#Librarias
library(tidyverse)
library(magrittr)
library(skimr)
library(janitor)
library(tidymodels)
library(ranger)
library(xgboost)
library(vip)
#Cargar datos
data <- read_csv('Data/WA_Fn-UseC_-Telco-Customer-Churn.csv',
show_col_types = FALSE)
#Verificar y corregir columnas
data %>%
glimpse
## Rows: 7,043
## Columns: 21
## $ customerID <chr> "7590-VHVEG", "5575-GNVDE", "3668-QPYBK", "7795-CFOCW…
## $ gender <chr> "Female", "Male", "Male", "Male", "Female", "Female",…
## $ SeniorCitizen <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ Partner <chr> "Yes", "No", "No", "No", "No", "No", "No", "No", "Yes…
## $ Dependents <chr> "No", "No", "No", "No", "No", "No", "Yes", "No", "No"…
## $ tenure <dbl> 1, 34, 2, 45, 2, 8, 22, 10, 28, 62, 13, 16, 58, 49, 2…
## $ PhoneService <chr> "No", "Yes", "Yes", "No", "Yes", "Yes", "Yes", "No", …
## $ MultipleLines <chr> "No phone service", "No", "No", "No phone service", "…
## $ InternetService <chr> "DSL", "DSL", "DSL", "DSL", "Fiber optic", "Fiber opt…
## $ OnlineSecurity <chr> "No", "Yes", "Yes", "Yes", "No", "No", "No", "Yes", "…
## $ OnlineBackup <chr> "Yes", "No", "Yes", "No", "No", "No", "Yes", "No", "N…
## $ DeviceProtection <chr> "No", "Yes", "No", "Yes", "No", "Yes", "No", "No", "Y…
## $ TechSupport <chr> "No", "No", "No", "Yes", "No", "No", "No", "No", "Yes…
## $ StreamingTV <chr> "No", "No", "No", "No", "No", "Yes", "Yes", "No", "Ye…
## $ StreamingMovies <chr> "No", "No", "No", "No", "No", "Yes", "No", "No", "Yes…
## $ Contract <chr> "Month-to-month", "One year", "Month-to-month", "One …
## $ PaperlessBilling <chr> "Yes", "No", "Yes", "No", "Yes", "Yes", "Yes", "No", …
## $ PaymentMethod <chr> "Electronic check", "Mailed check", "Mailed check", "…
## $ MonthlyCharges <dbl> 29.85, 56.95, 53.85, 42.30, 70.70, 99.65, 89.10, 29.7…
## $ TotalCharges <dbl> 29.85, 1889.50, 108.15, 1840.75, 151.65, 820.50, 1949…
## $ Churn <chr> "No", "No", "Yes", "No", "Yes", "Yes", "No", "No", "Y…
data %>%
summarise_all(list(
.n=~sum(!is.na(.)),
.na=~sum(is.na(.)),
.min=~min(.,na.rm = T),
.max=~max(.,na.rm = T),
.clase=~class(.),
.valor_distinto=~n_distinct(.)
)) %>% mutate(across(everything(),~as.character(.))) %>%
pivot_longer(everything(),
names_to = c("varible",".value"),
names_sep = c("_\\.")) %>% gt::gt()
| varible | n | na | min | max | clase | valor_distinto |
|---|---|---|---|---|---|---|
| customerID | 7043 | 0 | 0002-ORFBO | 9995-HOTOH | character | 7043 |
| gender | 7043 | 0 | Female | Male | character | 2 |
| SeniorCitizen | 7043 | 0 | 0 | 1 | numeric | 2 |
| Partner | 7043 | 0 | No | Yes | character | 2 |
| Dependents | 7043 | 0 | No | Yes | character | 2 |
| tenure | 7043 | 0 | 0 | 72 | numeric | 73 |
| PhoneService | 7043 | 0 | No | Yes | character | 2 |
| MultipleLines | 7043 | 0 | No | Yes | character | 3 |
| InternetService | 7043 | 0 | DSL | No | character | 3 |
| OnlineSecurity | 7043 | 0 | No | Yes | character | 3 |
| OnlineBackup | 7043 | 0 | No | Yes | character | 3 |
| DeviceProtection | 7043 | 0 | No | Yes | character | 3 |
| TechSupport | 7043 | 0 | No | Yes | character | 3 |
| StreamingTV | 7043 | 0 | No | Yes | character | 3 |
| StreamingMovies | 7043 | 0 | No | Yes | character | 3 |
| Contract | 7043 | 0 | Month-to-month | Two year | character | 3 |
| PaperlessBilling | 7043 | 0 | No | Yes | character | 2 |
| PaymentMethod | 7043 | 0 | Bank transfer (automatic) | Mailed check | character | 4 |
| MonthlyCharges | 7043 | 0 | 18.25 | 118.75 | numeric | 1585 |
| TotalCharges | 7032 | 11 | 18.8 | 8684.8 | numeric | 6531 |
| Churn | 7043 | 0 | No | Yes | character | 2 |
#Convertir a factor
data %>%
mutate( Churn = factor(Churn,
levels= c("Yes","No"),
labels= c("si", "no"))
) -> data
data %>%
mutate(
SeniorCitizen = factor(SeniorCitizen,
levels = c(0, 1), labels = c('no', 'si')),
gender = factor(gender,
levels = c('Female', 'Male'), labels = c('Mujeres', 'Hombres')),
Partner = factor(Partner,
levels = c('Yes', 'No'), labels = c('si', 'No')),
Dependents = factor(Dependents,
levels = c('Yes', 'No'), labels = c('si', 'No')),
PhoneService = factor(PhoneService,
levels = c('Yes', 'No'), labels = c('si', 'No')),
PaperlessBilling = factor(PaperlessBilling,
levels = c('Yes', 'No'), labels = c('si', 'No')),
MultipleLines = factor(MultipleLines,
levels = c('Yes', 'No', "No phone service"), labels = c('si', 'no', 'sin servicio')),
InternetService = factor(InternetService,
levels = c('DSL', 'Fiber optic', 'No'), labels = c('DSL', 'Fibra optica', 'No')),
OnlineSecurity = factor(OnlineSecurity,
levels = c('No', 'Yes', 'No internet service'), labels = c('No', 'Yes', 'sin servicio')),
OnlineBackup = factor(OnlineBackup,
levels = c('Yes', 'No', 'No internet service'), labels = c('si', 'no', 'sin servicio')),
DeviceProtection = factor(DeviceProtection,
levels = c('Yes', 'No', 'No internet service'), labels = c('si', 'no', 'sin servicio')),
TechSupport = factor(TechSupport,
levels = c('Yes', 'No', 'No internet service'), labels = c('si', 'no', 'sin servicio')),
StreamingTV = factor(StreamingTV,
levels = c('Yes', 'No', 'No internet service'), labels = c('si', 'no', 'sin servicio')),
StreamingMovies = factor(StreamingMovies,
levels = c('Yes', 'No', 'No internet service'), labels = c('si', 'no', 'sin servicio')),
Contract = factor(Contract,
levels = c('Month-to-month', 'One year', 'Two year'), labels = c('mes a mes', 'un año', 'dos años')),
PaymentMethod = factor(PaymentMethod,
levels = c('Electronic check', 'Mailed check', 'Bank transfer (automatic)', 'Credit card (automatic)'),
labels = c('cheque electronico', 'cheque mail', 'transferencia bancaria', 'transferencia automatica'))
) -> data
#EDA
skim(data)
| Name | data |
| Number of rows | 7043 |
| Number of columns | 21 |
| _______________________ | |
| Column type frequency: | |
| character | 1 |
| factor | 17 |
| numeric | 3 |
| ________________________ | |
| Group variables | None |
Variable type: character
| skim_variable | n_missing | complete_rate | min | max | empty | n_unique | whitespace |
|---|---|---|---|---|---|---|---|
| customerID | 0 | 1 | 10 | 10 | 0 | 7043 | 0 |
Variable type: factor
| skim_variable | n_missing | complete_rate | ordered | n_unique | top_counts |
|---|---|---|---|---|---|
| gender | 0 | 1 | FALSE | 2 | Hom: 3555, Muj: 3488 |
| SeniorCitizen | 0 | 1 | FALSE | 2 | no: 5901, si: 1142 |
| Partner | 0 | 1 | FALSE | 2 | No: 3641, si: 3402 |
| Dependents | 0 | 1 | FALSE | 2 | No: 4933, si: 2110 |
