OBJETIVO: Utilizar la lirberia dplyr para analizar datos de salarios

# 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

Los datos

# Cargar datos de salarios
# salarios <- read.csv("Va la ruta en donde estan los datos")
salarios <- read_csv("C:/Users/tthan/Documents/CIENCIA DE LOS DATOS/Datos/Salaries.csv")
## Parsed with column specification:
## cols(
##   Id = col_double(),
##   EmployeeName = col_character(),
##   JobTitle = col_character(),
##   BasePay = col_double(),
##   OvertimePay = col_double(),
##   OtherPay = col_double(),
##   Benefits = col_logical(),
##   TotalPay = col_double(),
##   TotalPayBenefits = col_double(),
##   Year = col_double(),
##   Notes = col_logical(),
##   Agency = col_character(),
##   Status = col_logical()
## )
## Warning: 150614 parsing failures.
##   row      col           expected   actual                                                               file
## 36160 Benefits 1/0/T/F/TRUE/FALSE 44430.12 'C:/Users/tthan/Documents/CIENCIA DE LOS DATOS/Datos/Salaries.csv'
## 36161 Benefits 1/0/T/F/TRUE/FALSE 69810.19 'C:/Users/tthan/Documents/CIENCIA DE LOS DATOS/Datos/Salaries.csv'
## 36162 Benefits 1/0/T/F/TRUE/FALSE 53102.29 'C:/Users/tthan/Documents/CIENCIA DE LOS DATOS/Datos/Salaries.csv'
## 36163 Benefits 1/0/T/F/TRUE/FALSE 72047.88 'C:/Users/tthan/Documents/CIENCIA DE LOS DATOS/Datos/Salaries.csv'
## 36164 Benefits 1/0/T/F/TRUE/FALSE 44438.25 'C:/Users/tthan/Documents/CIENCIA DE LOS DATOS/Datos/Salaries.csv'
## ..... ........ .................. ........ ..................................................................
## See problems(...) for more details.
head (salarios)
## # A tibble: 6 x 13
##      Id EmployeeName JobTitle BasePay OvertimePay OtherPay Benefits
##   <dbl> <chr>        <chr>      <dbl>       <dbl>    <dbl> <lgl>   
## 1     1 NATHANIEL F~ GENERAL~ 167411.          0   400184. NA      
## 2     2 GARY JIMENEZ CAPTAIN~ 155966.     245132.  137811. NA      
## 3     3 ALBERT PARD~ CAPTAIN~ 212739.     106088.   16453. NA      
## 4     4 CHRISTOPHER~ WIRE RO~  77916       56121.  198307. NA      
## 5     5 PATRICK GAR~ DEPUTY ~ 134402.       9737   182235. NA      
## 6     6 DAVID SULLI~ ASSISTA~ 118602        8601   189083. NA      
## # ... with 6 more variables: TotalPay <dbl>, TotalPayBenefits <dbl>,
## #   Year <dbl>, Notes <lgl>, Agency <chr>, Status <lgl>
str(salarios)
## Classes 'spec_tbl_df', 'tbl_df', 'tbl' and 'data.frame': 148654 obs. of  13 variables:
##  $ Id              : num  1 2 3 4 5 6 7 8 9 10 ...
##  $ EmployeeName    : chr  "NATHANIEL FORD" "GARY JIMENEZ" "ALBERT PARDINI" "CHRISTOPHER CHONG" ...
##  $ JobTitle        : chr  "GENERAL MANAGER-METROPOLITAN TRANSIT AUTHORITY" "CAPTAIN III (POLICE DEPARTMENT)" "CAPTAIN III (POLICE DEPARTMENT)" "WIRE ROPE CABLE MAINTENANCE MECHANIC" ...
##  $ BasePay         : num  167411 155966 212739 77916 134402 ...
##  $ OvertimePay     : num  0 245132 106088 56121 9737 ...
##  $ OtherPay        : num  400184 137811 16453 198307 182235 ...
##  $ Benefits        : logi  NA NA NA NA NA NA ...
##  $ TotalPay        : num  567595 538909 335280 332344 326373 ...
##  $ TotalPayBenefits: num  567595 538909 335280 332344 326373 ...
##  $ Year            : num  2011 2011 2011 2011 2011 ...
##  $ Notes           : logi  NA NA NA NA NA NA ...
