{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Analysis of the waiting list"
]
},
{
"cell_type": "code",
"execution_count": 23,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"import pandas as pd\n",
"import numpy as np\n",
"import time\n",
"\n",
"import warnings\n",
"warnings.filterwarnings('ignore')"
]
},
{
"cell_type": "code",
"execution_count": 24,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"import pandas as pd\n",
"import numpy as np\n",
"data = pd.read_csv(\"shortExampleWL.csv\", \n",
" low_memory=False, \n",
" error_bad_lines=False,\n",
" sep=\",\")"
]
},
{
"cell_type": "code",
"execution_count": 25,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array(['Unnamed: 0', 'X', 'dateBirth', 'sex', 'specialty', 'entryDate',\n",
" 'exitDate', 'reason'], dtype=object)"
]
},
"execution_count": 25,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data.columns.values"
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"
\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" Unnamed: 0 | \n",
" X | \n",
" dateBirth | \n",
" sex | \n",
" specialty | \n",
" entryDate | \n",
" exitDate | \n",
" reason | \n",
"
\n",
" \n",
" \n",
" \n",
" 0 | \n",
" 45190 | \n",
" 45189 | \n",
" 21/05/1981 | \n",
" 2 | \n",
" Urología | \n",
" 10/06/2016 | \n",
" 17/06/2016 | \n",
" CALCULO URETER | \n",
"
\n",
" \n",
" 1 | \n",
" 114550 | \n",
" 114549 | \n",
" 19/05/1973 | \n",
" 2 | \n",
" Cirugía Adulto | \n",
" 01/04/2014 | \n",
" 29/04/2014 | \n",
" Otros quistes foliculares de la piel y del tej... | \n",
"
\n",
" \n",
" 2 | \n",
" 88208 | \n",
" 88207 | \n",
" 26/05/1974 | \n",
" 2 | \n",
" Medicina Interna | \n",
" 05/01/2015 | \n",
" 28/01/2015 | \n",
" BOCIO DIFUSO | \n",
"
\n",
" \n",
" 3 | \n",
" 186157 | \n",
" 186156 | \n",
" 25/12/1949 | \n",
" 1 | \n",
" Oftalmología | \n",
" 12/11/2011 | \n",
" 23/01/2012 | \n",
" Otra atencion medica | \n",
"
\n",
" \n",
" 4 | \n",
" 211304 | \n",
" 211303 | \n",
" 02/09/1962 | \n",
" 2 | \n",
" Cirugía Adulto | \n",
" 17/03/2011 | \n",
" 01/04/2011 | \n",
" Consulta no Especificada | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" Unnamed: 0 X dateBirth sex specialty entryDate \\\n",
"0 45190 45189 21/05/1981 2 Urología 10/06/2016 \n",
"1 114550 114549 19/05/1973 2 Cirugía Adulto 01/04/2014 \n",
"2 88208 88207 26/05/1974 2 Medicina Interna 05/01/2015 \n",
"3 186157 186156 25/12/1949 1 Oftalmología 12/11/2011 \n",
"4 211304 211303 02/09/1962 2 Cirugía Adulto 17/03/2011 \n",
"\n",
" exitDate reason \n",
"0 17/06/2016 CALCULO URETER \n",
"1 29/04/2014 Otros quistes foliculares de la piel y del tej... \n",
"2 28/01/2015 BOCIO DIFUSO \n",
"3 23/01/2012 Otra atencion medica \n",
"4 01/04/2011 Consulta no Especificada "
]
},
"execution_count": 26,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data.head(5) "
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"I create a reduced version with the data I am interested"
]
},
{
"cell_type": "code",
"execution_count": 27,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" dateBirth | \n",
" sex | \n",
" specialty | \n",
" entryDate | \n",
" exitDate | \n",
" reason | \n",
"
\n",
" \n",
" \n",
" \n",
" 0 | \n",
" 21/05/1981 | \n",
" 2 | \n",
" Urología | \n",
" 10/06/2016 | \n",
