Objetivo: Analizar Datos de Salarios utilizando
Cargamos las librerias
library(readr)
library(dplyr)
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
require(stats) #Para tener la misma semilla cuando la generemos
Cargamos los datos de Salarios
salarios <- read.csv("C:/Users/Gerencia Banthai/Documents/Ciencia de los datos/Datos/Salaries.csv",
encoding = "UTF-8")
# salarios Con esta linea de codigo checamos si nos trajimos los datos
#Verificamos los registros en Head para ver los primeros registros
head(salarios)
## Id EmployeeName JobTitle
## 1 1 NATHANIEL FORD GENERAL MANAGER-METROPOLITAN TRANSIT AUTHORITY
## 2 2 GARY JIMENEZ CAPTAIN III (POLICE DEPARTMENT)
## 3 3 ALBERT PARDINI CAPTAIN III (POLICE DEPARTMENT)
## 4 4 CHRISTOPHER CHONG WIRE ROPE CABLE MAINTENANCE MECHANIC
## 5 5 PATRICK GARDNER DEPUTY CHIEF OF DEPARTMENT,(FIRE DEPARTMENT)
## 6 6 DAVID SULLIVAN ASSISTANT DEPUTY CHIEF II
## BasePay OvertimePay OtherPay Benefits TotalPay TotalPayBenefits Year
## 1 167411.2 0.00 400184.2 NA 567595.4 567595.4 2011
## 2 155966.0 245131.88 137811.4 NA 538909.3 538909.3 2011
## 3 212739.1 106088.18 16452.6 NA 335279.9 335279.9 2011
## 4 77916.0 56120.71 198306.9 NA 332343.6 332343.6 2011
## 5 134401.6 9737.00 182234.6 NA 326373.2 326373.2 2011
## 6 118602.0 8601.00 189082.7 NA 316285.7 316285.7 2011
## Notes Agency Status
## 1 NA San Francisco
## 2 NA San Francisco
## 3 NA San Francisco
## 4 NA San Francisco
## 5 NA San Francisco
## 6 NA San Francisco
Filtando el registro por nombre de empleado
filter(salarios,EmployeeName == "Kevin Lee")
## Id EmployeeName JobTitle BasePay
## 1 39716 Kevin Lee Police Officer 3 115866.90
## 2 40571 Kevin Lee Police Officer 3 117171.41
## 3 42511 Kevin Lee Electrical Transit System Mech 79220.54
## 4 49271 Kevin Lee Deputy Court Clerk III 84512.32
## 5 49440 Kevin Lee Deputy Court Clerk III 84512.34
## 6 50124 Kevin Lee Personnel Analyst 83382.00
## 7 52234 Kevin Lee Senior Parking Control Officer 66774.03
## 8 53932 Kevin Lee Transit Operator 57397.32
## 9 55120 Kevin Lee IS Administrator 2 68940.44
## 10 112386 Kevin Lee Sergeant 3 137982.14
## 11 123142 Kevin Lee IT Operations Support Admin IV 91606.03
## 12 124166 Kevin Lee Personnel Analyst 88353.01
## 13 124659 Kevin Lee Transit Operator 67230.30
## OvertimePay OtherPay Benefits TotalPay TotalPayBenefits Year Notes
## 1 23523.30 9313.54 34906.20 148703.74 183609.94 2012 NA
## 2 19606.88 4244.90 34610.10 141023.19 175633.29 2012 NA
## 3 40247.39 3353.49 38781.04 122821.42 161602.46 2012 NA
## 4 0.00 1469.99 36080.30 85982.31 122062.61 2012 NA
## 5 0.00 975.44 35902.02 85487.78 121389.80 2012 NA
## 6 0.00 0.00 35210.59 83382.00 118592.59 2012 NA
## 7 9599.08 1092.62 31902.38 77465.73 109368.11 2012 NA
## 8 9989.83 1800.48 34577.54 69187.63 103765.17 2012 NA
## 9 0.00 0.00 30650.48 68940.44 99590.92 2012 NA
## 10 18537.19 16039.62 43039.12 172558.95 215598.07 2014 NA
## 11 0.00 1013.00 34109.61 92619.03 126728.64 2014 NA
## 12 0.00 0.00 33172.33 88353.01 121525.34 2014 NA
## 13 10961.25 4050.85 36777.83 82242.40 119020.23 2014 NA
## Agency Status
## 1 San Francisco
## 2 San Francisco
## 3 San Francisco
## 4 San Francisco
## 5 San Francisco
## 6 San Francisco
## 7 San Francisco
## 8 San Francisco
## 9 San Francisco
## 10 San Francisco FT
## 11 San Francisco FT
## 12 San Francisco FT
## 13 San Francisco FT
Filtramos cuantas personas ganan entre 150,000 y 170,000 en el año 2012
cuantas <- filter(salarios,TotalPayBenefits>=150000 & TotalPayBenefits <= 170000 & Year == 2012)
str(cuantas)
## 'data.frame': 2913 obs. of 13 variables:
## $ Id : int 41218 41219 41220 41221 41222 41223 41224 41225 41226 41227 ...
## $ EmployeeName : Factor w/ 110810 levels "A Bernard Fatooh",..: 16010 20663 88354 60640 94542 73444 45099 108649 89546 64494 ...
## $ JobTitle : Factor w/ 2159 levels "Account Clerk",..: 1565 2087 234 806 615 1414 1413 1565 1415 625 ...
## $ BasePay : num 112611 102662 97609 110847 88374 ...
## $ OvertimePay : num 5648 19465 22952 3927 33428 ...
## $ OtherPay : num 6037 6254 8148 18492 10512 ...
## $ Benefits : num 45699 41608 41273 36714 37660 ...
## $ TotalPay : num 124296 128382 128709 133266 132314 ...
## $ TotalPayBenefits: num 169995 169990 169982 169980 169973 ...
## $ Year : int 2012 2012 2012 2012 2012 2012 2012 2012 2012 2012 ...
## $ Notes : logi NA NA NA NA NA NA ...
## $ Agency : Factor w/ 1 level "San Francisco": 1 1 1 1 1 1 1 1 1 1 ...
## $ Status : Factor w/ 3 levels "","FT","PT": 1 1 1 1 1 1 1 1 1 1 ...
nrow(cuantas)
## [1] 2913
Filtramos usando selec para solo traer determinadas columnas
registros <- select(salarios, Id, EmployeeName, TotalPayBenefits, Year)
#registros Solo lo ponemos para checar que este haciendo lo que queremos
cuales <- filter(registros,TotalPayBenefits>=150000 & TotalPayBenefits <= 170000 & Year == 2012)
head(cuales,20) #Mostramos los primeros 20 para ver si funciona
## Id EmployeeName TotalPayBenefits Year
## 1 41218 Cheryl De Lemos 169995.4 2012
## 2 41219 Daniel Godfrey 169990.1 2012
## 3 41220 Robert Harvey 169982.0 2012
## 4 41221 Lawrence McDonnell 169980.4 2012
## 5 41222 Sergio Chavez 169973.1 2012
## 6 41223 Michael Grande 169970.4 2012
## 7 41224 Jeffrey Chow 169963.2 2012
## 8 41225 Winilyn Hidalgo 169960.5 2012
## 9 41226 Rodney Lee 169960.3 2012
## 10 41227 Lucille Palma 169940.8 2012
## 11 41228 Jonathan Rapp 169939.2 2012
## 12 41229 Ajay Saxena 169936.3 2012
## 13 41230 Albert Tom 169933.8 2012
## 14 41231 Edith Hammond 169930.6 2012
## 15 41232 Hector Tam 169925.7 2012
## 16 41233 Eugene Ling 169898.1 2012
## 17 41234 Xing Wang 169897.1 2012
## 18 41235 Crystal McDonald 169893.1 2012
## 19 41236 Patrick Cox 169890.4 2012
## 20 41237 Balraj Singh Rai 169887.5 2012
Ordenar los datos con arrange
datosOrdenados <- arrange(cuales,EmployeeName)
head(datosOrdenados) # Checammos los primeros para ver si esta funcionando
## Id EmployeeName TotalPayBenefits Year
## 1 42773 Aaron Ballonado 159732.7 2012
## 2 41480 Aaron Cowhig 168330.4 2012
## 3 42067 Aaron Fischer 164280.9 2012
## 4 41965 Aaron Smith 164960.6 2012
## 5 42777 Aaron Yoo 159711.9 2012
## 6 42739 Abraham Abarca 159988.9 2012
tail(datosOrdenados) # Checammos los ultimos para ver si esta funcionando
## Id EmployeeName TotalPayBenefits Year
## 2908 41326 Yvonne Fuentes-Pattishall 169171.5 2012
## 2909 43221 Zahid Khan 156872.5 2012
## 2910 42623 Zara Grace Janer 160766.9 2012
## 2911 44083 Zhong Qiu 150289.4 2012
## 2912 41647 Zoila Maguina 167054.6 2012
## 2913 42196 Zula Jones 163422.7 2012
Agregar columnas nuevas al conjunto de datos
Pueden ser al original o al que ya se tiene fitrado
Agregar un valor de 0 o 1 para genero
# Poner una semilla igual todos para generar la misma muestra
set.seed(1000) # Un valor de semilla
# Vamos a generar los generos 0 y 1 donde 0 es Masculino y 1 es Femenino
generos <- rep(0:1, 5000) # Generamos un universo de 5000 valores entre 0 y 1
generos <- sample(generos, 2913) # Del universo que generamos tomamos una muestra de 2913 registros
generos
## [1] 1 1 0 0 1 0 1 1 1 0 1 0 0 1 1 1 1 0 1 1 1 0 1 0 1 0 1 1 1 1 0 0 0 0
## [35] 1 1 1 0 1 0 0 1 1 0 0 1 1 0 1 1 1 1 1 0 0 1 0 0 1 0 0 0 0 0 1 0 0 0
## [69] 1 0 0 1 1 1 0 0 0 1 1 0 0 0 0 0 0 0 0 0 0 1 1 0 1 1 1 0 1 0 0 0 1 1
## [103] 0 0 1 1 0 0 0 1 1 0 0 1 0 0 0 0 1 1 0 0 0 1 1 1 1 1 0 1 0 0 1 0 0 1
## [137] 1 1 0 0 0 1 1 0 1 0 1 0 0 0 0 1 0 0 0 1 0 1 0 1 1 1 0 0 0 1 1 1 1 0
## [171] 0 0 0 0 0 0 0 1 1 0 0 0 1 0 0 1 0 1 0 0 1 1 0 1 0 0 0 0 0 0 0 1 1 1
## [205] 1 1 1 1 0 0 1 0 1 0 0 1 0 1 0 1 1 1 1 1 0 1 0 0 0 1 0 0 0 1 0 1 1 0
## [239] 0 0 0 0 1 1 1 0 0 0 0 0 0 0 0 0 1 1 0 1 1 0 1 1 1 0 1 0 0 1 1 0 1 0
## [273] 0 0 1 0 0 1 1 0 0 1 0 0 1 0 1 0 1 0 1 0 1 1 0 0 0 1 0 1 0 0 0 0 0 0
## [307] 1 1 0 0 1 1 1 1 1 0 0 0 1 1 1 1 1 0 0 0 1 0 1 0 0 0 1 