Skip to content

Instantly share code, notes, and snippets.

@vkumar8282

vkumar8282/texas_pudf_part1_importing.ipynb

Last active February 2, 2019 03:09
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save vkumar8282/c3a89d264953751fc2e0d49084771ad8 to your computer and use it in GitHub Desktop.
Save vkumar8282/c3a89d264953751fc2e0d49084771ad8 to your computer and use it in GitHub Desktop.
Download ZIP
Importing the Texas Public Use Data File into Jupyter Notebook
Display the source blob
Display the rendered blob
Raw
texas_pudf_part1_importing.ipynb
{
"cells": [
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"\n",
"data = pd.read_csv(\n",
" \"C:\\\\Users\\\\Vikas\\\\PUDF_base1_1q2012_tab.txt\",\n",
" delimiter=\"\\t\",\n",
" header=0,\n",
" dtype=\"str\"\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>RECORD_ID</th>\n",
" <th>DISCHARGE</th>\n",
" <th>THCIC_ID</th>\n",
" <th>PROVIDER_NAME</th>\n",
" <th>TYPE_OF_ADMISSION</th>\n",
" <th>SOURCE_OF_ADMISSION</th>\n",
" <th>SPEC_UNIT_1</th>\n",
" <th>SPEC_UNIT_2</th>\n",
" <th>SPEC_UNIT_3</th>\n",
" <th>SPEC_UNIT_4</th>\n",
" <th>...</th>\n",
" <th>APR_DRG</th>\n",
" <th>RISK_MORTALITY</th>\n",
" <th>ILLNESS_SEVERITY</th>\n",
" <th>APR_GROUPER_VERSION_NBR</th>\n",
" <th>APR_GROUPER_ERROR_CODE</th>\n",
" <th>ATTENDING_PHYSICIAN_UNIF_ID</th>\n",
" <th>OPERATING_PHYSICIAN_UNIF_ID</th>\n",
" <th>ENCOUNTER_INDICATOR</th>\n",
" <th>CERT_STATUS</th>\n",
" <th>FILLER_SPACE</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>120120107482</td>\n",
" <td>2012Q1</td>\n",
" <td>000100</td>\n",
" <td>Austin State Hospital</td>\n",
" <td>2</td>\n",
" <td>8</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>052</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>07290</td>\n",
" <td>00</td>\n",
" <td>9999999998</td>\n",
" <td>NaN</td>\n",
" <td>01</td>\n",
" <td>2</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>120120107487</td>\n",
" <td>2012Q1</td>\n",
" <td>000100</td>\n",
" <td>Austin State Hospital</td>\n",
" <td>2</td>\n",
" <td>8</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>756</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>07290</td>\n",
" <td>00</td>\n",
" <td>9999999998</td>\n",
" <td>NaN</td>\n",
" <td>01</td>\n",
" <td>2</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>120120107568</td>\n",
" <td>2012Q1</td>\n",
" <td>000100</td>\n",
" <td>Austin State Hospital</td>\n",
" <td>2</td>\n",
" <td>8</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>754</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>07290</td>\n",
" <td>00</td>\n",
" <td>9999999998</td>\n",
" <td>NaN</td>\n",
" <td>01</td>\n",
" <td>2</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>120120107381</td>\n",
" <td>2012Q1</td>\n",
" <td>000100</td>\n",
" <td>Austin State Hospital</td>\n",
" <td>2</td>\n",
" <td>8</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>754</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>07290</td>\n",
" <td>00</td>\n",
" <td>9999999998</td>\n",
" <td>NaN</td>\n",
" <td>01</td>\n",
" <td>2</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>120120107410</td>\n",
" <td>2012Q1</td>\n",
" <td>000100</td>\n",
" <td>Austin State Hospital</td>\n",
" <td>2</td>\n",
" <td>8</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>754</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>07290</td>\n",
" <td>00</td>\n",
" <td>9999999998</td>\n",
" <td>NaN</td>\n",
" <td>01</td>\n",
" <td>2</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 194 columns</p>\n",
"</div>"
],
"text/plain": [
" RECORD_ID DISCHARGE THCIC_ID PROVIDER_NAME TYPE_OF_ADMISSION \\\n",
"0 120120107482 2012Q1 000100 Austin State Hospital 2 \n",
"1 120120107487 2012Q1 000100 Austin State Hospital 2 \n",
"2 120120107568 2012Q1 000100 Austin State Hospital 2 \n",
"3 120120107381 2012Q1 000100 Austin State Hospital 2 \n",
"4 120120107410 2012Q1 000100 Austin State Hospital 2 \n",
"\n",
" SOURCE_OF_ADMISSION SPEC_UNIT_1 SPEC_UNIT_2 SPEC_UNIT_3 SPEC_UNIT_4 \\\n",
"0 8 NaN NaN NaN NaN \n",
"1 8 NaN NaN NaN NaN \n",
"2 8 NaN NaN NaN NaN \n",
"3 8 NaN NaN NaN NaN \n",
"4 8 NaN NaN NaN NaN \n",
"\n",
" ... APR_DRG RISK_MORTALITY ILLNESS_SEVERITY \\\n",
"0 ... 052 1 1 \n",
"1 ... 756 1 1 \n",
"2 ... 754 1 1 \n",
"3 ... 754 1 1 \n",
"4 ... 754 1 1 \n",
"\n",
" APR_GROUPER_VERSION_NBR APR_GROUPER_ERROR_CODE ATTENDING_PHYSICIAN_UNIF_ID \\\n",
"0 07290 00 9999999998 \n",
"1 07290 00 9999999998 \n",
"2 07290 00 9999999998 \n",
"3 07290 00 9999999998 \n",
"4 07290 00 9999999998 \n",
"\n",
" OPERATING_PHYSICIAN_UNIF_ID ENCOUNTER_INDICATOR CERT_STATUS FILLER_SPACE \n",
"0 NaN 01 2 NaN \n",
"1 NaN 01 2 NaN \n",
"2 NaN 01 2 NaN \n",
"3 NaN 01 2 NaN \n",
"4 NaN 01 2 NaN \n",
"\n",
"[5 rows x 194 columns]"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data.head()"
]
}
],
"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": "3.6.5"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment