</th>\n",
       "      <th>2008</th>\n",
       "      <td>NaN</td>\n",
       "      <td>1</td>\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>...</td>\n",
       "      <td>45300.0</td>\n",
       "      <td>12.0</td>\n",
       "      <td>57.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2009</th>\n",
       "      <td>NaN</td>\n",
       "      <td>1</td>\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>...</td>\n",
       "      <td>45300.0</td>\n",
       "      <td>12.0</td>\n",
       "      <td>57.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2010</th>\n",
       "      <td>NaN</td>\n",
       "      <td>1</td>\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>...</td>\n",
       "      <td>45300.0</td>\n",
       "      <td>12.0</td>\n",
       "      <td>57.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">00010E7BEA69142C</th>\n",
       "      <th>2008</th>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\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>...</td>\n",
       "      <td>48864.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2009</th>\n",
       "      <td>71.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>48864.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>2</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1620.0</td>\n",
       "      <td>180.000000</td>\n",
       "      <td>1620.0</td>\n",
       "      <td>90.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>FFFF58406F9882DD</th>\n",
       "      <th>2010</th>\n",
       "      <td>NaN</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>47020.0</td>\n",
       "      <td>48.0</td>\n",
       "      <td>469.0</td>\n",
       "      <td>4</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>FFFFCA5AFABA1CF6</th>\n",
       "      <th>2008</th>\n",
       "      <td>69.0</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>47894.0</td>\n",
       "      <td>51.0</td>\n",
       "      <td>59.0</td>\n",
       "      <td>6</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1100.0</td>\n",
       "      <td>183.333333</td>\n",
       "      <td>1100.0</td>\n",
       "      <td>91.666667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"3\" valign=\"top\">FFFFF4859B6D7402</th>\n",
       "      <th>2008</th>\n",
       "      <td>NaN</td>\n",
       "      <td>1</td>\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>...</td>\n",
       "      <td>39300.0</td>\n",
       "      <td>25.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2009</th>\n",
       "      <td>69.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>39300.0</td>\n",
       "      <td>25.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>3</td>\n",
       "      <td>8068.0</td>\n",
       "      <td>2689.333333</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>8068.0</td>\n",
       "      <td>1344.666667</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2010</th>\n",
       "      <td>NaN</td>\n",
       "      <td>1</td>\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>...</td>\n",
       "      <td>39300.0</td>\n",
       "      <td>25.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>343384 rows × 58 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                       MEAN_AGE  B_SEX  BENE_RACE_CD  B_ALZHDMTA  B_CHF  \\\n",
       "DESYNPUF_ID      YEAR                                                     \n",
       "0000438E79D01BEA 2008       NaN      1             1           0      0   \n",
       "                 2009       NaN      1             1           0      0   \n",
       "                 2010       NaN      1             1           0      0   \n",
       "00010E7BEA69142C 2008       NaN      0             1           1      0   \n",
       "                 2009      71.0      0             1           1      0   \n",
       "...                         ...    ...           ...         ...    ...   \n",
       "FFFF58406F9882DD 2010       NaN      1             1           0      1   \n",
       "FFFFCA5AFABA1CF6 2008      69.0      1             2           0      1   \n",
       "FFFFF4859B6D7402 2008       NaN      1             1           0      0   \n",
       "                 2009      69.0      1             1           0      0   \n",
       "                 2010       NaN      1             1           0      0   \n",
       "\n",
       "                       B_CNCR  B_COPD  B_DEPRESSN  B_DIABETES  B_ISCHMCHT  \\\n",
       "DESYNPUF_ID      YEAR                                                       \n",
       "0000438E79D01BEA 2008       0       0           0           0           0   \n",
       "                 2009       0       0           0           0           0   \n",
       "                 2010       0       0           0           0           0   \n",
       "00010E7BEA69142C 2008       0       0           0           0           0   \n",
       "                 2009       0       0           1           0           0   \n",
       "...                       ...     ...         ...         ...         ...   \n",
       "FFFF58406F9882DD 2010       0       1           0           0           1   \n",
       "FFFFCA5AFABA1CF6 2008       0       0           1           1           1   \n",
       "FFFFF4859B6D7402 2008       0       0           0           0           0   \n",
       "                 2009       0       0           1           0           1   \n",
       "                 2010       0       0           0           0           0   \n",
       "\n",
       "                       ...     CBSA  FIPS_STATE_CODE  FIPS_COUNTY_CODE  \\\n",
       "DESYNPUF_ID      YEAR  ...                                               \n",
       "0000438E79D01BEA 2008  ...  45300.0             12.0              57.0   \n",
       "                 2009  ...  45300.0             12.0              57.0   \n",
       "                 2010  ...  45300.0             12.0              57.0   \n",
       "00010E7BEA69142C 2008  ...  48864.0             10.0               3.0   \n",
       "                 2009  ...  48864.0             10.0               3.0   \n",
       "...                    ...      ...              ...               ...   \n",
       "FFFF58406F9882DD 2010  ...  47020.0             48.0             469.0   \n",
       "FFFFCA5AFABA1CF6 2008  ...  47894.0             51.0              59.0   \n",
       "FFFFF4859B6D7402 2008  ...  39300.0             25.0               5.0   \n",
       "                 2009  ...  39300.0             25.0               5.0   \n",
       "                 2010  ...  39300.0             25.0               5.0   \n",
       "\n",
       "                       TOTCHRONIC  TOTIPCOST   MEANIPCOST  TOTOPCOST  \\\n",
       "DESYNPUF_ID      YEAR                                                  \n",
       "0000438E79D01BEA 2008           0        0.0     0.000000        0.0   \n",
       "                 2009           0        0.0     0.000000        0.0   \n",
       "                 2010           0        0.0     0.000000        0.0   \n",
       "00010E7BEA69142C 2008           1        0.0     0.000000        0.0   \n",
       "                 2009           2        0.0     0.000000     1620.0   \n",
       "...                           ...        ...          ...        ...   \n",
       "FFFF58406F9882DD 2010           4        0.0     0.000000        0.0   \n",
       "FFFFCA5AFABA1CF6 2008           6        0.0     0.000000     1100.0   \n",
       "FFFFF4859B6D7402 2008           0        0.0     0.000000        0.0   \n",
       "                 2009           3     8068.0  2689.333333        0.0   \n",
       "                 2010           0        0.0     0.000000        0.0   \n",
       "\n",
       "                       MEANOPCOST  ALLCOSTS    MEANCOSTS  \n",
       "DESYNPUF_ID      YEAR                                     \n",
       "0000438E79D01BEA 2008    0.000000       0.0     0.000000  \n",
       "                 2009    0.000000       0.0     0.000000  \n",
       "                 2010    0.000000       0.0     0.000000  \n",
       "00010E7BEA69142C 2008    0.000000       0.0     0.000000  \n",
       "                 2009  180.000000    1620.0    90.000000  \n",
       "...                           ...       ...          ...  \n",
       "FFFF58406F9882DD 2010    0.000000       0.0     0.000000  \n",
       "FFFFCA5AFABA1CF6 2008  183.333333    1100.0    91.666667  \n",
       "FFFFF4859B6D7402 2008    0.000000       0.0     0.000000  \n",
       "                 2009    0.000000    8068.0  1344.666667  \n",
       "                 2010    0.000000       0.0     0.000000  \n",
       "\n",
       "[343384 rows x 58 columns]"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cc_summary"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "cc_summary2 = cc_summary.copy()\n",
    "cc_summary2.reset_index()\n",
    "cc_summary_all = cc_summary2.groupby(\"DESYNPUF_ID\").aggregate({\"MEAN_AGE\":\"mean\",\n",
    "                                                               \"B_SEX\":\"mean\",\n",
    "                                                               \"BENE_RACE_CD\":\"mean\",\n",
    "                                                               \"B_ALZHDMTA\":\"mean\",\n",
    "                                                               \"B_CHF\":\"mean\",\n",
    "                                                               \"B_CNCR\":\"mean\",\n",
    "                                                               \"B_COPD\":\"mean\",\n",
    "                                                               \"B_DEPRESSN\":\"mean\",\n",
    "                                                               \"B_DIABETES\":\"mean\",\n",
    "                                                               \"B_ISCHMCHT\":\"mean\",\n",
    "                                                               \"B_OSTEOPRS\":\"mean\",\n",
    "                                                               \"B_CHRNKIDN\":\"mean\",\n",
    "                                                               \"B_RA_OA\":\"mean\",\n",
    "                                                               \"B_STRKETIA\":\"mean\",\n",
    "                                                               \"B_ESRD\":\"mean\",\n",
    "                                                               \"MEAN_HI_CVRAGE_TOT_MONS\":\"mean\",\n",
    "                                                               \"MEAN_SMI_CVRAGE_TOT_MONS\":\"mean\",\n",
    "                                                               \"MEAN_HMO_CVRAGE_TOT_MONS\":\"mean\",\n",
    "                                                               \"MEAN_CVRG_MOS_NUM\":\"mean\",\n",
    "                                                               \"TOTAL_VISITS\":[\"sum\", \"mean\"],\n",
    "                                                               \"TOTAL_CLAIMS\":[\"sum\", \"mean\"],\n",
    "                                                               \"NUM_PRVDRS\":\"mean\",\n",
    "                                                               \"TOT_CLM_PMT_AMT\":\"sum\",\n",
    "                                                               \"MEAN_CLM_PMT_AMT\":\"mean\",\n",
    "                                                               \"TOT_NCH_PRMRY_PYR_CLM_PD_AMT\":\"sum\",\n",
    "                                                               \"NUM_AT_PHYSNS\":\"mean\",\n",
    "                                                               \"NUM_OP_PHYSNS\":\"mean\",\n",
    "                                                               \"NUM_OT_PHYSNS\":\"mean\",\n",
    "                                                               \"TOT_ADMTNG_ICD9_CDS\":\"sum\",\n",
    "                                                               \"TOTAL_INP_DAYS\":\"sum\",\n",
    "                                                               \"MEAN_INP_STAY\": \"mean\",\n",
    "                                                               \"MIN_INP_STAY\": \"min\",\n",
    "                                                               \"MAX_INP_STAY\":\"max\",\n",
    "                                                               \"TOT_CLM_DRG_CDS\": \"sum\",\n",
    "                                                               \"TOT_MEDREIMB_IP\":\"sum\",\n",
    "                                                               \"MEAN_MEDREIMB_IP\":\"mean\",\n",
    "                                                               \"TOT_BENRES_IP\":\"sum\",\n",
    "                                                               \"MEAN_BENRES_IP\":\"mean\",\n",
    "                                                               \"TOT_PPPYMT_IP\":\"sum\",\n",
    "                                                               \"MEAN_PPPYMT_IP\":\"mean\",\n",
    "                                                               \"TOT_MEDREIMB_OP\":\"sum\",\n",
    "                                                               \"MEAN_MEDREIMB_OP\":\"mean\",\n",