1 1 1 0 1 0 0
## [341] 0 0 1 0 0 0 0 0 1 1 1 1 0 1 0 1 0 1 0 1 0 1 0 0 1 1 1 0 0 0 1 1 1 1
## [375] 1 0 0 0 1 0 1 0 0 0 0 1 1 0 0 0 1 1 1 0 0 1 1 0 1 1 1 0 0 1 1 0 0 0
## [409] 0 0 1 0 1 1 1 0 1 1 0 0 1 1 0 1 1 0 1 1 1 1 0 1 0 0 0 1 0 1 1 1 0 1
## [443] 0 1 1 0 1 1 0 1 1 1 0 1 1 0 0 1 1 0 0 1 0 1 0 1 1 1 0 0 0 1 0 0 1 0
## [477] 1 0 1 1 1 0 1 1 0 1 1 0 0 1 0 1 1 1 1 0 1 1 0 1 0 0 0 0 1 1 1 0 0 1
## [511] 1 1 1 1 1 1 0 0 0 0 0 0 1 1 0 0 1 1 1 1 0 0 1 0 1 0 0 1 0 1 1 0 0 1
## [545] 1 1 1 1 0 0 0 1 1 0 0 1 1 1 1 1 0 0 1 0 0 1 0 1 1 0 0 1 1 0 0 1 1 1
## [579] 0 0 0 0 1 1 1 0 1 0 0 1 0 0 1 0 1 1 1 0 0 0 1 0 0 0 0 1 0 1 0 1 0 0
## [613] 0 0 0 1 1 1 1 1 1 1 0 1 1 1 1 0 1 0 1 0 0 1 1 0 0 0 0 1 0 0 1 0 1 0
## [647] 1 1 0 0 1 1 1 1 0 1 0 0 1 1 1 0 0 1 0 0 1 1 1 1 1 0 1 1 1 1 1 0 1 0
## [681] 1 0 1 0 0 1 1 1 1 1 1 1 1 1 1 1 0 1 0 0 1 1 1 1 0 1 0 0 1 1 1 0 0 0
## [715] 0 0 0 1 1 0 0 1 0 0 0 1 0 1 0 1 1 0 1 1 1 1 1 0 1 1 0 1 0 1 0 0 0 0
## [749] 0 0 1 1 0 1 0 1 1 0 1 0 0 1 0 0 0 1 0 1 1 0 0 1 1 1 0 1 1 1 0 0 1 1
## [783] 1 1 0 1 0 0 1 1 1 0 0 0 0 0 0 0 0 0 1 0 1 0 0 1 0 1 1 1 1 0 1 0 1 0
## [817] 1 1 0 0 1 1 1 1 1 0 0 0 0 1 0 1 0 1 0 1 0 1 0 1 1 0 1 1 1 0 0 1 1 0
## [851] 0 1 1 1 1 0 1 1 0 0 1 0 1 1 0 1 1 1 0 0 1 0 1 1 0 0 1 0 0 0 0 0 0 0
## [885] 1 1 0 0 1 1 1 1 1 0 0 0 0 0 1 1 0 0 0 0 0 0 0 0 1 0 1 0 0 1 0 1 0 1
## [919] 0 1 1 0 1 1 0 0 1 0 1 0 1 0 1 1 1 0 0 0 1 0 1 1 1 1 0 1 1 0 1 1 0 0
## [953] 0 1 1 1 0 1 0 0 1 0 1 0 1 0 1 0 0 1 1 0 0 0 0 0 0 1 0 1 0 1 1 1 1 0
## [987] 0 1 0 1 1 1 1 1 1 1 1 1 0 1 0 0 0 0 0 0 1 0 1 1 0 1 0 1 0 1 1 0 0 0
## [1021] 1 1 1 0 0 0 0 0 0 1 1 0 1 0 1 1 0 0 0 0 1 1 0 0 0 0 0 0 1 1 0 1 0 0
## [1055] 0 1 1 1 0 0 1 0 1 0 0 1 0 1 0 0 0 1 1 1 1 0 0 1 0 1 0 0 0 1 0 1 1 0
## [1089] 1 1 0 0 0 0 1 0 0 1 1 0 1 1 0 1 0 0 1 0 1 0 0 1 0 0 0 0 1 0 0 1 0 1
## [1123] 1 0 1 0 1 1 0 0 0 1 1 0 0 0 1 0 1 0 0 1 1 1 1 0 1 1 1 1 1 0 0 0 1 0
## [1157] 1 0 0 0 1 1 0 1 1 0 0 1 1 1 0 0 1 0 1 0 0 0 0 0 0 1 1 0 0 1 1 0 1 1
## [1191] 1 1 1 1 0 0 1 0 1 0 0 0 0 1 1 1 1 1 1 1 1 1 1 0 1 1 1 0 1 1 1 0 1 0
## [1225] 0 0 0 1 0 1 1 0 1 1 1 1 1 1 0 1 0 0 1 0 1 0 1 0 0 1 1 0 1 0 1 1 1 0
## [1259] 1 1 1 1 1 1 1 1 0 1 0 1 1 1 0 1 1 0 1 0 0 0 0 0 0 0 1 0 0 1 1 1 1 1
## [1293] 0 0 1 0 1 0 1 1 1 1 1 1 0 1 0 0 1 0 0 1 1 1 0 0 1 0 1 0 0 1 0 1 0 1
## [1327] 0 1 1 1 1 1 0 0 1 1 0 0 0 1 0 1 1 0 1 1 0 1 1 0 1 0 0 1 1 0 0 0 1 0
## [1361] 0 0 1 1 0 1 1 0 1 1 0 1 1 0 1 0 1 1 1 0 1 0 0 1 1 0 0 1 1 0 0 0 1 0
## [1395] 0 1 1 0 1 0 1 0 0 0 1 0 1 1 0 1 1 0 1 1 1 0 0 1 0 1 0 0 1 1 0 0 1 0
## [1429] 0 0 1 1 0 1 1 0 1 1 0 1 1 1 0 1 1 0 1 1 1 1 0 1 1 0 1 1 1 1 1 1 0 1
## [1463] 0 1 0 1 0 0 0 0 0 0 1 0 0 1 1 1 0 0 0 1 0 1 0 0 0 1 0 1 0 0 1 1 1 0
## [1497] 1 1 0 0 0 0 0 1 1 0 0 1 0 0 0 0 0 1 1 0 1 1 0 0 0 1 1 0 0 0 0 1 0 0
## [1531] 1 1 1 1 1 1 1 0 1 1 0 1 0 0 0 1 0 1 0 0 1 1 1 1 0 1 1 0 1 0 0 0 1 0
## [1565] 1 1 1 0 0 1 1 0 1 0 0 1 0 0 0 1 0 0 1 1 0 0 1 0 0 0 0 1 0 0 0 0 0 0
## [1599] 1 1 1 0 0 0 0 0 1 0 0 1 1 1 1 1 1 1 0 0 1 0 0 0 0 1 0 0 0 1 1 0 1 0
## [1633] 0 1 1 0 0 0 0 1 0 0 1 0 0 0 0 1 1 0 1 0 0 0 0 0 1 1 0 0 0 0 1 0 0 1
## [1667] 1 0 1 0 1 0 0 0 1 0 1 1 0 1 1 1 1 1 0 1 1 1 1 1 0 0 1 1 0 1 0 1 1 1
## [1701] 0 1 1 0 0 0 1 1 0 0 1 0 1 1 0 1 1 1 1 0 0 0 1 1 1 1 1 0 1 1 1 0 0 0
## [1735] 0 0 0 1 0 0 0 0 0 0 0 1 1 0 1 0 1 1 1 1 1 0 0 0 0 0 1 1 1 0 0 0 0 0
## [1769] 1 1 1 1 0 1 0 0 0 0 0 0 1 0 0 1 1 1 1 0 0 0 0 0 1 0 0 0 0 1 0 1 0 1
## [1803] 0 0 0 0 0 0 0 0 0 1 1 0 1 0 0 1 1 0 0 0 1 1 0 0 1 1 1 0 1 1 1 0 0 1
## [1837] 1 1 1 1 0 1 0 0 0 0 1 1 0 0 1 0 1 0 0 0 1 1 1 0 0 0 1 0 0 1 1 0 0 1
## [1871] 0 0 0 0 0 1 0 0 1 0 0 0 0 1 1 1 1 0 1 1 0 0 0 0 1 1 0 0 0 0 1 1 0 0
## [1905] 1 1 1 1 0 0 0 0 0 1 1 0 0 1 0 0 1 0 0 0 0 0 0 1 0 1 0 0 1 1 1 1 1 0
## [1939] 1 1 0 1 1 1 1 1 1 0 1 1 0 0 0 1 1 1 1 1 0 0 1 1 1 1 1 1 0 0 0 0 0 1
## [1973] 0 1 1 1 1 1 1 1 1 0 0 0 0 1 1 0 0 0 0 1 1 1 1 0 0 1 0 1 0 1 0 1 0 0
## [2007] 1 1 0 1 0 0 1 0 0 0 1 0 1 0 1 1 1 0 0 0 1 0 1 0 1 1 1 1 1 0 1 1 1 1
## [2041] 1 0 0 0 1 1 1 1 0 0 0 1 1 0 1 1 0 0 1 1 1 1 0 0 0 1 0 1 1 1 