| PhoneService | 0 | 1 | FALSE | 2 | si: 6361, No: 682 |
| MultipleLines | 0 | 1 | FALSE | 3 | no: 3390, si: 2971, sin: 682 |
| InternetService | 0 | 1 | FALSE | 3 | Fib: 3096, DSL: 2421, No: 1526 |
| OnlineSecurity | 0 | 1 | FALSE | 3 | No: 3498, Yes: 2019, sin: 1526 |
| OnlineBackup | 0 | 1 | FALSE | 3 | no: 3088, si: 2429, sin: 1526 |
| DeviceProtection | 0 | 1 | FALSE | 3 | no: 3095, si: 2422, sin: 1526 |
| TechSupport | 0 | 1 | FALSE | 3 | no: 3473, si: 2044, sin: 1526 |
| StreamingTV | 0 | 1 | FALSE | 3 | no: 2810, si: 2707, sin: 1526 |
| StreamingMovies | 0 | 1 | FALSE | 3 | no: 2785, si: 2732, sin: 1526 |
| Contract | 0 | 1 | FALSE | 3 | mes: 3875, dos: 1695, un : 1473 |
| PaperlessBilling | 0 | 1 | FALSE | 2 | si: 4171, No: 2872 |
| PaymentMethod | 0 | 1 | FALSE | 4 | che: 2365, che: 1612, tra: 1544, tra: 1522 |
| Churn | 0 | 1 | FALSE | 2 | no: 5174, si: 1869 |
Variable type: numeric
| skim_variable | n_missing | complete_rate | mean | sd | p0 | p25 | p50 | p75 | p100 | hist |
|---|---|---|---|---|---|---|---|---|---|---|
| tenure | 0 | 1 | 32.37 | 24.56 | 0.00 | 9.00 | 29.00 | 55.00 | 72.00 | ▇▃▃▃▆ |
| MonthlyCharges | 0 | 1 | 64.76 | 30.09 | 18.25 | 35.50 | 70.35 | 89.85 | 118.75 | ▇▅▆▇▅ |
| TotalCharges | 11 | 1 | 2283.30 | 2266.77 | 18.80 | 401.45 | 1397.47 | 3794.74 | 8684.80 | ▇▂▂▂▁ |
data %>%
reframe(
tibble(
Descrip= c('P_0', 'P_02', 'P_25', 'P_50' , 'P_75', 'P_98', 'P_100') ,
Valor= quantile( TotalCharges, c(0, 0.2, 0.25, 0.50 ,0.75, 0.98, 1), na.rm= T)
)
) %>%
gt::gt()
| Descrip | Valor |
|---|---|
| P_0 | 18.800 |
| P_02 | 267.070 |
| P_25 | 401.450 |
| P_50 | 1397.475 |
| P_75 | 3794.738 |
| P_98 | 7721.096 |
| P_100 | 8684.800 |
#Media por Partner
data %>%
group_by(Partner) %>%
summarise(media=mean(TotalCharges,
na.rm =T )) %>%
gt::gt()
| Partner | media |
|---|---|
| si | 3032.272 |
| No | 1584.960 |
#Distribuciòn de TotalCharges por Partner
data %>%
ggplot(aes(TotalCharges,
color=Partner))+
geom_density()+
scale_y_continuous(labels = scales::number_format())+
theme_dark()
Existe una diferencia importante en los registros de dinero cobrado a los clientes al considerar aquellos que tienen pareja. Al revisar el gráfico anterior, se evidencia que las personas que informaron tener pareja son las que presentan los cobros más altos. Esto se refleja en la distribución, donde se observa una densidad mayor para valores altos en comparación con las personas que declararon no tener pareja.
data %>%
group_by(SeniorCitizen, Churn) %>%
summarise(
N = n(),
Porc = round(100*N/nrow(data),2)
) %>%
mutate(Porc_grupo = round(100*N/sum(N),2)) -> valores_Sc
## `summarise()` has grouped output by 'SeniorCitizen'. You can override using the
## `.groups` argument.
valores_Sc %>%
ungroup() %>%
gt::gt()
| SeniorCitizen | Churn | N | Porc | Porc_grupo |
|---|---|---|---|---|
| no | si | 1393 | 19.78 | 23.61 |
| no | no | 4508 | 64.01 | 76.39 |
| si | si | 476 | 6.76 | 41.68 |
| si | no | 666 | 9.46 | 58.32 |
# Comentado por conflictos con paquete
# tigerstats::rowPerc(xtabs(~SeniorCitizen+Churn, data=data) )
ggplot(valores_Sc, aes(x = SeniorCitizen, y = Porc_grupo, fill = Churn)) +
geom_col(stat = "identity", position = "dodge") +
geom_text(aes(label = Porc_grupo), vjust = 1.5,
position = position_dodge(.9))
## Warning in geom_col(stat = "identity", position = "dodge"): Ignoring unknown
## parameters: `stat`
De los adultos mayores el 41% abandonó el servicio, mientras que de los
no adultos mayores apenas un 24% abandonó el servicio. Aparentemente, un
adulto mayor tiene mayor probabilidad de abandonar el servicio.
valores_Ml <- data %>%
count(Churn,MultipleLines) %>%
group_by(Churn) %>%
mutate(n_chur=sum(n),
porcentaje_personas=n/n_chur) %>%
ungroup()
valores_Ml %>%
gt::gt()%>%
gt::fmt_percent(columns=porcentaje_personas)
| Churn | MultipleLines | n | n_chur | porcentaje_personas |
|---|---|---|---|---|
| si | si | 850 | 1869 | 45.48% |
| si | no | 849 | 1869 | 45.43% |
| si | sin servicio | 170 | 1869 | 9.10% |
| no | si | 2121 | 5174 | 40.99% |
| no | no | 2541 | 5174 | 49.11% |
| no | sin servicio | 512 | 5174 | 9.90% |
######Gráfico
valores_Ml %>%
ggplot(aes(Churn, y = porcentaje_personas, fill = MultipleLines)) +
geom_col(position = "dodge") +
geom_text(aes(label = scales::percent(porcentaje_personas,accuracy = 0.01)), vjust = -0.8,
position = position_dodge(.9))
Entre las categorías de MultipleLines no hay mayor diferencia, entre los que abandonan o no el servicio. Los porcentajes son muy parecidos.
data %>%
count(Churn,TechSupport) %>%
group_by(Churn) %>%
mutate(n_chur=sum(n),
porcentaje_personas=n/n_chur) %>%
ungroup() %>%
ggplot(aes(Churn,
porcentaje_personas,
fill = TechSupport)) +
geom_col(position = "dodge") +
geom_text(aes(label = scales::percent(porcentaje_personas,
accuracy = 0.01)),
vjust = -0.8,
position = position_dodge(.9))
Las personas que se van de la compañía en promedio el 77.37% no tienen
soporte técnico y solo el 16.59% de los que se van indican tener soporte
técnico.
data %>%
count(Churn,PaymentMethod) %>%
group_by(Churn) %>%
mutate(n_chur=sum(n),
porcentaje_personas=n/n_chur) %>%
ungroup() %>%
ggplot(aes(Churn,
porcentaje_personas,
fill = PaymentMethod)) +
geom_col(position = "dodge") +
geom_text(aes(label = scales::percent(porcentaje_personas,
accuracy = 0.1)),
vjust = -0.8,
position = position_dodge(.9))
A excepción de los que pagan con cheque electrónico los porcentajes de abandono son muy parecidos. En el caso de los que pagan con cheque electrónico un 57.3% abandona el servicio.
data %>% tabyl(Churn, Dependents ) -> t1
t1 %>% adorn_totals(c("row", "col")) %>% adorn_percentages("all") %>%
adorn_pct_formatting(rounding = "half up", digits = 0) %>% adorn_ns() %>%
adorn_title("combined") %>% knitr::kable()
| Churn/Dependents | si | No | Total |
|---|---|---|---|
| si | 5% (326) | 22% (1,543) | 27% (1,869) |
| no | 25% (1,784) | 48% (3,390) | 73% (5,174) |
| Total | 30% (2,110) | 70% (4,933) | 100% (7,043) |
data %>% count(Churn, Dependents) %>%
mutate(porc = n / sum(n)) %>%
ggplot(aes(fill=Dependents, y=porc, x=Churn)) +
geom_col(position="stack") +
geom_text(aes(label=scales::percent(porc)),position = position_stack(vjust=0.5))+
scale_y_continuous(labels = scales::percent_format())
De la muestra analizada alrededor del 27% corresponde a individuos que dejaron sus planes en el último mes. Además se conoce que el 4,6% de estos individuos contaban con personas dependientes.