" 17/06/2016 | \n",
" CALCULO URETER | \n",
"
\n",
" \n",
" 1 | \n",
" 19/05/1973 | \n",
" 2 | \n",
" Cirugía Adulto | \n",
" 01/04/2014 | \n",
" 29/04/2014 | \n",
" Otros quistes foliculares de la piel y del tej... | \n",
"
\n",
" \n",
" 2 | \n",
" 26/05/1974 | \n",
" 2 | \n",
" Medicina Interna | \n",
" 05/01/2015 | \n",
" 28/01/2015 | \n",
" BOCIO DIFUSO | \n",
"
\n",
" \n",
" 3 | \n",
" 25/12/1949 | \n",
" 1 | \n",
" Oftalmología | \n",
" 12/11/2011 | \n",
" 23/01/2012 | \n",
" Otra atencion medica | \n",
"
\n",
" \n",
" 4 | \n",
" 02/09/1962 | \n",
" 2 | \n",
" Cirugía Adulto | \n",
" 17/03/2011 | \n",
" 01/04/2011 | \n",
" Consulta no Especificada | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" dateBirth sex specialty entryDate exitDate \\\n",
"0 21/05/1981 2 Urología 10/06/2016 17/06/2016 \n",
"1 19/05/1973 2 Cirugía Adulto 01/04/2014 29/04/2014 \n",
"2 26/05/1974 2 Medicina Interna 05/01/2015 28/01/2015 \n",
"3 25/12/1949 1 Oftalmología 12/11/2011 23/01/2012 \n",
"4 02/09/1962 2 Cirugía Adulto 17/03/2011 01/04/2011 \n",
"\n",
" reason \n",
"0 CALCULO URETER \n",
"1 Otros quistes foliculares de la piel y del tej... \n",
"2 BOCIO DIFUSO \n",
"3 Otra atencion medica \n",
"4 Consulta no Especificada "
]
},
"execution_count": 27,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"rdata = data[[\"dateBirth\",\"sex\",\"specialty\",\"entryDate\",\"exitDate\",\"reason\"]]\n",
"rdata.head(5)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"I want to treat dates as dates!"
]
},
{
"cell_type": "code",
"execution_count": 28,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" dateBirth | \n",
" sex | \n",
" specialty | \n",
" entryDate | \n",
" exitDate | \n",
" reason | \n",
"
\n",
" \n",
" \n",
" \n",
" 0 | \n",
" 1981-05-21 | \n",
" 2 | \n",
" Urología | \n",
" 2016-06-10 | \n",
" 2016-06-17 | \n",
" CALCULO URETER | \n",
"
\n",
" \n",
" 1 | \n",
" 1973-05-19 | \n",
" 2 | \n",
" Cirugía Adulto | \n",
" 2014-04-01 | \n",
" 2014-04-29 | \n",
" Otros quistes foliculares de la piel y del tej... | \n",
"
\n",
" \n",
" 2 | \n",
" 1974-05-26 | \n",
" 2 | \n",
" Medicina Interna | \n",
" 2015-01-05 | \n",
" 2015-01-28 | \n",
" BOCIO DIFUSO | \n",
"
\n",
" \n",
" 3 | \n",
" 1949-12-25 | \n",
" 1 | \n",
" Oftalmología | \n",
" 2011-11-12 | \n",
" 2012-01-23 | \n",
" Otra atencion medica | \n",
"
\n",
" \n",
" 4 | \n",
" 1962-09-02 | \n",
" 2 | \n",
" Cirugía Adulto | \n",
" 2011-03-17 | \n",
" 2011-04-01 | \n",
" Consulta no Especificada | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" dateBirth sex specialty entryDate exitDate \\\n",
"0 1981-05-21 2 Urología 2016-06-10 2016-06-17 \n",
"1 1973-05-19 2 Cirugía Adulto 2014-04-01 2014-04-29 \n",
"2 1974-05-26 2 Medicina Interna 2015-01-05 2015-01-28 \n",
"3 1949-12-25 1 Oftalmología 2011-11-12 2012-01-23 \n",
"4 1962-09-02 2 Cirugía Adulto 2011-03-17 2011-04-01 \n",
"\n",
" reason \n",
"0 CALCULO URETER \n",
"1 Otros quistes foliculares de la piel y del tej... \n",
"2 BOCIO DIFUSO \n",
"3 Otra atencion medica \n",
"4 Consulta no Especificada "
]
},
"execution_count": 28,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"rdata['dateBirth'] = pd.to_datetime(rdata['dateBirth'],format='%d/%m/%Y')\n",
