Análisis Predictivo de Compra M1

1. Instalar paquetes y llamar librerías

# install.packages("ggplot2")
# install.packages("lattice")
# install.packages("caret")
# install.packages("DataExplorer")

library(ggplot2)
library(lattice)
library(caret)
library(DataExplorer)

2. Crear la base de datos

# Cargamos el dataset proporcionado
df <- read.csv("/Users/erickcaballero/Downloads/M1_data.csv")

# Convertimos las variables categóricas a FACTOR para que el modelo realice clasificación
# Es fundamental que la variable objetivo (m1_purchase) sea factor.
df$m1_purchase <- as.factor(df$m1_purchase)
df$trust_apple <- as.factor(df$trust_apple)
df$user_pcmac <- as.factor(df$user_pcmac)
df$familiarity_m1 <- as.factor(df$familiarity_m1)
df$gender <- as.factor(df$gender)
df$status <- as.factor(df$status)
df$domain <- as.factor(df$domain)

# Verificamos la estructura
str(df)

## 'data.frame':    133 obs. of  22 variables:
##  $ trust_apple        : Factor w/ 2 levels "No","Yes": 1 2 2 2 2 2 2 1 2 2 ...
##  $ interest_computers : int  4 2 5 2 4 3 3 3 4 5 ...
##  $ age_computer       : int  8 4 6 6 4 1 2 0 2 0 ...
##  $ user_pcmac         : Factor w/ 4 levels "Apple","Hp","Other",..: 4 4 4 1 1 1 1 4 1 1 ...
##  $ appleproducts_count: int  0 1 0 4 7 2 7 0 6 7 ...
##  $ familiarity_m1     : Factor w/ 2 levels "No","Yes": 1 1 1 1 2 1 1 1 2 2 ...
##  $ f_batterylife      : int  5 5 3 4 5 5 4 5 4 5 ...
##  $ f_price            : int  4 5 4 3 3 5 3 5 4 3 ...
##  $ f_size             : int  3 5 2 3 3 4 4 4 3 5 ...
##  $ f_multitasking     : int  4 3 4 4 4 4 5 4 4 5 ...
##  $ f_noise            : int  4 4 1 4 4 5 5 3 4 5 ...
##  $ f_performance      : int  2 5 4 4 5 5 5 3 4 5 ...
##  $ f_neural           : int  2 2 2 4 3 5 3 2 3 3 ...
##  $ f_synergy          : int  1 2 2 4 4 4 3 2 3 5 ...
##  $ f_performanceloss  : int  1 4 2 3 4 2 2 3 4 5 ...
##  $ m1_consideration   : int  1 2 4 2 4 2 3 1 5 5 ...
##  $ m1_purchase        : Factor w/ 2 levels "No","Yes": 2 1 2 1 2 1 2 1 2 2 ...
##  $ gender             : Factor w/ 2 levels "Female","Male": 2 2 2 1 2 1 2 2 2 2 ...
##  $ age_group          : int  2 2 2 2 5 2 6 2 8 4 ...
##  $ income_group       : int  2 3 2 2 7 2 7 2 7 6 ...
##  $ status             : Factor w/ 6 levels "Employed","Retired",..: 4 1 4 4 1 4 1 4 1 1 ...
##  $ domain             : Factor w/ 22 levels "Administration & Public Services",..: 21 10 13 3 12 17 13 22 13 12 ...

3. Entender la base de datos

summary(df)