    "                                                               \"TOT_BENRES_OP\":\"sum\",\n",
    "                                                               \"MEAN_BENRES_OP\":\"mean\",\n",
    "                                                               \"TOT_PPPYMT_OP\":\"sum\",\n",
    "                                                               \"MEAN_PPPYMT_OP\":\"mean\",\n",
    "                                                               \"CBSA\":\"mean\",\n",
    "                                                               \"FIPS_STATE_CODE\":\"mean\",\n",
    "                                                               \"FIPS_COUNTY_CODE\":\"mean\", \n",
    "                                                               \"TOTIPCOST\":\"sum\",\n",
    "                                                               \"MEANIPCOST\":\"mean\",\n",
    "                                                               \"TOTOPCOST\":\"sum\",\n",
    "                                                               \"MEANOPCOST\":\"sum\",\n",
    "                                                               \"ALLCOSTS\":\"sum\",\n",
    "                                                               \"MEANCOSTS\":\"mean\"})\n",
    "\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "cc_summary_all.columns = [\"MEAN_AGE\", \"B_SEX\", \"BENE_RACE_CD\", \n",
    "                          \"B_ALZHDMTA\", \"B_CHF\", \"B_CNCR\", \"B_COPD\",\"B_DEPRESSN\", \"B_DIABETES\", \n",
    "                          \"B_ISCHMCHT\", \"B_OSTEOPRS\", \"B_CHRNKIDN\", \"B_RA_OA\",\"B_STRKETIA\", \"B_ESRD\", \n",
    "                          \"MEAN_HI_CVRAGE_TOT_MONS\", \n",
    "                          \"MEAN_SMI_CVRAGE_TOT_MONS\",\n",
    "                          \"MEAN_HMO_CVRAGE_TOT_MONS\", \n",
    "                          \"MEAN_CVRG_MOS_NUM\", \n",
    "                          \"TOTAL_VISITS\",\"MEAN_TOTAL_VISITS\",\n",
    "                          \"TOTAL_CLAIMS\",\"MEAN_TOTAL_CLAIMS\",\n",
    "                          \"MEAN_NUM_PRVDRS\", \n",
    "                          \"TOT_CLM_PMT_AMT\", \"MEAN_CLM_PMT_AMT\", \n",
    "                          \"TOT_NCH_PRMRY_PYR_CLM_PD_AMT\",\n",
    "                          \"MEAN_NUM_AT_PHYSNS\", \"MEAN_NUM_OP_PHYSNS\",\"MEAN_NUM_OT_PHYSNS\", \n",
    "                          \"TOT_ADMTNG_ICD9_CDS\", \n",
    "                          \"TOTAL_INP_DAYS\", \"MEAN_INP_STAY\", \"MIN_INP_STAY\",\"MAX_INP_STAY\",\n",
    "                          \"TOT_CLM_DRG_CDS\", \n",
    "                          \"TOT_MEDREIMB_IP\", \"MEAN_MEDREIMB_IP\",\n",
    "                          \"TOT_BENRES_IP\", \"MEAN_BENRES_IP\", \n",
    "                          \"TOT_PPPYMT_IP\", \"MEAN_PPPYMT_IP\", \n",
    "                          \"TOT_MEDREIMB_OP\",\"MEAN_MEDREIMB_OP\",\n",
    "                          \"TOT_BENRES_OP\",\"MEAN_BENRES_OP\",\n",
    "                          \"TOT_PPPYMT_OP\",\"MEAN_PPPYMT_OP\",\n",
    "                          \"CBSA\", \"FIPS_STATE_CODE\",\"FIPS_COUNTY_CODE\", \n",
    "                          \"TOTIPCOST\", \"MEANIPCOST\", \"TOTOPCOST\",\n",
    "                         \"MEANOPCOST\", \"ALLCOSTS\", \"MEANCOSTS\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "cc_summary_all.loc[cc_summary_all[\"B_ALZHDMTA\"]>0, \"B_ALZHDMTA\"] = 1\n",
    "cc_summary_all.loc[cc_summary_all[\"B_CHF\"]>0, \"B_CHF\"] = 1\n",
    "cc_summary_all.loc[cc_summary_all[\"B_CNCR\"]>0, \"B_CNCR\"] = 1\n",
    "cc_summary_all.loc[cc_summary_all[\"B_COPD\"]>0, \"B_COPD\"] = 1\n",
    "cc_summary_all.loc[cc_summary_all[\"B_DEPRESSN\"]>0, \"B_DEPRESSN\"] = 1\n",
    "cc_summary_all.loc[cc_summary_all[\"B_DIABETES\"]>0, \"B_DIABETES\"] = 1\n",
    "cc_summary_all.loc[cc_summary_all[\"B_ISCHMCHT\"]>0, \"B_ISCHMCHT\"] = 1\n",
    "cc_summary_all.loc[cc_summary_all[\"B_OSTEOPRS\"]>0, \"B_OSTEOPRS\"] = 1\n",
    "cc_summary_all.loc[cc_summary_all[\"B_CHRNKIDN\"]>0, \"B_CHRNKIDN\"] = 1\n",
    "cc_summary_all.loc[cc_summary_all[\"B_RA_OA\"]>0, \"B_RA_OA\"] = 1\n",
    "cc_summary_all.loc[cc_summary_all[\"B_STRKETIA\"]>0, \"B_STRKETIA\"] = 1\n",
    "cc_summary_all.loc[cc_summary_all[\"B_ESRD\"]>0, \"B_ESRD\"] = 1\n",
    "\n",
    "cc_summary_all[\"TOTCHRONIC\"] = cc_summary_all[\"B_ALZHDMTA\"] + cc_summary_all[\"B_CHF\"] + cc_summary_all[\"B_CNCR\"] + cc_summary_all[\"B_COPD\"] + cc_summary_all[\"B_DEPRESSN\"] + cc_summary_all[\"B_DIABETES\"] + cc_summary_all[\"B_ISCHMCHT\"] + cc_summary_all[\"B_OSTEOPRS\"] + cc_summary_all[\"B_CHRNKIDN\"] + cc_summary_all[\"B_RA_OA\"] + cc_summary_all[\"B_STRKETIA\"]\n",
    "cc_summary_all[\"MEAN_AGE\"] = cc_summary_all[\"MEAN_AGE\"].round(decimals=1)\n",
    "cc_summary_all[\"VISITS_FLAG\"] = 0\n",
    "cc_summary_all.loc[cc_summary_all[\"TOTAL_VISITS\"]>0, \"VISITS_FLAG\"] = 1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='TOTCHRONIC', ylabel='count'>"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x720 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.rcParams[\"figure.figsize\"] = (10.0, 10.0)\n",
    "sb.set_theme(style=\"whitegrid\", palette=\"mako\")\n",
    "sb.countplot(data=cc_summary_all, x=\"TOTCHRONIC\", palette=\"mako\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Over the three year period, 25% of the beneficiaries had none of the noted chronic conditions.\n",
    "\n",
    "7% had 1, \n",
    "\n",
    "7% had 2, \n",
    "\n",
    "8% had 3, \n",
    "\n",
    "8% had 4, \n",
    "\n",
    "9% had 5, \n",
    "\n",
    "10% had 6,\n",
    "\n",
    "9% had 7,\n",
    "\n",
    "8% had 8,\n",
    "\n",
    "and the remaining 9% had 9 or more.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.0     0.248240\n",
       "6.0     0.095205\n",
       "7.0     0.090657\n",
       "5.0     0.089600\n",
       "4.0     0.084022\n",
       "8.0     0.081856\n",
       "3.0     0.075366\n",
       "1.0     0.070320\n",
       "2.0     0.066659\n",
       "9.0     0.061097\n",
       "10.0    0.030342\n",
       "11.0    0.006636\n",
       "Name: TOTCHRONIC, dtype: float64"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cc_summary_all[\"TOTCHRONIC\"].value_counts(normalize=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0     0.350100\n",
       "1     0.126992\n",
       "2     0.119522\n",
       "3     0.113546\n",
       "4     0.108068\n",
       "5     0.066733\n",
       "6     0.050797\n",
       "7     0.036355\n",
       "8     0.016434\n",
       "9     0.009462\n",
       "10    0.001494\n",
       "11    0.000498\n",
       "Name: TOTCHRONIC, dtype: float64"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cc_summary[:2008][\"TOTCHRONIC\"].value_counts(normalize=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 991604 entries, 0 to 991603\n",
      "Columns: 123 entries, DESYNPUF_ID to B_ESRD\n",
      "dtypes: datetime64[ns](2), float64(30), int64(21), object(70)\n",
      "memory usage: 930.5+ MB\n"
     ]
    }
   ],
   "source": [
    "desynpuf.drop([\"SP_ALZHDMTA\", \"SP_CHF\", \"SP_CNCR\", \"SP_DEPRESSN\", \"SP_DIABETES\", \"SP_ISCHMCHT\", \"SP_ESRD\",\n",
    "              \"SP_OSTEOPRS\", \"SP_COPD\", \"SP_CHRNKIDN\", \"SP_RA_OA\", \"SP_STRKETIA\", \"BENE_SEX_IDENT_CD\"], inplace=True, axis=1)\n",
    "\n",
    "desynpuf.info()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Visits 2008-2010\n",
    "\n",
    "Total Inpatient Claims: 66,029\n",
    "\n",
    "Total Outpatient Claims: 776,259"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "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></th>\n",
       "      <th>COUNT</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>YEAR</th>\n",
       "      <th>CLAIM_TYPE</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">2008</th>\n",
       "      <th>INPATIENT</th>\n",
       "      <td>27240</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>OUTPATIENT</th>\n",
       "      <td>282069</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">2009</th>\n",
       "      <th>INPATIENT</th>\n",
       "      <td>24873</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>OUTPATIENT</th>\n",
       "      <td>320990</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">2010</th>\n",
       "      <th>INPATIENT</th>\n",
       "      <td>13916</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>OUTPATIENT</th>\n",
       "      <td>173200</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                  COUNT\n",
       "YEAR CLAIM_TYPE        \n",
       "2008 INPATIENT    27240\n",
       "     OUTPATIENT  282069\n",
       "2009 INPATIENT    24873\n",
       "     OUTPATIENT  320990\n",
       "2010 INPATIENT    13916\n",
       "     OUTPATIENT  173200"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "claims_breakdown = desynpuf.groupby([\"YEAR\", \"CLAIM_TYPE\"])[\"CLAIM_TYPE\"].count().to_frame()\n",
    "claims_breakdown.columns = [\"COUNT\"]\n",
    "claims_breakdown.head(6)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "OUTPATIENT    776259\n",
       "INPATIENT      66029\n",
       "Name: CLAIM_TYPE, dtype: int64"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "desynpuf[\"CLAIM_TYPE\"].value_counts()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "As the total number of chronic conditions increases, the total visits increases.\n",
    "\n",
    "No surprises there!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAA4YAAAFCCAYAAACtlcOGAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjMuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8vihELAAAACXBIWXMAAAsTAAALEwEAmpwYAAAyQElEQVR4nO3de3RU5b3/8c/kKnDAJDbAYBARi0YuAkG5FWlDTKhNSLxwabisooTlAcGaYtEDQrl5DKWEA2JtsZCjFbqaImAgBaRUK9ixHKBKBCUKgpAQEEgFRhIy2b8//DHLdCYMue0dZr9fa7lmZu9nz/Od7xLcH5+9ZxyGYRgCAAAAANhWiNUFAAAAAACsRTAEAAAAAJsjGAIAAACAzREMAQAAAMDmCIYAAAAAYHNhVhdghurqal28eFHh4eFyOBxWlwMAAAAApjIMQ5cvX1arVq0UEuK7PmiLYHjx4kUdOnTI6jIAAAAAwFJdu3ZV69atfbbbIhiGh4dL+qYJERERFlcDAAAAAOaqrKzUoUOHvNno39kiGF65fDQiIkKRkZEWVwMAAAAA1qjt1jq+fAYAAAAAbI5gCAAAAAA2RzAEAAAAAJsjGAIAAACAzREMAQAAAMDmCIYAAAAAYHMEQwAAAACwOYIhAAAAANgcwRAAAAAAmoDL5VJ2drZcLpfVpQQUZnUBAAAAABCM8vLyVFxcLLfbrf79+1tdzlWxYggAAAAATcDtdtd4bM4IhgAAAABgcwRDAAAAALA5giEAAAAA2BzBEAAAAABsjmAIAAAAADZHMAQAAAAAmzMlGJ47d05ZWVlKSUlRWlqannjiCZ09e1aSdOTIEY0aNUopKSkaNWqUPv/8c7/v4fF4NHfuXCUlJen+++9Xfn6+GaUDAAAACCIeo9rqEppUfT+fKT9w73A4NHHiRPXr10+SlJOTo8WLF+v555/XnDlzlJmZqfT0dG3cuFGzZ8/Wq6++6vMeBQUFOnbsmLZt26by8nJlZGRowIABiouLM+MjAAAAAAgCoY4Q7Tj6vilzfV11yfto1pyJnfrV6zhTVgyjoqK8oVCSevXqpZKSEp05c0YHDhxQamqqJCk1NVUHDhzwriZ+W2FhoUaMGKGQkBDFxMQoKSlJW7ZsMaN8AAAAAAhqpqwYflt1dbXWrl2rxMRElZaWql27dgoNDZUkhYaGqm3btiotLVVMTEyN40pLS9WhQwfva6fTqZMnT9Zp7qKiooZ/AAAAAADXrYSEBKtLaHJ79uyp8zGmB8P58+erZcuWGjt2rA4cOGDq3N27d1dkZKSpcwIAAACAmfyF34qKiqsulJn6raQ5OTk6evSoli5dqpCQEDmdTpWVlcnj8Uj65gtmTp06JafT6XOs0+lUSUmJ93Vpaanat29vWu0AAAAAEKxMC4a5ubkqKirSihUrFBERIUm66aabFB8fr02bNkmSNm3apPj4eJ/LSCVp2LBhys/PV3V1tc6ePavt27crJSXFrPIBAAAAIGiZcilpcXGxXn75Zd16660aPXq0JCkuLk4rVqzQL37xCz3zzDN66aWX1KZNG+Xk5HiPy8rK0rRp09SjRw+lp6frgw8+UHJysiRpypQp6tixoxnlAwAAAEBQMyUYfve739Unn3zid1+XLl1q/U3ClStXep+HhoZq7ty5TVIfAAAAADS2iBsiazw2Z6beYwgAAAAAdnFfRpI63dlZ92UkWV1KQKZ/KykAAAAA2MF3775T3737TqvLuCasGAIAAACAzREMAQAAAMDmCIYAAAAAYHMEQwAAAACwOYIhAAAAANgcwRAAAAAAbI5gCAAAAKBBXC6XsrOz5XK5rC4F9cTvGAIAAABokLy8PBUXF8vtdqt///5Wl4N6YMUQAAAAQIO43e4aj7j+EAwBAAAAwOYIhgAAAABgcwRDAAAAIEhVVXusLqHJBPNnswJfPgMAAAAEqbCQUC3Zu6HJ5ymvuOh9NGM+Scruk2HKPHbBiiEAAAAA2BzBEAAAAABsjmAIAAAAoEFCI8NrPOL6QzAEAAAA0CBdU/oppsvN6prSz+pSUE98+QwAAACABmkX31nt4jtbXQYagBVDAAAAALA5giEAAAAA2Jwpl5Lm5ORo69atOnHihAoKCtS1a1cdP35cU6ZM8Y45f/68Lly4oH/84x8+xy9fvlxr1qxR27ZtJUl9+vTRnDlzzCgdAAAAAIKeKcFw6NChGj9+vMaMGePdFhcXp40bN3pfL1y4UB6Pp9b3yMjI0IwZM5q0TgAAAACwI1OCYd++fa+6v7KyUgUFBfrd735nRjkAAAAAgG9pFt9KumPHDrVr107dunWrdczmzZu1c+dOxcbGaurUqerdu3ed5ykqKmpImQAAAMB1JSEhweoSmtSePXvqfEyw90SqX1+aRTBct26dHn744Vr3jx49Wo8//rjCw8O1a9cuTZ48WYWFhYqOjq7TPN27d1dkZGRDywUAAADQDNgh5NWHv75UVFRcdaHM8m8lLSsr0+7du5WWllbrmNjYWIWHh0uSBg0aJKfTqeLiYrNKBAAAAICgZnkwXL9+vYYMGXLV1b+ysjLv84MHD+rEiRPq3Jkf0AQAAACAxmDKpaQLFizQtm3b9OWXX2rChAmKiorS5s2bJX0TDGfOnOlzTFZWlqZNm6YePXpoyZIl+uijjxQSEqLw8HAtWrRIsbGxZpQOAAAAAEHPYRiGYXURTe3K9bTcYwgAAAC7WbJ3g9UlNInsPhn1PnbH0fcbr5BmJrFTP7/bA2Uiyy8lBQAAAABYi2AIAAAAADZHMAQAAAAAmyMYAgAAAHXgcrmUnZ0tl8tldSlAo2kWP3APAAAAXC/y8vJUXFwst9ut/v37W10O0ChYMQQAAADqwO1213gEggHBEAAAAABsjmAIAACA616lx2N1CU0q2D8frMc9hgAAALjuRYSG6idb15gyV5n7vPfRrDnzUjJNmQf2xYohAAAAANgcwRAAAACoA0dEeI1HIBgQDAEAAIA6uPF7fRTZ0akbv9fH6lKARsM9hgAAAEAdtOhyi1p0ucXqMoBGxYohAAAAANgcwRAAAAAAbI5gCAAAAAA2RzAEAAAAAJsjGAIAAACAzREMAQAAAMDmCIYAAAAAYHMEQwAAAACwOYIhAAAAANhcmBmT5OTkaOvWrTpx4oQKCgrUtWtXSVJiYqIiIiIUGRkpSZo+fboGDx7sc7zH49GCBQv07rvvyuFwaNKkSRoxYoQZpQMAAABA0DMlGA4dOlTjx4/XmDFjfPYtW7bMGxRrU1BQoGPHjmnbtm0qLy9XRkaGBgwYoLi4uKYqGQAAAABsw5RLSfv27Sun01nv4wsLCzVixAiFhIQoJiZGSUlJ2rJlSyNWCAAAAAD2ZcqK4dVMnz5dhmEoISFB2dnZatOmjc+Y0tJSdejQwfva6XTq5MmTdZ6rqKioQbUCAACgeUpISLC6hCa3Z8+eOh8T7H2hJ/7Vpy+WBsPXX39dTqdTlZWVWrhwoebNm6fFixc32Xzdu3f33s8IAAAAXE/sEGjqip74568vFRUVV10os/RbSa9cXhoREaHMzEzt3bu31nElJSXe16WlpWrfvr0pNQIAAABAsLMsGLrdbp0/f16SZBiGCgsLFR8f73fssGHDlJ+fr+rqap09e1bbt29XSkqKmeUCAAAAQNAyJRguWLBA9913n06ePKkJEyboRz/6kc6cOaNx48YpLS1NqampOnLkiObMmeM9