cms_user_manual_transformation_and_analysis.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "a130c67d",
   "metadata": {},
   "source": [
    "# Use the code below to load the data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "e135a293",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2023-04-05T15:34:00.204789Z",
     "start_time": "2023-04-05T15:33:59.539785Z"
    }
   },
   "outputs": [],
   "source": [
    "# import pandas library\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "7134807b",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2023-04-05T15:34:34.317042Z",
     "start_time": "2023-04-05T15:34:00.206789Z"
    }
   },
   "outputs": [],
   "source": [
    "# load data\n",
    "# note: Each file except for dme and beneficiary_YYYY contain mixed data types. \n",
    "# to prevent DtypeWarning, specify dtype option on import or set low_memory=False as shown below.\n",
    "\n",
    "synthetic_bene_df = pd.read_csv('data/beneficiary_2022.csv', sep=\"|\", low_memory=False)\n",
    "synthetic_inpatient_df = pd.read_csv('data/inpatient.csv',  sep=\"|\", low_memory=False)\n",
    "synthetic_outpatient_df = pd.read_csv('data/outpatient.csv', sep=\"|\",low_memory=False)\n",
    "synthetic_carrier_df = pd.read_csv('data/carrier.csv', sep=\"|\", low_memory=False)\n",
    "synthetic_hha_df = pd.read_csv('data/hha.csv', sep=\"|\", low_memory=False)\n",
    "synthetic_hospice_df = pd.read_csv('data/hospice.csv', sep=\"|\", low_memory=False)\n",
    "synthetic_hospice_df = pd.read_csv('data/dme.csv', sep=\"|\", low_memory=False)\n",
    "synthetic_snf_df = pd.read_csv('data/snf.csv', sep=\"|\", low_memory=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9fdcbc2f",
   "metadata": {},
   "source": [
    "______________________________________________________________________________________________________________________"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "46184f52",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2023-04-05T15:34:34.599015Z",
     "start_time": "2023-04-05T15:34:34.320010Z"
    }
   },
   "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>BENE_ID</th>\n",
       "      <th>CLM_ID</th>\n",
       "      <th>CLM_ADMSN_DT</th>\n",
       "      <th>NCH_BENE_DSCHRG_DT</th>\n",
       "      <th>PRNCPAL_DGNS_CD</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>-10000010254618</td>\n",
       "      <td>-10000930037831</td>\n",
       "      <td>25-Mar-2015</td>\n",
       "      <td>25-Mar-2015</td>\n",
       "      <td>S134XX</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>-10000010254653</td>\n",
       "      <td>-10000930038030</td>\n",
       "      <td>24-Sep-2015</td>\n",
       "      <td>24-Sep-2015</td>\n",
       "      <td>Z3480</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>-10000010254653</td>\n",
       "      <td>-10000930038031</td>\n",
       "      <td>09-May-2017</td>\n",
       "      <td>10-May-2017</td>\n",
       "      <td>T7432X</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>-10000010254656</td>\n",
       "      <td>-10000930038162</td>\n",
       "      <td>14-Jan-2017</td>\n",
       "      <td>14-Jan-2017</td>\n",
       "      <td>S8290X</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>-10000010254656</td>\n",
       "      <td>-10000930038162</td>\n",
       "      <td>14-Jan-2017</td>\n",
       "      <td>14-Jan-2017</td>\n",
       "      <td>S8290X</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>58061</th>\n",
       "      <td>-10000010288008</td>\n",
       "      <td>-10000931485965</td>\n",
       "      <td>08-Jan-2020</td>\n",
       "      <td>14-Jan-2020</td>\n",
       "      <td>T50901A</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>58062</th>\n",
       "      <td>-10000010288008</td>\n",
       "      <td>-10000931485967</td>\n",
       "      <td>23-Oct-2020</td>\n",
       "      <td>23-Oct-2020</td>\n",
       "      <td>T50901A</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>58063</th>\n",
       "      <td>-10000010288008</td>\n",
       "      <td>-10000931485969</td>\n",
       "      <td>22-Aug-2021</td>\n",
       "      <td>23-Aug-2021</td>\n",
       "      <td>T50901A</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>58064</th>\n",
       "      <td>-10000010288008</td>\n",
       "      <td>-10000931485971</td>\n",
       "      <td>13-Sep-2021</td>\n",
       "      <td>16-Sep-2021</td>\n",
       "      <td>T50901A</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>58065</th>\n",
       "      <td>-10000010288010</td>\n",
       "      <td>-10000931486024</td>\n",
       "      <td>11-Jun-2017</td>\n",
       "      <td>11-Jun-2017</td>\n",
       "      <td>S93409</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>58066 rows × 5 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "              BENE_ID          CLM_ID CLM_ADMSN_DT NCH_BENE_DSCHRG_DT  \\\n",
       "0     -10000010254618 -10000930037831  25-Mar-2015        25-Mar-2015   \n",
       "1     -10000010254653 -10000930038030  24-Sep-2015        24-Sep-2015   \n",
       "2     -10000010254653 -10000930038031  09-May-2017        10-May-2017   \n",
       "3     -10000010254656 -10000930038162  14-Jan-2017        14-Jan-2017   \n",
       "4     -10000010254656 -10000930038162  14-Jan-2017        14-Jan-2017   \n",
       "...               ...             ...          ...                ...   \n",
       "58061 -10000010288008 -10000931485965  08-Jan-2020        14-Jan-2020   \n",
       "58062 -10000010288008 -10000931485967  23-Oct-2020        23-Oct-2020   \n",
       "58063 -10000010288008 -10000931485969  22-Aug-2021        23-Aug-2021   \n",
       "58064 -10000010288008 -10000931485971  13-Sep-2021        16-Sep-2021   \n",
       "58065 -10000010288010 -10000931486024  11-Jun-2017        11-Jun-2017   \n",
       "\n",
       "      PRNCPAL_DGNS_CD  \n",
       "0              S134XX  \n",
       "1               Z3480  \n",
       "2              T7432X  \n",
       "3              S8290X  \n",
       "4              S8290X  \n",
       "...               ...  \n",
       "58061         T50901A  \n",
       "58062         T50901A  \n",
       "58063         T50901A  \n",
       "58064         T50901A  \n",
       "58065          S93409  \n",
       "\n",
       "[58066 rows x 5 columns]"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# note: Each file consists of many columns. \n",
    "# if you would like to limit the columns loaded into a particular dataframe, input the 'usecols' parameter argument which is specific to the read_csv function in the pandas library.\n",
    "\n",
    "synthetic_inpatient_df_spec_cols = pd.read_csv('data/inpatient.csv', \n",
    "usecols=['BENE_ID','CLM_ID','CLM_ADMSN_DT','NCH_BENE_DSCHRG_DT','PRNCPAL_DGNS_CD'], \n",
    "sep=\"|\")\n",
    "\n",
    "synthetic_inpatient_df_spec_cols"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.9.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}