Practica Seis

Utilizar la libreria “dplyr” para analizar datos de salarios

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

Cargar los datos

# Cargar datos de salarios
# salarios <- read.csv("Va la ruta en donde estan los datos")
salarios <- read.csv("C:/Users/Matilda/Documents/Ciencia de los datos/Datos/Salaries.csv", encoding = "UTF-8")

# salarios   # Ya no los queremos ver

str(salarios)

## 'data.frame':    148654 obs. of  13 variables:
##  $ X.U.FEFF.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)

##   X.U.FEFF.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

##   X.U.FEFF.Id      EmployeeName
## 1           1    NATHANIEL FORD
## 2           2      GARY JIMENEZ
## 3           3    ALBERT PARDINI
## 4           4 CHRISTOPHER CHONG
## 5           5   PATRICK GARDNER
## 6           6    DAVID SULLIVAN
##                                         JobTitle  BasePay OvertimePay
## 1 GENERAL MANAGER-METROPOLITAN TRANSIT AUTHORITY 167411.2        0.00
## 2                CAPTAIN III (POLICE DEPARTMENT) 155966.0   245131.88
## 3                CAPTAIN III (POLICE DEPARTMENT) 212739.1   106088.18
## 4           WIRE ROPE CABLE MAINTENANCE MECHANIC  77916.0    56120.71
## 5   DEPUTY CHIEF OF DEPARTMENT,(FIRE DEPARTMENT) 134401.6     9737.00
## 6                      ASSISTANT DEPUTY CHIEF II 118602.0     8601.00
##   OtherPay Benefits TotalPay TotalPayBenefits Year Notes        Agency
## 1 400184.2       NA 567595.4         567595.4 2011    NA San Francisco
## 2 137811.4       NA 538909.3         538909.3 2011    NA San Francisco
## 3  16452.6       NA 335279.9         335279.9 2011    NA San Francisco
## 4 198306.9       NA 332343.6         332343.6 2011    NA San Francisco
## 5 182234.6       NA 326373.2         326373.2 2011    NA San Francisco
## 6 189082.7       NA 316285.7         316285.7 2011    NA San Francisco
##   Status
## 1       
## 2       
## 3       
## 4       
## 5       
## 6

Analisis elemental

La media

Desviacion

Máximo

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 maximo de Ingreso Total",minimo)

## [1] "Valor maximo de Ingreso Total -618.13"

paste("Valor maximo de Ingreso Total",media)

## [1] "Valor maximo de Ingreso Total 93692.5548105668"

paste("Valor maximo de Ingreso Total",desvstd)

## [1] "Valor maximo de Ingreso Total 62793.5334832377"