##  $ Agency          : chr  "San Francisco" "San Francisco" "San Francisco" "San Francisco" ...
##  $ Status          : logi  NA NA NA NA NA NA ...
##  - attr(*, "problems")=Classes 'tbl_df', 'tbl' and 'data.frame': 150614 obs. of  5 variables:
##   ..$ row     : int  36160 36161 36162 36163 36164 36165 36166 36167 36168 36169 ...
##   ..$ col     : chr  "Benefits" "Benefits" "Benefits" "Benefits" ...
##   ..$ expected: chr  "1/0/T/F/TRUE/FALSE" "1/0/T/F/TRUE/FALSE" "1/0/T/F/TRUE/FALSE" "1/0/T/F/TRUE/FALSE" ...
##   ..$ actual  : chr  "44430.12" "69810.19" "53102.29" "72047.88" ...
##   ..$ file    : chr  "'C:/Users/tthan/Documents/CIENCIA DE LOS DATOS/Datos/Salaries.csv'" "'C:/Users/tthan/Documents/CIENCIA DE LOS DATOS/Datos/Salaries.csv'" "'C:/Users/tthan/Documents/CIENCIA DE LOS DATOS/Datos/Salaries.csv'" "'C:/Users/tthan/Documents/CIENCIA DE LOS DATOS/Datos/Salaries.csv'" ...
##  - attr(*, "spec")=
##   .. cols(
##   ..   Id = col_double(),
##   ..   EmployeeName = col_character(),
##   ..   JobTitle = col_character(),
##   ..   BasePay = col_double(),
##   ..   OvertimePay = col_double(),
##   ..   OtherPay = col_double(),
##   ..   Benefits = col_logical(),
##   ..   TotalPay = col_double(),
##   ..   TotalPayBenefits = col_double(),
##   ..   Year = col_double(),
##   ..   Notes = col_logical(),
##   ..   Agency = col_character(),
##   ..   Status = col_logical()
##   .. )
summary (salarios)
##        Id         EmployeeName         JobTitle            BasePay      
##  Min.   :     1   Length:148654      Length:148654      Min.   :  -166  
##  1st Qu.: 37164   Class :character   Class :character   1st Qu.: 33588  
##  Median : 74328   Mode  :character   Mode  :character   Median : 65007  
##  Mean   : 74328                                         Mean   : 66325  
##  3rd Qu.:111491                                         3rd Qu.: 94691  
##  Max.   :148654                                         Max.   :319275  
##                                                         NA's   :609     
##   OvertimePay           OtherPay        Benefits          TotalPay       
##  Min.   :    -0.01   Min.   : -7058.6   Mode:logical   Min.   :  -618.1  
##  1st Qu.:     0.00   1st Qu.:     0.0   NA's:148654    1st Qu.: 36169.0  
##  Median :     0.00   Median :   811.3                  Median : 71426.6  
##  Mean   :  5066.06   Mean   :  3648.8                  Mean   : 74768.3  
##  3rd Qu.:  4658.18   3rd Qu.:  4236.1                  3rd Qu.:105839.1  
##  Max.   :245131.88   Max.   :400184.2                  Max.   :567595.4  
##  NA's   :4           NA's   :4                                           
##  TotalPayBenefits        Year       Notes            Agency         
##  Min.   :  -618.1   Min.   :2011   Mode:logical   Length:148654     
##  1st Qu.: 44065.7   1st Qu.:2012   NA's:148654    Class :character  
##  Median : 92404.1   Median :2013                  Mode  :character  
##  Mean   : 93692.6   Mean   :2013                                    
##  3rd Qu.:132876.5   3rd Qu.:2014                                    
##  Max.   :567595.4   Max.   :2014                                    
##                                                                     
##   Status       
##  Mode:logical  
##  NA's:148654   
##                
##                
##                
##                
##

