OBJETIVO. Analizar datos de salarios
Utilizar la libreria “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("https://raw.githubusercontent.com/rpizarrog/Curso-Titulacion-Data-Science-/master/2019/Datos/Salaries.csv")
# salarios # Ya no los queremos ver
str(salarios)
## 'data.frame': 148654 obs. of 13 variables:
## $ Id : int 1 2 3 4 5 6 7 8 9 10 ...
## $ EmployeeName : Factor w/ 110810 levels "A Bernard Fatooh",..: 77636 34712 1560 17232 81101 23164 3271 22709 73975 47938 ...
## $ JobTitle : Factor w/ 2159 levels "Account Clerk",..: 836 298 298 2149 594 135 246 609 246 370 ...
## $ BasePay : num 167411 155966 212739 77916 134402 ...
## $ OvertimePay : num 0 245132 106088 56121 9737 ...
## $ OtherPay : num 400184 137811 16453 198307 182235 ...
## $ Benefits : num NA NA NA NA NA NA NA NA NA NA ...
## $ TotalPay : num 567595 538909 335280 332344 326373 ...
## $ TotalPayBenefits: num 567595 538909 335280 332344 326373 ...
## $ Year : int 2011 2011 2011 2011 2011 2011 2011 2011 2011 2011 ...
## $ 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 ...
summary(salarios)
## Id EmployeeName
## Min. : 1 Kevin Lee : 13
## 1st Qu.: 37164 Richard Lee : 11
## Median : 74328 Steven Lee : 11
## Mean : 74328 William Wong: 11
## 3rd Qu.:111491 John Chan : 9
## Max. :148654 KEVIN LEE : 9
## (Other) :148590
## JobTitle BasePay
## Transit Operator : 7036 Min. : -166
## Special Nurse : 4389 1st Qu.: 33588
## Registered Nurse : 3736 Median : 65007
## Public Svc Aide-Public Works: 2518 Mean : 66325
## Police Officer 3 : 2421 3rd Qu.: 94691
## Custodian : 2418 Max. :319275
## (Other) :126136 NA's :609
## OvertimePay OtherPay Benefits
## Min. : -0.01 Min. : -7058.6 Min. : -33.89
## 1st Qu.: 0.00 1st Qu.: 0.0 1st Qu.:11535.40
## Median : 0.00 Median : 811.3 Median :28628.62
## Mean : 5066.06 Mean : 3648.8 Mean :25007.89
## 3rd Qu.: 4658.18 3rd Qu.: 4236.1 3rd Qu.:35566.86
## Max. :245131.88 Max. :400184.2 Max. :96570.66
## NA's :4 NA's :4 NA's :36163
## TotalPay TotalPayBenefits Year Notes
## Min. : -618.1 Min. : -618.1 Min. :2011 Mode:logical
## 1st Qu.: 36169.0 1st Qu.: 44065.7 1st Qu.:2012 NA's:148654
## Median : 71426.6 Median : 92404.1 Median :2013
## Mean : 74768.3 Mean : 93692.6 Mean :2013
## 3rd Qu.:105839.1 3rd Qu.:132876.5 3rd Qu.:2014
## Max. :567595.4 Max. :567595.4 Max. :2014
##
## Agency Status
## San Francisco:148654 :110535
## FT: 22334
## PT: 15785
##
##
##
##
head(salarios) # Los primeros seis registros
## 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
Analisis elemental
La media
Desviacion
MAximo
Minimo
maximo <- max(salarios$TotalPayBenefits)
minimo <- min(salarios$TotalPayBenefits)
media <- mean(salarios$TotalPayBenefits)
desvstd <- sd(salarios$TotalPayBenefits)
Mostrar los valores estadisticos
paste("Valor maximo de Ingreso Total",maximo)
## [1] "Valor maximo de Ingreso Total 567595.43"
paste("Valor minimo de Ingreso Total",minimo)
## [1] "Valor minimo de Ingreso Total -618.13"
paste("Valor media de Ingreso Total",media)
## [1] "Valor media de Ingreso Total 93692.5548105668"
paste("Valor desviacion std de Ingreso Total",desvstd)
## [1] "Valor desviacion std de Ingreso Total 62793.5334832377"