1 0 1 0
## [2075] 0 0 1 0 0 1 0 0 0 0 0 1 0 0 0 1 0 0 0 1 0 0 1 1 1 1 0 1 0 1 0 0 0 1
## [2109] 0 1 1 0 1 0 1 1 1 0 1 1 1 1 1 0 1 1 1 0 0 1 1 0 0 0 1 1 0 0 1 0 0 0
## [2143] 1 0 0 0 1 1 1 1 1 1 1 0 0 0 0 1 0 0 0 0 1 1 0 1 0 0 1 0 1 0 0 0 1 1
## [2177] 0 1 1 0 0 0 0 0 0 1 0 0 0 0 1 0 0 1 0 0 1 0 0 1 1 1 1 1 1 1 0 1 1 1
## [2211] 0 0 1 0 0 0 1 1 1 0 1 0 0 0 0 1 0 1 1 1 0 0 1 0 0 0 1 0 1 1 0 1 0 0
## [2245] 0 1 1 0 1 0 1 1 0 1 1 0 0 0 0 0 0 0 1 0 0 0 1 0 1 1 0 0 0 0 1 1 1 1
## [2279] 1 1 1 1 0 1 1 0 0 1 0 0 1 0 0 1 0 1 1 0 1 1 0 1 1 1 1 0 1 1 0 0 0 1
## [2313] 1 0 0 1 0 1 0 0 1 0 1 0 1 1 1 0 0 1 1 1 1 1 1 1 1 1 1 0 1 0 0 1 1 0
## [2347] 0 0 1 0 1 1 0 1 0 1 0 1 0 1 0 0 0 1 1 1 0 0 1 0 1 0 1 1 0 1 0 1 0 1
## [2381] 0 1 0 1 1 0 1 0 1 1 0 1 1 1 1 0 0 0 1 1 0 0 1 0 1 0 1 0 0 1 0 0 1 1
## [2415] 0 0 0 0 0 1 0 1 1 0 0 1 1 0 1 1 1 1 0 1 0 0 1 0 0 0 1 0 0 1 0 1 1 0
## [2449] 0 1 1 1 0 1 0 0 0 0 1 0 0 0 1 1 0 1 0 1 1 1 1 0 0 0 0 0 1 1 1 0 1 1
## [2483] 1 0 0 0 0 1 1 1 1 1 0 1 1 1 1 0 1 0 0 1 1 0 1 0 0 1 1 0 0 0 1 1 1 1
## [2517] 0 1 1 0 1 0 0 1 0 0 1 1 0 0 0 0 0 1 0 1 1 1 0 0 1 0 1 1 1 0 1 0 0 0
## [2551] 0 0 1 1 1 1 1 1 0 1 0 0 0 0 0 0 1 1 0 1 1 0 0 0 0 0 0 0 1 0 1 0 0 0
## [2585] 1 1 1 1 0 1 1 1 1 0 1 0 0 1 0 0 0 1 1 1 0 0 0 0 1 1 0 0 0 1 0 1 1 1
## [2619] 1 1 0 0 1 0 1 0 1 0 1 1 0 0 1 0 1 1 1 1 1 0 1 0 0 0 1 0 1 0 1 0 1 0
## [2653] 1 0 0 0 1 0 1 1 1 0 0 1 0 0 1 0 1 1 0 0 1 1 1 0 1 1 0 1 0 1 0 1 1 0
## [2687] 0 1 0 0 1 1 0 0 1 0 1 0 1 1 1 0 0 0 1 1 0 0 0 0 0 1 1 0 0 1 1 1 0 1
## [2721] 1 0 1 0 1 0 0 1 1 0 1 0 1 1 0 0 1 0 1 1 1 0 1 1 0 0 1 0 0 0 1 0 0 1
## [2755] 0 1 1 0 0 0 0 1 0 0 0 1 1 0 0 0 0 1 1 0 1 1 1 1 1 1 1 0 0 0 0 0 0 0
## [2789] 1 1 0 0 1 1 1 1 1 0 1 1 0 0 0 1 1 1 1 0 0 0 1 1 1 1 1 0 1 1 0 0 1 1
## [2823] 0 0 0 1 1 1 1 0 1 0 1 1 0 1 1 1 1 1 1 0 1 1 0 0 0 0 0 0 1 1 0 0 0 0
## [2857] 0 1 1 0 0 0 0 1 0 1 1 1 0 0 1 0 1 1 0 1 0 1 0 1 1 1 1 1 0 0 1 0 1 0
## [2891] 1 0 0 1 0 0 0 0 0 0 0 0 0 0 1 1 1 0 0 0 1 1 0
cuales <- mutate(cuales, genero = generos) # Agrega columna genero a cuales
head(cuales, 100)# Mostramos los primeros 100 para revisar que esta bien
## Id EmployeeName TotalPayBenefits Year genero
## 1 41218 Cheryl De Lemos 169995.4 2012 1
## 2 41219 Daniel Godfrey 169990.1 2012 1
## 3 41220 Robert Harvey 169982.0 2012 0
## 4 41221 Lawrence McDonnell 169980.4 2012 0
## 5 41222 Sergio Chavez 169973.1 2012 1
## 6 41223 Michael Grande 169970.4 2012 0
## 7 41224 Jeffrey Chow 169963.2 2012 1
## 8 41225 Winilyn Hidalgo 169960.5 2012 1
## 9 41226 Rodney Lee 169960.3 2012 1
## 10 41227 Lucille Palma 169940.8 2012 0
## 11 41228 Jonathan Rapp 169939.2 2012 1
## 12 41229 Ajay Saxena 169936.3 2012 0
## 13 41230 Albert Tom 169933.8 2012 0
## 14 41231 Edith Hammond 169930.6 2012 1
## 15 41232 Hector Tam 169925.7 2012 1
## 16 41233 Eugene Ling 169898.1 2012 1
## 17 41234 Xing Wang 169897.1 2012 1
## 18 41235 Crystal McDonald 169893.1 2012 0
## 19 41236 Patrick Cox 169890.4 2012 1
## 20 41237 Balraj Singh Rai 169887.5 2012 1
## 21 41238 Jennifer Northridge 169879.5 2012 1
## 22 41239 Roger Fong 169876.2 2012 0
## 23 41240 Edgar Tabo 169876.1 2012 1
## 24 41241 Kin Lee 169864.1 2012 0
## 25 41242 Kevin Adkins 169849.0 2012 1
## 26 41243 Curtis Caldwell 169837.2 2012 0
## 27 41244 Dianna Yanez 169831.5 2012 1
## 28 41245 Samuel Yu 169820.4 2012 1
## 29 41246 Eugene Shu 169811.9 2012 1
## 30 41247 Dale Winniford 169799.7 2012 1
## 31 41248 Clifford Burkhart 169798.2 2012 0
## 32 41249 Suzanne Miller 169794.0 2012 0
## 33 41250 Catheryn Williams 169791.3 2012 0
## 34 41251 Stephen Gritsch 169741.6 2012 0
## 35 41252 Maria Cecilia Martin 169740.3 2012 1
## 36 41253 Russell Roby 169736.7 2012 1
## 37 41254 Lawrence Soe 169732.1 2012 1
## 38 41255 Stephon Degand 169723.0 2012 0
## 39 41256 Michelle Tong 169704.5 2012 1
## 40 41257 James Kazarian 169704.2 2012 0
## 41 41258 Violeta Del Mundo 169699.7 2012 0
## 42 41259 Fred Lew 169693.3 2012 1
## 43 41260 Donald Bannett 169688.4 2012 1
## 44 41261 Miles Young 169673.6 