data %>% tabyl(Churn,OnlineSecurity ) -> t2
t2 %>% adorn_totals(c("row", "col")) %>% adorn_percentages("all") %>%
adorn_pct_formatting(rounding = "half up", digits = 0) %>% adorn_ns()%>% adorn_title("combined")%>% knitr::kable()
| Churn/OnlineSecurity | No | Yes | sin servicio | Total |
|---|---|---|---|---|
| si | 21% (1,461) | 4% (295) | 2% (113) | 27% (1,869) |
| no | 29% (2,037) | 24% (1,724) | 20% (1,413) | 73% (5,174) |
| Total | 50% (3,498) | 29% (2,019) | 22% (1,526) | 100% (7,043) |
data %>% count(Churn, OnlineSecurity) %>%
mutate(porc = n / sum(n)) %>%
ggplot(aes(fill=OnlineSecurity, y=porc, x=Churn)) +
geom_col(position="stack") +
geom_text(aes(label=scales::percent(porc)),position = position_stack(vjust=0.5))+
scale_y_continuous(labels = scales::percent_format())
El 20,74% de los indviduos analizados y que abandonaron el servicio no contaban con seguridad en línea. Por otro lado aquellos que no salieron del plan reflejaron una participación similar con relación al servicio de seguridad en línea.
data %>% tabyl(Churn,StreamingMovies) -> t3
t3 %>% adorn_totals(c("row", "col")) %>% adorn_percentages("all") %>%
adorn_pct_formatting(rounding = "half up", digits = 0) %>% adorn_ns()%>% adorn_title("combined")%>% knitr::kable()
| Churn/StreamingMovies | si | no | sin servicio | Total |
|---|---|---|---|---|
| si | 12% (818) | 13% (938) | 2% (113) | 27% (1,869) |
| no | 27% (1,914) | 26% (1,847) | 20% (1,413) | 73% (5,174) |
| Total | 39% (2,732) | 40% (2,785) | 22% (1,526) | 100% (7,043) |
data %>% count(Churn, StreamingMovies) %>%
mutate(porc = n / sum(n)) %>%
ggplot(aes(fill=StreamingMovies, y=porc, x=Churn)) +
geom_col(position="stack") +
geom_text(aes(label=scales::percent(porc)),position = position_stack(vjust=0.5))+
scale_y_continuous(labels = scales::percent_format())
El 13,32% de los indviduos analizados y que abandonaron el servicio no contaban con servicio de Streaming Movies. Sin embargo, tanto para el grupo que abandonaron o mantuvieron el servicio no se evidencia una importancia relevante para su salidad del plan.
data %>% group_by(Churn) %>%
summarise(n = n(),
promedio = mean(TotalCharges,na.rm = T),
n_missing = sum(is.na(TotalCharges)),
desv = sd(TotalCharges, na.rm =T)) -> t4
t4 %>%
gt::gt()
| Churn | n | promedio | n_missing | desv |
|---|---|---|---|---|
| si | 1869 | 1531.796 | 0 | 1890.823 |
| no | 5174 | 2555.344 | 11 | 2329.457 |
data %>%
ggplot(aes(x = Churn, y = TotalCharges, fill = Churn)) +
geom_boxplot() +
stat_summary(fun = mean, geom = "point", shape = 3, size = 3,
color = "white", position = position_dodge(width = 0.75)) +
labs(title = "Churn vs Total Charges",
x = "Churn",
y = "Total Charges") +
theme_minimal()
En promedio el gasto total en el servicio de telecomunicaciones para los individuos que salieron del plan es inferior por usuario en alrededor de USD 1000. Para los usuarios que salieron del servicio se evidencia datos atípicos elevados que alcanzan los valores máximos de los usarios que no salieron del servicio. Cabe señalar que, para los usuarios que no abandoron el servicio su extipendio total del plan se concentra entre el rango intercuartílico. Adicionalmente, se observa que la variable gasto total cuenta con 11 valores perdidos.
ggplot(data, aes(x = Churn, y = MonthlyCharges, fill = PaymentMethod)) +
geom_boxplot()
Los montos de pago de aquellos que abandonan el servicio son superiores a aquellos que permanecen con excepción de los que pagan por cheque electrónico.
data %>% group_by(Churn,Dependents) %>%
summarise(n = n(),
promedio = mean(MonthlyCharges,na.rm = T),
n_missing = sum(is.na(MonthlyCharges)),
desv = sd(MonthlyCharges, na.rm =T),
.groups="drop") -> t5
t5 %>%
gt::gt() %>%
gt::fmt_number(columns = c(promedio,desv),
decimals = 2)
| Churn | Dependents | n | promedio | n_missing | desv |
|---|---|---|---|---|---|
| si | si | 326 | 72.87 | 0 | 25.76 |
| si | No | 1543 | 74.77 | 0 | 24.42 |
| no | si | 1784 | 57.08 | 0 | 31.61 |
| no | No | 3390 | 63.47 | 0 | 30.59 |
data %>%
ggplot(aes(x = Churn, y = MonthlyCharges, fill = Dependents)) +
geom_boxplot() +
stat_summary(fun = mean, geom = "point", shape = 3, size = 3, color = "white", position = position_dodge(width = 0.75)) +
labs(title = "Monthtly Charges for Dependents vs Churn",
x = "Churn",
y = "Monthly Charges")
La distribución del gasto mensual de aquellos individuos que no salieron del plan se concentra dentro del cuartil 1 y cuartil 3, además entre el máximo y mínimo de los que dejaron el servicio respecto de los que se quedaron no se verifica mayor diferencia. Es importante destacar que, tanto el promedio como la mediana del pago mensual es superior en los individuos que salieron del plan de los que se quedaron, no obstante no se verifica mayor diferencia respecto de contar o no con dependientes en los usuarios que abandonaron el plan.
data %>% select_if(where(is.numeric)) %>% GGally::ggpairs()
Según el gráfico anterior existe una alta correlación positiva entre las variables TotalChanges y tenure, con 0.826, seguida de la correlación entre las variables TotalChages y MonthyChanges, con una correlación moderada de 0.651.
data %>%
group_by(Churn) %>%
count(name = "frec") %>%
ungroup() %>%
mutate( Porc= frec/sum(frec)) %>%
gt::gt() %>%
gt::fmt_percent(columns=Porc)
| Churn | frec | Porc |
|---|---|---|
| si | 1869 | 26.54% |
| no | 5174 | 73.46% |
data %>%
group_by(Churn) %>%
count( name = 'frec') %>%
ungroup() %>%
mutate( Porc= frec/sum(frec)) %>%
ggplot( aes(x= Churn, y= Porc)) +
geom_segment( aes(xend= Churn, y=0, yend=Porc),
color= "steelblue", linewidth= 1) +
geom_point( size=5, color= "steelblue") +
coord_flip() +
scale_y_continuous( labels = percent_format()) +
labs(title= 'Porcentaje de Clientes que Abandonan',
y= "Porcentaje", x= "Churn") +
theme_bw()
El porcentaje de clientes que abandonan el servicio de telecomunicaciones es aproximadamente 3 a 1 en el muestra de análisis.