JisrS/v375ckpaenKy4uTsnJyRo5cqSmTJmijh07mlE6AACAbblcLmVnZ8vlclldCoAmZso9hrNmzdKsWbN8tm/YsKHWY1auXOl9Hhoaqrlz5zZFaQAAAKhFXl6eiouL5Xa71b9/f6vLAdCELL3HEAAAAM2X2+2u8QggeBEMAQAAriOVniqrS2hSwf75gObK8t8xBAAAwLWLCA1T6u/zTJnr0vmvJEkl578ybc5NY39iyjwAamLFEAAAAP6Fh9d8BBC0CIYAAADwK7z33Qpp307hve+2uhQATazel5L+61//0o033tiYtQAAAKAZCe0Yp9COcVaXAcAEAVcMN2zYoHfffdf7ev/+/RoyZIj69++vlJQUHT58uEkLBAAAAAA0rYDBcNWqVYqNjfW+nj17tgYOHKg333xTAwcO1KJFi5q0QAAAAABA0wp4KWlpaam6du3qfX7o0CGtXr1aUVFR+tnPfqbk5OQmLxIAAAAA0HQCrhiGhobq8uXLkqR9+/bptttuU1RUlCSpRYsWunTpUpMWCAAAAABoWgGD4b333qvc3Fx9/PHHeu211/SDH/zAu+/w4cM1LjMFAAAAAFx/AgbDmTNn6sCBA/rxj3+sFi1aKCsry7tv48aNGjx4cJMWCAAAAABoWgHvMTx+/LheffVVv/umT5/e6AUBAAAAAMwVcMXw2yuEAAAAAIDgEzAYGoZhRh0AAAAAAIsEvJRUkr744our7u/YsWOjFAMAAAAAMF/AYPj1118rOTm51pVDh8OhgwcPNnphAAAAAABzBAyGLVq00L59+8yoBQAAAABggYD3GDocDjPqAAAAAABYhC+fAQAAAACbCxgMCwsLzagDAAAAAGCRgPcY5ubmBnyTRYsWNUoxAAAAAADzBQyGt9xyS4MnycnJ0datW3XixAkVFBSoa9euOnfunH7+85/r2LFjioiIUKdOnTRv3jzFxMT4HL98+XKtWbNGbdu2lST16dNHc+bMaXBdAAAAAIBrCIZPPPFEgycZOnSoxo8frzFjxni3ORwOTZw4Uf369ZP0TXhcvHixnn/+eb/vkZGRoRkzZjS4FgAAAABATQHvMSwpKdHJkye9r7/++mvl5ubqP//zP/Xb3/5WHo8n4CR9+/aV0+mssS0qKsobCiWpV69eKikpqUvtAAAAAIBGEHDFcObMmcrMzFT79u0lSfPmzdPu3bt1//33a926dbpw4YKys7MbVER1dbXWrl2rxMTEWsds3rxZO3fuVGxsrKZOnarevXvXeZ6ioqKGlAkAAILUwYMH9c4772jIkCGKj4+3upyrSkhIsLqEJrdnz546H0Nf/Av2vtAT/+rTl4DB8OOPP9agQYMkSW63W4WFhXr99dfVvXt3PfLII5o0aVKDg+H8+fPVsmVLjR071u/+0aNH6/HHH1d4eLh27dqlyZMnq7CwUNHR0XWap3v37oqMjGxQrQAAIPisXLlShw8fVmhoaK3nIzCPHU7c64O++KIn/vnrS0VFxVUXygJeSnr58mW1bNlSkrR//361atVK3bt3lyR16dJF586dq2+9kr65t/Do0aNaunSpQkL8lxMbG6vw8HBJ0qBBg+R0OlVcXNygeQEAAK5wu901HgHAbgIGw7i4OL3//vuSpB07dtS4L/Ds2bNq0aJFvSfPzc1VUVGRVqxYoYiIiFrHlZWVeZ8fPHhQJ06cUOfOnes9LwAAaP4qq6qsLqFJBfvnA3B9uaZvJZ0yZYo6duyow4cP67XXXvPu+8tf/qIePXoEnGTBggXatm2bvvzyS02YMEFRUVFaunSpXn75Zd16660aPXq0pG9C6IoVKyRJWVlZmjZtmnr06KElS5boo48+UkhIiMLDw7Vo0SLFxsbW9zMDAIDrQERYmJL+5xVT5jLKv5IknSj/yrQ5tz850ZR5AOBaBAyGSUlJWrdunT7++GPddddd6tixo3ffbbfdpl69egWcZNasWZo1a5bP9k8++aTWY1auXOl9npOTE3AOAACAegsLq/kIADZzTX/7derUSZ06dfLZzs2eAAAgKNzZQ/r0Y+n2O62uBAAsETAYPv3003I4HFcds2jRokYrCAAAwGyOdjdL7W62ugwAsEzAYOhvpRAAAAAAEDwCBsPx48erTZs2ZtQCAAAAALBAwJ+rGDRokKZNm6a3335bHo/HjJoAAAAAACYKGAzz8/N1880367nnntPgwYP1/PPP6+DBg2bUBgAAAAAwQcBLSe+8807deeedevrpp7Vr1y5t3LhRmZmZiouL04MPPqi0tDR+UxAAAAAArmPX/GM9ISEhGjx4sAYPHiy3261t27Zp2bJlWrJkiYqKipqyRgAAAABAE6rzr7iWlZXpzTff1IYNG1ReXq60tLSmqAsAAAAAYJJrCoaXLl3S1q1btWHDBu3evVt9+/ZVVlaWUlJS1KJFi6auEQAAAADQhAIGwxkzZuitt95Su3btlJ6erueff15Op9OM2gAAAAAAJggYDCMjI7Vq1Sr16tUr4Jvt2bNHCQkJjVEXAAAAAMAkAX+uYt68edcUCiUpKyurofUAAAAAAEwWMBjWhWEYjfl2AAAAAAATNGowdDgcjfl2AAAAAAATNGowBAAAAABcfwiGAAAAAGBzDQ6G1dXV3ufcYwgAQPPmcrmUnZ0tl8tldSkAgGakQcGwsrJS3bp1877et29fgwsCAABNJy8vTx988IHy8vKsLgUA0Iw0eMWQVUIAAK4fbre7xiMAAFIjBEO+iRQAgIarvFxldQlNJpg/GwAEizCrCwAAAFJEeJiG/uLlpp/o7L8kSSfO/suc+ST95RePmzIPAKD+AgbDzMzMWlcFv/3FM1eTk5OjrVu36sSJEyooKFDXrl0lSUeOHNEzzzyj8vJyRUVFKScnR7feeqvP8R6PRwsWLNC7774rh8OhSZMmacSIEdc0NwAA+JbQsJqPAADoGoJhoAA2cuTIgJMMHTpU48eP15gxY2psnzNnjjIzM5Wenq6NGzdq9uzZevXVV32OLygo0LFjx7Rt2zaVl5crIyNDAwYMUFxcXMC5AQDAt3TqLh3/RIq7w+pKAADNSMBg+OCDD151/6effhpwkr59+/psO3PmjA4cOKDVq1dLklJTUzV//nydPXtWMTExNcYWFhZqxIgRCgkJUUxMjJKSkrRlyxZNnDgx4NwAAOBbYpzf/AMAwLfU6zqSc+fOafPmzXrjjTd06NAhFRUV1fk9SktL1a5dO4WGhkqSQkND1bZtW5WWlvoEw9LSUnXo0MH72ul06uTJk3Wesz51AgBghoSEBKtLaFJ79uyp8zHB3hOJvtSGvvhHX3zRE//q05drDoZVVVV6++23tX79er3zzjvyeDyaOHGiXn7ZnBvXG0P37t0VGRlpdRkAANiOHU7E6oO++Edf/KMvvuiJf/76UlFRcdWFsoA/V7F//37Nnz9fgwYN0syZM3XTTTdp9erViomJ0U9+8hO1bdu2XsU6nU6VlZXJ4/FI+uYLZk6dOiWn0/fyFqfTqZKSEu/r0tJStW/fvl7zAgAAAABquqYvn4mKitKsWbP0wx/+UGFh3xzS0N8vvOmmmxQfH69NmzYpPT1dmzZtUnx8vM9lpJI0bNgw5efnKzk5WeXl5dq+fbtef/31Bs0PAAAAAPhGwBXDKVOmqHXr1nruuef09NNPa8eOHaqqqtsP1S5YsED33XefTp48qQkTJuhHP/qRJOkXv/iFfv/73yslJUW///3vNXfuXO8xWVlZ2r9/vyQpPT1dcXFxSk5O1siRIzVlyhR17NixTjUAAAAAAPwLuGI4depUTZ06Vbt379aGDRv09NNPKywsTG63W4cOHdKAAQMCTjJr1izNmjXLZ3uXLl2Un5/v95iVK1d6n4eGhtYIjQAAAACAxhNwxfDKt3/ec889WrhwoXbt2qWZM2fq3nvv1WOPPaZHHnmkyYsEAAAAADSdgCuGDzzwgPbu3et9fcMNN2j48OEaPny4ysrKtHHjxiYtEAAAAADQtAKuGBqGUeu+du3aadKkSY1aEAAAAADAXAFXDB0OhwzDuGpADAkJmC8BAAAAAM1UwGDodrt11113+d1nGIYcDocOHjzY6IUBAAAAAMwRMBi2aNFCmzZtMqMWAAAAAIAFrulS0ptvvtmMWgAAAAAAFmjQl88AAAAAAK5/AYPht39ovqKiQqdOnVJFRUWTFgUAAAAAME/AYNi3b1998MEHGjdunPr06aMhQ4aoT58+GjNmjP75z3+aUCIAAPXjcrmUnZ0tl8tldSkAADRrAYPhvn379JOf/ERdunTRqlWrtHnzZq1atUq33367JkyYoH379plRJwAAdZaXl6cPPvhAeXl5VpcCAECzFvDLZ5YuXars7GyNGzfOu+22225Tv379dPvttys3N1evvvpqkxYJAAgelZerFBEe8D8/jcLtdtd4NIOZnw8AgMYS8L9cRUVF+vWvf+1330MPPaTc3NxGLwoAELwiwsOU9OSLpsxlnC6XJJ04XW7anNv/5wlT5gEAoDEFvJTU4XCoqqrK776qqio5HI5GLwoAgEYREl7zEQAA+BUwGN5zzz1avXq1332rV6/WPffc0+hFAQDQKNrFS62+880jAACoVcBLSX/2s58pMzNTBw4c0LBhwxQbG6vTp09ry5Yt2rdvn9asWWNGnQAA1JmjdXupdXurywAAoNkLGAxvv/12/elPf9Ly5cv1q1/9SufOnVN0dLQGDBig/Px8derUyYw6AQAAAABNJGAw3LRpk1JTU/XLX/7SjHoAAAAAACYLeI/h7NmzzagDAAAAAGCRgMHQMAwz6gAAAAAAWCTgpaTV1dVyuVxXDYgDBgxo1KIAAAAAAOYJGAwrKys1c+bMWoOhw+HQX/7yl0YvDAAAAABgjoDBsEWLFk0a/I4fP64pU6Z4X58/f14XLlzQP/7xjxrjli9frjVr1qht27aSpD59+mjOnDlNVhcAAAAA2EXAYNjU4uLitHHjRu/rhQsXyuPx+B2bkZGhGTNmmFUaAAAAANhCs/rymcrKShUUFOjhhx82bU4AAAAAsLuAK4b79u0zow5J0o4dO9SuXTt169bN7/7Nmzdr586dio2N1dSpU9W7d+86vX9RUVFjlAkAaICEhASrS2hye/bsqfMxwd4XeuIfffGPvvhHX3zRE//q0xfLLyX9tnXr1tW6Wjh69Gg9/vjjCg8P165duzR58mQVFhYqOjr6mt+/e/fuioyMbKxyAQDwyw4nHXVFT/yjL/7RF//oiy964p+/vlRUVFx1oSzgpaRmKSsr0+7du5WWluZ3f2xsrMLDwyVJgwYNktPpVHFxsZklAgAAAEBQajbBcP369RoyZEitK4BlZWXe5wcPHtSJEyfUuXNns8oDAAAAgKDVbC4lXb9+vWbOnFljW1ZWlqZNm6YePXpoyZIl+uijjxQSEqLw8HAtWrRIsbGxFlULAAAAAMGj2QTDrVu3+mxbuXKl93lOTo6Z5QDAdcXlcumPf/yjRo4cqf79+1tdDgAAuM40m2AIAKi/vLw8FRcXy+12EwwBAECdNZt7DAEg2FRWVpk2l9vtrvFoBjM/HwAAaFqsGAJAE4mICNOw8bmmzHX5ZLkk6cTJctPm3PLqU6bMAwAAmh4rhgAQDELCaj4CAADUAcEQAIJAaJuuckTcpNA2Xa0uBQAAXIf4X8sAEARCbminkBvaWV0GAAC4TrFiCAAAAAA2RzAEAAAAAJsjGAIAAACAzREMAQAAAMDmCIYAAAAAYHMEQwAAAACwOYIhAAAAANgcwRAAAAAAbI5gCAAAAAA2RzAEAAAAAJsjGAK4rrhcLmVnZ8vlclldCgAAQNAIs7oAAKiLvLw8FRcXy+12q3///laXAwAAEBRYMQTQYJWVl02by+1213g0g5mfDwAAwAqsGAJosIiIcD3wo1mmzFVZcUaSVFJyxrQ5CzcvMGUeAAAAq7BiCOA6E/pvjwAAAGgogiGA60poWEc5QtooNKyj1aUAAAAEjWZxKWliYqIiIiIUGRkpSZo+fboGDx5cY4zH49GCBQv07rvvyuFwaNKkSRoxYoQV5QKwUGhotEJDo60uAwAAIKg0i2AoScuWLVPXrl1r3V9QUKBjx45p27ZtKi8vV0ZGhgYMGKC4uDgTqwQAAACA4HPdXEpaWFioESNGKCQkRDExMUpKStKWLVusLgsAAAAArnvNZsVw+vTpMgxDCQkJys7OVps2bWrsLy0tVYcOHbyvnU6nTp48Wac5ioqKGqVWADUlJCRYXUKT27NnT52PoS/+0Rf/gr0v9MQ/+uIfffGPvviiJ/7Vpy/NIhi+/vrrcjqdqqys1MKFCzVv3jwtXry40efp3r279z5GAKgLO/xHpD7oi3/0xRc98Y+++Edf/KMvvuiJf/76UlFRcdWFsmZxKanT6ZQkRUREKDMzU3v37vU7pqSkxPu6tLRU7du3N61GAAAAAAhWlgdDt9ut8+fPS5IMw1BhYaHi4+N9xg0bNkz5+fmqrq7W2bNntX37dqWkpJhdLgAAAAAEHcsvJT1z5oymTp0qj8ej6upqdenSRXPmzJEkZWVladq0aerRo4fS09P1wQcfKDk5WZI0ZcoUdezI75gBAAAAQENZHgw7duyoDRs2+N23cuVK7/PQ0FDNnTvXpKoAAAAAwD4sv5QUAAAAAGAtgiEAAAAA2BzBEAAAAABsjmAIAAAAADZHMAQAAAAAmyMYAs2Uy+VSdna2XC6X1aUAAAAgyFn+cxUA/MvLy1NxcbHcbrf69+9vdTkAAAAIYqwYAs2U2+2u8QgAAAA0FYIhUEeVFZVWl9BkgvmzAQAAoHZcSgrUUURkhH7Qf1yTz+O44bQcodLxY6dMmU+S/up6zZR5AAAA0LywYgg0U8bl1jI8ETIut7a6FAAAAAQ5VgyB5spzgwzPDVZXAQAAABtgxRAAAAAAbI5gCAAAAAA2RzAEAAAAAJsjGAIAAACAzREMAQAAAMDmCIYAAAAAYHMEQwAAAACwOYIhAAAAANgcwRAAAAAAbI5gCAAAAAA2F2Z1AefOndPPf/5zHTt2TBEREerUqZPmzZunmJiYGuOWL1+uNWvWqG3btpKkPn36aM6cOVaUDAAAAABBxfJg6HA4NHHiRPXr10+SlJOTo8WLF+v555/3GZuRkaEZM2aYXSIAAAAABDXLLyWNioryhkJJ6tWrl0pKSiysCAAAAADsxfIVw2+rrq7W2rVrlZiY6Hf/5s2btXPnTsXGxmrq1Knq3bt3nd6/qKioMcqEzSUkJFhdQpPas2dPnY8J9p5I9KU29MU/+uKLnvhHX/yjL/7RF1/0xL/69KVZBcP58+erZcuWGjt2rM++0aNH6/HHH1d4eLh27dqlyZMnq7CwUNHR0df8/t27d1dkZGRjlgwEHTv8ZVkf9MU/+uIfffFFT/yjL/7RF//oiy964p+/vlRUVFx1oczyS0mvyMnJ0dGjR7V06VKFhPiWFRsbq/DwcEnSoEGD5HQ6VVxcbHaZAAAAABB0mkUwzM3NVVFRkVasWKGIiAi/Y8rKyrzPDx48qBMnTqhz585mlYgm5nK5lJ2dLZfLZXUpAAAAgO1YfilpcXGxXn75Zd16660aPXq0JCkuLk4rVqxQVlaWpk2bph49emjJkiX66KOPFBISovDwcC1atEixsbEWV4/GkpeXp+LiYrndbvXv39/qcgAAAABbsTwYfve739Unn3zid9/KlSu9z3NycswqCf9fRUWFafdkut3uGo9mMPPzAQAAAM2Z5cEQzVdkZKT6dB1sylyt24UpLCJER498Ydqcew+9a8o8AAAAQHPXLO4xBL7+l0eXL1Xr6395rC4FAAAAsB1WDNEsVF0ydOFSldVlAAAAALbEiiEAAAAA2BzBEAAAAABsjmAIAAAAADZHMAQAAAAAmyMYAgAAAIDNEQwBAAAAwOYIhgAAAABgcwRDAAAAALA5giEAAAAA2BzBEAAAAABsjmAIAAAAADZHMAQAAAAAmyMYAgAAAIDNEQwBAAAAwOYIhgAAAABgcwRDAAAAALA5giEAAAAA2BzB0GQul0vZ2dlyuVxWlwIAAAAAkqQwqwuwm7y8PBUXF8vtdqt///5WlwMAAAAAzWPF8MiRIxo1apRSUlI0atQoff755z5jPB6P5s6dq6SkJN1///3Kz89vtPkvXbrUaO/VHAX75wMAAADQMM1ixXDOnDnKzMxUenq6Nm7cqNmzZ+vVV1+tMaagoEDHjh3Ttm3bVF5eroyMDA0YMEBxcXENnv+GG25Qp9hbG/w+16Jl65aKio3SO9v+ZtqcR09/bso8AAAAAK5PlgfDM2fO6MCBA1q9erUkKTU1VfPnz9fZs2cVExPjHVdYWKgRI0YoJCREMTExSkpK0pYtWzRx4sSAcxiGIUmqrKysdUxsu9gGfpJrd/niZbVq2UqtWrYyZb6Kiop6H3vTd2ICD7pONaQv0TFtGrGS5qMhPYmKatmIlTQvDepL68hGrKR5adCfoVb0xZ/oFhGNWEnz0aCeRAZnT6QG/t0SHt6IlTQvDelL6xDLT22bTEP6EmmENmIlzUdDeuLwNGIhzUxtfbmSha5ko3/nMGrbY5KioiLNmDFDmzdv9m574IEH9Mtf/lLdunXzbktLS9PChQvVs2dPSdLKlStVVlamWbNmBZzj/PnzOnToUOMXDwAAAADXka5du6p169Y+24P3f6t8S6tWrdS1a1eFh4fL4XBYXQ4AAAAAmMowDF2+fFmtWvm/atHyYOh0OlVWViaPx6PQ0FB5PB6dOnVKTqfTZ1xJSYl3xbC0tFQdOnS4pjlCQkL8pmIAAAAAsIsbbrih1n2WfyvpTTfdpPj4eG3atEmStGnTJsXHx9e4v1CShg0bpvz8fFVXV+vs2bPavn27UlJSrCgZAAAAAIKK5fcYStJnn32mZ555Rl999ZXatGmjnJwc3XbbbcrKytK0adPUo0cPeTwezZs3T7t27ZIkZWVladSoURZXDgAAAADXv2YRDAEAAAAA1rH8UlIAAAAAgLUIhgAAAABgcwRDAAAAALA5giEAAAAA2BzBsIkcOXJEo0aNUkpKikaNGqXPP//cZ4zH49HcuXOVlJSk+++/X/n5+eYXaqKcnBwlJibqjjvu0KFDh/yOsVtPJOncuXPKyspSSkqK0tLS9MQTT+js2bM+4+zWm8mTJ2v48OHKyMhQZmamDh486DPGbj35thdffLHWP0t27EtiYqKGDRum9PR0paen69133/UZY8e+VFRUaM6cOUpOTlZaWpqee+45nzF26svx48e9/46kp6crMTFR9957r884O/Xkir/+9a/KyMhQenq60tLStG3bNp8xduzL22+/rQcffFBpaWkaO3asvvjiC58xwd6X2s7fruVcVwre/tTWl2s535WaaV8MNIlx48YZGzZsMAzDMDZs2GCMGzfOZ8z69euNRx991PB4PMaZM2eMwYMHG1988YXZpZpm9+7dRklJifGDH/zA+OSTT/yOsVtPDMMwzp07Z7hcLu/rF154wXj22Wd9xtmtN1999ZX3+VtvvWVkZGT4jLFbT64oKioyHnvsMeP73/++3z9LduzL1f5eucKOfZk/f76xcOFCo7q62jAMwzh9+rTPGDv25YoFCxYYc+fO9dlut55UV1cbffv29f4ZOnjwoNGrVy/D4/HUGGe3vpSXlxv33nuvcfjwYcMwvjmfe/TRR33GBXtfajt/u5ZzXcMI3v7U1pdrOd81jObZF1YMm8CZM2d04MABpaamSpJSU1N14MABn1WgwsJCjRgxQiEhIYqJiVFSUpK2bNliRcmm6Nu3r5xO51XH2K0nkhQVFaV+/fp5X/fq1UslJSU+4+zWm9atW3ufX7hwQQ6Hw2eM3XoiSZWVlZo3b57mzJnjtyeSPftyLezWl4sXL2rDhg168sknvf+ufOc73/EZZ7e+XFFZWamCggI9/PDDPvvs2JOQkBCdP39eknT+/Hm1bdtWISE1TxPt1pejR4/qO9/5jjp37ixJGjJkiHbu3Gm78zl/52/Xeq4rBW9/ajuvvZbzXal59iXM0tmDVGlpqdq1a6fQ0FBJUmhoqNq2bavS0lLFxMTUGNehQwfva6fTqZMnT5peb3Ni955UV1dr7dq1SkxM9Nlnx97MnDlTu3btkmEYeuWVV3z227En//M//6Phw4erY8eOtY6xY18kafr06TIMQwkJCcrOzlabNm1q7LdbX7744gtFRUXpxRdf1Pvvv69WrVrpySefVN++fWuMs1tfrtixY4fatWunbt26+eyzW08cDoeWLl2qyZMnq2XLlrp48aJ+85vf+IyzW186d+6sL7/8Uh9++KF69uypgoICSeJ8Ttd+rntlrN36cy2aY19YMQSakfnz56tly5YaO3as1aU0CwsXLtTbb7+tp556SosWLbK6HMvt27dP+/fvV2ZmptWlNDuvv/663nzzTa1bt06GYWjevHlWl2S5qqoqffHFF7rrrrv0xhtvaPr06Zo6daouXLhgdWnNwrp16/yuFtpRVVWVfvOb3+ill17SX//6V/3617/WU089pYsXL1pdmqVat26t3Nxc/fd//7ceeughnTlzRm3atFFYGOsqCE4EwybgdDpVVlYmj8cj6ZubS0+dOuWzrOx0OmtcMlhaWqr27dubWmtzY+ee5OTk6OjRo1q6dKnP5TuSvXuTkZGh999/X+fOnaux3W492b17tw4fPqyhQ4cqMTFRJ0+e1GOPPaadO3fWGGe3vkjy/v0aERGhzMxM7d271+8YO/WlQ4cOCgsL817qdffddys6OlpHjhypMc5ufZGksrIy7d69W2lpaX73260nBw8e1KlTp5SQkCBJSkhIUIsWLfTZZ5/VGGe3vkjSwIEDtXbtWr3xxhsaO3asLl265HPFhh37cq3nulfG2q0/16I59oVg2ARuuukmxcfHa9OmTZKkTZs2KT4+3mdpfdiwYcrPz1d1dbXOnj2r7du3KyUlxYqSmw279iQ3N1dFRUVasWKFIiIi/I6xU28uXryo0tJS7+sdO3boxhtvVFRUVI1xduqJJE2aNEk7d+7Ujh07tGPHDrVv316/+93v9L3vfa/GOLv1xe12e++NMgxDhYWFio+P9xlnt77ExMSoX79+2rVrl6RvvkHwzJkz6tSpU41xduuLJK1fv15DhgxRdHS03/1260n79u118uRJHT58WJL02Wef6csvv9Qtt9xSY5zd+iJJp0+flvTNrR5LlizR6NGj1bJlyxpj7NiXaz3XlezZn2vRLPti6VffBLFPP/3UeOSRR4zk5GTjkUceMT777DPDMAxj4sSJxocffmgYhmFUVVUZs2fPNoYOHWoMHTrU+MMf/mBlyU1u/vz5xuDBg434+Hhj4MCBxgMPPGAYhr17YhiGcejQIaNr165GcnKyMXz4cGP48OHG5MmTDcOwb29Onz5tjBgxwkhNTTWGDx9ujBs3zigqKjIMw7498efb33hm574cO3bMSE9PN1JTU40HHnjAmDp1qlFWVmYYhr37Yhjf9Gbs2LFGamqqkZGRYbz99tuGYdCX5ORk45133qmxze492bhxo5GammqkpaUZaWlpxltvvWUYBn35r//6L2PYsGHG0KFDjdmzZxuXLl0yDMNefant/K22c13DsEd/autLbdsNo/n3xWEYhmFtNAUAAAAAWIlLSQEAAADA5giGAAAAAGBzBEMAAAAAsDmCIQAAAADYHMEQAAAAAGyOYAgAAAAANkcwBAAEjd69e3v/ufPOO9WzZ0/v6zfffFOS9Omnn+rxxx9XQkKCevfurXHjxmnv3r2SpP/7v//zju/Vq5fuuOOOGu9ZUlKiI0eOaNq0aerXr58SEhKUlpam1atXy+Px6Pjx47rjjjtUVVVVo65nnnlGubm5kuQdc+U9ExMT9dvf/tbns7zxxhtKS0vT3XffrUGDBmnOnDn66quvvPuXL1+uO+64Q3/+85+926qqqnTHHXfo+PHjPvNKUmVlpZYvX67k5GT16tVLiYmJevbZZ73jAQD2FWZ1AQAANJZ9+/Z5nycmJmrBggUaOHCgd9uxY8f04x//WJmZmXrhhRcUFhamN954Q4899phWrVqlvn37et/j+PHjGjp0qHbv3q2wsDDv8SNHjtRDDz2kgoICtW3bVocPH9aKFSt08eLFOtV65X3379+vcePGqVu3bho0aJAkadWqVXrllVf0wgsvaMCAASorK9PcuXM1YcIErV27VhEREZKkqKgoLVu2TMnJyQoNDQ0457Rp01RWVqbFixfrrrvu0tdff60333xTf//73zVixIg61Q8ACC6sGAIAbGP58uXq1auXnnrqKUVFRek//uM/NH78eA0fPlyLFy8OePyyZcvUu3dvPfvss2rbtq0k6bbbbtOvfvUrtWnTpl419ejRQ7fffrsOHjwoSbpw4YKWL1+uWbNm6b777lN4eLji4uK0dOlSlZSUeFc+Jel73/uewsPDa2yrzXvvvaf33ntPL730knr27KmwsDC1bt1aY8aMIRQCAAiGAAD7eO+99zRs2DCf7T/84Q+1d+9eff3111c9/u9//7tSUlIataZ//vOfKi4uVqdOnSRJe/fuVUVFhZKTk2uMa9Wqle677z6999573m0Oh0NPPvmkXnzxRV2+fPmq87z33nvq2bOnnE5no9YPAAgOXEoKALCNc+fOKTY21md7bGysqqur9dVXX6lFixa1Hl9eXu73+H/Xv3//Gq8vXbqkxx57zGdMZWWlKioq9OijjyopKclbY3R0tPfy1X+v86OPPqqxbejQoXr55ZeVn5+vkSNHNrh2AIA9EQwBALYRHR2t06dP+2w/ffq0QkJCAl4OGhUV5ff4f+dyuWoEu2eeecbvGIfDof/93//Vpk2bdPnyZUVERCg6Olrnzp1TVVWVTzg8ffq0oqOjfd7rpz/9qZ599lmlp6dftfbPP/88YO0AAHviUlIAgG0MGDBAW7Zs8dn+5z//Wb169brqauGV47dt29Zo9YSGhurRRx9VZGSk1qxZI+mbb1aNiIjwmcftdutvf/ubBgwY4PM+gwYNUqdOnbzv4c/AgQP14Ycf6uTJk41WPwAgeBAMAQC28cQTT2jfvn3Kzc1VeXm5Lly4oNdee00bN27U9OnTAx4/bdo07du3Tzk5Od6Vw6NHj2r69Ok1fkqiriZNmqRXXnlFFRUVat26taZMmaIFCxbob3/7my5fvqzjx4/rySefVPv27WtdFfzpT3+qV155pdY5Bg4cqIEDB2rKlCkqKipSVVWVLly4oLVr1+pPf/pTvWsHAAQHgiEAwDZuvfVWrVmzRh9//LESExM1ePBgbdu2Ta+88ooSEhICHn/LLbfoD3/4g06cOKHU1FQlJCRo6tSp6t69u1q1alXvur7//e/rxhtv1B//+EdJUlZWlp566iktWrRICQkJGjlypJxOp/Ly8rw/VfHvEhIS1LNnz6vOs2zZMg0ZMkRPPfWU+vbtq7S0NBUVFdX4SQ8AgD05DMMwrC4CAAAAAGAdVgwBAAAAwOYIhgAAAABgcwRDAAAAALA5giEAAAAA2BzBEAAAAABsjmAIAAAAADZHMAQAAAAAmyMYAgAAAIDNEQwBAAAAwOb+Hwn8rKfEoszMAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<Figure size 1080x360 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sb.set(rc={\"figure.figsize\":(15, 5)})\n",
