Telco_Cusomer_Churn = read.table("Telco_Cusomer_Churn.csv",
header=TRUE, sep =",", row.names = 1,dec=".",
stringsAsFactors = TRUE)
summary(Telco_Cusomer_Churn)
## gender SeniorCitizen Partner Dependents tenure
## Female:3488 Min. :0.0000 No :3641 No :4933 Min. : 0.00
## Male :3555 1st Qu.:0.0000 Yes:3402 Yes:2110 1st Qu.: 9.00
## Median :0.0000 Median :29.00
## Mean :0.1621 Mean :32.37
## 3rd Qu.:0.0000 3rd Qu.:55.00
## Max. :1.0000 Max. :72.00
##
## PhoneService MultipleLines InternetService
## No : 682 No :3390 DSL :2421
## Yes:6361 No phone service: 682 Fiber optic:3096
## Yes :2971 No :1526
##
##
##
##
## OnlineSecurity OnlineBackup
## No :3498 No :3088
## No internet service:1526 No internet service:1526
## Yes :2019 Yes :2429
##
##
##
##
## DeviceProtection TechSupport
## No :3095 No :3473
## No internet service:1526 No internet service:1526
## Yes :2422 Yes :2044
##
##
##
##
## StreamingTV StreamingMovies Contract
## No :2810 No :2785 Month-to-month:3875
## No internet service:1526 No internet service:1526 One year :1473
## Yes :2707 Yes :2732 Two year :1695
##
##
##
##
## PaperlessBilling PaymentMethod MonthlyCharges
## No :2872 Bank transfer (automatic):1544 Min. : 18.25
## Yes:4171 Credit card (automatic) :1522 1st Qu.: 35.50
## Electronic check :2365 Median : 70.35
## Mailed check :1612 Mean : 64.76
## 3rd Qu.: 89.85
## Max. :118.75
##
## TotalCharges Churn
## Min. : 18.8 No :5174
## 1st Qu.: 401.4 Yes:1869
## Median :1397.5
## Mean :2283.3
## 3rd Qu.:3794.7
## Max. :8684.8
## NA's :11
library(corrplot)
## corrplot 0.95 loaded
attach(Telco_Cusomer_Churn)
nuevosDatos = data.frame(tenure, MonthlyCharges, TotalCharges)
r = cor(na.omit(nuevosDatos))
corrplot(r, method="number")
library(ggplot2)
ggplot(Telco_Cusomer_Churn, aes(x = Churn,
y = MonthlyCharges, fill = Churn)) +
geom_boxplot() +
labs(title = "Cargos Mensuales por Nivel de Rotación",
x = "Rotación (Fuga)",
y = "Cargos Mensuales",
fill = "Rotación") +
theme_minimal()
# Interpretación Clave:
# * Observar la Mediana: Si la mediana de 'Si' es significativamente más alta que la de 'No',
# sugiere que los clientes con planes o servicios más caros (cargos mensuales altos)
# tienen mayor probabilidad de fuga.
ggplot(Telco_Cusomer_Churn, aes(y=TotalCharges, x=Churn, fill=Churn))+
geom_boxplot()
## Warning: Removed 11 rows containing non-finite outside the scale range
## (`stat_boxplot()`).
{r}
## tenure MonthlyCharges TotalCharges
## tenure 1.0000000 0.2468618 0.8258805
## MonthlyCharges 0.2468618 1.0000000 0.6510648
## TotalCharges 0.8258805 0.6510648 1.0000000
ggplot(Telco_Cusomer_Churn, aes(x=Churn, fill=gender))+
geom_bar()
ggplot(Telco_Cusomer_Churn,aes(x=tenure,y=MonthlyCharges))+
geom_jitter()+
geom_smooth(method = "lm", colour = "gold")
## `geom_smooth()` using formula = 'y ~ x'
{r}
## tenure MonthlyCharges TotalCharges
## tenure 1.0000000 0.2468618 0.8258805
## MonthlyCharges 0.2468618 1.0000000 0.6510648
## TotalCharges 0.8258805 0.6510648 1.0000000
y=MonthlyCharges
x=tenure
cor(y=MonthlyCharges,x=tenure)
## [1] 0.2478999
modelo=lm(y ~ x)
summary(modelo)
##
## Call:
## lm(formula = y ~ x)
##
## Residuals:
## Min 1Q Median 3Q Max
## -57.498 -27.251 6.245 24.943 54.376
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 54.92978 0.57476 95.57 <2e-16 ***
## x 0.30372 0.01415 21.47 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 29.15 on 7041 degrees of freedom
## Multiple R-squared: 0.06145, Adjusted R-squared: 0.06132
## F-statistic: 461 on 1 and 7041 DF, p-value: < 2.2e-16
library(ggplot2)
library(gridExtra)
g1= ggplot(Telco_Cusomer_Churn,aes(x=Churn,y = MonthlyCharges))+
geom_boxplot(fill="blue")
g2= ggplot(Telco_Cusomer_Churn, aes(x=Churn, y = TotalCharges))+
geom_boxplot(fill="red")
g3= ggplot(Telco_Cusomer_Churn, aes(x=Churn, fill = gender))+
geom_bar()
g4= ggplot(Telco_Cusomer_Churn,aes(x=tenure,y=MonthlyCharges))+
geom_jitter()+
geom_smooth(method = "lm",colour = "skyblue")
grid.arrange(g1, g2, g3, g4)
## Warning: Removed 11 rows containing non-finite outside the scale range
## (`stat_boxplot()`).
## `geom_smooth()` using formula = 'y ~ x'