2012 0
## 45 41262 Victor Le 169660.8 2012 0
## 46 41263 Eric Louie 169660.2 2012 1
## 47 41264 Lawrence Ng 169654.4 2012 1
## 48 41265 Eduard Ochoa 169639.7 2012 0
## 49 41266 Geoffrey Clayton 169635.6 2012 1
## 50 41267 Rona Sandler 169633.7 2012 1
## 51 41268 Larry Para 169624.0 2012 1
## 52 41269 Tracy Miesen 169619.6 2012 1
## 53 41270 Linda Moore 169607.8 2012 1
## 54 41271 Kaushal Bhaskar 169591.4 2012 0
## 55 41272 Moses Bautista 169562.9 2012 0
## 56 41273 Sophal Chea 169556.0 2012 1
## 57 41274 John Edward Herbert 169540.4 2012 0
## 58 41275 Shao Ping Lai 169540.4 2012 0
## 59 41276 William McCarthy 169527.5 2012 1
## 60 41277 Keith Baraka 169526.0 2012 0
## 61 41278 Richie Owyang 169518.8 2012 0
## 62 41279 Kenyon Bowers 169509.4 2012 0
## 63 41280 Herbert Mariano 169502.8 2012 0
## 64 41281 Maria Perez 169493.4 2012 0
## 65 41282 Gail Clabby 169492.0 2012 1
## 66 41283 Philip Secondez 169485.0 2012 0
## 67 41284 Marco Desangles 169480.8 2012 0
## 68 41285 Wilfredo Arquiza 169479.5 2012 0
## 69 41286 David Sands 169467.2 2012 1
## 70 41287 M J Castagnola 169463.2 2012 0
## 71 41288 Edwin Gaffud 169454.9 2012 0
## 72 41289 Sarah Lindley 169453.5 2012 1
## 73 41290 Carlos Manfredi 169442.4 2012 1
## 74 41291 Cathal Hennessy 169442.1 2012 1
## 75 41292 Diana Rosenstein 169432.1 2012 0
## 76 41293 Mary Russo 169431.2 2012 0
## 77 41294 Jeffrey Spano 169411.1 2012 0
## 78 41295 Craig Wong 169409.1 2012 1
## 79 41296 Fidel Gonzalez 169378.5 2012 1
## 80 41297 Deborah Heuerman 169373.7 2012 0
## 81 41298 Maria Lopez 169357.5 2012 0
## 82 41299 Diane Scarlet 169355.0 2012 0
## 83 41300 Cassandra Chapman-Tabor 169343.9 2012 0
## 84 41301 Gabriel Rodriguez 169331.7 2012 0
## 85 41302 Jeff Lai 169315.0 2012 0
## 86 41303 Thomas Macmahon 169308.8 2012 0
## 87 41304 Burton Wan 169307.1 2012 0
## 88 41305 Edwin Lee 169304.4 2012 0
## 89 41306 Kenneth Lim 169296.0 2012 0
## 90 41307 Thanh Nguyen 169295.9 2012 1
## 91 41308 Robert Boughn 169290.0 2012 1
## 92 41309 Joseph Boyle 169275.7 2012 0
## 93 41310 Antonio Balingit 169272.0 2012 1
## 94 41311 Garrett Edwards 169266.9 2012 1
## 95 41312 Shane Oneill 169255.5 2012 1
## 96 41313 Mary Callahan 169245.2 2012 0
## 97 41314 George Engel 169243.8 2012 1
## 98 41315 Barry Parker 169242.4 2012 0
## 99 41316 Jonathan Rider 169240.6 2012 0
## 100 41317 William Reilly 169239.7 2012 0
Agregar columna de estado civil y poner valores de 1 al 5 donde 1 Soltero 2 Casado 3 Feliz 4 divorsiado 5 Viudo
# Poner una semilla igual todos para generar la misma muestra
set.seed(1000) # Un valor de semilla
# Vamos a generar el estado civil y poner valores de 1 al 5 donde 1 Soltero 2 Casado 3 Feliz 4 divorsiado 5 Viudo
edociviles <- rep(1:5, 5000) # Generamos un universo de 5000 valores entre 1 y 5
edociviles <- sample(edociviles, 2913) # Del universo que generamos tomamos una muestra de 2913 registros
edociviles
## [1] 3 4 2 2 5 5 5 5 1 1 4 2 1 4 3 2 3 2 5 4 1 1 4 1 1 2 4 5 5 3 4 2 4 4
## [35] 4 2 5 5 3 1 1 4 3 3 1 5 4 2 5 2 2 1 3 3 1 4 1 2 1 5 5 5 4 3 2 4 4 3
## [69] 5 3 4 2 2 1 1 5 3 1 4 4 1 2 1 3 2 3 4 1 2 1 1 3 4 3 1 5 5 1 5 3 1 5
## [103] 5 3 4 4 4 1 3 2 5 2 1 5 3 2 3 2 1 1 4 5 1 1 4 4 2 4 2 1 5 1 4 2 3 5
## [137] 1 2 5 3 3 4 1 4 1 1 5 5 4 5 2 2 5 5 1 1 4 5 2 4 5 1 5 5 2 5 5 1 5 5
## [171] 4 5 5 1 1 2 5 5 4 4 3 4 1 5 5 1 5 4 5 2 1 5 5 4 3 4 3 2 4 3 2 3 5 1
## [205] 3 2 4 2 1 4 2 3 5 5 4 5 4 2 3 5 1 5 4 5 5 3 4 3 5 1 3 5 1 4 2 3 3 2
## [239] 4 1 5 5 2 4 2 1 3 3 4 1 1 2 1 3 1 1 4 3 1 3 4 2 5 4 5 1 4 3 5 2 3 1
## [273] 3 1 4 5 2 4 4 1 2 4 3 4 2 2 5 2 3 1 3 2 3 5 1 2 2 5 4 3 5 4 1 2 2 2
## [307] 5 2 3 4 3 4 1 4 1 3 2 1 2 1 2 2 2 5 5 3 2 1 3 4 1 2 3 2 2 2 5 5 3 2
## [341] 2 3 3 4 3 5 3 2 1 2 2 2 2 2 1 5 1 3 1 4 4 2 5 3 4 2 3 4 4 5 4 2 5 5
## [375] 2 3 3 5 3 1 1 2 4 2 2 4 1 3 4 4 3 5 5 1 1 2 4 1 2 1 3 2 4 5 2 1 5 3
## [409] 4 4 5 2 3 5 2 3 1 3 2 1 1 4 5 2 5 3 2 2 5 4 4 3 5 1 2 5 5 4 4 5 4 5
## [443] 2 3 2 1 5 5 4 1 1 5 2 1 2 2 2 2 2 3 4 5 5 2 5 3 4 2 1 1 2 5 2 2 3 4