    "sb.set_theme(style=\"whitegrid\")\n",
    "sb.barplot(x=\"TOTCHRONIC\", y=\"TOTAL_VISITS\", data=cc_summary_all, palette=\"mako\");"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Costs also increased as number of conditions increased, really beginning to take off after 6 chronic conditions."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1080x360 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sb.set(rc={\"figure.figsize\":(15, 5)})\n",
    "sb.set_theme(style=\"whitegrid\")\n",
    "sb.barplot(x=\"TOTCHRONIC\", y=\"ALLCOSTS\", data=cc_summary_all, palette=\"mako\");"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [],
   "source": [
    "SUM_TOTAL = cc_summary_all[\"ALLCOSTS\"].sum()\n",
    "cc_summary_all[\"PERCENT_COSTS\"] = cc_summary_all[\"ALLCOSTS\"] / SUM_TOTAL * 100"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x720 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "corr_subset = cc_summary_all[[\"TOTAL_INP_DAYS\", \"ALLCOSTS\", \"TOTCHRONIC\", \"MEAN_AGE\", \"BENE_RACE_CD\", \"B_SEX\"]]\n",
    "correlations = corr_subset.corr(method=\"pearson\")\n",
    "lh_corr = correlations.where(np.tril(np.ones(correlations.shape)).astype(np.bool))\n",
    "\n",
    "plt.rcParams[\"figure.figsize\"] = (10.0, 10.0)\n",
    "corr_hmap=sb.heatmap(lh_corr, annot=True, cmap=\"mako\", fmt=\".2f\")\n",
    "fig = corr_hmap.get_figure()\n",
    "fig.savefig(\"desynpuf_corr1_heatmap.png\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "There is a small association between being in a higher age category and the number of chronic conditions.\n",
    "\n",
    "There is also a (slightly stronger) association between being female, and living to an older age.\n",
    "\n",
    "There is also an association between being white and living to an older age. :-(\n",
    "\n",
    "There is a strong correlation between the number of chronic conditions and total number of inpatient days and a very strong correlation between the total number of inpatient days and total costs. Outpatient visits are more numerous, but clearly, inpatient visits are more expensive.\n",
    "\n",
    "Let's see this by specific condition."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x720 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "cost_ed_conds = cc_summary_all[[\"TOTAL_INP_DAYS\", \"ALLCOSTS\", \"MEAN_AGE\", \"BENE_RACE_CD\", \"B_SEX\",\n",
    "                                \"B_ALZHDMTA\", \"B_CHF\", \"B_CNCR\", \"B_DEPRESSN\", \"B_DIABETES\", \n",
    "                                \"B_ISCHMCHT\", \"B_OSTEOPRS\", \"B_COPD\", \"B_CHRNKIDN\", \"B_ESRD\",\n",
    "                                \"B_RA_OA\", \"B_STRKETIA\"]]\n",
    "cost_ed_corr = cost_ed_conds.corr(method=\"pearson\")\n",
    "lr_cost_ed_corr = cost_ed_corr.where(np.tril(np.ones(cost_ed_corr.shape)).astype(np.bool))\n",
    "\n",
    "plt.rcParams[\"figure.figsize\"] = (10.0, 10.0)\n",
    "cost_ed_hmap=sb.heatmap(lr_cost_ed_corr, annot=True, cmap=\"mako\", fmt=\".2f\")\n",
    "fig = cost_ed_hmap.get_figure()\n",
    "fig.tight_layout()\n",
    "fig.savefig(\"cost_desynpuf_conditions_heatmap.png\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This graph does a great job of showing where all the multicollinearity is between all these variables.\n",
    "\n",
    "Luckily, it doesn't look like our demographic data has much of an impact here - those correlations with the outcomes are small.\n",
    "\n",
    "### Most Inpatient Days by Condition\n",
    "\n",
    "CKD, COPD, ESRD & CHF, Diabetes, Alzheimer's & Stroke, Depression & Ischemic Heart Disease, RA/OA, Osteoporosis & Cancer\n",
    "\n",
    "### Highest Cost by Condition\n",
    "\n",
    "CKD, COPD, ESRD, Diabetes & CHF, Alzheimer's, Depression & Stroke, Ischemic Heart Disease, RA/OA, Osteoporosis & Cancer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [],
   "source": [
    "cc_summary.to_csv(\"/home/kylier/python/DS/data/PUF/PUF_BENE_SUMMARY_YEARS.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [],
   "source": [
    "cc_summary_all.to_csv(\"/home/kylier/python/DS/data/PUF/PUF_BENE_SUMMARY_ALL.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "Index: 116339 entries, 0000438E79D01BEA to FFFFF4859B6D7402\n",
      "Data columns (total 60 columns):\n",
      " #   Column                        Non-Null Count   Dtype  \n",
      "---  ------                        --------------   -----  \n",
      " 0   MEAN_AGE                      86464 non-null   float64\n",
      " 1   B_SEX                         116339 non-null  int64  \n",
      " 2   BENE_RACE_CD                  116339 non-null  int64  \n",
      " 3   B_ALZHDMTA                    116339 non-null  float64\n",
      " 4   B_CHF                         116339 non-null  float64\n",
      " 5   B_CNCR                        116339 non-null  float64\n",
      " 6   B_COPD                        116339 non-null  float64\n",
      " 7   B_DEPRESSN                    116339 non-null  float64\n",
      " 8   B_DIABETES                    116339 non-null  float64\n",
      " 9   B_ISCHMCHT                    116339 non-null  float64\n",
      " 10  B_OSTEOPRS                    116339 non-null  float64\n",
      " 11  B_CHRNKIDN                    116339 non-null  float64\n",
      " 12  B_RA_OA                       116339 non-null  float64\n",
      " 13  B_STRKETIA                    116339 non-null  float64\n",
      " 14  B_ESRD                        116339 non-null  float64\n",
      " 15  MEAN_HI_CVRAGE_TOT_MONS       116339 non-null  float64\n",
      " 16  MEAN_SMI_CVRAGE_TOT_MONS      116339 non-null  float64\n",
      " 17  MEAN_HMO_CVRAGE_TOT_MONS      116339 non-null  float64\n",
      " 18  MEAN_CVRG_MOS_NUM             116339 non-null  float64\n",
      " 19  TOTAL_VISITS                  116339 non-null  int64  \n",
      " 20  MEAN_TOTAL_VISITS             116339 non-null  float64\n",
      " 21  TOTAL_CLAIMS                  116339 non-null  int64  \n",
      " 22  MEAN_TOTAL_CLAIMS             116339 non-null  float64\n",
      " 23  MEAN_NUM_PRVDRS               116339 non-null  float64\n",
      " 24  TOT_CLM_PMT_AMT               116339 non-null  float64\n",
      " 25  MEAN_CLM_PMT_AMT              86464 non-null   float64\n",
      " 26  TOT_NCH_PRMRY_PYR_CLM_PD_AMT  116339 non-null  float64\n",
      " 27  MEAN_NUM_AT_PHYSNS            116339 non-null  float64\n",
      " 28  MEAN_NUM_OP_PHYSNS            116339 non-null  float64\n",
      " 29  MEAN_NUM_OT_PHYSNS            116339 non-null  float64\n",
      " 30  TOT_ADMTNG_ICD9_CDS           116339 non-null  int64  \n",
      " 31  TOTAL_INP_DAYS                116339 non-null  float64\n",
      " 32  MEAN_INP_STAY                 37566 non-null   float64\n",
      " 33  MIN_INP_STAY                  37566 non-null   float64\n",
      " 34  MAX_INP_STAY                  37566 non-null   float64\n",
      " 35  TOT_CLM_DRG_CDS               116339 non-null  int64  \n",
      " 36  TOT_MEDREIMB_IP               116339 non-null  float64\n",
      " 37  MEAN_MEDREIMB_IP              116339 non-null  float64\n",
      " 38  TOT_BENRES_IP                 116339 non-null  float64\n",
      " 39  MEAN_BENRES_IP                116339 non-null  float64\n",
      " 40  TOT_PPPYMT_IP                 116339 non-null  float64\n",
      " 41  MEAN_PPPYMT_IP                116339 non-null  float64\n",
      " 42  TOT_MEDREIMB_OP               116339 non-null  float64\n",
      " 43  MEAN_MEDREIMB_OP              116339 non-null  float64\n",
      " 44  TOT_BENRES_OP                 116339 non-null  float64\n",
      " 45  MEAN_BENRES_OP                116339 non-null  float64\n",
      " 46  TOT_PPPYMT_OP                 116339 non-null  float64\n",
      " 47  MEAN_PPPYMT_OP                116339 non-null  float64\n",
      " 48  CBSA                          89478 non-null   float64\n",
      " 49  FIPS_STATE_CODE               114530 non-null  float64\n",
      " 50  FIPS_COUNTY_CODE              114530 non-null  float64\n",
      " 51  TOTIPCOST                     116339 non-null  float64\n",
      " 52  MEANIPCOST                    116339 non-null  float64\n",
      " 53  TOTOPCOST                     116339 non-null  float64\n",
      " 54  MEANOPCOST                    116339 non-null  float64\n",
      " 55  ALLCOSTS                      116339 non-null  float64\n",
      " 56  MEANCOSTS                     116339 non-null  float64\n",
      " 57  TOTCHRONIC                    116339 non-null  float64\n",
      " 58  VISITS_FLAG                   116339 non-null  int64  \n",
      " 59  PERCENT_COSTS                 116339 non-null  float64\n",
      "dtypes: float64(53), int64(7)\n",
      "memory usage: 59.1+ MB\n"
     ]
    }
   ],
   "source": [
    "cc_summary_all.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "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>DESYNPUF_ID</th>\n",
       "      <th>MEAN_AGE</th>\n",
       "      <th>B_SEX</th>\n",
       "      <th>BENE_RACE_CD</th>\n",
       "      <th>B_ALZHDMTA</th>\n",
       "      <th>B_CHF</th>\n",
       "      <th>B_CNCR</th>\n",
       "      <th>B_COPD</th>\n",
       "      <th>B_DEPRESSN</th>\n",
       "      <th>B_DIABETES</th>\n",
       "      <th>...</th>\n",
       "      <th>FIPS_COUNTY_CODE</th>\n",
       "      <th>TOTIPCOST</th>\n",
       "      <th>MEANIPCOST</th>\n",
       "      <th>TOTOPCOST</th>\n",
       "      <th>MEANOPCOST</th>\n",
       "      <th>ALLCOSTS</th>\n",
       "      <th>MEANCOSTS</th>\n",
       "      <th>TOTCHRONIC</th>\n",
       "      <th>VISITS_FLAG</th>\n",
       "      <th>PERCENT_COSTS</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0000438E79D01BEA</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>57.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>00010E7BEA69142C</td>\n",
       "      <td>71.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1620.0</td>\n",
       "      <td>180.000000</td>\n",
       "      <td>1620.0</td>\n",
       "      <td>45.000000</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0.000022</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>00015BF6509E1DF7</td>\n",
       "      <td>75.1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>...</td>\n",
       "      <td>119.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>25860.0</td>\n",
       "      <td>2873.333333</td>\n",
       "      <td>25860.0</td>\n",
       "      <td>478.888889</td>\n",
       "      <td>7.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0.000356</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>00018DD17736A661</td>\n",
       "      <td>73.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>101.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>6930.0</td>\n",
       "      <td>330.000000</td>\n",
       "      <td>6930.0</td>\n",
       "      <td>165.000000</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0.000095</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>000240D599ED789C</td>\n",
       "      <td>67.0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>...</td>\n",
       "      <td>35.0</td>\n",
       "      <td>461726.0</td>\n",
       "      <td>9190.888889</td>\n",
       "      <td>47330.0</td>\n",
       "      <td>2066.666667</td>\n",
       "      <td>509056.0</td>\n",
       "      <td>4939.888889</td>\n",
       "      <td>6.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0.007014</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>116334</th>\n",
       "      <td>FFFDFD377BF9EC59</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>11.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>116335</th>\n",
       "      <td>FFFF1E240FFD97D8</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>19.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>116336</th>\n",
       "      <td>FFFF58406F9882DD</td>\n",
       "      <td>69.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>...</td>\n",
       "      <td>469.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1230.0</td>\n",
       "      <td>136.666667</td>\n",
       "      <td>1230.0</td>\n",
       "      <td>22.777778</td>\n",
       "      <td>7.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0.000017</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>116337</th>\n",
       "      <td>FFFFCA5AFABA1CF6</td>\n",
       "      <td>69.0</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>...</td>\n",
       "      <td>59.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1100.0</td>\n",