Filtrar datos del empleado Kevin Lee del año 2014

filter(salarios, EmployeeName == "Kevin Lee")
## # A tibble: 13 x 13
##        Id EmployeeName JobTitle BasePay OvertimePay OtherPay Benefits
##     <dbl> <chr>        <chr>      <dbl>       <dbl>    <dbl> <lgl>   
##  1  39716 Kevin Lee    Police ~ 115867.      23523.    9314. NA      
##  2  40571 Kevin Lee    Police ~ 117171.      19607.    4245. NA      
##  3  42511 Kevin Lee    Electri~  79221.      40247.    3353. NA      
##  4  49271 Kevin Lee    Deputy ~  84512.          0     1470. NA      
##  5  49440 Kevin Lee    Deputy ~  84512.          0      975. NA      
##  6  50124 Kevin Lee    Personn~  83382           0        0  NA      
##  7  52234 Kevin Lee    Senior ~  66774.       9599.    1093. NA      
##  8  53932 Kevin Lee    Transit~  57397.       9990.    1800. NA      
##  9  55120 Kevin Lee    IS Admi~  68940.          0        0  NA      
## 10 112386 Kevin Lee    Sergean~ 137982.      18537.   16040. NA      
## 11 123142 Kevin Lee    IT Oper~  91606.          0     1013  NA      
## 12 124166 Kevin Lee    Personn~  88353.          0        0  NA      
## 13 124659 Kevin Lee    Transit~  67230.      10961.    4051. NA      
## # ... with 6 more variables: TotalPay <dbl>, TotalPayBenefits <dbl>,
## #   Year <dbl>, Notes <lgl>, Agency <chr>, Status <lgl>
filter(salarios, EmployeeName == "Kevin Lee" & Year == 2014)
## # A tibble: 4 x 13
##       Id EmployeeName JobTitle BasePay OvertimePay OtherPay Benefits
##    <dbl> <chr>        <chr>      <dbl>       <dbl>    <dbl> <lgl>   
## 1 112386 Kevin Lee    Sergean~ 137982.      18537.   16040. NA      
## 2 123142 Kevin Lee    IT Oper~  91606.          0     1013  NA      
## 3 124166 Kevin Lee    Personn~  88353.          0        0  NA      
## 4 124659 Kevin Lee    Transit~  67230.      10961.    4051. NA      
## # ... with 6 more variables: TotalPay <dbl>, TotalPayBenefits <dbl>,
## #   Year <dbl>, Notes <lgl>, Agency <chr>, Status <lgl>

Cuántos empleados están entre un salario total de 150000 y 170000 en el 2012

cuantos <- filter(salarios, TotalPayBenefits >= 150000 & TotalPayBenefits <= 170000 & Year == 2012)

