Random Forest - Churn
Emilio Ciuffardi A01612569
2026-02-25
Teoría
Bosques Aleatorios: son un algoritmo de aprendizaje automático supervisado, utilizado para clasificación y regresión, que combina múltiples árboles de decisión entrenados con subconjuntos aleatorios de datos (bagging).
Instalar paquetes y librerías
#install.packages("caret")
library(caret)
#install.packages("randomForest")
library(randomForest)Leer archivo
churn <- read.csv("C:\\Users\\Emili\\OneDrive\\Desktop\\TEC\\Tec 6to Semestre Concentracion\\Modulo 2\\Archivos CSV\\customer_churn.csv")
head(churn)## CustomerID Age Gender Tenure Usage.Frequency Support.Calls Payment.Delay
## 1 2 30 Female 39 14 5 18
## 2 3 65 Female 49 1 10 8
## 3 4 55 Female 14 4 6 18
## 4 5 58 Male 38 21 7 7
## 5 6 23 Male 32 20 5 8
## 6 8 51 Male 33 25 9 26
## Subscription.Type Contract.Length Total.Spend Last.Interaction Churn
## 1 Standard Annual 932 17 1
## 2 Basic Monthly 557 6 1
## 3 Basic Quarterly 185 3 1
## 4 Standard Monthly 396 29 1
## 5 Basic Monthly 617 20 1
## 6 Premium Annual 129 8 1Entender datos
summary(churn)## CustomerID Age Gender Tenure
## Min. : 2 Min. :18.00 Length:440833 Min. : 1.00
## 1st Qu.:113622 1st Qu.:29.00 Class :character 1st Qu.:16.00
## Median :226126 Median :39.00 Mode :character Median :32.00
## Mean :225399 Mean :39.37 Mean :31.26
## 3rd Qu.:337739 3rd Qu.:48.00 3rd Qu.:46.00
## Max. :449999 Max. :65.00 Max. :60.00
## NA's :1 NA's :1 NA's :1
## Usage.Frequency Support.Calls Payment.Delay Subscription.Type
## Min. : 1.00 Min. : 0.000 Min. : 0.00 Length:440833
## 1st Qu.: 9.00 1st Qu.: 1.000 1st Qu.: 6.00 Class :character
## Median :16.00 Median : 3.000 Median :12.00 Mode :character
## Mean :15.81 Mean : 3.604 Mean :12.97
## 3rd Qu.:23.00 3rd Qu.: 6.000 3rd Qu.:19.00
## Max. :30.00 Max. :10.000 Max. :30.00
## NA's :1 NA's :1 NA's :1
## Contract.Length Total.Spend Last.Interaction Churn
## Length:440833 Min. : 100.0 Min. : 1.00 Min. :0.0000
## Class :character 1st Qu.: 480.0 1st Qu.: 7.00 1st Qu.:0.0000
## Mode :character Median : 661.0 Median :14.00 Median :1.0000
## Mean : 631.6 Mean :14.48 Mean :0.5671
## 3rd Qu.: 830.0 3rd Qu.:22.00 3rd Qu.:1.0000
## Max. :1000.0 Max. :30.00 Max. :1.0000
## NA's :1 NA's :1 NA's :1str(churn)## 'data.frame': 440833 obs. of 12 variables:
## $ CustomerID : int 2 3 4 5 6 8 9 10 11 12 ...
## $ Age : int 30 65 55 58 23 51 58 55 39 64 ...
## $ Gender : chr "Female" "Female" "Female" "Male" ...
## $ Tenure : int 39 49 14 38 32 33 49 37 12 3 ...
## $ Usage.Frequency : int 14 1 4 21 20 25 12 8 5 25 ...
## $ Support.Calls : int 5 10 6 7 5 9 3 4 7 2 ...
## $ Payment.Delay : int 18 8 18 7 8 26 16 15 4 11 ...
## $ Subscription.Type: chr "Standard" "Basic" "Basic" "Standard" ...
## $ Contract.Length : chr "Annual" "Monthly" "Quarterly" "Monthly" ...
## $ Total.Spend : num 932 557 185 396 617 129 821 445 969 415 ...
## $ Last.Interaction : int 17 6 3 29 20 8 24 30 13 29 ...
## $ Churn : int 1 1 1 1 1 1 1 1 1 1 ...Transformar datos correspondientes
#eliminar NA