##  trust_apple interest_computers  age_computer   user_pcmac appleproducts_count
##  No : 19     Min.   :2.000      Min.   :0.000   Apple:86   Min.   :0.000      
##  Yes:114     1st Qu.:3.000      1st Qu.:1.000   Hp   : 1   1st Qu.:1.000      
##              Median :4.000      Median :3.000   Other: 1   Median :3.000      
##              Mean   :3.812      Mean   :2.827   PC   :45   Mean   :2.609      
##              3rd Qu.:5.000      3rd Qu.:5.000              3rd Qu.:4.000      
##              Max.   :5.000      Max.   :9.000              Max.   :8.000      
##                                                                               
##  familiarity_m1 f_batterylife      f_price          f_size      f_multitasking
##  No :75         Min.   :1.000   Min.   :1.000   Min.   :1.000   Min.   :2.00  
##  Yes:58         1st Qu.:4.000   1st Qu.:3.000   1st Qu.:2.000   1st Qu.:4.00  
##                 Median :5.000   Median :4.000   Median :3.000   Median :4.00  
##                 Mean   :4.526   Mean   :3.872   Mean   :3.158   Mean   :4.12  
##                 3rd Qu.:5.000   3rd Qu.:5.000   3rd Qu.:4.000   3rd Qu.:5.00  
##                 Max.   :5.000   Max.   :5.000   Max.   :5.000   Max.   :5.00  
##                                                                               
##     f_noise      f_performance      f_neural       f_synergy    
##  Min.   :1.000   Min.   :2.000   Min.   :1.000   Min.   :1.000  
##  1st Qu.:3.000   1st Qu.:4.000   1st Qu.:2.000   1st Qu.:3.000  
##  Median :4.000   Median :5.000   Median :3.000   Median :4.000  
##  Mean   :3.729   Mean   :4.398   Mean   :3.165   Mean   :3.466  
##  3rd Qu.:5.000   3rd Qu.:5.000   3rd Qu.:4.000   3rd Qu.:4.000  
##  Max.   :5.000   Max.   :5.000   Max.   :5.000   Max.   :5.000  
##                                                                 
##  f_performanceloss m1_consideration m1_purchase    gender     age_group    
##  Min.   :1.000     Min.   :1.000    No :45      Female:61   Min.   : 1.00  
##  1st Qu.:3.000     1st Qu.:3.000    Yes:88      Male  :72   1st Qu.: 2.00  
##  Median :4.000     Median :4.000                            Median : 2.00  
##  Mean   :3.376     Mean   :3.609                            Mean   : 2.97  
##  3rd Qu.:4.000     3rd Qu.:5.000                            3rd Qu.: 3.00  
##  Max.   :5.000     Max.   :5.000                            Max.   :10.00  
##                                                                            
##   income_group                   status               domain  
##  Min.   :1.00   Employed            :41   IT & Technology:33  
##  1st Qu.:1.00   Retired             : 1   Marketing      :21  
##  Median :2.00   Self-Employed       : 5   Business       :14  
##  Mean   :2.97   Student             :84   Engineering    : 7  
##  3rd Qu.:4.00   Student ant employed: 1   Finance        : 7  
##  Max.   :7.00   Unemployed          : 1   Science        : 7  
##                                           (Other)        :44

plot_missing(df)

## Warning: `aes_string()` was deprecated in ggplot2 3.0.0.
## ℹ Please use tidy evaluation idioms with `aes()`.
## ℹ See also `vignette("ggplot2-in-packages")` for more information.
## ℹ The deprecated feature was likely used in the DataExplorer package.
##   Please report the issue at
##   <https://github.com/boxuancui/DataExplorer/issues>.
## This warning is displayed once per session.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.

plot_histogram(df)

plot_correlation(df)

## 1 features with more than 20 categories ignored!
## domain: 22 categories

4. Partir la base de datos

# Normalmente 80-20
set.seed(123)
renglones_entrenamiento <- createDataPartition(df$m1_purchase, p=0.8, list=FALSE)
entrenamiento <- df[renglones_entrenamiento, ]
prueba <- df[-renglones_entrenamiento, ]

5. Modelado de Algoritmos

Modelo 1. SVM Lineal

modelo1 <- train(m1_purchase ~ ., data=entrenamiento,
                 method = "svmLinear",
                 preProcess = c("scale", "center"),
                 trControl = trainControl(method="cv", number=10),
                 tuneGrid = data.frame(C=1)
                 )

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainAgriculture, domainCommunication , domainRetired

## Warning in .local(x, ...): Variable(s) `' constant. Cannot scale data.

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainRetired

## Warning in .local(x, ...): Variable(s) `' constant. Cannot scale data.

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacHp, user_pcmacOther,
## statusRetired, statusStudent ant employed, statusUnemployed,
## domainCommunication , domainRealestate, domainRetired