       "      <td>183.333333</td>\n",
       "      <td>1100.0</td>\n",
       "      <td>91.666667</td>\n",
       "      <td>6.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0.000015</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>116338</th>\n",
       "      <td>FFFFF4859B6D7402</td>\n",
       "      <td>69.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>5.0</td>\n",
       "      <td>8068.0</td>\n",
       "      <td>896.444444</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>8068.0</td>\n",
       "      <td>448.222222</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0.000111</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>116339 rows × 61 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "             DESYNPUF_ID  MEAN_AGE  B_SEX  BENE_RACE_CD  B_ALZHDMTA  B_CHF  \\\n",
       "0       0000438E79D01BEA       NaN      1             1         0.0    0.0   \n",
       "1       00010E7BEA69142C      71.0      0             1         1.0    0.0   \n",
       "2       00015BF6509E1DF7      75.1      0             1         1.0    1.0   \n",
       "3       00018DD17736A661      73.0      0             1         0.0    0.0   \n",
       "4       000240D599ED789C      67.0      0             2         1.0    1.0   \n",
       "...                  ...       ...    ...           ...         ...    ...   \n",
       "116334  FFFDFD377BF9EC59       NaN      0             3         0.0    0.0   \n",
       "116335  FFFF1E240FFD97D8       NaN      0             1         0.0    0.0   \n",
       "116336  FFFF58406F9882DD      69.0      1             1         0.0    1.0   \n",
       "116337  FFFFCA5AFABA1CF6      69.0      1             2         0.0    1.0   \n",
       "116338  FFFFF4859B6D7402      69.0      1             1         0.0    0.0   \n",
       "\n",
       "        B_CNCR  B_COPD  B_DEPRESSN  B_DIABETES  ...  FIPS_COUNTY_CODE  \\\n",
       "0          0.0     0.0         0.0         0.0  ...              57.0   \n",
       "1          0.0     0.0         1.0         0.0  ...               3.0   \n",
       "2          0.0     1.0         0.0         1.0  ...             119.0   \n",
       "3          0.0     1.0         0.0         0.0  ...             101.0   \n",
       "4          0.0     0.0         0.0         1.0  ...              35.0   \n",
       "...        ...     ...         ...         ...  ...               ...   \n",
       "116334     0.0     0.0         0.0         0.0  ...              11.0   \n",
       "116335     0.0     0.0         0.0         0.0  ...              19.0   \n",
       "116336     0.0     1.0         1.0         1.0  ...             469.0   \n",
       "116337     0.0     0.0         1.0         1.0  ...              59.0   \n",
       "116338     0.0     0.0         1.0         0.0  ...               5.0   \n",
       "\n",
       "        TOTIPCOST   MEANIPCOST  TOTOPCOST   MEANOPCOST  ALLCOSTS    MEANCOSTS  \\\n",
       "0             0.0     0.000000        0.0     0.000000       0.0     0.000000   \n",
       "1             0.0     0.000000     1620.0   180.000000    1620.0    45.000000   \n",
       "2             0.0     0.000000    25860.0  2873.333333   25860.0   478.888889   \n",
       "3             0.0     0.000000     6930.0   330.000000    6930.0   165.000000   \n",
       "4        461726.0  9190.888889    47330.0  2066.666667  509056.0  4939.888889   \n",
       "...           ...          ...        ...          ...       ...          ...   \n",
       "116334        0.0     0.000000        0.0     0.000000       0.0     0.000000   \n",
       "116335        0.0     0.000000        0.0     0.000000       0.0     0.000000   \n",
       "116336        0.0     0.000000     1230.0   136.666667    1230.0    22.777778   \n",
       "116337        0.0     0.000000     1100.0   183.333333    1100.0    91.666667   \n",
       "116338     8068.0   896.444444        0.0     0.000000    8068.0   448.222222   \n",
       "\n",
       "        TOTCHRONIC  VISITS_FLAG  PERCENT_COSTS  \n",
       "0              0.0            0       0.000000  \n",
       "1              2.0            1       0.000022  \n",
       "2              7.0            1       0.000356  \n",
       "3              2.0            1       0.000095  \n",
       "4              6.0            1       0.007014  \n",
       "...            ...          ...            ...  \n",
       "116334         0.0            0       0.000000  \n",
       "116335         0.0            0       0.000000  \n",
       "116336         7.0            1       0.000017  \n",
       "116337         6.0            1       0.000015  \n",
       "116338         3.0            1       0.000111  \n",
       "\n",
       "[116339 rows x 61 columns]"
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cc_summary3 = cc_summary_all.copy()\n",
    "cc_summary3.reset_index(inplace=True)\n",
    "cc_summary3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [],
   "source": [
    "cc_county = cc_summary3.groupby([\"FIPS_STATE_CODE\", \"FIPS_COUNTY_CODE\"]).aggregate({\"DESYNPUF_ID\":\"count\",\n",
    "                                                                                    \"VISITS_FLAG\":\"sum\",\n",
    "                                                                                    \"MEAN_AGE\":\"mean\",\n",
    "                                                                                  \"B_SEX\":\"mean\",\n",
    "                                                                                  \"BENE_RACE_CD\":\"mean\",\n",
    "                                                                                  \"B_ALZHDMTA\":\"sum\",\n",
    "                                                                                  \"B_CHF\":\"sum\",\n",
    "                                                                                  \"B_CNCR\":\"sum\",\n",
    "                                                                                  \"B_COPD\":\"sum\",\n",
    "                                                                                  \"B_DEPRESSN\":\"sum\",\n",
    "                                                                                  \"B_DIABETES\":\"sum\",\n",
    "                                                                                  \"B_ISCHMCHT\":\"sum\",\n",
    "                                                                                  \"B_OSTEOPRS\":\"sum\",\n",
    "                                                                                  \"B_CHRNKIDN\":\"sum\",\n",
    "                                                                                  \"B_RA_OA\":\"sum\",\n",
    "                                                                                  \"B_STRKETIA\":\"sum\",\n",
    "                                                                                  \"B_ESRD\":\"sum\",\n",
    "                                                                                  \"MEAN_HI_CVRAGE_TOT_MONS\":\"mean\",\n",
    "                                                                                  \"MEAN_SMI_CVRAGE_TOT_MONS\":\"mean\",\n",
    "                                                                                  \"MEAN_HMO_CVRAGE_TOT_MONS\":\"mean\",\n",
    "                                                                                  \"MEAN_CVRG_MOS_NUM\":\"mean\",\n",
    "                                                                                  \"TOTAL_VISITS\":\"sum\",\n",
    "                                                                                    \"MEAN_TOTAL_VISITS\":\"mean\",\n",
    "                                                                                  \"TOTAL_CLAIMS\":\"sum\",\n",
    "                                                                                    \"MEAN_TOTAL_CLAIMS\":\"mean\",\n",
    "                                                                                  \"MEAN_NUM_PRVDRS\":\"mean\",\n",
    "                                                                                  \"TOT_CLM_PMT_AMT\":\"sum\",\n",
    "                                                                                    \"MEAN_CLM_PMT_AMT\":\"mean\",\n",
    "                                                                                  \"TOT_NCH_PRMRY_PYR_CLM_PD_AMT\":\"sum\",\n",
    "                                                                                  \"MEAN_NUM_AT_PHYSNS\":\"mean\",\n",
    "                                                                                  \"MEAN_NUM_OP_PHYSNS\":\"mean\",\n",
    "                                                                                  \"MEAN_NUM_OT_PHYSNS\":\"mean\",\n",
    "                                                                                   \"TOT_ADMTNG_ICD9_CDS\":\"sum\",\n",
    "                                                                                   \"TOTAL_INP_DAYS\":\"sum\",\n",
    "                                                                                   \"MEAN_INP_STAY\":\"mean\",\n",
    "                                                                                   \"MIN_INP_STAY\": \"min\",\n",
    "                                                                                   \"MAX_INP_STAY\": \"max\",\n",
    "                                                                                   \"TOT_CLM_DRG_CDS\":\"sum\",\n",
    "                                                                                    \"TOT_MEDREIMB_IP\":\"sum\",\n",
    "                                                                                    \"MEAN_MEDREIMB_IP\":\"mean\",\n",
    "                                                                                  \"TOT_BENRES_IP\":\"sum\",\n",
    "                                                                                    \"MEAN_BENRES_IP\":\"mean\",\n",
    "                                                                                  \"TOT_PPPYMT_IP\":\"sum\",\n",
    "                                                                                    \"MEAN_PPPYMT_IP\":\"mean\",\n",
    "                                                                                  \"TOT_MEDREIMB_OP\":\"sum\",\n",
    "                                                                                    \"MEAN_MEDREIMB_OP\":\"mean\",\n",
    "                                                                                  \"TOT_BENRES_OP\":\"sum\",\n",
    "                                                                                    \"MEAN_BENRES_OP\":\"mean\",\n",
    "                                                                                  \"TOT_PPPYMT_OP\":\"sum\",\n",
    "                                                                                    \"MEAN_PPPYMT_OP\":\"mean\",\n",
    "                                                                                  \"CBSA\":\"mean\",\n",
    "                                                                                  \"TOTCHRONIC\":[\"sum\",\"mean\"],\n",
    "                                                                                  \"TOTIPCOST\":\"sum\",\n",
    "                                                                                  \"MEANIPCOST\":\"mean\",\n",
    "                                                                                   \"TOTOPCOST\":\"sum\",\n",
    "                                                                                  \"MEANOPCOST\":\"mean\",\n",
    "                                                                                   \"ALLCOSTS\":\"sum\",\n",
    "                                                                                   \"MEANCOSTS\":\"mean\"})\n",
    "\n",
    "\n",
    "cc_county.columns = [\"BENE_COUNT\", \"BENE_USERS\", \"MEAN_AGE\", \"MEAN_SEX\", \"MEAN_RACE_CD\", \"ALZHDMTA_CASES\", \"CHF_CASES\", \n",
    "                     \"CNCR_CASES\", \"COPD_CASES\",\"DEPRESSN_CASES\", \"DIABETES_CASES\", \"ISCHMCHT_CASES\", \n",
    "                     \"OSTEOPRS_CASES\", \"CHRNKIDN_CASES\", \"RA_OA_CASES\",\"STRKETIA_CASES\", \"ESRD_CASES\", \n",
    "                     \"MEAN_HI_CVRAGE_TOT_MONS\", \"MEAN_SMI_CVRAGE_TOT_MONS\",\"MEAN_HMO_CVRAGE_TOT_MONS\", \n",
    "                     \"MEAN_CVRG_MOS_NUM\", \"TOTAL_VISITS\", \"MEAN_TOTAL_VISITS\",\"TOTAL_CLAIMS\",\"MEAN_TOTAL_CLAIMS\",\n",
    "                     \"MEAN_NUM_PRVDRS\", \"TOT_CLM_PMT_AMT\", \"MEAN_CLM_PMT_AMT\", \"TOT_NCH_PRMRY_PYR_CLM_PD_AMT\",\n",
    "                     \"MEAN_NUM_AT_PHYSNS\",\"MEAN_NUM_OP_PHYSNS\",\"MEAN_NUM_OT_PHYSNS\",\"TOT_ADMTNG_ICD9_CDS\",\n",
    "                     \"TOTAL_INP_DAYS\", \"MEAN_INP_STAY\", \"MIN_INP_STAY\", \"MAX_INP_STAY\",\n",
    "                     \"TOT_CLM_DRG_CDS\", \"TOT_MEDREIMB_IP\", \"MEAN_MEDREIMB_IP\", \"TOT_BENRES_IP\", \"MEAN_BENRES_IP\",\n",
    "                      \"TOT_PPPYMT_IP\", \"MEAN_PPPYMT_IP\", \"TOT_MEDREIMB_OP\", \"MEAN_MEDREIMB_OP\",\"TOT_BENRES_OP\",\n",
