Recursos Humanos
Liz Manzano A01280625
2022-10-04
Importar base de datos
#file.choose()
bdcol <- read.csv("/Users/lizmanzano/Desktop/RETO ANALÍTICA/BDCOLRH.csv")
bdbaj <- read.csv("/Users/lizmanzano/Desktop/RETO ANALÍTICA/BaseD_Limpia RH_ Bajas .csv")Entender base de datos
summary(bdcol)## numero_de_empleado nombre_completo edad genero
## Min. : 1.00 Length:113 Min. :18.00 Length:113
## 1st Qu.: 31.00 Class :character 1st Qu.:26.00 Class :character
## Median : 63.00 Mode :character Median :34.00 Mode :character
## Mean : 75.86 Mean :36.07
## 3rd Qu.:127.00 3rd Qu.:45.00
## Max. :169.00 Max. :73.00
##
## fecha_de_alta antiguedad BAJA puesto
## Length:113 Min. : 0.000 Min. :3 Length:113
## Class :character 1st Qu.: 0.000 1st Qu.:3 Class :character
## Mode :character Median : 0.000 Median :3 Mode :character
## Mean : 1.425 Mean :3
## 3rd Qu.: 2.000 3rd Qu.:3
## Max. :12.000 Max. :3
## NA's :100
## departamento mano_de_obra salario_diario colonia
## Length:113 Length:113 Min. :144.4 Length:113
## Class :character Class :character 1st Qu.:176.7 Class :character
## Mode :character Mode :character Median :180.7 Mode :character
## Mean :181.4
## 3rd Qu.:180.7
## Max. :441.4
##
## municipio
## Length:113
## Class :character
## Mode :character
##
##
##
## summary(bdbaj)## nombre edad genero fecha_de_alta
## Length:237 Min. : 0.00 Length:237 Length:237
## Class :character 1st Qu.:23.00 Class :character Class :character
## Mode :character Median :29.00 Mode :character Mode :character
## Mean :30.52
## 3rd Qu.:37.00
## Max. :61.00
## motivo_de_baja dias_de_trabajo baja puesto_que_desempeña
## Length:237 Min. : 0.00 Length:237 Length:237
## Class :character 1st Qu.: 9.00 Class :character Class :character
## Mode :character Median : 21.00 Mode :character Mode :character
## Mean : 83.42
## 3rd Qu.: 49.00
## Max. :1966.00
## salario_imss colonia municipio estado
## Min. :144.4 Length:237 Length:237 Length:237
## 1st Qu.:180.7 Class :character Class :character Class :character
## Median :180.7 Mode :character Mode :character Mode :character
## Mean :178.6
## 3rd Qu.:180.7
## Max. :500.0
## estado_civil
## Length:237
## Class :character
## Mode :character
##
##
## Cargar librerías
library(foreign)
library(dplyr) # data manipulation ##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionlibrary(forcats) # to work with categorical variables
library(ggplot2) # data visualization
library(janitor) # data exploration and cleaning ##
## Attaching package: 'janitor'## The following objects are masked from 'package:stats':
##
## chisq.test, fisher.testlibrary(Hmisc) # several useful functions for data analysis ## Loading required package: lattice## Loading required package: survival## Loading required package: Formula##
## Attaching package: 'Hmisc'## The following objects are masked from 'package:dplyr':
##
## src, summarize## The following objects are masked from 'package:base':
##
## format.pval, unitslibrary(dlookr) # summaries and visualization of missing values NAs##
## Attaching package: 'dlookr'## The following object is masked from 'package:Hmisc':
##
## describe## The following object is masked from 'package:base':
##
## transformlibrary(corrplot) # correlation plots## corrplot 0.92 loadedlibrary(jtools) # presentation of regression analysis ##
## Attaching package: 'jtools'## The following object is masked from 'package:Hmisc':
##
## %nin%library(lmtest) # diagnostic checks - linear regression analysis ## Loading required package: zoo##
## Attaching package: 'zoo'## The following objects are masked from 'package:base':
##
## as.Date, as.Date.numericlibrary(car) # diagnostic checks - linear regression analysis## Loading required package: carData##
## Attaching package: 'car'## The following object is masked from 'package:dplyr':
##
## recodelibrary(olsrr) # diagnostic checks - linear regression analysis ##
## Attaching package: 'olsrr'## The following object is masked from 'package:datasets':
##
## riverslibrary(kableExtra) # HTML table attributes##
## Attaching package: 'kableExtra'## The following object is masked from 'package:dplyr':
##
## group_rowsLiberar estructura del conjunto de datos
str(bdcol)## 'data.frame': 113 obs. of 13 variables:
## $ numero_de_empleado: int 1 2 3 4 5 6 7 8 9 10 ...
## $ nombre_completo : chr "NICOLAS MARTINEZ DE LOERA" "MARIANA DE LEON MORENO" "JOSE LUIS HERNANDEZ CERVANTES" "MARIA CAZARES MORALES" ...