## Warning in .local(x, ...): Variable(s) `' constant. Cannot scale data.

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainRetired

## Warning in .local(x, ...): Variable(s) `' constant. Cannot scale data.

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainRetired

## Warning in .local(x, ...): Variable(s) `' constant. Cannot scale data.

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainRetired

## Warning in .local(x, ...): Variable(s) `' constant. Cannot scale data.

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainLaw, domainRetired

## Warning in .local(x, ...): Variable(s) `' constant. Cannot scale data.

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainRetail, domainRetired

## Warning in .local(x, ...): Variable(s) `' constant. Cannot scale data.

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainConsulting , domainRetired

## Warning in .local(x, ...): Variable(s) `' constant. Cannot scale data.

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainLogistics, domainRetired

## Warning in .local(x, ...): Variable(s) `' constant. Cannot scale data.

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainRetired

## Warning in .local(x, ...): Variable(s) `' constant. Cannot scale data.

resultado_entrenamiento1 <- predict(modelo1, entrenamiento)
resultado_prueba1 <- predict(modelo1, prueba)

mcre1 <- confusionMatrix(resultado_entrenamiento1, entrenamiento$m1_purchase)
mcrp1 <- confusionMatrix(resultado_prueba1, prueba$m1_purchase)
mcrp1

## Confusion Matrix and Statistics
## 
##           Reference
## Prediction No Yes
##        No   3   6
##        Yes  6  11
##                                           
##                Accuracy : 0.5385          
##                  95% CI : (0.3337, 0.7341)
##     No Information Rate : 0.6538          
##     P-Value [Acc > NIR] : 0.9231          
##                                           
##                   Kappa : -0.0196         
##                                           
##  Mcnemar's Test P-Value : 1.0000          
##                                           
##             Sensitivity : 0.3333          
##             Specificity : 0.6471          
##          Pos Pred Value : 0.3333          
##          Neg Pred Value : 0.6471          
##              Prevalence : 0.3462          
##          Detection Rate : 0.1154          
##    Detection Prevalence : 0.3462          
##       Balanced Accuracy : 0.4902          
##                                           
##        'Positive' Class : No              
## 

Modelo 2. SVM Radial

modelo2 <- train(m1_purchase ~ ., data=entrenamiento,
                 method = "svmRadial",
                 preProcess = c("scale", "center"),
                 trControl = trainControl(method="cv", number=10),
                 tuneGrid = data.frame(sigma=0.01, C=1)
                 )

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainRetired

## Warning in .local(x, ...): Variable(s) `' constant. Cannot scale data.

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacHp, user_pcmacOther,
## statusRetired, statusUnemployed, domainAgriculture, domainCommunication ,
## domainLogistics, domainRetired

## Warning in .local(x, ...): Variable(s) `' constant. Cannot scale data.

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainRetired

## Warning in .local(x, ...): Variable(s) `' constant. Cannot scale data.

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainRetired

## Warning in .local(x, ...): Variable(s) `' constant. Cannot scale data.

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainLaw, domainRetired

## Warning in .local(x, ...): Variable(s) `' constant. Cannot scale data.

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainRetail, domainRetired

## Warning in .local(x, ...): Variable(s) `' constant. Cannot scale data.

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainRetired

## Warning in .local(x, ...): Variable(s) `' constant. Cannot scale data.

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusStudent ant employed, statusUnemployed, domainCommunication ,
## domainRealestate, domainRetired

## Warning in .local(x, ...): Variable(s) `' constant. Cannot scale data.

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainConsulting , domainRetired

## Warning in .local(x, ...): Variable(s) `' constant. Cannot scale data.

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainEconomics, domainRetired

## Warning in .local(x, ...): Variable(s) `' constant. Cannot scale data.

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainRetired

## Warning in .local(x, ...): Variable(s) `' constant. Cannot scale data.

resultado_entrenamiento2 <- predict(modelo2, entrenamiento)
resultado_prueba2 <- predict(modelo2, prueba)

mcre2 <- confusionMatrix(resultado_entrenamiento2, entrenamiento$m1_purchase)
mcrp2 <- confusionMatrix(resultado_prueba2, prueba$m1_purchase)
mcrp2