#data %>% select(-customerID) -> data
set.seed(1234) # Semilla para aleatorios
split <- data %>%
initial_split(
prop = 0.8, # Porcentaje al train
strata = Churn # Estratificación del muestreo
)
train <- training(split)
dim(train)
## [1] 5634 21
test <- testing(split)
dim(test)
## [1] 1409 21
receta <- train %>%
recipe(Churn ~ . ) %>% ## Crea la receta
## Eliminar variables que no usaremos
step_rm(customerID) %>%
## Crear nuevas variables (insight desde el EDA)
# step_mutate( account_length_anio= account_length/12 )
## Imputar los datos
# step_impute_mean()
step_impute_knn(TotalCharges ) %>%
## Estandarizacion/Normalizacion de numericas
step_normalize( all_numeric(), -all_outcomes()) %>%
## Crear una categoría "otros" que agrupe a categorias pequeñas
step_other(all_nominal(), -all_outcomes() , threshold = 0.07, other = "otros") %>%
## Crear una categoría "new" para observaciones con labels "no muestreados"
step_novel(all_nominal(), -all_outcomes() , new_level = "new") %>%
## Crear variables indicadoras para cada categoría
step_dummy(all_nominal(), -all_outcomes() ) %>% # Dummy
## Eliminar automáticamente variables con alta correlacion
## para evitar la multicolinealidad xi ~ xj
# step_corr(all_numeric(), -all_outcomes(), threshold = 0.9) %>%
## Tambien podemos eliminar variables con multicolinealidad "a mano"
#step_rm(total_day_charge, total_eve_charge,
#total_night_charge, total_intl_charge) %>% # Eliminar
## Eliminar columnas con varianza cercana a cero
step_nzv(all_predictors()) %>%
themis::step_upsample(Churn, over_ratio = 0.9, skip= TRUE, seed= 123)
receta
##
## ── Recipe ──────────────────────────────────────────────────────────────────────
##
## ── Inputs
## Number of variables by role
## outcome: 1
## predictor: 20
##
## ── Operations
## • Variables removed: customerID
## • K-nearest neighbor imputation for: TotalCharges
## • Centering and scaling for: all_numeric() and -all_outcomes()
## • Collapsing factor levels for: all_nominal() and -all_outcomes()
## • Novel factor level assignment for: all_nominal() and -all_outcomes()
## • Dummy variables from: all_nominal() and -all_outcomes()
## • Sparse, unbalanced variable filter on: all_predictors()
## • Up-sampling based on: Churn
set.seed(1234)
cv <- vfold_cv(train, v = 5, repeats = 1, strata = Churn)
cv
## # 5-fold cross-validation using stratification
## # A tibble: 5 × 2
## splits id
## <list> <chr>
## 1 <split [4507/1127]> Fold1
## 2 <split [4507/1127]> Fold2
## 3 <split [4507/1127]> Fold3
## 4 <split [4507/1127]> Fold4
## 5 <split [4508/1126]> Fold5
metricas <- metric_set(accuracy, sens, spec, bal_accuracy)
metricas
## A metric set, consisting of:
## - `accuracy()`, a class metric | direction: maximize
## - `sens()`, a class metric | direction: maximize
## - `spec()`, a class metric | direction: maximize
## - `bal_accuracy()`, a class metric | direction: maximize
rf_sp <-
rand_forest(
mtry = tune(), trees = tune(), min_n = tune() ) %>%
set_engine("ranger", importance = "impurity") %>%
set_mode("classification")
rf_sp
## Random Forest Model Specification (classification)
##
## Main Arguments:
## mtry = tune()
## trees = tune()
## min_n = tune()
##
## Engine-Specific Arguments:
## importance = impurity
##
## Computational engine: ranger
rf_wflow <-
workflow() %>%
add_recipe(receta) %>%
add_model(rf_sp)
rf_wflow
## ══ Workflow ════════════════════════════════════════════════════════════════════
## Preprocessor: Recipe
## Model: rand_forest()
##
## ── Preprocessor ────────────────────────────────────────────────────────────────
## 8 Recipe Steps
##
## • step_rm()
## • step_impute_knn()
## • step_normalize()
## • step_other()
## • step_novel()
## • step_dummy()
## • step_nzv()
## • step_upsample()
##
## ── Model ───────────────────────────────────────────────────────────────────────
## Random Forest Model Specification (classification)
##
## Main Arguments:
## mtry = tune()
## trees = tune()
## min_n = tune()
##
## Engine-Specific Arguments:
## importance = impurity
##
## Computational engine: ranger
set.seed(123)
rf_grid <- rf_sp %>%
## preguntamos los parametros tuneables del modelo
parameters() %>%
## Vamos a definir un rango para el min_n y mtry
update(min_n= min_n( range= c(70, 170)),
mtry= mtry( range= c(4, 7))) %>%
grid_latin_hypercube(size = 10) #preguntar como se construye la malla
rf_grid %>%
gt::gt()
| mtry | trees | min_n |
|---|---|---|
| 5 | 70 | 144 |
| 6 | 467 | 91 |
| 6 | 1737 | 158 |
| 6 | 1124 | 162 |
| 7 | 773 | 80 |
| 4 | 1370 | 116 |
| 6 | 950 | 130 |
| 5 | 325 | 83 |
| 5 | 1904 | 126 |
| 5 | 1441 | 106 |
La data luego de aplicar la receta registra 31 variables, por tanto, se utiliza como criterio para establecer el hiperpárametro “mtry” la raíz cuadrada del número de variables analizadas siendo esta igual a 5,56. Con la finalidad de contar con un rango para la elección de variables se establece entre 4 a 7.
###Paralelización
#parallel::detectCores(logical=FALSE)
set.seed(123)
rf_tuned <- tune_grid(
rf_wflow, ## Modelo
resamples= cv, ## Crossvalidation
grid = rf_grid, ## Malla de Busqueda
metrics = metricas, ## Metricas
control= control_grid(allow_par = T, save_pred = T) ## Paralel y Pred
)
## Warning: package 'themis' was built under R version 4.3.3
rf_tuned
## # Tuning results
## # 5-fold cross-validation using stratification
## # A tibble: 5 × 5
## splits id .metrics .notes .predictions
## <list> <chr> <list> <list> <list>
## 1 <split [4507/1127]> Fold1 <tibble [40 × 7]> <tibble [0 × 3]> <tibble>
## 2 <split [4507/1127]> Fold2 <tibble [40 × 7]> <tibble [0 × 3]> <tibble>
## 3 <split [4507/1127]> Fold3 <tibble [40 × 7]> <tibble [0 × 3]> <tibble>
## 4 <split [4507/1127]> Fold4 <tibble [40 × 7]> <tibble [0 × 3]> <tibble>
## 5 <split [4508/1126]> Fold5 <tibble [40 × 7]> <tibble [0 × 3]> <tibble>
show_best(rf_tuned, metric = 'accuracy', n = 10)%>%
gt::gt() %>%
gt::fmt_percent(columns = mean,
decimals = 2)
| mtry | trees | min_n | .metric | .estimator | mean | n | std_err | .config |
|---|---|---|---|---|---|---|---|---|
| 5 | 325 | 83 | accuracy | binary | 76.82% | 5 | 0.009591922 | Preprocessor1_Model08 |
| 4 | 1370 | 116 | accuracy | binary | 76.82% | 5 | 0.008914298 | Preprocessor1_Model06 |
| 6 | 950 | 130 | accuracy | binary | 76.78% | 5 | 0.010440599 | Preprocessor1_Model07 |
| 7 | 773 | 80 | accuracy | binary | 76.78% | 5 | 0.008703191 | Preprocessor1_Model05 |
| 6 | 467 | 91 | accuracy | binary | 76.68% | 5 | 0.008892465 | Preprocessor1_Model02 |
| 5 | 1904 | 126 | accuracy | binary | 76.68% | 5 | 0.010000934 | Preprocessor1_Model09 |
| 5 | 1441 | 106 | accuracy | binary | 76.62% | 5 | 0.010255550 | Preprocessor1_Model10 |
| 6 | 1124 | 162 | accuracy | binary | 76.62% | 5 | 0.009952380 | Preprocessor1_Model04 |
