empresa<-read.csv("https://raw.githubusercontent.com/VictorGuevaraP/Mineria-de-datos/master/Perdida%20de%20clientes.csv", sep = ";")
head(empresa)
##   Plan_Internacional Min_En_Dia Min_Internacionales Reclamos
## 1                 no      265.1                10.0        1
## 2                 no      161.6                13.7        1
## 3                 no      243.4                12.2        0
## 4                 si      299.4                 6.6        2
## 5                 si      166.7                10.1        3
## 6                 si      223.4                 6.3        0
##   Llamadas_Internacionales Desafiliado
## 1                        3          no
## 2                        3          no
## 3                        5          no
## 4                        7          no
## 5                        3          no
## 6                        6          no
str(empresa)
## 'data.frame':    3333 obs. of  6 variables:
##  $ Plan_Internacional      : Factor w/ 2 levels "no","si": 1 1 1 2 2 2 1 2 1 2 ...
##  $ Min_En_Dia              : num  265 162 243 299 167 ...
##  $ Min_Internacionales     : num  10 13.7 12.2 6.6 10.1 6.3 7.5 7.1 8.7 11.2 ...
##  $ Reclamos                : int  1 1 0 2 3 0 3 0 1 0 ...
##  $ Llamadas_Internacionales: int  3 3 5 7 3 6 7 6 4 5 ...
##  $ Desafiliado             : Factor w/ 2 levels "no","si": 1 1 1 1 1 1 1 1 1 1 ...
summary(empresa)
##  Plan_Internacional   Min_En_Dia    Min_Internacionales    Reclamos    
##  no:3010            Min.   :  0.0   Min.   : 0.00       Min.   :0.000  
##  si: 323            1st Qu.:143.7   1st Qu.: 8.50       1st Qu.:1.000  
##                     Median :179.4   Median :10.30       Median :1.000  
##                     Mean   :179.8   Mean   :10.24       Mean   :1.563  
##                     3rd Qu.:216.4   3rd Qu.:12.10       3rd Qu.:2.000  
##                     Max.   :350.8   Max.   :20.00       Max.   :9.000  
##  Llamadas_Internacionales Desafiliado
##  Min.   : 0.000           no:2850    
##  1st Qu.: 3.000           si: 483    
##  Median : 4.000                      
##  Mean   : 4.479                      
##  3rd Qu.: 6.000                      
##  Max.   :20.000

Analisis bivariado y multivariado

#Diagrama de Dispercion
plot(empresa$Min_En_Dia,empresa$Min_Internacionales , 
     main="GRAFICO DE CORRELACION ENTRE 2 VARIABLES", 
     xlab="MINUTOS INTERNACIONAES",
     ylab = "MINUTOS AL DIA",
     col=c(4,7))

###Segun el diagrama no hay correlacion entre las variables Min_En_Dia y Lamadas_Internacionales

pairs(empresa$Min_En_Dia ~ empresa$Min_Internacionale)

plot(empresa)

#COEFICIENTE DE CORELACION
str(empresa)
## 'data.frame':    3333 obs. of  6 variables:
##  $ Plan_Internacional      : Factor w/ 2 levels "no","si": 1 1 1 2 2 2 1 2 1 2 ...
##  $ Min_En_Dia              : num  265 162 243 299 167 ...
##  $ Min_Internacionales     : num  10 13.7 12.2 6.6 10.1 6.3 7.5 7.1 8.7 11.2 ...
##  $ Reclamos                : int  1 1 0 2 3 0 3 0 1 0 ...
##  $ Llamadas_Internacionales: int  3 3 5 7 3 6 7 6 4 5 ...
##  $ Desafiliado             : Factor w/ 2 levels "no","si": 1 1 1 1 1 1 1 1 1 1 ...
cor(empresa[,2:4])
##                      Min_En_Dia Min_Internacionales    Reclamos
## Min_En_Dia           1.00000000         -0.01015459 -0.01342319
## Min_Internacionales -0.01015459          1.00000000 -0.00963968
## Reclamos            -0.01342319         -0.00963968  1.00000000

El coeficiente de correlacion es -0.01, por lo tanto existe correlacion negativa muy debil entre las variables Min_En_Dia, Min_Internacionale

cov(empresa[,2:4])
##                       Min_En_Dia Min_Internacionales    Reclamos
## Min_En_Dia          2966.6964865         -1.54414905 -0.96178959
## Min_Internacionales   -1.5441490          7.79436806 -0.03540307
## Reclamos              -0.9617896         -0.03540307  1.73051669
#install.packages("VIM")
#install.packages("corrplot")
library(VIM)
## Loading required package: colorspace
## Loading required package: grid
## Loading required package: data.table
## VIM is ready to use. 
##  Since version 4.0.0 the GUI is in its own package VIMGUI.
## 
##           Please use the package to use the new (and old) GUI.
## Suggestions and bug-reports can be submitted at: https://github.com/alexkowa/VIM/issues
## 
## Attaching package: 'VIM'
## The following object is masked from 'package:datasets':
## 
##     sleep
library(corrplot)
## corrplot 0.84 loaded
corrplot(cor(empresa[,2:4]))

library(corrplot)
data(iris)
library(PerformanceAnalytics)
## Loading required package: xts
## Loading required package: zoo
## 
## Attaching package: 'zoo'
## The following objects are masked from 'package:base':
## 
##     as.Date, as.Date.numeric
## 
## Attaching package: 'xts'
## The following objects are masked from 'package:data.table':
## 
##     first, last
## 
## Attaching package: 'PerformanceAnalytics'
## The following object is masked from 'package:graphics':
## 
##     legend
chart.Correlation(empresa[,2:4])

### Se aprecia que las variables min al dia y minutos internacionales tienen una distrubucion normal y tambien que en las otras variables hay muy poca relacion entre ellas