str(cuantos)    # Estructura de cuantos
## Classes 'spec_tbl_df', 'tbl_df', 'tbl' and 'data.frame': 2913 obs. of  13 variables:
##  $ Id              : num  41218 41219 41220 41221 41222 ...
##  $ EmployeeName    : chr  "Cheryl De Lemos" "Daniel Godfrey" "Robert Harvey" "Lawrence McDonnell" ...
##  $ JobTitle        : chr  "Registered Nurse" "Utility Plumber Supervisor 1" "Automotive Mechanic Sprv 1" "Firefighter" ...
##  $ BasePay         : num  112611 102662 97609 110847 88374 ...
##  $ OvertimePay     : num  5648 19465 22952 3927 33428 ...
##  $ OtherPay        : num  6037 6254 8148 18492 10512 ...
##  $ Benefits        : logi  NA NA NA NA NA NA ...
##  $ TotalPay        : num  124296 128382 128709 133266 132314 ...
##  $ TotalPayBenefits: num  169995 169990 169982 169980 169973 ...
##  $ Year            : num  2012 2012 2012 2012 2012 ...
##  $ Notes           : logi  NA NA NA NA NA NA ...
##  $ Agency          : chr  "San Francisco" "San Francisco" "San Francisco" "San Francisco" ...
##  $ Status          : logi  NA NA NA NA NA NA ...
##  - attr(*, "problems")=Classes 'tbl_df', 'tbl' and 'data.frame': 150614 obs. of  5 variables:
##   ..$ row     : int  36160 36161 36162 36163 36164 36165 36166 36167 36168 36169 ...
##   ..$ col     : chr  "Benefits" "Benefits" "Benefits" "Benefits" ...
##   ..$ expected: chr  "1/0/T/F/TRUE/FALSE" "1/0/T/F/TRUE/FALSE" "1/0/T/F/TRUE/FALSE" "1/0/T/F/TRUE/FALSE" ...
##   ..$ actual  : chr  "44430.12" "69810.19" "53102.29" "72047.88" ...
##   ..$ file    : chr  "'C:/Users/tthan/Documents/CIENCIA DE LOS DATOS/Datos/Salaries.csv'" "'C:/Users/tthan/Documents/CIENCIA DE LOS DATOS/Datos/Salaries.csv'" "'C:/Users/tthan/Documents/CIENCIA DE LOS DATOS/Datos/Salaries.csv'" "'C:/Users/tthan/Documents/CIENCIA DE LOS DATOS/Datos/Salaries.csv'" ...
##  - attr(*, "spec")=
##   .. cols(
##   ..   Id = col_double(),
##   ..   EmployeeName = col_character(),
##   ..   JobTitle = col_character(),
##   ..   BasePay = col_double(),
##   ..   OvertimePay = col_double(),
##   ..   OtherPay = col_double(),
##   ..   Benefits = col_logical(),
##   ..   TotalPay = col_double(),
##   ..   TotalPayBenefits = col_double(),
##   ..   Year = col_double(),
##   ..   Notes = col_logical(),
##   ..   Agency = col_character(),
##   ..   Status = col_logical()
##   .. )
nrow(cuantos)   # Cuantos registros
## [1] 2913

Cuantos regsitros hay por encima del cuartil 75

cuartil75 <- quantile(salarios$TotalPayBenefits, 0.75)
cuantos <- filter(salarios, TotalPayBenefits >= cuartil75)