| 6 | 1737 | 158 | accuracy | binary | 76.62% | 5 | 0.009770258 | Preprocessor1_Model03 |
| 5 | 70 | 144 | accuracy | binary | 76.41% | 5 | 0.009384949 | Preprocessor1_Model01 |
show_best(rf_tuned, metric = 'sens', n = 10) %>%
gt::gt() %>%
gt::fmt_percent(columns = mean,
decimals = 2)
| mtry | trees | min_n | .metric | .estimator | mean | n | std_err | .config |
|---|---|---|---|---|---|---|---|---|
| 4 | 1370 | 116 | sens | binary | 74.11% | 5 | 0.015743950 | Preprocessor1_Model06 |
| 6 | 1737 | 158 | sens | binary | 73.78% | 5 | 0.011517843 | Preprocessor1_Model03 |
| 6 | 1124 | 162 | sens | binary | 73.78% | 5 | 0.012361016 | Preprocessor1_Model04 |
| 5 | 70 | 144 | sens | binary | 73.71% | 5 | 0.013192698 | Preprocessor1_Model01 |
| 5 | 1904 | 126 | sens | binary | 73.71% | 5 | 0.013192698 | Preprocessor1_Model09 |
| 6 | 950 | 130 | sens | binary | 73.38% | 5 | 0.012761728 | Preprocessor1_Model07 |
| 5 | 1441 | 106 | sens | binary | 73.24% | 5 | 0.013708295 | Preprocessor1_Model10 |
| 5 | 325 | 83 | sens | binary | 72.84% | 5 | 0.013268786 | Preprocessor1_Model08 |
| 6 | 467 | 91 | sens | binary | 72.64% | 5 | 0.009364548 | Preprocessor1_Model02 |
| 7 | 773 | 80 | sens | binary | 72.17% | 5 | 0.009830728 | Preprocessor1_Model05 |
show_best(rf_tuned, metric = 'spec', n = 10)%>%
gt::gt() %>%
gt::fmt_percent(columns = mean,
decimals = 2)
| mtry | trees | min_n | .metric | .estimator | mean | n | std_err | .config |
|---|---|---|---|---|---|---|---|---|
| 7 | 773 | 80 | spec | binary | 78.45% | 5 | 0.008401188 | Preprocessor1_Model05 |
| 5 | 325 | 83 | spec | binary | 78.26% | 5 | 0.008397753 | Preprocessor1_Model08 |
| 6 | 467 | 91 | spec | binary | 78.14% | 5 | 0.008873514 | Preprocessor1_Model02 |
| 6 | 950 | 130 | spec | binary | 78.01% | 5 | 0.010178449 | Preprocessor1_Model07 |
| 5 | 1441 | 106 | spec | binary | 77.85% | 5 | 0.009223959 | Preprocessor1_Model10 |
| 4 | 1370 | 116 | spec | binary | 77.80% | 5 | 0.007230052 | Preprocessor1_Model06 |
| 5 | 1904 | 126 | spec | binary | 77.75% | 5 | 0.009297852 | Preprocessor1_Model09 |
| 6 | 1124 | 162 | spec | binary | 77.65% | 5 | 0.009590338 | Preprocessor1_Model04 |
| 6 | 1737 | 158 | spec | binary | 77.65% | 5 | 0.009384198 | Preprocessor1_Model03 |
| 5 | 70 | 144 | spec | binary | 77.39% | 5 | 0.008428486 | Preprocessor1_Model01 |
show_best(rf_tuned, metric = 'bal_accuracy', n = 10)%>%
gt::gt() %>%
gt::fmt_percent(columns = mean,
decimals = 2)
| mtry | trees | min_n | .metric | .estimator | mean | n | std_err | .config |
|---|---|---|---|---|---|---|---|---|
| 4 | 1370 | 116 | bal_accuracy | binary | 75.96% | 5 | 0.010880902 | Preprocessor1_Model06 |
| 5 | 1904 | 126 | bal_accuracy | binary | 75.73% | 5 | 0.010856210 | Preprocessor1_Model09 |
| 6 | 1124 | 162 | bal_accuracy | binary | 75.72% | 5 | 0.010525350 | Preprocessor1_Model04 |
| 6 | 1737 | 158 | bal_accuracy | binary | 75.72% | 5 | 0.010231820 | Preprocessor1_Model03 |
| 6 | 950 | 130 | bal_accuracy | binary | 75.70% | 5 | 0.010955612 | Preprocessor1_Model07 |
| 5 | 325 | 83 | bal_accuracy | binary | 75.55% | 5 | 0.010722115 | Preprocessor1_Model08 |
| 5 | 70 | 144 | bal_accuracy | binary | 75.55% | 5 | 0.010457200 | Preprocessor1_Model01 |
| 5 | 1441 | 106 | bal_accuracy | binary | 75.54% | 5 | 0.011282778 | Preprocessor1_Model10 |
| 6 | 467 | 91 | bal_accuracy | binary | 75.39% | 5 | 0.008979525 | Preprocessor1_Model02 |
| 7 | 773 | 80 | bal_accuracy | binary | 75.31% | 5 | 0.009022861 | Preprocessor1_Model05 |
Revisando los resultados de las métricas de evaluación del modelo y considerando que es de interés para le empresa contar con la mejor estimación de los individuos que realmente abandonan el servicio se selecciona como referencia los hiperpárametros del modelo número 6 que presenta los mejores resultados en sensibilidad, para ajustar el modelo final.
set.seed(123)
rf_grid_2 <- crossing(
min_n = seq(114, 118, 2),
mtry = c(4, 5),
trees= seq(1270, 1570, 100)
)
rf_grid_2%>%
gt::gt()
| min_n | mtry | trees |
|---|---|---|
| 114 | 4 | 1270 |
| 114 | 4 | 1370 |
| 114 | 4 | 1470 |
| 114 | 4 | 1570 |
| 114 | 5 | 1270 |
| 114 | 5 | 1370 |
| 114 | 5 | 1470 |
| 114 | 5 | 1570 |
| 116 | 4 | 1270 |
| 116 | 4 | 1370 |
| 116 | 4 | 1470 |
| 116 | 4 | 1570 |
| 116 | 5 | 1270 |
| 116 | 5 | 1370 |
| 116 | 5 | 1470 |
| 116 | 5 | 1570 |
| 118 | 4 | 1270 |
| 118 | 4 | 1370 |
| 118 | 4 | 1470 |
| 118 | 4 | 1570 |
| 118 | 5 | 1270 |
| 118 | 5 | 1370 |
| 118 | 5 | 1470 |
| 118 | 5 | 1570 |
set.seed(123)
rf_tuned_2 <- tune_grid(
rf_wflow, ## Modelo
resamples= cv, ## Crossvalidation
grid = rf_grid_2, ## Malla de Busqueda
metrics = metricas, ## Metricas
control= control_grid(allow_par = T, save_pred = T) ## Paralel y Pred
)
rf_tuned_2
## # Tuning results
## # 5-fold cross-validation using stratification
## # A tibble: 5 × 5
## splits id .metrics .notes .predictions
## <list> <chr> <list> <list> <list>
## 1 <split [4507/1127]> Fold1 <tibble [96 × 7]> <tibble [0 × 3]> <tibble>
## 2 <split [4507/1127]> Fold2 <tibble [96 × 7]> <tibble [0 × 3]> <tibble>
## 3 <split [4507/1127]> Fold3 <tibble [96 × 7]> <tibble [0 × 3]> <tibble>
## 4 <split [4507/1127]> Fold4 <tibble [96 × 7]> <tibble [0 × 3]> <tibble>
## 5 <split [4508/1126]> Fold5 <tibble [96 × 7]> <tibble [0 × 3]> <tibble>
Evaluamos que modelo resulto mejor de la segunda grilla de hiperpárametros
show_best(rf_tuned_2, metric = 'accuracy', n = 10)%>%
gt::gt() %>%
gt::fmt_percent(columns = mean,
decimals = 2)
| mtry | trees | min_n | .metric | .estimator | mean | n | std_err | .config |
|---|---|---|---|---|---|---|---|---|
| 4 | 1470 | 116 | accuracy | binary | 76.84% | 5 | 0.009517598 | Preprocessor1_Model11 |
| 4 | 1270 | 118 | accuracy | binary | 76.77% | 5 | 0.008798099 | Preprocessor1_Model17 |
| 5 | 1270 | 114 | accuracy | binary | 76.75% | 5 | 0.009485337 | Preprocessor1_Model05 |
| 4 | 1270 | 116 | accuracy | binary | 76.75% | 5 | 0.009196969 | Preprocessor1_Model09 |
| 4 | 1570 | 118 | accuracy | binary | 76.75% | 5 | 0.008753040 | Preprocessor1_Model20 |
| 4 | 1470 | 118 | accuracy | binary | 76.73% | 5 | 0.010074315 | Preprocessor1_Model19 |
| 4 | 1570 | 116 | accuracy | binary | 76.73% | 5 | 0.009373133 | Preprocessor1_Model12 |
| 5 | 1470 | 114 | accuracy | binary | 76.71% | 5 | 0.009529661 | Preprocessor1_Model07 |
| 4 | 1370 | 118 | accuracy | binary | 76.71% | 5 | 0.009867331 | Preprocessor1_Model18 |
| 5 | 1370 | 118 | accuracy | binary | 76.71% | 5 | 0.010002056 | Preprocessor1_Model22 |
show_best(rf_tuned_2, metric = 'sens', n = 10)%>%
gt::gt() %>%
gt::fmt_percent(columns = mean,
decimals = 2)
| mtry | trees | min_n | .metric | .estimator | mean | n | std_err | .config |
|---|---|---|---|---|---|---|---|---|