churn <- na.omit(churn
)
churn$Churn <- as.factor(churn$Churn)
churn$Contract.Length <- as.factor(churn$Contract.Length)
churn$Subscription.Type <- as.factor(churn$Subscription.Type)
churn$Gender <- as.factor(churn$Gender)
#verificar transformación exitosa
str(churn)## 'data.frame': 440832 obs. of 12 variables:
## $ CustomerID : int 2 3 4 5 6 8 9 10 11 12 ...
## $ Age : int 30 65 55 58 23 51 58 55 39 64 ...
## $ Gender : Factor w/ 2 levels "Female","Male": 1 1 1 2 2 2 1 1 2 1 ...
## $ Tenure : int 39 49 14 38 32 33 49 37 12 3 ...
## $ Usage.Frequency : int 14 1 4 21 20 25 12 8 5 25 ...
## $ Support.Calls : int 5 10 6 7 5 9 3 4 7 2 ...
## $ Payment.Delay : int 18 8 18 7 8 26 16 15 4 11 ...
## $ Subscription.Type: Factor w/ 3 levels "Basic","Premium",..: 3 1 1 3 1 2 3 2 3 3 ...
## $ Contract.Length : Factor w/ 3 levels "Annual","Monthly",..: 1 2 3 2 2 1 3 1 3 3 ...
## $ Total.Spend : num 932 557 185 396 617 129 821 445 969 415 ...
## $ Last.Interaction : int 17 6 3 29 20 8 24 30 13 29 ...
## $ Churn : Factor w/ 2 levels "0","1": 2 2 2 2 2 2 2 2 2 2 ...
## - attr(*, "na.action")= 'omit' Named int 199296
## ..- attr(*, "names")= chr "199296"Partir datos 80/20
set.seed(123)
data_entrenamiento <- createDataPartition(churn$Churn, p=0.8, list=FALSE)
entrenamiento <- churn[data_entrenamiento, ]
prueba <- churn[-data_entrenamiento, ]Modelo de Bosques Aleatorios
modelo <- randomForest(Churn ~ . -CustomerID, data = entrenamiento, ntree = 100, importance = TRUE)Matriz de Confusión datos de entrenamiento
resultado_entrenamiento <- predict(modelo, entrenamiento)
mcre <- confusionMatrix(resultado_entrenamiento, entrenamiento$Churn)
mcre## Confusion Matrix and Statistics
##
## Reference
## Prediction 0 1
## 0 152667 0
## 1 0 200000
##
## Accuracy : 1
## 95% CI : (1, 1)
## No Information Rate : 0.5671
## P-Value [Acc > NIR] : < 2.2e-16
##
## Kappa : 1
##
## Mcnemar's Test P-Value : NA
##
## Sensitivity : 1.0000
## Specificity : 1.0000
## Pos Pred Value : 1.0000
## Neg Pred Value : 1.0000
## Prevalence : 0.4329
## Detection Rate : 0.4329
## Detection Prevalence : 0.4329
## Balanced Accuracy : 1.0000
##
## 'Positive' Class : 0
## Matriz de Confusión datos de prueba
resultado_prueba <- predict(modelo, prueba)
mcrp <- confusionMatrix(resultado_prueba, prueba$Churn)
mcrp## Confusion Matrix and Statistics
##
## Reference
## Prediction 0 1
## 0 38165 7
## 1 1 49992
##
## Accuracy : 0.9999
## 95% CI : (0.9998, 1)
## No Information Rate : 0.5671
## P-Value [Acc > NIR] : <2e-16
##
## Kappa : 0.9998
##
## Mcnemar's Test P-Value : 0.0771
##
## Sensitivity : 1.0000
## Specificity : 0.9999
## Pos Pred Value : 0.9998
## Neg Pred Value : 1.0000
## Prevalence : 0.4329
## Detection Rate : 0.4329
## Detection Prevalence : 0.4330
## Balanced Accuracy : 0.9999
##
## 'Positive' Class : 0
## Resultados
plot(modelo)
varImpPlot(modelo)
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