## [477] 5 1 2 5 5 3 3 1 2 4 5 4 5 3 4 4 5 2 3 2 1 2 4 5 1 5 1 1 5 2 4 1 5 1
## [511] 1 3 2 3 5 1 2 2 1 4 3 5 2 3 4 2 4 5 1 4 2 5 1 4 3 3 1 1 4 2 1 3 1 1
## [545] 1 3 1 2 5 2 2 4 4 3 4 4 2 1 4 2 3 4 3 1 3 4 3 1 1 5 4 4 5 2 2 1 5 2
## [579] 1 5 4 5 2 2 3 4 3 3 1 2 1 5 5 5 5 2 4 1 3 2 2 3 3 5 3 1 2 5 5 3 3 1
## [613] 5 4 3 2 2 3 2 3 2 5 4 2 3 2 3 3 1 2 1 3 3 5 5 3 2 2 4 1 4 3 2 1 5 5
## [647] 5 5 5 5 5 2 4 3 5 2 1 3 2 3 5 2 2 5 1 5 1 5 2 5 4 2 3 4 1 5 4 4 3 2
## [681] 2 2 2 2 2 1 3 2 3 4 4 3 4 2 3 2 2 1 2 1 3 1 5 4 4 3 2 2 3 5 3 4 5 1
## [715] 2 1 4 5 2 4 2 4 1 1 1 3 4 4 2 3 5 2 3 2 5 1 1 2 3 3 5 2 2 2 1 4 1 4
## [749] 3 1 3 5 2 2 5 1 1 5 5 3 2 1 2 3 2 3 1 5 4 5 3 2 4 5 5 2 3 1 1 4 5 1
## [783] 1 5 3 1 2 5 3 1 4 4 3 4 4 4 4 4 4 2 4 3 5 5 1 4 4 3 3 3 5 2 2 4 3 1
## [817] 2 3 1 1 1 5 2 2 4 2 5 5 1 2 4 4 2 2 3 2 1 1 1 1 5 2 4 4 1 5 2 3 3 4
## [851] 4 2 4 2 1 5 1 2 1 1 3 2 3 2 5 3 1 5 5 2 5 4 4 3 1 5 1 2 4 4 1 4 1 4
## [885] 4 3 4 3 2 4 4 4 3 3 4 3 1 1 4 4 5 1 1 3 2 4 5 5 5 1 5 3 1 3 3 3 2 2
## [919] 5 5 3 3 5 1 1 5 2 1 3 3 5 2 1 2 1 5 2 3 2 2 3 1 2 3 5 1 2 3 1 1 2 1
## [953] 3 5 4 4 5 2 2 4 2 2 1 2 4 1 4 2 4 1 2 4 3 3 5 4 4 2 2 3 1 1 1 4 3 5
## [987] 4 1 2 3 1 5 3 3 4 2 5 5 1 3 3 1 1 2 5 4 3 4 1 5 1 5 5 3 5 4 2 2 1 5
## [1021] 4 2 3 1 1 4 2 5 4 2 5 1 1 5 1 1 5 3 2 1 3 3 2 5 2 1 2 5 4 4 4 3 4 4
## [1055] 1 5 3 1 3 5 2 5 3 2 4 5 1 1 4 1 4 3 4 4 5 4 5 2 2 4 2 4 1 5 1 4 3 5
## [1089] 4 1 3 4 3 1 2 1 5 4 3 5 1 4 1 3 3 1 3 2 4 1 5 1 2 2 3 3 4 3 3 4 3 3
## [1123] 2 3 3 1 5 1 3 1 1 5 4 3 2 4 5 3 1 2 2 5 1 3 3 4 2 5 1 5 4 4 2 5 5 5
## [1157] 5 4 5 3 1 3 1 1 3 1 5 5 4 1 3 3 1 2 5 4 2 3 2 3 3 1 2 5 3 1 1 2 4 4
## [1191] 5 4 2 3 4 3 5 5 3 2 1 3 2 5 2 1 4 4 1 1 2 3 3 2 4 3 5 5 4 5 5 3 5 1
## [1225] 1 5 5 5 5 2 1 4 5 2 2 1 4 2 3 1 2 2 4 4 4 1 3 1 4 1 4 3 2 5 5 2 1 5
## [1259] 3 3 1 4 2 1 5 1 2 1 4 2 5 4 1 3 5 3 3 4 5 3 4 2 1 5 1 3 3 1 4 2 5 3
## [1293] 4 4 3 3 3 1 1 4 5 2 5 5 1 1 5 2 4 2 4 1 4 4 2 3 1 1 1 3 4 1 4 5 5 5
## [1327] 5 2 3 4 3 4 3 1 2 5 3 5 1 1 1 2 3 3 5 1 3 2 1 1 2 4 3 5 2 2 5 4 2 1
## [1361] 1 3 4 2 2 5 2 2 4 3 3 2 5 5 4 2 4 5 4 4 4 3 2 4 3 1 1 4 4 2 4 1 3 2
## [1395] 1 2 5 3 3 4 4 3 3 5 2 5 3 5 4 4 5 2 5 2 1 3 1 3 3 2 4 5 4 1 4 3 1 3
## [1429] 3 4 1 1 3 5 3 2 5 3 1 5 1 4 5 2 4 1 3 4 1 3 3 2 5 1 2 5 3 2 3 2 4 4
## [1463] 3 5 3 1 2 1 5 5 2 1 4 5 3 5 5 2 4 2 5 1 4 5 5 1 5 2 1 4 3 3 2 4 5 3
## [1497] 4 4 2 1 4 5 3 2 2 4 5 1 2 2 5 4 5 5 1 2 3 2 4 3 3 1 3 5 3 5 1 1 1 3
## [1531] 1 1 3 5 5 1 5 5 5 2 3 2 5 2 1 5 1 3 3 4 4 2 5 5 5 4 4 2 5 4 1 2 3 4
## [1565] 1 1 2 3 1 5 4 2 1 4 1 1 3 5 3 3 1 5 1 5 2 5 5 4 1 2 1 2 5 5 5 2 1 3
## [1599] 3 5 2 1 5 2 2 2 2 2 1 5 1 5 4 1 5 3 3 5 5 5 4 5 5 2 4 5 4 3 4 5 5 3
## [1633] 3 4 3 1 4 5 2 1 1 1 3 1 5 4 1 1 5 5 4 4 3 5 2 2 3 5 3 2 2 4 5 4 5 5
## [1667] 4 5 4 5 5 5 4 3 1 2 1 2 1 2 3 2 1 1 5 1 3 3 1 4 2 3 3 1 4 4 4 4 4 5
## [1701] 1 1 5 5 1 1 2 2 4 1 4 2 2 3 3 4 2 4 5 5 1 3 1 4 3 5 5 4 3 2 3 3 5 1
## [1735] 2 5 2 2 4 1 4 3 5 3 3 2 5 1 3 5 4 3 2 5 4 5 1 3 2 5 2 2 1 4 1 1 2 3
## [1769] 5 1 4 4 5 1 5 4 3 1 5 1 5 5 3 4 1 5 1 4 2 5 5 5 5 1 5 3 2 2 4 5 1 3
## [1803] 4 1 4 4 2 3 4 2 4 5 4 5 1 3 5 4 2 2 1 5 3 5 1 3 3 3 1 5 5 3 5 4 1 1
## [1837] 4 1 1 5 4 3 5 5 2 1 2 1 5 3 4 2 1 4 1 1 1 4 1 1 2 3 3 4 4 2 5 4 2 3
## [1871] 3 1 5 4 2 2 1 3 3 2 4 2 4 2 4 2 2 3 1 1 5 1 5 4 3 4 1 5 4 5 2 1 3 5
## [1905] 1 2 5 4 2 2 2 5 1 2 3 4 5 1 1 3 1 5 3 5 3 2 4 4 5 3 5 3 1 3 3 1 1 5
## [1939] 4 1 1 5 2 4 1 3 3 5 3 4 5 3 4 4 4 4 2 3 4 3 2 3 2 2 3 1 1 5 3 4 2 2
## [1973] 5 4 4 1 4 4 2 3 2 4 4 2 5 2 5 1 5 1 4 3 4 4 3 5 4 1 1 2 5 1 5 3 4 2
## [2007] 2 5 2 4 1 3 5 4 4 1 5 2 3 4 1 4 5 3 2 1 5 4 2 5 5 4 4 3 5 2 5 1 5 3
## [2041] 1 2 3 4 2 1 1 5 3 2 5 2 5 4 2 1 2 5 4 1 1 1 1 1 4 2 5 2 1 5 1 5 5 2
## [2075] 4 4 1 2 4 2 1 1 3 2 4 3 1 2 2 1 2 1 2 2 1 4 5 4 3 1 5 1 1 4 3 4 4 4
## [2109] 2 4 4 2 3 4 1 4 3 5 2 4 4 4 2 2 4 4 5 1 2 3 2 5 4 3 3 2 1 3 4 5 3 4
## [2143] 3 2 4 3 2 5 3 1 5 1 4 4 1 4 1 2 5 4 3 2 4 4 1 3 5 3 2 4 2 3 4 3 1 3
## [2177] 4 2 4 4 5 1 2 3 3 5 3 2 1 3 4 3 5 1 2 5 3 2 4 4 5 2 1 5 4 1 5 5 4 4