"rdata['entryDate'] = pd.to_datetime(rdata['entryDate'],format='%d/%m/%Y')\n",
"rdata['exitDate'] = pd.to_datetime(rdata['exitDate'],format='%d/%m/%Y')\n",
"\n",
"rdata.head(5)"
]
},
{
"cell_type": "code",
"execution_count": 29,
"metadata": {},
"outputs": [],
"source": [
"diff=rdata['exitDate'] - rdata['entryDate']\n",
"#diff.values.astype('timedelta64[D]')\n",
"rdata['wtime'] = diff"
]
},
{
"cell_type": "code",
"execution_count": 30,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" dateBirth | \n",
" sex | \n",
" specialty | \n",
" entryDate | \n",
" exitDate | \n",
" reason | \n",
" wtime | \n",
"
\n",
" \n",
" \n",
" \n",
" 0 | \n",
" 1981-05-21 | \n",
" 2 | \n",
" Urología | \n",
" 2016-06-10 | \n",
" 2016-06-17 | \n",
" CALCULO URETER | \n",
" 7 days | \n",
"
\n",
" \n",
" 1 | \n",
" 1973-05-19 | \n",
" 2 | \n",
" Cirugía Adulto | \n",
" 2014-04-01 | \n",
" 2014-04-29 | \n",
" Otros quistes foliculares de la piel y del tej... | \n",
" 28 days | \n",
"
\n",
" \n",
" 2 | \n",
" 1974-05-26 | \n",
" 2 | \n",
" Medicina Interna | \n",
" 2015-01-05 | \n",
" 2015-01-28 | \n",
" BOCIO DIFUSO | \n",
" 23 days | \n",
"
\n",
" \n",
" 3 | \n",
" 1949-12-25 | \n",
" 1 | \n",
" Oftalmología | \n",
" 2011-11-12 | \n",
" 2012-01-23 | \n",
" Otra atencion medica | \n",
" 72 days | \n",
"
\n",
" \n",
" 4 | \n",
" 1962-09-02 | \n",
" 2 | \n",
" Cirugía Adulto | \n",
" 2011-03-17 | \n",
" 2011-04-01 | \n",
" Consulta no Especificada | \n",
" 15 days | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" dateBirth sex specialty entryDate exitDate \\\n",
"0 1981-05-21 2 Urología 2016-06-10 2016-06-17 \n",
"1 1973-05-19 2 Cirugía Adulto 2014-04-01 2014-04-29 \n",
"2 1974-05-26 2 Medicina Interna 2015-01-05 2015-01-28 \n",
"3 1949-12-25 1 Oftalmología 2011-11-12 2012-01-23 \n",
"4 1962-09-02 2 Cirugía Adulto 2011-03-17 2011-04-01 \n",
"\n",
" reason wtime \n",
"0 CALCULO URETER 7 days \n",
"1 Otros quistes foliculares de la piel y del tej... 28 days \n",
"2 BOCIO DIFUSO 23 days \n",
"3 Otra atencion medica 72 days \n",
"4 Consulta no Especificada 15 days "
]
},
"execution_count": 30,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"rdata.head(5)"
]
},
{
"cell_type": "code",
"execution_count": 37,
"metadata": {},
"outputs": [],
"source": [
"age = rdata['exitDate']-rdata['dateBirth']"
]
},
{
"cell_type": "code",
"execution_count": 41,
"metadata": {},
"outputs": [],
"source": [
"import datetime\n",
"\n",
"now = datetime.datetime.now()"
]
},
{
"cell_type": "code",
"execution_count": 43,
"metadata": {},
"outputs": [],
"source": [
"age = now - rdata['dateBirth']"
]
},
{
"cell_type": "code",
"execution_count": 44,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([1175938721390200000, 1428572321390200000, 1396431521390200000, ...,\n",
" 1445593121390200000, 1611740321390200000, 1160386721390200000], dtype='timedelta64[ns]')"
]
},
"execution_count": 44,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"age.values"
]
},
{
"cell_type": "code",
"execution_count": 67,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0 37.0\n",
"1 45.0\n",
"2 44.0\n",
"3 68.0\n",
"4 55.0\n",
"5 65.0\n",
"6 9.0\n",
"7 37.0\n",
"8 68.0\n",
"9 40.0\n",
"10 29.0\n",
"11 76.0\n",
"12 66.0\n",
"13 66.0\n",
"14 46.0\n",
"15 43.0\n",
"16 80.0\n",
"17 13.0\n",