| 4 | 1570 | 116 | sens | binary | 73.85% | 5 | 0.01400695 | Preprocessor1_Model12 |
| 4 | 1470 | 118 | sens | binary | 73.78% | 5 | 0.01633669 | Preprocessor1_Model19 |
| 4 | 1270 | 116 | sens | binary | 73.71% | 5 | 0.01516493 | Preprocessor1_Model09 |
| 4 | 1370 | 116 | sens | binary | 73.71% | 5 | 0.01592058 | Preprocessor1_Model10 |
| 4 | 1270 | 118 | sens | binary | 73.71% | 5 | 0.01389470 | Preprocessor1_Model17 |
| 4 | 1370 | 114 | sens | binary | 73.58% | 5 | 0.01374903 | Preprocessor1_Model02 |
| 4 | 1570 | 114 | sens | binary | 73.58% | 5 | 0.01453984 | Preprocessor1_Model04 |
| 5 | 1470 | 114 | sens | binary | 73.58% | 5 | 0.01246913 | Preprocessor1_Model07 |
| 4 | 1470 | 116 | sens | binary | 73.58% | 5 | 0.01586427 | Preprocessor1_Model11 |
| 4 | 1470 | 114 | sens | binary | 73.51% | 5 | 0.01396697 | Preprocessor1_Model03 |
show_best(rf_tuned_2, metric = 'spec', n = 10)%>%
gt::gt() %>%
gt::fmt_percent(columns = mean,
decimals = 2)
| mtry | trees | min_n | .metric | .estimator | mean | n | std_err | .config |
|---|---|---|---|---|---|---|---|---|
| 4 | 1470 | 116 | spec | binary | 78.01% | 5 | 0.007626337 | Preprocessor1_Model11 |
| 5 | 1370 | 118 | spec | binary | 77.97% | 5 | 0.009307187 | Preprocessor1_Model22 |
| 4 | 1370 | 118 | spec | binary | 77.94% | 5 | 0.008514508 | Preprocessor1_Model18 |
| 4 | 1570 | 118 | spec | binary | 77.94% | 5 | 0.007638444 | Preprocessor1_Model20 |
| 5 | 1270 | 114 | spec | binary | 77.92% | 5 | 0.008828907 | Preprocessor1_Model05 |
| 5 | 1570 | 118 | spec | binary | 77.89% | 5 | 0.008602431 | Preprocessor1_Model24 |
| 5 | 1470 | 116 | spec | binary | 77.87% | 5 | 0.009168637 | Preprocessor1_Model15 |
| 4 | 1270 | 118 | spec | binary | 77.87% | 5 | 0.007378859 | Preprocessor1_Model17 |
| 5 | 1470 | 114 | spec | binary | 77.85% | 5 | 0.008993232 | Preprocessor1_Model07 |
| 4 | 1570 | 114 | spec | binary | 77.85% | 5 | 0.008682746 | Preprocessor1_Model04 |
show_best(rf_tuned_2, metric = 'bal_accuracy', n = 10)%>%
gt::gt() %>%
gt::fmt_percent(columns = mean,
decimals = 2)
| mtry | trees | min_n | .metric | .estimator | mean | n | std_err | .config |
|---|---|---|---|---|---|---|---|---|
| 4 | 1570 | 116 | bal_accuracy | binary | 75.81% | 5 | 0.01071294 | Preprocessor1_Model12 |
| 4 | 1470 | 116 | bal_accuracy | binary | 75.80% | 5 | 0.01143105 | Preprocessor1_Model11 |
| 4 | 1270 | 118 | bal_accuracy | binary | 75.79% | 5 | 0.01029785 | Preprocessor1_Model17 |
| 4 | 1470 | 118 | bal_accuracy | binary | 75.79% | 5 | 0.01191147 | Preprocessor1_Model19 |
| 4 | 1270 | 116 | bal_accuracy | binary | 75.78% | 5 | 0.01100681 | Preprocessor1_Model09 |
| 4 | 1370 | 116 | bal_accuracy | binary | 75.74% | 5 | 0.01129458 | Preprocessor1_Model10 |
| 5 | 1270 | 114 | bal_accuracy | binary | 75.71% | 5 | 0.01034855 | Preprocessor1_Model05 |
| 5 | 1470 | 114 | bal_accuracy | binary | 75.71% | 5 | 0.01027413 | Preprocessor1_Model07 |
| 4 | 1570 | 114 | bal_accuracy | binary | 75.71% | 5 | 0.01129857 | Preprocessor1_Model04 |
| 4 | 1570 | 118 | bal_accuracy | binary | 75.69% | 5 | 0.01028621 | Preprocessor1_Model20 |
Se verifica que el modelo obtenido de la primera malla de hiperparámetros tiene mejores resultados en sensibilidad que la segunda grilla, por tanto se selecciona el mejor modelo del primer ejercicio. ### Modelo final
## Definir la mejor combinacion
rf_pars_fin <- select_best(rf_tuned, metric = 'sens')
## Finalizar (darle valores a parametros tuneables) el workflow
rf_wflow_fin <-
rf_wflow %>%
finalize_workflow(rf_pars_fin)
rf_wflow_fin
## ══ Workflow ════════════════════════════════════════════════════════════════════
## Preprocessor: Recipe
## Model: rand_forest()
##
## ── Preprocessor ────────────────────────────────────────────────────────────────
## 8 Recipe Steps
##
## • step_rm()
## • step_impute_knn()
## • step_normalize()
## • step_other()
## • step_novel()
## • step_dummy()
## • step_nzv()
## • step_upsample()
##
## ── Model ───────────────────────────────────────────────────────────────────────
## Random Forest Model Specification (classification)
##
## Main Arguments:
## mtry = 4
## trees = 1370
## min_n = 116
##
## Engine-Specific Arguments:
## importance = impurity
##
## Computational engine: ranger
Entrenar el modelo final
rf_fitted <- fit(rf_wflow_fin, train)
rf_fitted
## ══ Workflow [trained] ══════════════════════════════════════════════════════════
## Preprocessor: Recipe
## Model: rand_forest()
##
## ── Preprocessor ────────────────────────────────────────────────────────────────
## 8 Recipe Steps
##
## • step_rm()
## • step_impute_knn()
## • step_normalize()
## • step_other()
## • step_novel()
## • step_dummy()
## • step_nzv()
## • step_upsample()
##
## ── Model ───────────────────────────────────────────────────────────────────────
## Ranger result
##
## Call:
## ranger::ranger(x = maybe_data_frame(x), y = y, mtry = min_cols(~4L, x), num.trees = ~1370L, min.node.size = min_rows(~116L, x), importance = ~"impurity", num.threads = 1, verbose = FALSE, seed = sample.int(10^5, 1), probability = TRUE)
##
## Type: Probability estimation
## Number of trees: 1370
## Sample size: 7864
## Number of independent variables: 30
## Mtry: 4
## Target node size: 116
## Variable importance mode: impurity
## Splitrule: gini
## OOB prediction error (Brier s.): 0.1478207
rf_model_fin <- extract_fit_parsnip(rf_fitted)
Evaluación en la data de entrenamiento
train %>%
predict(rf_fitted , new_data = . ) %>%
mutate(Real= train$Churn) %>%
conf_mat(truth = Real, estimate = .pred_class ) %>%
summary
## # A tibble: 13 × 3
## .metric .estimator .estimate
## <chr> <chr> <dbl>
## 1 accuracy binary 0.793
## 2 kap binary 0.523
## 3 sens binary 0.791
## 4 spec binary 0.793
## 5 ppv binary 0.580
## 6 npv binary 0.913
## 7 mcc binary 0.536
## 8 j_index binary 0.584
## 9 bal_accuracy binary 0.792
## 10 detection_prevalence binary 0.362
## 11 precision binary 0.580
## 12 recall binary 0.791
## 13 f_meas binary 0.669
test %>%
predict(rf_fitted, new_data = . ) %>%
mutate(Real= test$Churn) %>%
conf_mat(truth = Real, estimate = .pred_class ) %>%
summary
## # A tibble: 13 × 3
## .metric .estimator .estimate
## <chr> <chr> <dbl>
## 1 accuracy binary 0.779
## 2 kap binary 0.480
## 3 sens binary 0.722
## 4 spec binary 0.8
## 5 ppv binary 0.566
## 6 npv binary 0.888
## 7 mcc binary 0.487
## 8 j_index binary 0.522
## 9 bal_accuracy binary 0.761
## 10 detection_prevalence binary 0.339
## 11 precision binary 0.566
## 12 recall binary 0.722
## 13 f_meas binary 0.635
library(vip)
rf_model_fin %>%
vip(geom = "point")
Como parte del ejercicio de selección del mejor modelo para la determinación de la mejor estrategia para retención de clientes, se utiliza el algoritmo XGboost con la finalidad de elegir el modelo con mayor poder predictivo.