## [2211] 4 3 3 2 5 2 1 5 4 3 2 2 1 4 2 4 4 1 2 1 5 3 5 4 2 3 3 4 5 4 4 5 3 4
## [2245] 1 2 3 5 2 4 4 5 3 1 2 5 3 2 1 1 5 2 2 3 4 2 3 1 1 5 3 5 4 3 3 5 2 3
## [2279] 4 1 4 1 3 1 1 2 2 2 1 4 5 2 1 3 1 4 3 4 2 4 3 4 3 3 1 2 1 3 4 4 2 3
## [2313] 2 5 4 1 1 1 5 5 2 5 3 3 3 5 2 3 3 4 1 4 5 4 1 1 5 2 1 4 3 1 2 3 2 4
## [2347] 4 5 2 3 1 2 5 3 4 2 3 2 2 5 1 3 5 1 2 5 5 1 1 3 2 1 1 3 1 4 2 4 5 4
## [2381] 5 5 4 3 4 5 4 1 4 4 4 4 2 1 4 2 1 4 2 5 2 1 3 4 1 2 5 4 1 2 2 3 3 5
## [2415] 2 3 3 1 3 2 5 1 5 1 5 3 2 3 4 1 2 1 5 1 3 5 2 1 5 2 1 3 3 5 5 4 4 5
## [2449] 1 1 3 5 3 2 4 1 1 1 2 4 1 5 4 2 1 2 5 2 3 3 3 5 3 4 2 4 4 1 4 5 4 2
## [2483] 3 2 4 1 3 4 1 2 1 5 3 1 3 3 4 5 3 3 1 1 5 1 5 4 3 5 2 2 2 1 3 4 4 2
## [2517] 2 1 5 5 2 1 5 4 4 2 1 2 4 3 1 4 3 3 2 4 4 3 4 5 1 1 3 4 2 2 2 2 5 2
## [2551] 3 5 4 3 2 5 1 1 4 1 1 3 2 2 4 4 4 2 1 3 4 5 2 4 3 2 5 4 1 1 3 4 5 1
## [2585] 2 5 5 1 2 1 1 4 3 3 3 3 3 3 1 1 2 4 4 1 4 2 4 1 3 3 1 1 3 3 2 2 4 5
## [2619] 1 3 1 1 3 1 5 4 5 5 4 1 3 4 4 5 3 4 1 2 2 5 1 2 2 1 1 2 3 1 3 5 3 4
## [2653] 5 2 4 5 5 3 4 5 1 1 2 4 3 1 2 4 4 3 2 4 5 5 1 4 4 4 1 4 2 5 1 4 3 1
## [2687] 2 3 5 3 4 5 4 3 2 3 5 4 4 1 5 3 2 4 4 2 4 4 2 1 2 5 1 5 4 2 2 5 4 1
## [2721] 2 2 2 5 3 4 1 5 2 2 2 2 2 3 5 1 4 3 2 5 5 1 5 4 3 3 4 4 2 5 5 5 3 4
## [2755] 3 2 2 2 4 3 5 4 3 4 4 1 2 2 3 1 2 4 2 3 3 1 2 2 3 1 1 1 5 1 1 4 4 2
## [2789] 1 3 2 4 3 2 2 1 1 4 3 3 3 2 4 1 5 1 3 2 4 4 3 2 3 1 3 3 2 4 3 4 3 2
## [2823] 1 5 1 4 3 5 4 3 2 3 3 5 2 1 2 2 3 1 4 3 4 4 3 5 3 4 5 4 1 3 2 1 2 3
## [2857] 3 3 3 1 4 4 3 2 5 2 3 4 3 3 4 4 3 4 1 3 4 4 5 2 4 3 5 2 3 3 3 2 4 5
## [2891] 2 2 5 2 2 4 2 4 5 5 5 4 4 4 1 1 1 5 4 1 3 5 1
cuales <- mutate(cuales, edocivil = edociviles) # Agrega columna edocivil a cuales
head(cuales, 100) # Mostramos los primeros 100 para revisar que esta bien
## Id EmployeeName TotalPayBenefits Year genero edocivil
## 1 41218 Cheryl De Lemos 169995.4 2012 1 3
## 2 41219 Daniel Godfrey 169990.1 2012 1 4
## 3 41220 Robert Harvey 169982.0 2012 0 2
## 4 41221 Lawrence McDonnell 169980.4 2012 0 2
## 5 41222 Sergio Chavez 169973.1 2012 1 5
## 6 41223 Michael Grande 169970.4 2012 0 5
## 7 41224 Jeffrey Chow 169963.2 2012 1 5
## 8 41225 Winilyn Hidalgo 169960.5 2012 1 5
## 9 41226 Rodney Lee 169960.3 2012 1 1
## 10 41227 Lucille Palma 169940.8 2012 0 1
## 11 41228 Jonathan Rapp 169939.2 2012 1 4
## 12 41229 Ajay Saxena 169936.3 2012 0 2
## 13 41230 Albert Tom 169933.8 2012 0 1
## 14 41231 Edith Hammond 169930.6 2012 1 4
## 15 41232 Hector Tam 169925.7 2012 1 3
## 16 41233 Eugene Ling 169898.1 2012 1 2
## 17 41234 Xing Wang 169897.1 2012 1 3
## 18 41235 Crystal McDonald 169893.1 2012 0 2
## 19 41236 Patrick Cox 169890.4 2012 1 5
## 20 41237 Balraj Singh Rai 169887.5 2012 1 4
## 21 41238 Jennifer Northridge 169879.5 2012 1 1
## 22 41239 Roger Fong 169876.2 2012 0 1
## 23 41240 Edgar Tabo 169876.1 2012 1 4
## 24 41241 Kin Lee 169864.1 2012 0 1
## 25 41242 Kevin Adkins 169849.0 2012 1 1
## 26 41243 Curtis Caldwell 169837.2 2012 0 2
## 27 41244 Dianna Yanez 169831.5 2012 1 4
## 28 41245 Samuel Yu 169820.4 2012 1 5
## 29 41246 Eugene Shu 169811.9 2012 1 5
## 30 41247 Dale Winniford 169799.7 2012 1 3
## 31 41248 Clifford Burkhart 169798.2 2012 0 4
## 32 41249 Suzanne Miller 169794.0 2012 0 2
## 33 41250 Catheryn Williams 169791.3 2012 0 4
## 34 41251 Stephen Gritsch 169741.6 2012 0 4
## 35 41252 Maria Cecilia Martin 169740.3 2012 1 4
## 36 41253 Russell Roby 169736.7 2012 1 2
## 37 41254 Lawrence Soe 169732.1 2012 1 5
## 38 41255 Stephon Degand 169723.0 2012 0 5
## 39 41256 Michelle Tong 169704.5 2012 1 3
## 40 41257 James Kazarian 169704.2 2012 0 1
## 41 41258 Violeta Del Mundo 169699.7 2012 0 1
## 42 41259 Fred Lew 169693.3 2012 1 4
## 43 41260 Donald Bannett 169688.4 2012 1 3
## 44 41261 Miles Young 169673.6 2012 0 3
## 45 41262 Victor Le 169660.8 2012 0 1
## 46 41263 Eric Louie 169660.2 2012 1 5
## 47 41264 Lawrence Ng 169654.4 2012 1 4
## 48 41265 Eduard Ochoa 169639.7 2012 0 2
## 49 41266 Geoffrey Clayton 169635.6 2012 1 