    "                     \"MEAN_BENRES_OP\",\"TOT_PPPYMT_OP\", \"MEAN_PPPYMT_OP\",\"CBSA\", \"TOTAL_CC_CASES\", \"MEAN_CC_CASES\", \n",
    "                     \"TOTIPCOST\",\"MEANIPCOST\",\"TOTOPCOST\", \"MEANOPCOST\",\"ALLCOSTS\", \"MEANCOSTS\"]\n",
    "\n",
    "C_TOTAL = cc_county[\"ALLCOSTS\"].sum()\n",
    "cc_county[\"PERCENT_COSTS\"] = cc_county[\"ALLCOSTS\"] / C_TOTAL * 100\n",
    "cc_county[\"USE_PROPORTION\"] = cc_county[\"BENE_USERS\"]/cc_county[\"BENE_COUNT\"]\n",
    "cc_county[\"MEAN_AGE\"] = cc_county[\"MEAN_AGE\"].round(decimals=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "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>BENE_COUNT</th>\n",
       "      <th>BENE_USERS</th>\n",
       "      <th>MEAN_AGE</th>\n",
       "      <th>MEAN_SEX</th>\n",
       "      <th>MEAN_RACE_CD</th>\n",
       "      <th>ALZHDMTA_CASES</th>\n",
       "      <th>CHF_CASES</th>\n",
       "      <th>CNCR_CASES</th>\n",
       "      <th>COPD_CASES</th>\n",
       "      <th>DEPRESSN_CASES</th>\n",
       "      <th>...</th>\n",
       "      <th>TOTAL_CC_CASES</th>\n",
       "      <th>MEAN_CC_CASES</th>\n",
       "      <th>TOTIPCOST</th>\n",
       "      <th>MEANIPCOST</th>\n",
       "      <th>TOTOPCOST</th>\n",
       "      <th>MEANOPCOST</th>\n",
       "      <th>ALLCOSTS</th>\n",
       "      <th>MEANCOSTS</th>\n",
       "      <th>PERCENT_COSTS</th>\n",
       "      <th>USE_PROPORTION</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>FIPS_STATE_CODE</th>\n",
       "      <th>FIPS_COUNTY_CODE</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"5\" valign=\"top\">1.0</th>\n",
       "      <th>1.0</th>\n",
       "      <td>16</td>\n",
       "      <td>13</td>\n",
       "      <td>65.4</td>\n",
       "      <td>0.187500</td>\n",
       "      <td>1.312500</td>\n",
       "      <td>7.0</td>\n",
       "      <td>12.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>7.0</td>\n",
       "      <td>...</td>\n",
       "      <td>79.0</td>\n",
       "      <td>4.937500</td>\n",
       "      <td>534188.0</td>\n",
       "      <td>551.458333</td>\n",
       "      <td>188690.0</td>\n",
       "      <td>672.916667</td>\n",
       "      <td>722878.0</td>\n",
       "      <td>387.881944</td>\n",
       "      <td>0.010039</td>\n",
       "      <td>0.812500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3.0</th>\n",
       "      <td>95</td>\n",
       "      <td>65</td>\n",
       "      <td>70.3</td>\n",
       "      <td>0.463158</td>\n",
       "      <td>1.378947</td>\n",
       "      <td>34.0</td>\n",
       "      <td>46.0</td>\n",
       "      <td>18.0</td>\n",
       "      <td>22.0</td>\n",
       "      <td>33.0</td>\n",
       "      <td>...</td>\n",
       "      <td>356.0</td>\n",
       "      <td>3.747368</td>\n",
       "      <td>5087450.0</td>\n",
       "      <td>919.843275</td>\n",
       "      <td>2569180.0</td>\n",
       "      <td>962.491228</td>\n",
       "      <td>7656630.0</td>\n",
       "      <td>620.336842</td>\n",
       "      <td>0.106333</td>\n",
       "      <td>0.684211</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5.0</th>\n",
       "      <td>14</td>\n",
       "      <td>12</td>\n",
       "      <td>72.4</td>\n",
       "      <td>0.642857</td>\n",
       "      <td>1.500000</td>\n",
       "      <td>4.0</td>\n",
       "      <td>7.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>...</td>\n",
       "      <td>49.0</td>\n",
       "      <td>3.500000</td>\n",
       "      <td>760096.0</td>\n",
       "      <td>1232.888889</td>\n",
       "      <td>174140.0</td>\n",
       "      <td>827.142857</td>\n",
       "      <td>934236.0</td>\n",
       "      <td>754.301587</td>\n",
       "      <td>0.012974</td>\n",
       "      <td>0.857143</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7.0</th>\n",
       "      <td>17</td>\n",
       "      <td>12</td>\n",
       "      <td>69.0</td>\n",
       "      <td>0.411765</td>\n",
       "      <td>1.294118</td>\n",
       "      <td>7.0</td>\n",
       "      <td>9.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>6.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>...</td>\n",
       "      <td>76.0</td>\n",
       "      <td>4.470588</td>\n",
       "      <td>467694.0</td>\n",
       "      <td>766.627451</td>\n",
       "      <td>322920.0</td>\n",
       "      <td>945.098039</td>\n",
       "      <td>790614.0</td>\n",
       "      <td>540.830065</td>\n",
       "      <td>0.010980</td>\n",
       "      <td>0.705882</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9.0</th>\n",
       "      <td>22</td>\n",
       "      <td>12</td>\n",
       "      <td>68.8</td>\n",
       "      <td>0.636364</td>\n",
       "      <td>1.409091</td>\n",
       "      <td>4.0</td>\n",
       "      <td>6.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>...</td>\n",
       "      <td>48.0</td>\n",
       "      <td>2.181818</td>\n",
       "      <td>946942.0</td>\n",
       "      <td>497.404040</td>\n",
       "      <td>149310.0</td>\n",
       "      <td>433.484848</td>\n",
       "      <td>1096252.0</td>\n",
       "      <td>320.949495</td>\n",
       "      <td>0.015224</td>\n",
       "      <td>0.545455</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"5\" valign=\"top\">56.0</th>\n",
       "      <th>37.0</th>\n",
       "      <td>34</td>\n",
       "      <td>17</td>\n",
       "      <td>72.9</td>\n",
       "      <td>0.529412</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>8.0</td>\n",
       "      <td>14.0</td>\n",
       "      <td>8.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>7.0</td>\n",
       "      <td>...</td>\n",
       "      <td>87.0</td>\n",
       "      <td>2.558824</td>\n",
       "      <td>945512.0</td>\n",
       "      <td>246.601307</td>\n",
       "      <td>768760.0</td>\n",
       "      <td>783.921569</td>\n",
       "      <td>1714272.0</td>\n",
       "      <td>253.954248</td>\n",
       "      <td>0.023807</td>\n",
       "      <td>0.500000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>39.0</th>\n",
       "      <td>13</td>\n",
       "      <td>5</td>\n",
       "      <td>70.5</td>\n",
       "      <td>0.538462</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>...</td>\n",
       "      <td>23.0</td>\n",
       "      <td>1.769231</td>\n",
       "      <td>30408.0</td>\n",
       "      <td>43.316239</td>\n",
       "      <td>78220.0</td>\n",
       "      <td>501.538462</td>\n",
       "      <td>108628.0</td>\n",
       "      <td>105.247863</td>\n",
       "      <td>0.001509</td>\n",
       "      <td>0.384615</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>41.0</th>\n",
       "      <td>18</td>\n",
       "      <td>6</td>\n",
       "      <td>72.0</td>\n",
       "      <td>0.500000</td>\n",
       "      <td>1.111111</td>\n",
       "      <td>4.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>...</td>\n",
       "      <td>29.0</td>\n",
       "      <td>1.611111</td>\n",
       "      <td>45340.0</td>\n",
       "      <td>55.975309</td>\n",
       "      <td>77190.0</td>\n",
       "      <td>258.888889</td>\n",
       "      <td>122530.0</td>\n",
       "      <td>71.135802</td>\n",
       "      <td>0.001702</td>\n",
       "      <td>0.333333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>43.0</th>\n",
       "      <td>8</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.625000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</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>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>45.0</th>\n",
       "      <td>15</td>\n",
       "      <td>2</td>\n",
       "      <td>75.5</td>\n",
       "      <td>0.600000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>7.0</td>\n",
       "      <td>0.466667</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>2000.0</td>\n",
       "      <td>44.444444</td>\n",
       "      <td>2000.0</td>\n",
       "      <td>7.407407</td>\n",
       "      <td>0.000028</td>\n",
       "      <td>0.133333</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>3011 rows × 61 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                  BENE_COUNT  BENE_USERS  MEAN_AGE  MEAN_SEX  \\\n",
       "FIPS_STATE_CODE FIPS_COUNTY_CODE                                               \n",
       "1.0             1.0                       16          13      65.4  0.187500   \n",
       "                3.0                       95          65      70.3  0.463158   \n",
       "                5.0                       14          12      72.4  0.642857   \n",
       "                7.0                       17          12      69.0  0.411765   \n",
       "                9.0                       22          12      68.8  0.636364   \n",
       "...                                      ...         ...       ...       ...   \n",
       "56.0            37.0                      34          17      72.9  0.529412   \n",
       "                39.0                      13           5      70.5  0.538462   \n",
       "                41.0                      18           6      72.0  0.500000   \n",
       "                43.0                       8           0       NaN  0.625000   \n",
       "                45.0                      15           2      75.5  0.600000   \n",
       "\n",
       "                                  MEAN_RACE_CD  ALZHDMTA_CASES  CHF_CASES  \\\n",
       "FIPS_STATE_CODE FIPS_COUNTY_CODE                                            \n",
       "1.0             1.0                   1.312500             7.0       12.0   \n",
       "                3.0                   1.378947            34.0       46.0   \n",
       "                5.0                   1.500000             4.0        7.0   \n",
       "                7.0                   1.294118             7.0        9.0   \n",
       "                9.0                   1.409091             4.0        6.0   \n",
       "...                                        ...             ...        ...   \n",
       "56.0            37.0                  1.000000             8.0       14.0   \n",
       "                39.0                  1.000000             2.0        3.0   \n",
       "                41.0                  1.111111             4.0        3.0   \n",
       "                43.0                  1.000000             0.0        0.0   \n",
       "                45.0                  1.000000             1.0        1.0   \n",
       "\n",
       "                                  CNCR_CASES  COPD_CASES  DEPRESSN_CASES  ...  \\\n",
       "FIPS_STATE_CODE FIPS_COUNTY_CODE                                          ...   \n",
       "1.0             1.0                      3.0         4.0             7.0  ...   \n",
       "                3.0                     18.0        22.0            33.0  ...   \n",
       "                5.0                      0.0         2.0             5.0  ...   \n",
       "                7.0                      2.0         6.0            10.0  ...   \n",
       "                9.0                      4.0         3.0             4.0  ...   \n",
       "...                                      ...         ...             ...  ...   \n",
       "56.0            37.0                     8.0         5.0             7.0  ...   \n",
       "                39.0                     3.0         0.0             2.0  ...   \n",
       "                41.0                     2.0         2.0             3.0  ...   \n",
       "                43.0                     0.0         0.0             0.0  ...   \n",
       "                45.0                     0.0         1.0             0.0  ...   \n",
       "\n",
       "                                  TOTAL_CC_CASES  MEAN_CC_CASES  TOTIPCOST  \\\n",
       "FIPS_STATE_CODE FIPS_COUNTY_CODE                                             \n",
       "1.0             1.0                         79.0       4.937500   534188.0   \n",
       "                3.0                        356.0       3.747368  5087450.0   \n",
       "                5.0                         49.0       3.500000   760096.0   \n",
       "                7.0                         76.0       4.470588   467694.0   \n",
       "                9.0                         48.0       2.181818   946942.0   \n",
       "...                                          ...            ...        ...   \n",
       "56.0            37.0                        87.0       2.558824   945512.0   \n",
       "                39.0                        23.0       1.769231    30408.0   \n",
       "                41.0                        29.0       1.611111    45340.0   \n",
       "                43.0                         0.0       0.000000        0.0   \n",
       "                45.0                         7.0       0.466667        0.0   \n",
       "\n",
       "                                   MEANIPCOST  TOTOPCOST  MEANOPCOST  \\\n",
       "FIPS_STATE_CODE FIPS_COUNTY_CODE                                       \n",