## $ edad : int 67 43 73 32 57 38 55 26 27 37 ...
## $ genero : chr "MASCULINO" "FEMENINO" "MASCULINO" "FEMENINO" ...
## $ fecha_de_alta : chr "01/07/2010" "01/07/2011" "22/11/2011" "30/01/2013" ...
## $ antiguedad : int 12 11 11 9 8 8 7 6 5 5 ...
## $ BAJA : int NA NA NA NA NA NA NA NA NA NA ...
## $ puesto : chr "Supervisor de Máquin" "Supervisor de pegado" "Externo" "SUPERVISORA" ...
## $ departamento : chr "Produccion Cartón MDL" "Produccion Cartón MDL" "Externo" "Produccion Cartón MC" ...
## $ mano_de_obra : chr "Indirecto" "Indirecto" "Indirecto" "Indirecto" ...
## $ salario_diario : num 177 177 177 337 441 ...
## $ colonia : chr "UNIDAD LABORAL" "SANTA TERESITA" "VILLAS DE HUINALA" "PUEBLO NUEVO" ...
## $ municipio : chr "SAN NICOLAS DE LOS G" "APODACA" "APODACA" "APODACA" ...str(bdbaj)## 'data.frame': 237 obs. of 13 variables:
## $ nombre : chr "MARIO VALDEZ ORTIZ" "ISABEL BARRIOS MENDEZ" "MARIA ELIZABETH GOMEZ HERNANDEZ" "ALONDRA ABIGAIL ESCARCIA GOMEZ" ...
## $ edad : int 32 36 23 21 29 46 29 31 50 19 ...
## $ genero : chr "MASCULINO" "FEMENINO" "FEMENINO" "FEMENINO" ...
## $ fecha_de_alta : chr "9/3/2020" "9/11/2021" "10/11/2021" "10/11/2021" ...
## $ motivo_de_baja : chr "RENUNCIA VOLUNTARIA" "RENUNCIA VOLUNTARIA" "RENUNCIA VOLUNTARIA" "RENUNCIA VOLUNTARIA" ...
## $ dias_de_trabajo : int 628 60 59 59 51 37 37 31 18 224 ...
## $ baja : chr "27/11/2021" "8/1/2022" "8/1/2022" "8/1/2022" ...
## $ puesto_que_desempeña: chr "DISEÑO" "AYUDANTE GENERAL" "AYUDANTE GENERAL" "AYUDANTE GENERAL" ...
## $ salario_imss : num 500 152 152 152 152 ...
## $ colonia : chr "SAN NICOLAS DE LOS G" "COLINAS DEL AEROPÑUERTO" "PUEBLO NUEVO" "PUEBLO NUEVO" ...
## $ municipio : chr "SAN NICOLAS DE LOS G" "PESQUERIA" "APODACA" "APODACA" ...
## $ estado : chr "NUEVO LEÓN" "NUEVO LEÓN" "NUEVO LEÓN" "NUEVO LEÓN" ...
## $ estado_civil : chr "SOLTERO" "UNIÓN LIBRE" "CASADO" "SOLTERO" ...Seleccionar columnas y variables
bdcol1<-bdcol
bdbaj1<-bdbaj #bdcol1<-bdcol %>% select(-one_of('numero_de_empleado','fecha_de_alta' ,'BAJA', 'edad'))Renombrar variables
summary(bdcol1)## numero_de_empleado nombre_completo edad genero
## Min. : 1.00 Length:113 Min. :18.00 Length:113
## 1st Qu.: 31.00 Class :character 1st Qu.:26.00 Class :character
## Median : 63.00 Mode :character Median :34.00 Mode :character
## Mean : 75.86 Mean :36.07
## 3rd Qu.:127.00 3rd Qu.:45.00
## Max. :169.00 Max. :73.00
##
## fecha_de_alta antiguedad BAJA puesto
## Length:113 Min. : 0.000 Min. :3 Length:113
## Class :character 1st Qu.: 0.000 1st Qu.:3 Class :character
## Mode :character Median : 0.000 Median :3 Mode :character
## Mean : 1.425 Mean :3
## 3rd Qu.: 2.000 3rd Qu.:3
## Max. :12.000 Max. :3
## NA's :100
## departamento mano_de_obra salario_diario colonia
## Length:113 Length:113 Min. :144.4 Length:113
## Class :character Class :character 1st Qu.:176.7 Class :character
## Mode :character Mode :character Median :180.7 Mode :character
## Mean :181.4
## 3rd Qu.:180.7
## Max. :441.4
##
## municipio
## Length:113
## Class :character
## Mode :character
##
##
##
## names(bdcol1)<-c('Nom_Comp', 'Gen', 'Ant', 'Puesto', 'Dep', 'MDO', 'SalDiario', 'Col', 'Mun')
names(bdbaj1)<-c('Nom', 'Edad', 'Gen', 'Fecha_alta', 'MB', 'Días_trab', 'Baja', 'PuestDes', 'Sal_IMSS', 'Col', 'Mun', 'Estado', 'EstCiv')Cambiar fecha a formato fecha
bdcol1$Fecha_alta<-as.Date(bdcol$fecha_de_alta,format="%y/%m/%d")
bdbaj1$Fecha_alta<-as.Date(bdbaj1$Fecha_alta,format="%y/%m/%d")
bdbaj1$Baja<-as.Date(bdbaj1$Baja,format="%y/%m/%d") Calcular la variable “años” en años para entender más características de colaboradores
library(lubridate)##
## Attaching package: 'lubridate'## The following objects are masked from 'package:base':
##
## date, intersect, setdiff, unionedad<-trunc((bdcol1$Fecha_alta %--% bdcol1$Fecha_alta) / years(1))Crear intervalo de tiempo
bdcol1$edad<-edadEliminar NA’s y sustituir con 0’s
sum(is.na(bdcol1))## [1] 100sum(is.na(bdbaj1))## [1] 0bdcol1[is.na(bdcol1)]<-0
bdbaj1[is.na(bdbaj1)]<-0
summary(bdcol1)## Nom_Comp Gen Ant Puesto
## Min. : 1.00 Length:113 Min. :18.00 Length:113
## 1st Qu.: 31.00 Class :character 1st Qu.:26.00 Class :character
## Median : 63.00 Mode :character Median :34.00 Mode :character
## Mean : 75.86 Mean :36.07
## 3rd Qu.:127.00 3rd Qu.:45.00
## Max. :169.00 Max. :73.00
## Dep MDO SalDiario Col
## Length:113 Min. : 0.000 Min. :0.0000 Length:113
## Class :character 1st Qu.: 0.000 1st Qu.:0.0000 Class :character
## Mode :character Median : 0.000 Median :0.0000 Mode :character
## Mean : 1.425 Mean :0.3451
## 3rd Qu.: 2.000 3rd Qu.:0.0000
## Max. :12.000 Max. :3.0000
## Mun NA NA NA
## Length:113 Length:113 Min. :144.4 Length:113
## Class :character Class :character 1st Qu.:176.7 Class :character
## Mode :character Mode :character Median :180.7 Mode :character
## Mean :181.4
## 3rd Qu.:180.7
## Max. :441.4
## NA Fecha_alta edad
## Length:113 Min. :2001-06-20 Min. :0
## Class :character 1st Qu.:2006-07-20 1st Qu.:0
## Mode :character Median :2014-04-20 Median :0
## Mean :2014-06-16 Mean :0
## 3rd Qu.:2022-11-20 3rd Qu.:0
## Max. :2030-07-20 Max. :0summary(bdbaj1)## Nom Edad Gen Fecha_alta
## Length:237 Min. : 0.00 Length:237 Min. :2001-02-20
## Class :character 1st Qu.:23.00 Class :character 1st Qu.:2010-06-20
## Mode :character Median :29.00 Mode :character Median :2015-06-20
## Mean :30.52 Mean :2015-11-07
## 3rd Qu.:37.00 3rd Qu.:2021-12-20
## Max. :61.00 Max. :2031-05-20
## MB Días_trab Baja PuestDes
## Length:237 Min. : 0.00 Min. :2001-02-20 Length:237
## Class :character 1st Qu.: 9.00 1st Qu.:2011-04-20 Class :character
## Mode :character Median : 21.00 Median :2017-08-20 Mode :character
## Mean : 83.42 Mean :2017-08-09
## 3rd Qu.: 49.00 3rd Qu.:2025-04-20
## Max. :1966.00 Max. :2031-01-20
## Sal_IMSS Col Mun Estado
## Min. :144.4 Length:237 Length:237 Length:237
## 1st Qu.:180.7 Class :character Class :character Class :character
## Median :180.7 Mode :character Mode :character Mode :character
## Mean :178.6
## 3rd Qu.:180.7
## Max. :500.0
## EstCiv
## Length:237
## Class :character
## Mode :character
##
##
## bdcol1 <- na.omit(bdcol1)
bdbaj1 <- na.omit(bdbaj1)
summary(bdcol1)## Nom_Comp Gen Ant Puesto
## Min. : 1.00 Length:113 Min. :18.00 Length:113
## 1st Qu.: 31.00 Class :character 1st Qu.:26.00 Class :character
## Median : 63.00 Mode :character Median :34.00 Mode :character
## Mean : 75.86 Mean :36.07
## 3rd Qu.:127.00 3rd Qu.:45.00
## Max. :169.00 Max. :73.00
## Dep MDO SalDiario Col
## Length:113 Min. : 0.000 Min. :0.0000 Length:113
## Class :character 1st Qu.: 0.000 1st Qu.:0.0000 Class :character
## Mode :character Median : 0.000 Median :0.0000 Mode :character
## Mean : 1.425 Mean :0.3451
## 3rd Qu.: 2.000 3rd Qu.:0.0000
## Max. :12.000 Max. :3.0000
## Mun NA NA NA
## Length:113 Length:113 Min. :144.4 Length:113
## Class :character Class :character 1st Qu.:176.7 Class :character
## Mode :character Mode :character Median :180.7 Mode :character
## Mean :181.4
## 3rd Qu.:180.7
## Max. :441.4
## NA Fecha_alta edad
## Length:113 Min. :2001-06-20 Min. :0
## Class :character 1st Qu.:2006-07-20 1st Qu.:0
## Mode :character Median :2014-04-20 Median :0
## Mean :2014-06-16 Mean :0
## 3rd Qu.:2022-11-20 3rd Qu.:0
## Max. :2030-07-20 Max. :0summary(bdbaj1) ## Nom Edad Gen Fecha_alta
## Length:237 Min. : 0.00 Length:237 Min. :2001-02-20
## Class :character 1st Qu.:23.00 Class :character 1st Qu.:2010-06-20
## Mode :character Median :29.00 Mode :character Median :2015-06-20
## Mean :30.52 Mean :2015-11-07
## 3rd Qu.:37.00 3rd Qu.:2021-12-20
## Max. :61.00 Max. :2031-05-20
## MB Días_trab Baja PuestDes
## Length:237 Min. : 0.00 Min. :2001-02-20 Length:237
## Class :character 1st Qu.: 9.00 1st Qu.:2011-04-20 Class :character
## Mode :character Median : 21.00 Median :2017-08-20 Mode :character
## Mean : 83.42 Mean :2017-08-09
## 3rd Qu.: 49.00 3rd Qu.:2025-04-20
## Max. :1966.00 Max. :2031-01-20
## Sal_IMSS Col Mun Estado
## Min. :144.4 Length:237 Length:237 Length:237
## 1st Qu.:180.7 Class :character Class :character Class :character
## Median :180.7 Mode :character Mode :character Mode :character
## Mean :178.6
## 3rd Qu.:180.7
## Max. :500.0
## EstCiv
## Length:237
## Class :character
## Mode :character
##
##
## str(bdcol1)## 'data.frame': 113 obs. of 15 variables:
## $ Nom_Comp : int 1 2 3 4 5 6 7 8 9 10 ...
## $ Gen : chr "NICOLAS MARTINEZ DE LOERA" "MARIANA DE LEON MORENO" "JOSE LUIS HERNANDEZ CERVANTES" "MARIA CAZARES MORALES" ...
## $ Ant : int 67 43 73 32 57 38 55 26 27 37 ...
## $ Puesto : chr "MASCULINO" "FEMENINO" "MASCULINO" "FEMENINO" ...
## $ Dep : chr "01/07/2010" "01/07/2011" "22/11/2011" "30/01/2013" ...
## $ MDO : int 12 11 11 9 8 8 7 6 5 5 ...
## $ SalDiario : num 0 0 0 0 0 0 0 0 0 0 ...
## $ Col : chr "Supervisor de Máquin" "Supervisor de pegado" "Externo" "SUPERVISORA" ...
## $ Mun : chr "Produccion Cartón MDL" "Produccion Cartón MDL" "Externo" "Produccion Cartón MC" ...
## $ NA : chr "Indirecto" "Indirecto" "Indirecto" "Indirecto" ...
## $ NA : num 177 177 177 337 441 ...
## $ NA : chr "UNIDAD LABORAL" "SANTA TERESITA" "VILLAS DE HUINALA" "PUEBLO NUEVO" ...
## $ NA : chr "SAN NICOLAS DE LOS G" "APODACA" "APODACA" "APODACA" ...
## $ Fecha_alta: Date, format: "2001-07-20" "2001-07-20" ...
## $ edad : num 0 0 0 0 0 0 0 0 0 0 ...str(bdbaj1)## 'data.frame': 237 obs. of 13 variables:
## $ Nom : chr "MARIO VALDEZ ORTIZ" "ISABEL BARRIOS MENDEZ" "MARIA ELIZABETH GOMEZ HERNANDEZ" "ALONDRA ABIGAIL ESCARCIA GOMEZ" ...
## $ Edad : int 32 36 23 21 29 46 29 31 50 19 ...
## $ Gen : chr "MASCULINO" "FEMENINO" "FEMENINO" "FEMENINO" ...
## $ Fecha_alta: Date, format: "2009-03-20" "2009-11-20" ...
## $ MB : chr "RENUNCIA VOLUNTARIA" "RENUNCIA VOLUNTARIA" "RENUNCIA VOLUNTARIA" "RENUNCIA VOLUNTARIA" ...
## $ Días_trab : int 628 60 59 59 51 37 37 31 18 224 ...
## $ Baja : Date, format: "2027-11-20" "2008-01-20" ...
## $ PuestDes : chr "DISEÑO" "AYUDANTE GENERAL" "AYUDANTE GENERAL" "AYUDANTE GENERAL" ...
## $ Sal_IMSS : num 500 152 152 152 152 ...
## $ Col : chr "SAN NICOLAS DE LOS G" "COLINAS DEL AEROPÑUERTO" "PUEBLO NUEVO" "PUEBLO NUEVO" ...
## $ Mun : chr "SAN NICOLAS DE LOS G" "PESQUERIA" "APODACA" "APODACA" ...
## $ Estado : chr "NUEVO LEÓN" "NUEVO LEÓN" "NUEVO LEÓN" "NUEVO LEÓN" ...
## $ EstCiv : chr "SOLTERO" "UNIÓN LIBRE" "CASADO" "SOLTERO" ...Convertir variables
bdbaj1$Gen<-as.factor(bdbaj1$Gen)
bdcol1$Gen<-as.factor(bdcol1$Gen)
bdbaj1$PuestDes<-as.factor(bdbaj1$PuestDes)
bdcol1$Puesto<-as.factor(bdcol1$Puesto)
bdcol1$Dep<-as.factor(bdcol1$Dep)
bdbaj1$Mun<-as.factor(bdbaj1$Mun)
bdcol1$Mun<-as.factor(bdcol1$Mun)
bdbaj1$Estado<-as.factor(bdbaj1$Estado)
bdbaj1$EstCiv<-as.factor(bdbaj1$EstCiv)Verificar estructura
str(bdbaj1)## 'data.frame': 237 obs. of 13 variables:
## $ Nom : chr "MARIO VALDEZ ORTIZ" "ISABEL BARRIOS MENDEZ" "MARIA ELIZABETH GOMEZ HERNANDEZ" "ALONDRA ABIGAIL ESCARCIA GOMEZ" ...
## $ Edad : int 32 36 23 21 29 46 29 31 50 19 ...
## $ Gen : Factor w/ 2 levels "FEMENINO","MASCULINO": 2 1 1 1 1 1 1 2 2 2 ...
## $ Fecha_alta: Date, format: "2009-03-20" "2009-11-20" ...
## $ MB : chr "RENUNCIA VOLUNTARIA" "RENUNCIA VOLUNTARIA" "RENUNCIA VOLUNTARIA" "RENUNCIA VOLUNTARIA" ...
## $ Días_trab : int 628 60 59 59 51 37 37 31 18 224 ...
## $ Baja : Date, format: "2027-11-20" "2008-01-20" ...
## $ PuestDes : Factor w/ 31 levels "ANALISTA DE NOMINAS /AUX DE R.H.",..: 15 9 9 9 9 9 9 9 9 4 ...
## $ Sal_IMSS : num 500 152 152 152 152 ...
## $ Col : chr "SAN NICOLAS DE LOS G" "COLINAS DEL AEROPÑUERTO" "PUEBLO NUEVO" "PUEBLO NUEVO" ...
## $ Mun : Factor w/ 13 levels "APODACA","CADEREYTA",..: 10 7 1 1 1 1 1 5 4 1 ...
## $ Estado : Factor w/ 3 levels "COAHUILA","NUEVO LEÓN",..: 2 2 2 2 2 2 2 2 2 2 ...
## $ EstCiv : Factor w/ 5 levels "CASADO","DIVORCIADO",..: 3 5 1 3 3 3 5 5 3 3 ...str(bdcol1)## 'data.frame': 113 obs. of 15 variables:
## $ Nom_Comp : int 1 2 3 4 5 6 7 8 9 10 ...
## $ Gen : Factor w/ 113 levels "ADELAIDA MENDOZA NAVARRO",..: 92 78 55 71 111 42 11 96 43 110 ...
## $ Ant : int 67 43 73 32 57 38 55 26 27 37 ...
## $ Puesto : Factor w/ 2 levels "FEMENINO","MASCULINO": 2 1 2 1 1 2 1 2 2 1 ...
## $ Dep : Factor w/ 93 levels "01/06/2022","01/07/2010",..: 2 3 69 91 18 10 25 75 40 63 ...
## $ MDO : int 12 11 11 9 8 8 7 6 5 5 ...
## $ SalDiario : num 0 0 0 0 0 0 0 0 0 0 ...
## $ Col : chr "Supervisor de Máquin" "Supervisor de pegado" "Externo" "SUPERVISORA" ...
## $ Mun : Factor w/ 22 levels "","Ay.flexo",..: 18 18 13 17 8 4 8 19 4 10 ...
## $ NA : chr "Indirecto" "Indirecto" "Indirecto" "Indirecto" ...
## $ NA : num 177 177 177 337 441 ...
## $ NA : chr "UNIDAD LABORAL" "SANTA TERESITA" "VILLAS DE HUINALA" "PUEBLO NUEVO" ...
## $ NA : chr "SAN NICOLAS DE LOS G" "APODACA" "APODACA" "APODACA" ...
## $ Fecha_alta: Date, format: "2001-07-20" "2001-07-20" ...
## $ edad : num 0 0 0 0 0 0 0 0 0 0 ...summary(bdbaj1)## Nom Edad Gen Fecha_alta
## Length:237 Min. : 0.00 FEMENINO :140 Min. :2001-02-20
## Class :character 1st Qu.:23.00 MASCULINO: 97 1st Qu.:2010-06-20
## Mode :character Median :29.00 Median :2015-06-20
## Mean :30.52 Mean :2015-11-07
## 3rd Qu.:37.00 3rd Qu.:2021-12-20
## Max. :61.00 Max. :2031-05-20
##
## MB Días_trab Baja
## Length:237 Min. : 0.00 Min. :2001-02-20
## Class :character 1st Qu.: 9.00 1st Qu.:2011-04-20
## Mode :character Median : 21.00 Median :2017-08-20
## Mean : 83.42 Mean :2017-08-09
## 3rd Qu.: 49.00 3rd Qu.:2025-04-20
## Max. :1966.00 Max. :2031-01-20
##
## PuestDes Sal_IMSS Col
## AYUDANTE GENERAL :173 Min. :144.4 Length:237
## SOLDADOR : 11 1st Qu.:180.7 Class :character
## COSTURERA : 10 Median :180.7 Mode :character
## MONTACARGUISTA : 5 Mean :178.6
## AY. GENERAL : 4 3rd Qu.:180.7
## AUXILIAR DE EMBARQUES: 3 Max. :500.0
## (Other) : 31
## Mun Estado EstCiv
## APODACA :162 COAHUILA : 9 CASADO : 64
## PESQUERIA : 32 NUEVO LEÓN:227 DIVORCIADO : 3