## Confusion Matrix and Statistics
## 
##           Reference
## Prediction No Yes
##        No   1   3
##        Yes  8  14
##                                           
##                Accuracy : 0.5769          
##                  95% CI : (0.3692, 0.7665)
##     No Information Rate : 0.6538          
##     P-Value [Acc > NIR] : 0.8485          
##                                           
##                   Kappa : -0.0752         
##                                           
##  Mcnemar's Test P-Value : 0.2278          
##                                           
##             Sensitivity : 0.11111         
##             Specificity : 0.82353         
##          Pos Pred Value : 0.25000         
##          Neg Pred Value : 0.63636         
##              Prevalence : 0.34615         
##          Detection Rate : 0.03846         
##    Detection Prevalence : 0.15385         
##       Balanced Accuracy : 0.46732         
##                                           
##        'Positive' Class : No              
## 

Modelo 3. SVM Polinómico

modelo3 <- train(m1_purchase ~ ., data=entrenamiento,
                 method = "svmPoly",
                 preProcess = c("scale", "center"),
                 trControl = trainControl(method="cv", number=10),
                 tuneGrid = data.frame(degree=1, scale=1, C=1)
                 )

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainRetired

## Warning in .local(x, ...): Variable(s) `' constant. Cannot scale data.

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainRealestate, domainRetired

## Warning in .local(x, ...): Variable(s) `' constant. Cannot scale data.

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusSelf-Employed, statusStudent ant employed, statusUnemployed,
## domainCommunication , domainRetired

## Warning in .local(x, ...): Variable(s) `' constant. Cannot scale data.

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacHp, user_pcmacOther,
## statusRetired, statusUnemployed, domainCommunication , domainRetired

## Warning in .local(x, ...): Variable(s) `' constant. Cannot scale data.

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainConsulting , domainRetail,
## domainRetired

## Warning in .local(x, ...): Variable(s) `' constant. Cannot scale data.

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainRetired

## Warning in .local(x, ...): Variable(s) `' constant. Cannot scale data.

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainLogistics, domainRetired

## Warning in .local(x, ...): Variable(s) `' constant. Cannot scale data.

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainAgriculture, domainCommunication , domainLaw,
## domainRetired

## Warning in .local(x, ...): Variable(s) `' constant. Cannot scale data.

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainRetired

## Warning in .local(x, ...): Variable(s) `' constant. Cannot scale data.

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainRetired

## Warning in .local(x, ...): Variable(s) `' constant. Cannot scale data.

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainRetired

## Warning in .local(x, ...): Variable(s) `' constant. Cannot scale data.

resultado_entrenamiento3 <- predict(modelo3, entrenamiento)
resultado_prueba3 <- predict(modelo3, prueba)

mcre3 <- confusionMatrix(resultado_entrenamiento3, entrenamiento$m1_purchase)
mcrp3 <- confusionMatrix(resultado_prueba3, prueba$m1_purchase)
mcrp3

## Confusion Matrix and Statistics
## 
##           Reference
## Prediction No Yes
##        No   3   6
##        Yes  6  11
##                                           
##                Accuracy : 0.5385          
##                  95% CI : (0.3337, 0.7341)
##     No Information Rate : 0.6538          
##     P-Value [Acc > NIR] : 0.9231          
##                                           
##                   Kappa : -0.0196         
##                                           
##  Mcnemar's Test P-Value : 1.0000          
##                                           
##             Sensitivity : 0.3333          
##             Specificity : 0.6471          
##          Pos Pred Value : 0.3333          
##          Neg Pred Value : 0.6471          
##              Prevalence : 0.3462          
##          Detection Rate : 0.1154          
##    Detection Prevalence : 0.3462          
##       Balanced Accuracy : 0.4902          
##                                           
##        'Positive' Class : No              
## 