       "1.0             1.0                551.458333   188690.0  672.916667   \n",
       "                3.0                919.843275  2569180.0  962.491228   \n",
       "                5.0               1232.888889   174140.0  827.142857   \n",
       "                7.0                766.627451   322920.0  945.098039   \n",
       "                9.0                497.404040   149310.0  433.484848   \n",
       "...                                       ...        ...         ...   \n",
       "56.0            37.0               246.601307   768760.0  783.921569   \n",
       "                39.0                43.316239    78220.0  501.538462   \n",
       "                41.0                55.975309    77190.0  258.888889   \n",
       "                43.0                 0.000000        0.0    0.000000   \n",
       "                45.0                 0.000000     2000.0   44.444444   \n",
       "\n",
       "                                   ALLCOSTS   MEANCOSTS  PERCENT_COSTS  \\\n",
       "FIPS_STATE_CODE FIPS_COUNTY_CODE                                         \n",
       "1.0             1.0                722878.0  387.881944       0.010039   \n",
       "                3.0               7656630.0  620.336842       0.106333   \n",
       "                5.0                934236.0  754.301587       0.012974   \n",
       "                7.0                790614.0  540.830065       0.010980   \n",
       "                9.0               1096252.0  320.949495       0.015224   \n",
       "...                                     ...         ...            ...   \n",
       "56.0            37.0              1714272.0  253.954248       0.023807   \n",
       "                39.0               108628.0  105.247863       0.001509   \n",
       "                41.0               122530.0   71.135802       0.001702   \n",
       "                43.0                    0.0    0.000000       0.000000   \n",
       "                45.0                 2000.0    7.407407       0.000028   \n",
       "\n",
       "                                  USE_PROPORTION  \n",
       "FIPS_STATE_CODE FIPS_COUNTY_CODE                  \n",
       "1.0             1.0                     0.812500  \n",
       "                3.0                     0.684211  \n",
       "                5.0                     0.857143  \n",
       "                7.0                     0.705882  \n",
       "                9.0                     0.545455  \n",
       "...                                          ...  \n",
       "56.0            37.0                    0.500000  \n",
       "                39.0                    0.384615  \n",
       "                41.0                    0.333333  \n",
       "                43.0                    0.000000  \n",
       "                45.0                    0.133333  \n",
       "\n",
       "[3011 rows x 61 columns]"
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cc_county"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1080x360 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plot_copy = cc_county.reset_index()\n",
    "sb.set(rc={\"figure.figsize\":(15, 5)})\n",
    "sb.set_theme(style=\"whitegrid\")\n",
    "sb.barplot(x=\"FIPS_COUNTY_CODE\", y=\"USE_PROPORTION\", data=plot_copy, palette=\"mako\");"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "count    3011.000000\n",
       "mean       38.037197\n",
       "std        94.880771\n",
       "min         1.000000\n",
       "25%         6.000000\n",
       "50%        13.000000\n",
       "75%        32.000000\n",
       "max      2498.000000\n",
       "Name: BENE_COUNT, dtype: float64"
      ]
     },
     "execution_count": 43,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cc_county[\"BENE_COUNT\"].describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Representative Counties\n",
    "\n",
    "So, if we remove the counties with fewer than 50 beneficiaries, we have 490 counties.\n",
    "\n",
    "If we remove those with fewer than 30, we have 811 counties.\n",
    "\n",
    "There are 121 counties with ONE beneficiary.\n",
    "\n",
    "There are 693 counties with 5 OR FEWER beneficiaries, and 1267 counties with 10 OR FEWER.\n",
    "\n",
    "In some ways, these smaller counties are interesting.  Do they have so few beneficiaries because they are all very small?  Or, are they places where few people can access care, or where it is culturally normative not to?  Or, perhaps it is completely cost-prohibitive - even Medicare beneficiaries have to pay a premium or copays and while many very poor people would be eligible for Medicaid, in some states they might not be or it might be very difficult to get signed up or they just couldn't travel to the hospital or provider's office.\n",
    "\n",
    "Let me know what you think would be a good cut-off."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(490, 61)"
      ]
     },
     "execution_count": 44,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cc_reasonable = cc_county[(cc_county[\"BENE_COUNT\"]>49)]\n",
    "cc_reasonable.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='BENE_COUNT', ylabel='Count'>"
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1080x360 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sb.set(rc={\"figure.figsize\":(15, 5)})\n",
    "sb.set_theme(style=\"whitegrid\", palette=\"mako\")\n",
    "sb.histplot(x=cc_reasonable[\"BENE_COUNT\"], binwidth=10)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## My State :) \n",
    "\n",
    "There are a total of 10 counties in New Hampshire. The state is small, and some counties are sparsely populated.\n",
    "\n",
    "COOS County (7) is known to be a place where people have poor health and health care access.  Due to the constraint I tried on the # of beneficiaries per county (50), this one dropped off the list.\n",
    "\n",
    "Only the 5 most populous counties remain."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "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>FIPS_STATE_CODE</th>\n",
       "      <th>FIPS_COUNTY_CODE</th>\n",
       "      <th>BENE_COUNT</th>\n",
       "      <th>BENE_USERS</th>\n",
       "      <th>MEAN_AGE</th>\n",
       "      <th>MEAN_SEX</th>\n",
       "      <th>MEAN_RACE_CD</th>\n",
       "      <th>ALZHDMTA_CASES</th>\n",
       "      <th>CHF_CASES</th>\n",
       "      <th>CNCR_CASES</th>\n",
       "      <th>...</th>\n",
       "      <th>TOTAL_CC_CASES</th>\n",
       "      <th>MEAN_CC_CASES</th>\n",
       "      <th>TOTIPCOST</th>\n",
       "      <th>MEANIPCOST</th>\n",
       "      <th>TOTOPCOST</th>\n",
       "      <th>MEANOPCOST</th>\n",
       "      <th>ALLCOSTS</th>\n",
       "      <th>MEANCOSTS</th>\n",
       "      <th>PERCENT_COSTS</th>\n",
       "      <th>USE_PROPORTION</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>242</th>\n",
       "      <td>33.0</td>\n",
       "      <td>9.0</td>\n",
       "      <td>56</td>\n",
       "      <td>42</td>\n",
       "      <td>68.5</td>\n",
       "      <td>0.410714</td>\n",
       "      <td>1.089286</td>\n",
       "      <td>16.0</td>\n",
       "      <td>27.0</td>\n",
       "      <td>9.0</td>\n",
       "      <td>...</td>\n",
       "      <td>219.0</td>\n",
       "      <td>3.910714</td>\n",
       "      <td>1347266.0</td>\n",
       "      <td>617.706349</td>\n",
       "      <td>412150.0</td>\n",
       "      <td>489.464286</td>\n",
       "      <td>1759416.0</td>\n",
       "      <td>390.743056</td>\n",
       "      <td>0.024434</td>\n",
       "      <td>0.750000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>243</th>\n",
       "      <td>33.0</td>\n",
       "      <td>11.0</td>\n",
       "      <td>167</td>\n",
       "      <td>120</td>\n",
       "      <td>72.0</td>\n",
       "      <td>0.449102</td>\n",
       "      <td>1.005988</td>\n",
       "      <td>69.0</td>\n",
       "      <td>83.0</td>\n",
       "      <td>20.0</td>\n",
       "      <td>...</td>\n",
       "      <td>629.0</td>\n",
       "      <td>3.766467</td>\n",
       "      <td>4722608.0</td>\n",
       "      <td>542.347305</td>\n",
       "      <td>2705830.0</td>\n",
       "      <td>712.395210</td>\n",
       "      <td>7428438.0</td>\n",
       "      <td>391.386560</td>\n",
       "      <td>0.103164</td>\n",
       "      <td>0.718563</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>244</th>\n",
       "      <td>33.0</td>\n",
       "      <td>13.0</td>\n",
       "      <td>69</td>\n",
       "      <td>51</td>\n",
       "      <td>75.0</td>\n",
       "      <td>0.579710</td>\n",
       "      <td>1.014493</td>\n",
       "      <td>32.0</td>\n",
       "      <td>33.0</td>\n",
       "      <td>16.0</td>\n",
       "      <td>...</td>\n",
       "      <td>268.0</td>\n",
       "      <td>3.884058</td>\n",
       "      <td>2521050.0</td>\n",
       "      <td>511.017713</td>\n",
       "      <td>1340120.0</td>\n",
       "      <td>797.729469</td>\n",
       "      <td>3861170.0</td>\n",
       "      <td>390.847021</td>\n",
       "      <td>0.053623</td>\n",
       "      <td>0.739130</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>245</th>\n",
       "      <td>33.0</td>\n",
       "      <td>15.0</td>\n",
       "      <td>128</td>\n",
       "      <td>89</td>\n",
       "      <td>73.7</td>\n",
       "      <td>0.445312</td>\n",
       "      <td>1.031250</td>\n",
       "      <td>53.0</td>\n",
       "      <td>59.0</td>\n",
       "      <td>8.0</td>\n",
       "      <td>...</td>\n",
       "      <td>478.0</td>\n",
       "      <td>3.734375</td>\n",
       "      <td>2744210.0</td>\n",
       "      <td>527.986111</td>\n",
       "      <td>1234680.0</td>\n",
       "      <td>534.739583</td>\n",
       "      <td>3978890.0</td>\n",
       "      <td>353.116319</td>\n",
       "      <td>0.055258</td>\n",
       "      <td>0.695312</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>246</th>\n",
       "      <td>33.0</td>\n",
       "      <td>17.0</td>\n",
       "      <td>58</td>\n",
       "      <td>42</td>\n",
       "      <td>71.8</td>\n",
       "      <td>0.568966</td>\n",
       "      <td>1.068966</td>\n",
       "      <td>20.0</td>\n",
       "      <td>33.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>...</td>\n",
       "      <td>239.0</td>\n",
       "      <td>4.120690</td>\n",
       "      <td>2291728.0</td>\n",
       "      <td>810.394636</td>\n",
       "      <td>921030.0</td>\n",
       "      <td>736.551724</td>\n",
       "      <td>3212758.0</td>\n",
       "      <td>527.955939</td>\n",
       "      <td>0.044618</td>\n",
       "      <td>0.724138</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 63 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     FIPS_STATE_CODE  FIPS_COUNTY_CODE  BENE_COUNT  BENE_USERS  MEAN_AGE  \\\n",
       "242             33.0               9.0          56          42      68.5   \n",
       "243             33.0              11.0         167         120      72.0   \n",
       "244             33.0              13.0          69          51      75.0   \n",
       "245             33.0              15.0         128          89      73.7   \n",
       "246             33.0              17.0          58          42      71.8   \n",
       "\n",
       "     MEAN_SEX  MEAN_RACE_CD  ALZHDMTA_CASES  CHF_CASES  CNCR_CASES  ...  \\\n",
       "242  0.410714      1.089286            16.0       27.0         9.0  ...   \n",
       "243  0.449102      1.005988            69.0       83.0        20.0  ...   \n",
       "244  0.579710      1.014493            32.0       33.0        16.0  ...   \n",
       "245  0.445312      1.031250            53.0       59.0         8.0  ...   \n",
       "246  0.568966      1.068966            20.0       33.0        10.0  ...   \n",
       "\n",
       "     TOTAL_CC_CASES  MEAN_CC_CASES  TOTIPCOST  MEANIPCOST  TOTOPCOST  \\\n",
       "242           219.0       3.910714  1347266.0  617.706349   412150.0   \n",
       "243           629.0       3.766467  4722608.0  542.347305  2705830.0   \n",
       "244           268.0       3.884058  2521050.0  511.017713  1340120.0   \n",
       "245           478.0       3.734375  2744210.0  527.986111  1234680.0   \n",
       "246           239.0       4.120690  2291728.0  810.394636   921030.0   \n",
       "\n",
       "     MEANOPCOST   ALLCOSTS   MEANCOSTS  PERCENT_COSTS  USE_PROPORTION  \n",
       "242  489.464286  1759416.0  390.743056       0.024434        0.750000  \n",
       "243  712.395210  7428438.0  391.386560       0.103164        0.718563  \n",
       "244  797.729469  3861170.0  390.847021       0.053623        0.739130  \n",
       "245  534.739583  3978890.0  353.116319       0.055258        0.695312  \n",
       "246  736.551724  3212758.0  527.955939       0.044618        0.724138  \n",
       "\n",
       "[5 rows x 63 columns]"
      ]
     },
     "execution_count": 48,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "r = cc_reasonable.reset_index()\n",
    "r[r[\"FIPS_STATE_CODE\"] == 33]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "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>FIPS_STATE_CODE</th>\n",