5
## 50 41267 Rona Sandler 169633.7 2012 1 2
## 51 41268 Larry Para 169624.0 2012 1 2
## 52 41269 Tracy Miesen 169619.6 2012 1 1
## 53 41270 Linda Moore 169607.8 2012 1 3
## 54 41271 Kaushal Bhaskar 169591.4 2012 0 3
## 55 41272 Moses Bautista 169562.9 2012 0 1
## 56 41273 Sophal Chea 169556.0 2012 1 4
## 57 41274 John Edward Herbert 169540.4 2012 0 1
## 58 41275 Shao Ping Lai 169540.4 2012 0 2
## 59 41276 William McCarthy 169527.5 2012 1 1
## 60 41277 Keith Baraka 169526.0 2012 0 5
## 61 41278 Richie Owyang 169518.8 2012 0 5
## 62 41279 Kenyon Bowers 169509.4 2012 0 5
## 63 41280 Herbert Mariano 169502.8 2012 0 4
## 64 41281 Maria Perez 169493.4 2012 0 3
## 65 41282 Gail Clabby 169492.0 2012 1 2
## 66 41283 Philip Secondez 169485.0 2012 0 4
## 67 41284 Marco Desangles 169480.8 2012 0 4
## 68 41285 Wilfredo Arquiza 169479.5 2012 0 3
## 69 41286 David Sands 169467.2 2012 1 5
## 70 41287 M J Castagnola 169463.2 2012 0 3
## 71 41288 Edwin Gaffud 169454.9 2012 0 4
## 72 41289 Sarah Lindley 169453.5 2012 1 2
## 73 41290 Carlos Manfredi 169442.4 2012 1 2
## 74 41291 Cathal Hennessy 169442.1 2012 1 1
## 75 41292 Diana Rosenstein 169432.1 2012 0 1
## 76 41293 Mary Russo 169431.2 2012 0 5
## 77 41294 Jeffrey Spano 169411.1 2012 0 3
## 78 41295 Craig Wong 169409.1 2012 1 1
## 79 41296 Fidel Gonzalez 169378.5 2012 1 4
## 80 41297 Deborah Heuerman 169373.7 2012 0 4
## 81 41298 Maria Lopez 169357.5 2012 0 1
## 82 41299 Diane Scarlet 169355.0 2012 0 2
## 83 41300 Cassandra Chapman-Tabor 169343.9 2012 0 1
## 84 41301 Gabriel Rodriguez 169331.7 2012 0 3
## 85 41302 Jeff Lai 169315.0 2012 0 2
## 86 41303 Thomas Macmahon 169308.8 2012 0 3
## 87 41304 Burton Wan 169307.1 2012 0 4
## 88 41305 Edwin Lee 169304.4 2012 0 1
## 89 41306 Kenneth Lim 169296.0 2012 0 2
## 90 41307 Thanh Nguyen 169295.9 2012 1 1
## 91 41308 Robert Boughn 169290.0 2012 1 1
## 92 41309 Joseph Boyle 169275.7 2012 0 3
## 93 41310 Antonio Balingit 169272.0 2012 1 4
## 94 41311 Garrett Edwards 169266.9 2012 1 3
## 95 41312 Shane Oneill 169255.5 2012 1 1
## 96 41313 Mary Callahan 169245.2 2012 0 5
## 97 41314 George Engel 169243.8 2012 1 5
## 98 41315 Barry Parker 169242.4 2012 0 1
## 99 41316 Jonathan Rider 169240.6 2012 0 5
## 100 41317 William Reilly 169239.7 2012 0 3
Cuantos hay de genero 0 y de genero 1
# Genera una tabla cruzada o lo que es lo mismo la frecuencia de clases de algua variable en este caso es genero
table(cuales$genero)
##
## 0 1
## 1468 1445
Cuantos hay de cada Estado Civil
# Genera una tabla cruzada o lo que es lo mismo la frecuencia de clases de algua variable en este caso Estado civil
table(cuales$edocivil)
##
## 1 2 3 4 5
## 593 593 564 593 570
Vamos a ver un histograma
hist(cuales$genero)
hist(cuales$edocivil)
Interpretacion de la Practica
paste("En esta practica se filtro por nombre en este caso Kevin Lee del cual obtuvimos 13 registros, tambien filtramos las personas que reciben un sueldo entre 150,000 y 170,000 en el año 2012 de ahi obtuvimos 2913 registros, tambien filtramos las personas que estan por ensima del quartil al 75% que fueron 37164 registros, con la funcion selec solo nos trajimos algunas columnas para hacer mas entendibles los datos, ordenamos los datos con arrange y le agregamos 2 columnas a las cuales les asigamos variables aleatorias de genero y estado civil y por ultimo graficamos por genero y estado civil")
## [1] "En esta practica se filtro por nombre en este caso Kevin Lee del cual obtuvimos 13 registros, tambien filtramos las personas que reciben un sueldo entre 150,000 y 170,000 en el año 2012 de ahi obtuvimos 2913 registros, tambien filtramos las personas que estan por ensima del quartil al 75% que fueron 37164 registros, con la funcion selec solo nos trajimos algunas columnas para hacer mas entendibles los datos, ordenamos los datos con arrange y le agregamos 2 columnas a las cuales les asigamos variables aleatorias de genero y estado civil y por ultimo graficamos por genero y estado civil"