Modelo 4. Árbol de Decisión

modelo4 <- train(m1_purchase ~ ., data=entrenamiento,
                 method = "rpart",
                 preProcess = c("scale", "center"),
                 trControl = trainControl(method="cv", number=10),
                 tuneLength = 10
                 )

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainRetired

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainRetired

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainRetired

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainLogistics, domainRetired

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainRetail, domainRetired

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacHp, user_pcmacOther,
## statusRetired, statusStudent ant employed, statusUnemployed,
## domainCommunication , domainRealestate, domainRetired

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainAgriculture, domainCommunication , domainLaw,
## domainRetired

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainRetired

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainRetired

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainConsulting , domainRetired

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainRetired

resultado_entrenamiento4 <- predict(modelo4, entrenamiento)
resultado_prueba4 <- predict(modelo4, prueba)

mcre4 <- confusionMatrix(resultado_entrenamiento4, entrenamiento$m1_purchase)
mcrp4 <- confusionMatrix(resultado_prueba4, prueba$m1_purchase)
mcrp4

## Confusion Matrix and Statistics
## 
##           Reference
## Prediction No Yes
##        No   4   6
##        Yes  5  11
##                                           
##                Accuracy : 0.5769          
##                  95% CI : (0.3692, 0.7665)
##     No Information Rate : 0.6538          
##     P-Value [Acc > NIR] : 0.8485          
##                                           
##                   Kappa : 0.0892          
##                                           
##  Mcnemar's Test P-Value : 1.0000          
##                                           
##             Sensitivity : 0.4444          
##             Specificity : 0.6471          
##          Pos Pred Value : 0.4000          
##          Neg Pred Value : 0.6875          
##              Prevalence : 0.3462          
##          Detection Rate : 0.1538          
##    Detection Prevalence : 0.3846          
##       Balanced Accuracy : 0.5458          
##                                           
##        'Positive' Class : No              
## 

Modelo 5. Redes Neuronales

modelo5 <- train(m1_purchase ~ ., data=entrenamiento,
                 method = "nnet",
                 preProcess = c("scale", "center"),
                 trControl = trainControl(method="cv", number=10),
                 trace = FALSE
                 )

resultado_entrenamiento5 <- predict(modelo5, entrenamiento)
resultado_prueba5 <- predict(modelo5, prueba)

mcre5 <- confusionMatrix(resultado_entrenamiento5, entrenamiento$m1_purchase)
mcrp5 <- confusionMatrix(resultado_prueba5, prueba$m1_purchase)
mcrp5

## Confusion Matrix and Statistics
## 
##           Reference
## Prediction No Yes
##        No   4   6
##        Yes  5  11
##                                           
##                Accuracy : 0.5769          
##                  95% CI : (0.3692, 0.7665)
##     No Information Rate : 0.6538          
##     P-Value [Acc > NIR] : 0.8485          
##                                           
##                   Kappa : 0.0892          
##                                           
##  Mcnemar's Test P-Value : 1.0000          
##                                           
##             Sensitivity : 0.4444          
##             Specificity : 0.6471          
##          Pos Pred Value : 0.4000          
##          Neg Pred Value : 0.6875          
##              Prevalence : 0.3462          
##          Detection Rate : 0.1538          
##    Detection Prevalence : 0.3846          
##       Balanced Accuracy : 0.5458          
##                                           
##        'Positive' Class : No              
## 

Modelo 6. Bosques Aleatorios (Random Forest)

modelo6 <- train(m1_purchase ~ ., data=entrenamiento,
                 method = "rf",
                 preProcess = c("scale", "center"),
                 trControl = trainControl(method="cv", number=10),
                 tuneGrid = expand.grid(mtry = c(2,4,6))
                 )

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusStudent ant employed, statusUnemployed, domainCommunication ,
## domainRetired
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusStudent ant employed, statusUnemployed, domainCommunication ,
## domainRetired
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusStudent ant employed, statusUnemployed, domainCommunication ,
## domainRetired