       "      <th>FIPS_COUNTY_CODE</th>\n",
       "      <th>BENE_COUNT</th>\n",
       "      <th>BENE_USERS</th>\n",
       "      <th>MEAN_AGE</th>\n",
       "      <th>MEAN_SEX</th>\n",
       "      <th>MEAN_RACE_CD</th>\n",
       "      <th>ALZHDMTA_CASES</th>\n",
       "      <th>CHF_CASES</th>\n",
       "      <th>CNCR_CASES</th>\n",
       "      <th>...</th>\n",
       "      <th>TOTAL_CC_CASES</th>\n",
       "      <th>MEAN_CC_CASES</th>\n",
       "      <th>TOTIPCOST</th>\n",
       "      <th>MEANIPCOST</th>\n",
       "      <th>TOTOPCOST</th>\n",
       "      <th>MEANOPCOST</th>\n",
       "      <th>ALLCOSTS</th>\n",
       "      <th>MEANCOSTS</th>\n",
       "      <th>PERCENT_COSTS</th>\n",
       "      <th>USE_PROPORTION</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1685</th>\n",
       "      <td>33.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>47</td>\n",
       "      <td>36</td>\n",
       "      <td>72.7</td>\n",
       "      <td>0.446809</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>21.0</td>\n",
       "      <td>23.0</td>\n",
       "      <td>8.0</td>\n",
       "      <td>...</td>\n",
       "      <td>204.0</td>\n",
       "      <td>4.340426</td>\n",
       "      <td>1916552.0</td>\n",
       "      <td>576.482270</td>\n",
       "      <td>1220230.0</td>\n",
       "      <td>1015.319149</td>\n",
       "      <td>3136782.0</td>\n",
       "      <td>461.550827</td>\n",
       "      <td>0.043563</td>\n",
       "      <td>0.765957</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1686</th>\n",
       "      <td>33.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>31</td>\n",
       "      <td>22</td>\n",
       "      <td>71.6</td>\n",
       "      <td>0.612903</td>\n",
       "      <td>1.032258</td>\n",
       "      <td>12.0</td>\n",
       "      <td>15.0</td>\n",
       "      <td>6.0</td>\n",
       "      <td>...</td>\n",
       "      <td>117.0</td>\n",
       "      <td>3.774194</td>\n",
       "      <td>1148632.0</td>\n",
       "      <td>719.784946</td>\n",
       "      <td>366640.0</td>\n",
       "      <td>580.752688</td>\n",
       "      <td>1515272.0</td>\n",
       "      <td>456.684588</td>\n",
       "      <td>0.021044</td>\n",
       "      <td>0.709677</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1687</th>\n",
       "      <td>33.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>41</td>\n",
       "      <td>32</td>\n",
       "      <td>71.9</td>\n",
       "      <td>0.634146</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>11.0</td>\n",
       "      <td>23.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>...</td>\n",
       "      <td>168.0</td>\n",
       "      <td>4.097561</td>\n",
       "      <td>1248592.0</td>\n",
       "      <td>621.653117</td>\n",
       "      <td>531940.0</td>\n",
       "      <td>656.585366</td>\n",
       "      <td>1780532.0</td>\n",
       "      <td>420.257453</td>\n",
       "      <td>0.024728</td>\n",
       "      <td>0.780488</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1688</th>\n",
       "      <td>33.0</td>\n",
       "      <td>7.0</td>\n",
       "      <td>27</td>\n",
       "      <td>22</td>\n",
       "      <td>73.6</td>\n",
       "      <td>0.481481</td>\n",
       "      <td>1.111111</td>\n",
       "      <td>12.0</td>\n",
       "      <td>17.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>...</td>\n",
       "      <td>108.0</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>410116.0</td>\n",
       "      <td>300.230453</td>\n",
       "      <td>259140.0</td>\n",
       "      <td>631.604938</td>\n",
       "      <td>669256.0</td>\n",
       "      <td>255.382716</td>\n",
       "      <td>0.009294</td>\n",
       "      <td>0.814815</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1689</th>\n",
       "      <td>33.0</td>\n",
       "      <td>9.0</td>\n",
       "      <td>56</td>\n",
       "      <td>42</td>\n",
       "      <td>68.5</td>\n",
       "      <td>0.410714</td>\n",
       "      <td>1.089286</td>\n",
       "      <td>16.0</td>\n",
       "      <td>27.0</td>\n",
       "      <td>9.0</td>\n",
       "      <td>...</td>\n",
       "      <td>219.0</td>\n",
       "      <td>3.910714</td>\n",
       "      <td>1347266.0</td>\n",
       "      <td>617.706349</td>\n",
       "      <td>412150.0</td>\n",
       "      <td>489.464286</td>\n",
       "      <td>1759416.0</td>\n",
       "      <td>390.743056</td>\n",
       "      <td>0.024434</td>\n",
       "      <td>0.750000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1690</th>\n",
       "      <td>33.0</td>\n",
       "      <td>11.0</td>\n",
       "      <td>167</td>\n",
       "      <td>120</td>\n",
       "      <td>72.0</td>\n",
       "      <td>0.449102</td>\n",
       "      <td>1.005988</td>\n",
       "      <td>69.0</td>\n",
       "      <td>83.0</td>\n",
       "      <td>20.0</td>\n",
       "      <td>...</td>\n",
       "      <td>629.0</td>\n",
       "      <td>3.766467</td>\n",
       "      <td>4722608.0</td>\n",
       "      <td>542.347305</td>\n",
       "      <td>2705830.0</td>\n",
       "      <td>712.395210</td>\n",
       "      <td>7428438.0</td>\n",
       "      <td>391.386560</td>\n",
       "      <td>0.103164</td>\n",
       "      <td>0.718563</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1691</th>\n",
       "      <td>33.0</td>\n",
       "      <td>13.0</td>\n",
       "      <td>69</td>\n",
       "      <td>51</td>\n",
       "      <td>75.0</td>\n",
       "      <td>0.579710</td>\n",
       "      <td>1.014493</td>\n",
       "      <td>32.0</td>\n",
       "      <td>33.0</td>\n",
       "      <td>16.0</td>\n",
       "      <td>...</td>\n",
       "      <td>268.0</td>\n",
       "      <td>3.884058</td>\n",
       "      <td>2521050.0</td>\n",
       "      <td>511.017713</td>\n",
       "      <td>1340120.0</td>\n",
       "      <td>797.729469</td>\n",
       "      <td>3861170.0</td>\n",
       "      <td>390.847021</td>\n",
       "      <td>0.053623</td>\n",
       "      <td>0.739130</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1692</th>\n",
       "      <td>33.0</td>\n",
       "      <td>15.0</td>\n",
       "      <td>128</td>\n",
       "      <td>89</td>\n",
       "      <td>73.7</td>\n",
       "      <td>0.445312</td>\n",
       "      <td>1.031250</td>\n",
       "      <td>53.0</td>\n",
       "      <td>59.0</td>\n",
       "      <td>8.0</td>\n",
       "      <td>...</td>\n",
       "      <td>478.0</td>\n",
       "      <td>3.734375</td>\n",
       "      <td>2744210.0</td>\n",
       "      <td>527.986111</td>\n",
       "      <td>1234680.0</td>\n",
       "      <td>534.739583</td>\n",
       "      <td>3978890.0</td>\n",
       "      <td>353.116319</td>\n",
       "      <td>0.055258</td>\n",
       "      <td>0.695312</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1693</th>\n",
       "      <td>33.0</td>\n",
       "      <td>17.0</td>\n",
       "      <td>58</td>\n",
       "      <td>42</td>\n",
       "      <td>71.8</td>\n",
       "      <td>0.568966</td>\n",
       "      <td>1.068966</td>\n",
       "      <td>20.0</td>\n",
       "      <td>33.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>...</td>\n",
       "      <td>239.0</td>\n",
       "      <td>4.120690</td>\n",
       "      <td>2291728.0</td>\n",
       "      <td>810.394636</td>\n",
       "      <td>921030.0</td>\n",
       "      <td>736.551724</td>\n",
       "      <td>3212758.0</td>\n",
       "      <td>527.955939</td>\n",
       "      <td>0.044618</td>\n",
       "      <td>0.724138</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1694</th>\n",
       "      <td>33.0</td>\n",
       "      <td>19.0</td>\n",
       "      <td>20</td>\n",
       "      <td>14</td>\n",
       "      <td>72.9</td>\n",
       "      <td>0.350000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>3.0</td>\n",
       "      <td>8.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>...</td>\n",
       "      <td>49.0</td>\n",
       "      <td>2.450000</td>\n",
       "      <td>133718.0</td>\n",
       "      <td>296.544444</td>\n",
       "      <td>265790.0</td>\n",
       "      <td>736.833333</td>\n",
       "      <td>399508.0</td>\n",
       "      <td>275.855556</td>\n",
       "      <td>0.005548</td>\n",
       "      <td>0.700000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>10 rows × 63 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      FIPS_STATE_CODE  FIPS_COUNTY_CODE  BENE_COUNT  BENE_USERS  MEAN_AGE  \\\n",
       "1685             33.0               1.0          47          36      72.7   \n",
       "1686             33.0               3.0          31          22      71.6   \n",
       "1687             33.0               5.0          41          32      71.9   \n",
       "1688             33.0               7.0          27          22      73.6   \n",
       "1689             33.0               9.0          56          42      68.5   \n",
       "1690             33.0              11.0         167         120      72.0   \n",
       "1691             33.0              13.0          69          51      75.0   \n",
       "1692             33.0              15.0         128          89      73.7   \n",
       "1693             33.0              17.0          58          42      71.8   \n",
       "1694             33.0              19.0          20          14      72.9   \n",
       "\n",
       "      MEAN_SEX  MEAN_RACE_CD  ALZHDMTA_CASES  CHF_CASES  CNCR_CASES  ...  \\\n",
       "1685  0.446809      1.000000            21.0       23.0         8.0  ...   \n",
       "1686  0.612903      1.032258            12.0       15.0         6.0  ...   \n",
       "1687  0.634146      1.000000            11.0       23.0         5.0  ...   \n",
       "1688  0.481481      1.111111            12.0       17.0         4.0  ...   \n",
       "1689  0.410714      1.089286            16.0       27.0         9.0  ...   \n",
       "1690  0.449102      1.005988            69.0       83.0        20.0  ...   \n",
       "1691  0.579710      1.014493            32.0       33.0        16.0  ...   \n",
       "1692  0.445312      1.031250            53.0       59.0         8.0  ...   \n",
       "1693  0.568966      1.068966            20.0       33.0        10.0  ...   \n",
       "1694  0.350000      1.000000             3.0        8.0         0.0  ...   \n",
       "\n",
       "      TOTAL_CC_CASES  MEAN_CC_CASES  TOTIPCOST  MEANIPCOST  TOTOPCOST  \\\n",
       "1685           204.0       4.340426  1916552.0  576.482270  1220230.0   \n",
       "1686           117.0       3.774194  1148632.0  719.784946   366640.0   \n",
       "1687           168.0       4.097561  1248592.0  621.653117   531940.0   \n",
       "1688           108.0       4.000000   410116.0  300.230453   259140.0   \n",
       "1689           219.0       3.910714  1347266.0  617.706349   412150.0   \n",
       "1690           629.0       3.766467  4722608.0  542.347305  2705830.0   \n",
       "1691           268.0       3.884058  2521050.0  511.017713  1340120.0   \n",
       "1692           478.0       3.734375  2744210.0  527.986111  1234680.0   \n",
       "1693           239.0       4.120690  2291728.0  810.394636   921030.0   \n",
       "1694            49.0       2.450000   133718.0  296.544444   265790.0   \n",
       "\n",
       "       MEANOPCOST   ALLCOSTS   MEANCOSTS  PERCENT_COSTS  USE_PROPORTION  \n",
       "1685  1015.319149  3136782.0  461.550827       0.043563        0.765957  \n",
       "1686   580.752688  1515272.0  456.684588       0.021044        0.709677  \n",
       "1687   656.585366  1780532.0  420.257453       0.024728        0.780488  \n",
       "1688   631.604938   669256.0  255.382716       0.009294        0.814815  \n",
       "1689   489.464286  1759416.0  390.743056       0.024434        0.750000  \n",
       "1690   712.395210  7428438.0  391.386560       0.103164        0.718563  \n",
       "1691   797.729469  3861170.0  390.847021       0.053623        0.739130  \n",
       "1692   534.739583  3978890.0  353.116319       0.055258        0.695312  \n",
       "1693   736.551724  3212758.0  527.955939       0.044618        0.724138  \n",
       "1694   736.833333   399508.0  275.855556       0.005548        0.700000  \n",
       "\n",
       "[10 rows x 63 columns]"
      ]
     },
     "execution_count": 49,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "r = cc_county.reset_index()\n",
    "r[r[\"FIPS_STATE_CODE\"] == 33]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {},
   "outputs": [],
   "source": [
    "cc_county.to_csv(\"/home/kylier/python/DS/data/PUF/PUF_COUNTY_SUMMARY.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {},
   "outputs": [],
   "source": [
    "cc_reasonable.to_csv(\"/home/kylier/python/DS/data/PUF/PUF_COUNTY_SUMMARY_50.csv\")"
   ]
  },
  {
   "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": "3.8.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}