Para tal efecto, la aplicación del algoritmo XGboost inicia a partir de la receta establecida para los datos de abandono de clientes del servicio de telecomunicaciones.
xgb_sp <- boost_tree(mtry = tune(), trees = tune(),
loss_reduction = tune(), learn_rate= tune() ) %>%
set_engine("xgboost") %>%
set_mode("classification")
xgb_sp %>%
translate()
## Boosted Tree Model Specification (classification)
##
## Main Arguments:
## mtry = tune()
## trees = tune()
## learn_rate = tune()
## loss_reduction = tune()
##
## Computational engine: xgboost
##
## Model fit template:
## parsnip::xgb_train(x = missing_arg(), y = missing_arg(), weights = missing_arg(),
## colsample_bynode = tune(), nrounds = tune(), eta = tune(),
## gamma = tune(), nthread = 1, verbose = 0)
Previo a establecer la malla de búsqueda el algoritmo requiere la data incorporada las funciones establecidas en la receta, por tal motivo se aplica prep y bake. Posteriormente, se obtiene la malla de búsqueda
receta_prep = prep(receta, train)
finalize(mtry(), bake(receta_prep, new_data = NULL ))
## # Randomly Selected Predictors (quantitative)
## Range: [1, 31]
set.seed(123)
xgb_grid <- xgb_sp %>%
parameters() %>%
finalize(bake(receta_prep, new_data = NULL)) %>%
grid_latin_hypercube(size = 20)
xgb_grid
## # A tibble: 20 × 4
## mtry trees learn_rate loss_reduction
## <int> <int> <dbl> <dbl>
## 1 8 340 0.00151 5.11e- 4
## 2 9 514 0.00628 8.18e- 2
## 3 6 1881 0.00200 6.04e- 1
## 4 28 1318 0.169 5.69e- 9
## 5 14 1595 0.0503 1.08e- 2
## 6 3 65 0.00300 1.42e-10
## 7 22 1901 0.0388 1.42e- 4
## 8 28 1031 0.00557 2.23e- 5
## 9 21 1759 0.0131 1.31e+ 1
## 10 31 861 0.00106 4.42e-10
## 11 2 1186 0.0273 5.92e- 1
## 12 12 1406 0.00880 2.44e- 9
## 13 25 1652 0.0753 6.58e- 7
## 14 17 252 0.114 1.14e- 2
## 15 20 908 0.263 3.28e+ 0
## 16 19 791 0.0137 1.75e- 7
## 17 16 430 0.0687 6.27e- 8
## 18 26 1290 0.00392 1.25e- 6
## 19 5 683 0.0235 1.86e- 3
## 20 10 173 0.184 6.01e- 6
xgb_wflow <-
workflow() %>%
add_recipe(receta) %>%
add_model(xgb_sp)
xgb_wflow
## ══ Workflow ════════════════════════════════════════════════════════════════════
## Preprocessor: Recipe
## Model: boost_tree()
##
## ── Preprocessor ────────────────────────────────────────────────────────────────
## 8 Recipe Steps
##
## • step_rm()
## • step_impute_knn()
## • step_normalize()
## • step_other()
## • step_novel()
## • step_dummy()
## • step_nzv()
## • step_upsample()
##
## ── Model ───────────────────────────────────────────────────────────────────────
## Boosted Tree Model Specification (classification)
##
## Main Arguments:
## mtry = tune()
## trees = tune()
## learn_rate = tune()
## loss_reduction = tune()
##
## Computational engine: xgboost
set.seed(123)
xgb_tuned <- tune_grid(
xgb_wflow,
resamples= cv,
grid = xgb_grid,
metrics = metricas,
control= control_grid(allow_par = T, save_pred = T)
)
xgb_tuned
## # Tuning results
## # 5-fold cross-validation using stratification
## # A tibble: 5 × 5
## splits id .metrics .notes .predictions
## <list> <chr> <list> <list> <list>
## 1 <split [4507/1127]> Fold1 <tibble [80 × 8]> <tibble [0 × 3]> <tibble>
## 2 <split [4507/1127]> Fold2 <tibble [80 × 8]> <tibble [0 × 3]> <tibble>
## 3 <split [4507/1127]> Fold3 <tibble [80 × 8]> <tibble [0 × 3]> <tibble>
## 4 <split [4507/1127]> Fold4 <tibble [80 × 8]> <tibble [0 × 3]> <tibble>
## 5 <split [4508/1126]> Fold5 <tibble [80 × 8]> <tibble [0 × 3]> <tibble>
Evaluamos que modelo resulto mejor
show_best(xgb_tuned, metric = 'accuracy', n = 10)
## # A tibble: 10 × 10
## mtry trees learn_rate loss_reduction .metric .estimator mean n std_err
## <int> <int> <dbl> <dbl> <chr> <chr> <dbl> <int> <dbl>
## 1 5 683 0.0235 1.86e-3 accuracy binary 0.763 5 0.00639
## 2 12 1406 0.00880 2.44e-9 accuracy binary 0.761 5 0.00638
## 3 21 1759 0.0131 1.31e+1 accuracy binary 0.760 5 0.00700
## 4 19 791 0.0137 1.75e-7 accuracy binary 0.760 5 0.00534
## 5 6 1881 0.00200 6.04e-1 accuracy binary 0.759 5 0.00832
## 6 10 173 0.184 6.01e-6 accuracy binary 0.759 5 0.00563
## 7 2 1186 0.0273 5.92e-1 accuracy binary 0.758 5 0.00663
## 8 9 514 0.00628 8.18e-2 accuracy binary 0.758 5 0.00675
## 9 26 1290 0.00392 1.25e-6 accuracy binary 0.757 5 0.00721
## 10 28 1031 0.00557 2.23e-5 accuracy binary 0.756 5 0.00616
## # ℹ 1 more variable: .config <chr>
show_best(xgb_tuned, metric = 'sens', n = 10)
## # A tibble: 10 × 10
## mtry trees learn_rate loss_reduction .metric .estimator mean n std_err
## <int> <int> <dbl> <dbl> <chr> <chr> <dbl> <int> <dbl>
## 1 3 65 0.00300 1.42e-10 sens binary 0.766 5 0.0127
## 2 21 1759 0.0131 1.31e+ 1 sens binary 0.763 5 0.0113
## 3 8 340 0.00151 5.11e- 4 sens binary 0.761 5 0.0118
## 4 31 861 0.00106 4.42e-10 sens binary 0.748 5 0.0179
## 5 9 514 0.00628 8.18e- 2 sens binary 0.747 5 0.00979
## 6 6 1881 0.00200 6.04e- 1 sens binary 0.745 5 0.0114
## 7 28 1031 0.00557 2.23e- 5 sens binary 0.740 5 0.0127
## 8 26 1290 0.00392 1.25e- 6 sens binary 0.740 5 0.0141
## 9 19 791 0.0137 1.75e- 7 sens binary 0.726 5 0.00812
## 10 12 1406 0.00880 2.44e- 9 sens binary 0.721 5 0.00714
## # ℹ 1 more variable: .config <chr>
show_best(xgb_tuned, metric = 'spec', n = 10)
## # A tibble: 10 × 10
## mtry trees learn_rate loss_reduction .metric .estimator mean n std_err
## <int> <int> <dbl> <dbl> <chr> <chr> <dbl> <int> <dbl>
## 1 28 1318 0.169 0.00000000569 spec binary 0.804 5 0.00322
## 2 14 1595 0.0503 0.0108 spec binary 0.799 5 0.00321
## 3 22 1901 0.0388 0.000142 spec binary 0.795 5 0.00466
## 4 25 1652 0.0753 0.000000658 spec binary 0.794 5 0.00335
## 5 10 173 0.184 0.00000601 spec binary 0.790 5 0.00441
## 6 16 430 0.0687 0.0000000627 spec binary 0.788 5 0.00507
## 7 20 908 0.263 3.28 spec binary 0.783 5 0.00540
## 8 5 683 0.0235 0.00186 spec binary 0.782 5 0.00576
## 9 17 252 0.114 0.0114 spec binary 0.782 5 0.00320
## 10 2 1186 0.0273 0.592 spec binary 0.776 5 0.00748
## # ℹ 1 more variable: .config <chr>
show_best(xgb_tuned, metric = 'bal_accuracy', n = 10)
## # A tibble: 10 × 10
## mtry trees learn_rate loss_reduction .metric .estimator mean n std_err
## <int> <int> <dbl> <dbl> <chr> <chr> <dbl> <int> <dbl>
## 1 21 1759 0.0131 1.31e+ 1 bal_acc… binary 0.761 5 0.00816
## 2 3 65 0.00300 1.42e-10 bal_acc… binary 0.757 5 0.00938
## 3 8 340 0.00151 5.11e- 4 bal_acc… binary 0.756 5 0.00934
## 4 6 1881 0.00200 6.04e- 1 bal_acc… binary 0.755 5 0.00873
## 5 9 514 0.00628 8.18e- 2 bal_acc… binary 0.754 5 0.00727
## 6 26 1290 0.00392 1.25e- 6 bal_acc… binary 0.751 5 0.00924
## 7 28 1031 0.00557 2.23e- 5 bal_acc… binary 0.751 5 0.00799
## 8 19 791 0.0137 1.75e- 7 bal_acc… binary 0.749 5 0.00622
## 9 12 1406 0.00880 2.44e- 9 bal_acc… binary 0.748 5 0.00642
## 10 31 861 0.00106 4.42e-10 bal_acc… binary 0.748 5 0.00919
## # ℹ 1 more variable: .config <chr>
La selección de los hipepáramestros es con base al mejor modelo de sensibilidad y “bal_accuracy”, por tanto se el modelo final resulta ser el modelo 04, no se realizá un proceso búsqueda manual del mejor modelo debido a la amplitud de valores que puede tomar el learn_rate y la función de costo, así como la discrecionalidad de la amplitud de búsqueda.