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainAgriculture, domainCommunication , domainRetired
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainAgriculture, domainCommunication , domainRetired
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainAgriculture, domainCommunication , domainRetired

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainRealestate, domainRetired
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainRealestate, domainRetired
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainRealestate, domainRetired

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainRetired
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainRetired
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainRetired

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainRetired
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainRetired
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainRetired

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacHp, user_pcmacOther,
## statusRetired, statusUnemployed, domainCommunication , domainRetired
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacHp, user_pcmacOther,
## statusRetired, statusUnemployed, domainCommunication , domainRetired
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacHp, user_pcmacOther,
## statusRetired, statusUnemployed, domainCommunication , domainRetired

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainConsulting , domainRetail,
## domainRetired
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainConsulting , domainRetail,
## domainRetired
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainConsulting , domainRetail,
## domainRetired

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainRetired
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainRetired
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainRetired

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainLaw, domainLogistics,
## domainRetired
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainLaw, domainLogistics,
## domainRetired
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainLaw, domainLogistics,
## domainRetired

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainRetired
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainRetired
## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainRetired

## Warning in preProcess.default(thresh = 0.95, k = 5, freqCut = 19, uniqueCut =
## 10, : These variables have zero variances: user_pcmacOther, statusRetired,
## statusUnemployed, domainCommunication , domainRetired

resultado_entrenamiento6 <- predict(modelo6, entrenamiento)
resultado_prueba6 <- predict(modelo6, prueba)

mcre6 <- confusionMatrix(resultado_entrenamiento6, entrenamiento$m1_purchase)
mcrp6 <- confusionMatrix(resultado_prueba6, prueba$m1_purchase)
mcrp6

## Confusion Matrix and Statistics
## 
##           Reference
## Prediction No Yes
##        No   4   5
##        Yes  5  12
##                                           
##                Accuracy : 0.6154          
##                  95% CI : (0.4057, 0.7977)
##     No Information Rate : 0.6538          
##     P-Value [Acc > NIR] : 0.7358          
##                                           
##                   Kappa : 0.1503          
##                                           
##  Mcnemar's Test P-Value : 1.0000          
##                                           
##             Sensitivity : 0.4444          
##             Specificity : 0.7059          
##          Pos Pred Value : 0.4444          
##          Neg Pred Value : 0.7059          
##              Prevalence : 0.3462          
##          Detection Rate : 0.1538          
##    Detection Prevalence : 0.3462          
##       Balanced Accuracy : 0.5752          
##                                           
##        'Positive' Class : No              
## 

6. Tabla Comparativa de Resultados

resultados <- data.frame(
  "svmLinear" = c(mcre1$overall["Accuracy"], mcrp1$overall["Accuracy"]),
   "svmRadial" = c(mcre2$overall["Accuracy"], mcrp2$overall["Accuracy"]),
   "svmPoly"   = c(mcre3$overall["Accuracy"], mcrp3$overall["Accuracy"]),
   "rpart"     = c(mcre4$overall["Accuracy"], mcrp4$overall["Accuracy"]),
   "nnet"      = c(mcre5$overall["Accuracy"], mcrp5$overall["Accuracy"]),
   "rf"        = c(mcre6$overall["Accuracy"], mcrp6$overall["Accuracy"])
)

rownames(resultados) <- c("Precisión Entrenamiento", "Precisión Prueba")
resultados

##                         svmLinear svmRadial   svmPoly     rpart      nnet
## Precisión Entrenamiento 0.9065421 0.8598131 0.9065421 0.8037383 0.9439252
## Precisión Prueba        0.5384615 0.5769231 0.5384615 0.5769231 0.5769231
##                                rf
## Precisión Entrenamiento 0.9813084
## Precisión Prueba        0.6153846

7. Conclusiones

El análisis permite identificar qué modelo clasifica mejor la intención de compra (m1_purchase) basándose en los datos de comportamiento y demografía de los usuarios de Apple y PC. El modelo con mayor Accuracy en el set de es el que mejor generaliza para nuevos datos.