str(cuantos)    # Estructura de cuantos
## Classes 'spec_tbl_df', 'tbl_df', 'tbl' and 'data.frame': 37164 obs. of  13 variables:
##  $ Id              : num  1 2 3 4 5 6 7 8 9 10 ...
##  $ EmployeeName    : chr  "NATHANIEL FORD" "GARY JIMENEZ" "ALBERT PARDINI" "CHRISTOPHER CHONG" ...
##  $ JobTitle        : chr  "GENERAL MANAGER-METROPOLITAN TRANSIT AUTHORITY" "CAPTAIN III (POLICE DEPARTMENT)" "CAPTAIN III (POLICE DEPARTMENT)" "WIRE ROPE CABLE MAINTENANCE MECHANIC" ...
##  $ BasePay         : num  167411 155966 212739 77916 134402 ...
##  $ OvertimePay     : num  0 245132 106088 56121 9737 ...
##  $ OtherPay        : num  400184 137811 16453 198307 182235 ...
##  $ Benefits        : logi  NA NA NA NA NA NA ...
##  $ TotalPay        : num  567595 538909 335280 332344 326373 ...
##  $ TotalPayBenefits: num  567595 538909 335280 332344 326373 ...
##  $ Year            : num  2011 2011 2011 2011 2011 ...
##  $ Notes           : logi  NA NA NA NA NA NA ...
##  $ Agency          : chr  "San Francisco" "San Francisco" "San Francisco" "San Francisco" ...
##  $ Status          : logi  NA NA NA NA NA NA ...
##  - attr(*, "problems")=Classes 'tbl_df', 'tbl' and 'data.frame': 150614 obs. of  5 variables:
##   ..$ row     : int  36160 36161 36162 36163 36164 36165 36166 36167 36168 36169 ...
##   ..$ col     : chr  "Benefits" "Benefits" "Benefits" "Benefits" ...
##   ..$ expected: chr  "1/0/T/F/TRUE/FALSE" "1/0/T/F/TRUE/FALSE" "1/0/T/F/TRUE/FALSE" "1/0/T/F/TRUE/FALSE" ...
##   ..$ actual  : chr  "44430.12" "69810.19" "53102.29" "72047.88" ...
##   ..$ file    : chr  "'C:/Users/tthan/Documents/CIENCIA DE LOS DATOS/Datos/Salaries.csv'" "'C:/Users/tthan/Documents/CIENCIA DE LOS DATOS/Datos/Salaries.csv'" "'C:/Users/tthan/Documents/CIENCIA DE LOS DATOS/Datos/Salaries.csv'" "'C:/Users/tthan/Documents/CIENCIA DE LOS DATOS/Datos/Salaries.csv'" ...
##  - attr(*, "spec")=
##   .. cols(
##   ..   Id = col_double(),
##   ..   EmployeeName = col_character(),
##   ..   JobTitle = col_character(),
##   ..   BasePay = col_double(),
##   ..   OvertimePay = col_double(),
##   ..   OtherPay = col_double(),
##   ..   Benefits = col_logical(),
##   ..   TotalPay = col_double(),
##   ..   TotalPayBenefits = col_double(),
##   ..   Year = col_double(),
##   ..   Notes = col_logical(),
##   ..   Agency = col_character(),
##   ..   Status = col_logical()
##   .. )
nrow(cuantos)   # Cuantos registros
## [1] 37164

Proyectar atributos de un conjunto de datos por medio de select

Primero un select y luego un filter o viceversa

registros <- select(salarios, Id, EmployeeName, TotalPayBenefits, Year)
# registros
cuales <- filter(registros, TotalPayBenefits >= 150000 & TotalPayBenefits <= 170000 & Year == 2012)
cuales
## # A tibble: 2,913 x 4
##       Id EmployeeName       TotalPayBenefits  Year
##    <dbl> <chr>                         <dbl> <dbl>
##  1 41218 Cheryl De Lemos             169995.  2012
##  2 41219 Daniel Godfrey              169990.  2012
##  3 41220 Robert Harvey               169982.  2012
##  4 41221 Lawrence McDonnell          169980.  2012
##  5 41222 Sergio Chavez               169973.  2012
##  6 41223 Michael Grande              169970.  2012
##  7 41224 Jeffrey Chow                169963.  2012
##  8 41225 Winilyn Hidalgo             169960.  2012
##  9 41226 Rodney Lee                  169960.  2012
## 10 41227 Lucille Palma               169941.  2012
## # ... with 2,903 more rows