xgb_pars_fin <- select_best(xgb_tuned, metric = 'sens')
xgb_wflow_fin <-
xgb_wflow %>%
finalize_workflow(xgb_pars_fin)
xgb_wflow_fin
## ══ Workflow ════════════════════════════════════════════════════════════════════
## Preprocessor: Recipe
## Model: boost_tree()
##
## ── Preprocessor ────────────────────────────────────────────────────────────────
## 8 Recipe Steps
##
## • step_rm()
## • step_impute_knn()
## • step_normalize()
## • step_other()
## • step_novel()
## • step_dummy()
## • step_nzv()
## • step_upsample()
##
## ── Model ───────────────────────────────────────────────────────────────────────
## Boosted Tree Model Specification (classification)
##
## Main Arguments:
## mtry = 3
## trees = 65
## learn_rate = 0.00299866530863753
## loss_reduction = 1.42014018015466e-10
##
## Computational engine: xgboost
xgb_fitted <- fit(xgb_wflow_fin, train)
xgb_fitted
## ══ Workflow [trained] ══════════════════════════════════════════════════════════
## Preprocessor: Recipe
## Model: boost_tree()
##
## ── Preprocessor ────────────────────────────────────────────────────────────────
## 8 Recipe Steps
##
## • step_rm()
## • step_impute_knn()
## • step_normalize()
## • step_other()
## • step_novel()
## • step_dummy()
## • step_nzv()
## • step_upsample()
##
## ── Model ───────────────────────────────────────────────────────────────────────
## ##### xgb.Booster
## raw: 173.7 Kb
## call:
## xgboost::xgb.train(params = list(eta = 0.00299866530863753, max_depth = 6,
## gamma = 1.42014018015466e-10, colsample_bytree = 1, colsample_bynode = 0.1,
## min_child_weight = 1, subsample = 1), data = x$data, nrounds = 65L,
## watchlist = x$watchlist, verbose = 0, nthread = 1, objective = "binary:logistic")
## params (as set within xgb.train):
## eta = "0.00299866530863753", max_depth = "6", gamma = "1.42014018015466e-10", colsample_bytree = "1", colsample_bynode = "0.1", min_child_weight = "1", subsample = "1", nthread = "1", objective = "binary:logistic", validate_parameters = "TRUE"
## xgb.attributes:
## niter
## callbacks:
## cb.evaluation.log()
## # of features: 30
## niter: 65
## nfeatures : 30
## evaluation_log:
## iter training_logloss
## 1 0.6921809
## 2 0.6914972
## ---
## 64 0.6464204
## 65 0.6456987
xgb_model_fin <- pull_workflow_fit(xgb_fitted)
## Warning: `pull_workflow_fit()` was deprecated in workflows 0.2.3.
## ℹ Please use `extract_fit_parsnip()` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
xgb_model_fin
## parsnip model object
##
## ##### xgb.Booster
## raw: 173.7 Kb
## call:
## xgboost::xgb.train(params = list(eta = 0.00299866530863753, max_depth = 6,
## gamma = 1.42014018015466e-10, colsample_bytree = 1, colsample_bynode = 0.1,
## min_child_weight = 1, subsample = 1), data = x$data, nrounds = 65L,
## watchlist = x$watchlist, verbose = 0, nthread = 1, objective = "binary:logistic")
## params (as set within xgb.train):
## eta = "0.00299866530863753", max_depth = "6", gamma = "1.42014018015466e-10", colsample_bytree = "1", colsample_bynode = "0.1", min_child_weight = "1", subsample = "1", nthread = "1", objective = "binary:logistic", validate_parameters = "TRUE"
## xgb.attributes:
## niter
## callbacks:
## cb.evaluation.log()
## # of features: 30
## niter: 65
## nfeatures : 30
## evaluation_log:
## iter training_logloss
## 1 0.6921809
## 2 0.6914972
## ---
## 64 0.6464204
## 65 0.6456987
train %>%
predict(xgb_fitted , new_data = . ) %>%
mutate(Real= train$Churn) %>%
conf_mat(truth = Real, estimate = .pred_class ) %>%
summary
## # A tibble: 13 × 3
## .metric .estimator .estimate
## <chr> <chr> <dbl>
## 1 accuracy binary 0.763
## 2 kap binary 0.468
## 3 sens binary 0.777
## 4 spec binary 0.757
## 5 ppv binary 0.536
## 6 npv binary 0.904
## 7 mcc binary 0.485
## 8 j_index binary 0.535
## 9 bal_accuracy binary 0.767
## 10 detection_prevalence binary 0.384
## 11 precision binary 0.536
## 12 recall binary 0.777
## 13 f_meas binary 0.635
test %>%
predict(xgb_fitted , new_data = . ) %>%
mutate(Real= test$Churn) %>%
conf_mat(truth = Real, estimate = .pred_class ) %>%
summary
## # A tibble: 13 × 3
## .metric .estimator .estimate
## <chr> <chr> <dbl>
## 1 accuracy binary 0.769
## 2 kap binary 0.470
## 3 sens binary 0.746
## 4 spec binary 0.778
## 5 ppv binary 0.548
## 6 npv binary 0.894
## 7 mcc binary 0.481
## 8 j_index binary 0.524
## 9 bal_accuracy binary 0.762
## 10 detection_prevalence binary 0.361
## 11 precision binary 0.548
## 12 recall binary 0.746
## 13 f_meas binary 0.632
vip(xgb_model_fin)
Analizando la importancia de las variables en el modelo se verifica que el gasto mensual y total presentan una alta importancia en las variables sin embargo el gasto total es una combinación lineal del gasto mensual, por lo que se podría excluir del modelo una de las variabales para probar si incrementa su capacidad de predicción con respecto a sensibilidad y bal_accuracy.
Del análisis realizado se evidencia que ambos modelos (Random Forest y Xgboost ) presentan muy buena estimación con relación a sensibilidad, es decir con la capacidad de predicción de los individuos que abandonan el servicio, no obstante Xgboost presenta un resultado superior en el test de prueba (0.7459 > 0.7245), por tanto el modelo seleccionado es Xgboost.