"18 32.0\n",
"19 95.0\n",
"20 57.0\n",
"21 73.0\n",
"22 54.0\n",
"23 8.0\n",
"24 91.0\n",
"25 41.0\n",
"26 6.0\n",
"27 87.0\n",
"28 45.0\n",
"29 10.0\n",
" ... \n",
"2150 56.0\n",
"2151 17.0\n",
"2152 7.0\n",
"2153 17.0\n",
"2154 74.0\n",
"2155 42.0\n",
"2156 30.0\n",
"2157 42.0\n",
"2158 58.0\n",
"2159 52.0\n",
"2160 54.0\n",
"2161 76.0\n",
"2162 34.0\n",
"2163 57.0\n",
"2164 12.0\n",
"2165 30.0\n",
"2166 50.0\n",
"2167 61.0\n",
"2168 55.0\n",
"2169 22.0\n",
"2170 19.0\n",
"2171 65.0\n",
"2172 90.0\n",
"2173 19.0\n",
"2174 20.0\n",
"2175 24.0\n",
"2176 14.0\n",
"2177 45.0\n",
"2178 51.0\n",
"2179 36.0\n",
"Name: dateBirth, Length: 2180, dtype: float64"
]
},
"execution_count": 67,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"age.astype('timedelta64[Y]')"
]
},
{
"cell_type": "code",
"execution_count": 68,
"metadata": {},
"outputs": [],
"source": [
"rdata['age'] =age.astype('timedelta64[Y]')"
]
},
{
"cell_type": "code",
"execution_count": 69,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" dateBirth | \n",
" sex | \n",
" specialty | \n",
" entryDate | \n",
" exitDate | \n",
" reason | \n",
" wtime | \n",
" age | \n",
"
\n",
" \n",
" \n",
" \n",
" 0 | \n",
" 1981-05-21 | \n",
" 2 | \n",
" Urología | \n",
" 2016-06-10 | \n",
" 2016-06-17 | \n",
" CALCULO URETER | \n",
" 7 days | \n",
" 37.0 | \n",
"
\n",
" \n",
" 1 | \n",
" 1973-05-19 | \n",
" 2 | \n",
" Cirugía Adulto | \n",
" 2014-04-01 | \n",
" 2014-04-29 | \n",
" Otros quistes foliculares de la piel y del tej... | \n",
" 28 days | \n",
" 45.0 | \n",
"
\n",
" \n",
" 2 | \n",
" 1974-05-26 | \n",
" 2 | \n",
" Medicina Interna | \n",
" 2015-01-05 | \n",
" 2015-01-28 | \n",
" BOCIO DIFUSO | \n",
" 23 days | \n",
" 44.0 | \n",
"
\n",
" \n",
" 3 | \n",
" 1949-12-25 | \n",
" 1 | \n",
" Oftalmología | \n",
" 2011-11-12 | \n",
" 2012-01-23 | \n",
" Otra atencion medica | \n",
" 72 days | \n",
" 68.0 | \n",
"
\n",
" \n",
" 4 | \n",
" 1962-09-02 | \n",
" 2 | \n",
" Cirugía Adulto | \n",
" 2011-03-17 | \n",
" 2011-04-01 | \n",
" Consulta no Especificada | \n",
" 15 days | \n",
" 55.0 | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" dateBirth sex specialty entryDate exitDate \\\n",
"0 1981-05-21 2 Urología 2016-06-10 2016-06-17 \n",
"1 1973-05-19 2 Cirugía Adulto 2014-04-01 2014-04-29 \n",
"2 1974-05-26 2 Medicina Interna 2015-01-05 2015-01-28 \n",
"3 1949-12-25 1 Oftalmología 2011-11-12 2012-01-23 \n",
"4 1962-09-02 2 Cirugía Adulto 2011-03-17 2011-04-01 \n",
"\n",
" reason wtime age \n",
"0 CALCULO URETER 7 days 37.0 \n",
"1 Otros quistes foliculares de la piel y del tej... 28 days 45.0 \n",
"2 BOCIO DIFUSO 23 days 44.0 \n",
"3 Otra atencion medica 72 days 68.0 \n",
"4 Consulta no Especificada 15 days 55.0 "
]
},
"execution_count": 69,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"rdata.head()"
]
},
{
"cell_type": "code",
"execution_count": 75,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Index(['sex', 'specialty'], dtype='object')"
]
},
"execution_count": 75,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"features = rdata.columns[1:3]\n",
"features"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"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": "3.6.3"
}
},
"nbformat": 4,
"nbformat_minor": 2
}