## JUAREZ : 15 SALTILLO : 1 SOLTERO :110
## GUADALUPE : 10 Unión libre: 1
## RAMOS ARIZPE : 8 UNIÓN LIBRE: 59
## SAN NICOLAS DE LOS GARZA: 3
## (Other) : 7summary(bdcol1)## Nom_Comp Gen Ant
## Min. : 1.00 ADELAIDA MENDOZA NAVARRO : 1 Min. :18.00
## 1st Qu.: 31.00 ADRIANA BADILLO LOZANO : 1 1st Qu.:26.00
## Median : 63.00 ADRIANA IRENE ZAPATA GARCIA: 1 Median :34.00
## Mean : 75.86 ADRIANA PADILLO CASTILLO : 1 Mean :36.07
## 3rd Qu.:127.00 ALFREDO HERNANDEZ PASCUAL : 1 3rd Qu.:45.00
## Max. :169.00 ALMA DELIA LARA CAMPOS : 1 Max. :73.00
## (Other) :107
## Puesto Dep MDO SalDiario
## FEMENINO :61 14/06/2022: 4 Min. : 0.000 Min. :0.0000
## MASCULINO:52 03/08/2022: 3 1st Qu.: 0.000 1st Qu.:0.0000
## 23/08/2022: 3 Median : 0.000 Median :0.0000
## 01/06/2022: 2 Mean : 1.425 Mean :0.3451
## 02/08/2022: 2 3rd Qu.: 2.000 3rd Qu.:0.0000
## 03/11/2020: 2 Max. :12.000 Max. :3.0000
## (Other) :97
## Col Mun NA
## Length:113 :40 Length:113
## Class :character Producción Retorn :10 Class :character
## Mode :character Costura : 7 Mode :character
## Produccion Cartón MDL: 7
## Stabilus : 7
## Cedis : 6
## (Other) :36
## NA NA NA Fecha_alta
## Min. :144.4 Length:113 Length:113 Min. :2001-06-20
## 1st Qu.:176.7 Class :character Class :character 1st Qu.:2006-07-20
## Median :180.7 Mode :character Mode :character Median :2014-04-20
## Mean :181.4 Mean :2014-06-16
## 3rd Qu.:180.7 3rd Qu.:2022-11-20
## Max. :441.4 Max. :2030-07-20
##
## edad
## Min. :0
## 1st Qu.:0
## Median :0
## Mean :0
## 3rd Qu.:0
## Max. :0
## Verificar visualzación de datos
tapply(bdbaj1$Sal_IMSS,
list(bdbaj1$Gen,bdbaj1$EstCiv), mean)## CASADO DIVORCIADO SOLTERO Unión libre UNIÓN LIBRE
## FEMENINO 176.6727 180.68 178.5836 NA 175.7823
## MASCULINO 180.2840 180.68 182.6171 176.72 176.5513Reemplazar “outlier” de salario diario con la mediana
bdbaj1$Sal_IMSS<-replace(bdbaj1$Sal_IMSS,bdbaj1$Sal_IMSS>1000000,181)Gráficos
tapply(bdbaj1$Sal_IMSS,
list(bdbaj1$Gen,bdbaj1$EstCiv), mean)## CASADO DIVORCIADO SOLTERO Unión libre UNIÓN LIBRE
## FEMENINO 176.6727 180.68 178.5836 NA 175.7823
## MASCULINO 180.2840 180.68 182.6171 176.72 176.5513hist(bdbaj1$Edad, freq=TRUE, col='Darkblue', main="Histograma Edad",xlab="Edad en Años")
Dentro de este histograma se analizó la edad y la frecuencia que tiene. En este caso se puede observar que la edad que se ve mas presente dentro de la empresa es la de 20-30 años.
ggplot(bdbaj1, aes(Gen,Días_trab,fill=Gen)) +
geom_bar(stat = "identity") +
scale_fill_brewer(palette = "Set3") + ggtitle(" Días trabajadospor Genero")
En este gráfico se puede observar como los hombres cuentan con más días trabajados que las mujeres al momento de ser dados de baja de la empresa.
ggplot(bdbaj1, aes(x=Gen, y=Sal_IMSS, fill=Gen)) +
geom_bar(stat="identity") +
facet_grid(~EstCiv) + scale_fill_brewer(palette = "Set3")
Dentro de este gráfico se puede observar como en todos los rubros las mujeres ganan mas de su salario del IMSS que los hombres.