Ordenar los datos con arrange

datosOrdenados <- arrange(cuales, EmployeeName) # Por defaut es de menor a mayor

head(datosOrdenados)  # Los primeros seis
## # A tibble: 6 x 4
##      Id EmployeeName    TotalPayBenefits  Year
##   <dbl> <chr>                      <dbl> <dbl>
## 1 42773 Aaron Ballonado          159733.  2012
## 2 41480 Aaron Cowhig             168330.  2012
## 3 42067 Aaron Fischer            164281.  2012
## 4 41965 Aaron Smith              164961.  2012
## 5 42777 Aaron Yoo                159712.  2012
## 6 42739 Abraham Abarca           159989.  2012
tail(datosOrdenados)  # Los últimos seis
## # A tibble: 6 x 4
##      Id EmployeeName              TotalPayBenefits  Year
##   <dbl> <chr>                                <dbl> <dbl>
## 1 41326 Yvonne Fuentes-Pattishall          169172.  2012
## 2 43221 Zahid Khan                         156873.  2012
## 3 42623 Zara Grace Janer                   160767.  2012
## 4 44083 Zhong Qiu                          150289.  2012
## 5 41647 Zoila Maguina                      167055.  2012
## 6 42196 Zula Jones                         163423.  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 genros 0 y 1
generos <- rep(0:1, 5000)   # Es un repetición de 5000 valores entre 0 y 1. Solo necesitamos 2913, hacemos una muestra
generos <- sample(generos, 2913) # sample genera 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, 10)  # Los primeros 10
## # A tibble: 10 x 5
##       Id EmployeeName       TotalPayBenefits  Year genero
##    <dbl> <chr>                         <dbl> <dbl>  <int>
##  1 41218 Cheryl De Lemos             169995.  2012      1
##  2 41219 Daniel Godfrey              169990.  2012      1
##  3 41220 Robert Harvey               169982.  2012      0
##  4 41221 Lawrence McDonnell          169980.  2012      0
##  5 41222 Sergio Chavez               169973.  2012      1
##  6 41223 Michael Grande              169970.  2012      0
##  7 41224 Jeffrey Chow                169963.  2012      1
##  8 41225 Winilyn Hidalgo             169960.  2012      1
##  9 41226 Rodney Lee                  169960.  2012      1
## 10 41227 Lucille Palma               169941.  2012      0
cuales # Van todos
## # A tibble: 2,913 x 5
##       Id EmployeeName       TotalPayBenefits  Year genero
##    <dbl> <chr>                         <dbl> <dbl>  <int>
##  1 41218 Cheryl De Lemos             169995.  2012      1
##  2 41219 Daniel Godfrey              169990.  2012      1
##  3 41220 Robert Harvey               169982.  2012      0
##  4 41221 Lawrence McDonnell          169980.  2012      0
##  5 41222 Sergio Chavez               169973.  2012      1
##  6 41223 Michael Grande              169970.  2012      0
##  7 41224 Jeffrey Chow                169963.  2012      1
##  8 41225 Winilyn Hidalgo             169960.  2012      1
##  9 41226 Rodney Lee                  169960.  2012      1
## 10 41227 Lucille Palma               169941.  2012      0
## # ... with 2,903 more rows

Agregar columnas nuevas al conjunto de datos

Pueden ser al original o al que ya se tiene fitrado

Agregar un valor de 1, 2, 3, 4 o 5 para edocivil

# Poner una semilla igual todos para generar la misma muestra
set.seed(1000) # Un valor de semilla
# Vamos a generar genros 0 y 1
edociviles <- rep(1:5, 5000)   # Es un repetición de 5000 valores entre 0 y 1. Solo necesitamos 2913, hacemos una muestra
edociviles <- sample(edociviles, 2913) # sample genera 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, edocivil = edociviles) # Agrega columna edocivil a cuales
#head(cuales, 10)  # Los primeros 10
#cuales # Van todos

Cuantos hay de genero 0 y de genero 1

# Genera una tabla cruzada o lo que es o mismo al frecuencia de clases de algua variable en este caso genero
table(cuales$genero)
## 
##    0    1 
## 1468 1445

Cuantos hay de genero 0 y de genero 1

# Genera una tabla cruzada o lo que es o mismo al frecuencia de clases de algua variable en este caso genero
table(cuales$edocivil)
## Warning: Unknown or uninitialised column: 'edocivil'.
## < table of extent 0 >

Vamos a ver un histograma de genero

barplot(table(cuales$genero))

Analsis de Aprendizaje.

En esta practica se utilizar funciones ya utilizadas en las practias anteriores; en esta se aprendio que existe la funcion filter que dicha funcion nos ayuda a filtrar informacion de los atributos que uno requiera analizar. Asi mismo se aprendio agregar un atributo nuevo y asignarles valor.