##Importación de los datos:
data<-read.csv("C:\\Users\\DELL\\Downloads\\student-por.csv" ,sep = ";",dec = ".")##Transformar a factor las variables “character”
library(dplyr)## Warning: package 'dplyr' was built under R version 4.2.3##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, uniondf <- data %>%
mutate(across(where(is.character), as.factor))
str(df)## 'data.frame': 649 obs. of 33 variables:
## $ school : Factor w/ 2 levels "GP","MS": 1 1 1 1 1 1 1 1 1 1 ...
## $ sex : Factor w/ 2 levels "F","M": 1 1 1 1 1 2 2 1 2 2 ...
## $ age : int 18 17 15 15 16 16 16 17 15 15 ...
## $ address : Factor w/ 2 levels "R","U": 2 2 2 2 2 2 2 2 2 2 ...
## $ famsize : Factor w/ 2 levels "GT3","LE3": 1 1 2 1 1 2 2 1 2 1 ...
## $ Pstatus : Factor w/ 2 levels "A","T": 1 2 2 2 2 2 2 1 1 2 ...
## $ Medu : int 4 1 1 4 3 4 2 4 3 3 ...
## $ Fedu : int 4 1 1 2 3 3 2 4 2 4 ...
## $ Mjob : Factor w/ 5 levels "at_home","health",..: 1 1 1 2 3 4 3 3 4 3 ...
## $ Fjob : Factor w/ 5 levels "at_home","health",..: 5 3 3 4 3 3 3 5 3 3 ...
## $ reason : Factor w/ 4 levels "course","home",..: 1 1 3 2 2 4 2 2 2 2 ...
## $ guardian : Factor w/ 3 levels "father","mother",..: 2 1 2 2 1 2 2 2 2 2 ...
## $ traveltime: int 2 1 1 1 1 1 1 2 1 1 ...
## $ studytime : int 2 2 2 3 2 2 2 2 2 2 ...
## $ failures : int 0 0 0 0 0 0 0 0 0 0 ...
## $ schoolsup : Factor w/ 2 levels "no","yes": 2 1 2 1 1 1 1 2 1 1 ...
## $ famsup : Factor w/ 2 levels "no","yes": 1 2 1 2 2 2 1 2 2 2 ...
## $ paid : Factor w/ 2 levels "no","yes": 1 1 1 1 1 1 1 1 1 1 ...
## $ activities: Factor w/ 2 levels "no","yes": 1 1 1 2 1 2 1 1 1 2 ...
## $ nursery : Factor w/ 2 levels "no","yes": 2 1 2 2 2 2 2 2 2 2 ...
## $ higher : Factor w/ 2 levels "no","yes": 2 2 2 2 2 2 2 2 2 2 ...
## $ internet : Factor w/ 2 levels "no","yes": 1 2 2 2 1 2 2 1 2 2 ...
## $ romantic : Factor w/ 2 levels "no","yes": 1 1 1 2 1 1 1 1 1 1 ...
## $ famrel : int 4 5 4 3 4 5 4 4 4 5 ...
## $ freetime : int 3 3 3 2 3 4 4 1 2 5 ...
## $ goout : int 4 3 2 2 2 2 4 4 2 1 ...
## $ Dalc : int 1 1 2 1 1 1 1 1 1 1 ...
## $ Walc : int 1 1 3 1 2 2 1 1 1 1 ...
## $ health : int 3 3 3 5 5 5 3 1 1 5 ...
## $ absences : int 4 2 6 0 0 6 0 2 0 0 ...
## $ G1 : int 0 9 12 14 11 12 13 10 15 12 ...
## $ G2 : int 11 11 13 14 13 12 12 13 16 12 ...
## $ G3 : int 11 11 12 14 13 13 13 13 17 13 ...Con str() podemos observar que las variables character se transformaron a factor
##Creación de matriz con la conversion de Clases realizada :
Classes=sapply(df,class)
for (i in 1: ncol(df))
if (Classes[i]=="integer")
df[[i]]=as.numeric(df[[i]])
Classes=sapply(df,class)
Classes## school sex age address famsize Pstatus Medu
## "factor" "factor" "numeric" "factor" "factor" "factor" "numeric"
## Fedu Mjob Fjob reason guardian traveltime studytime
## "numeric" "factor" "factor" "factor" "factor" "numeric" "numeric"
## failures schoolsup famsup paid activities nursery higher
## "numeric" "factor" "factor" "factor" "factor" "factor" "factor"
## internet romantic famrel freetime goout Dalc Walc
## "factor" "factor" "numeric" "numeric" "numeric" "numeric" "numeric"
## health absences G1 G2 G3
## "numeric" "numeric" "numeric" "numeric" "numeric"View(df)##Detección de datos perdidos (Encontrar NA’S)
which(is.na(df))## integer(0)Se obtiene que no hay datos perdidos o faltantes en la base de datos “df (data student transformada)”.
##Realizar el escalamiento de las variables numéricas
df[,Classes=="integer"]= scale(df[,Classes=="integer"])
head(df)##10 datos
dataj<-df[,c(2,3,7,19,20,21,22,23,24,25,26)]tr = round(nrow(df)*0.7)
set.seed(1805753298) # semilla para el entrenamiento
muestra = sample.int(nrow(dataj), tr) # tomo una muestra del 70%
Train.higher = dataj[muestra,] #tomo los datos para entrenamiento
Val.higher = dataj[-muestra,] #tomo los datos para validación Las varibles categóricas aparecen con 0 y 1.
x=model.matrix(df$health~.,data=dataj)
head(x) (Intercept) sexM age Medu activitiesyes nurseryyes higheryes internetyes
1 1 0 18 4 0 1 1 0
2 1 0 17 1 0 0 1 1
3 1 0 15 1 0 1 1 1
4 1 0 15 4 1 1 1 1
5 1 0 16 3 0 1 1 0
6 1 1 16 4 1 1 1 1
romanticyes famrel freetime goout
1 0 4 3 4
2 0 5 3 3
3 0 4 3 2
4 1 3 2 2
5 0 4 3 2
6 0 5 4 2Interpretación:muestra información de estudiantes como sexo (sexM), edad (age), educación de la madre (Medu), actividades extracurriculares (activitiesyes), asistencia a guardería (nurseryyes), intención de seguir estudios superiores (higheryes), y acceso a Internet (internetyes). También incluye datos sobre relaciones románticas (romanticyes), relación familiar (famrel), tiempo libre (freetime), y frecuencia de salidas (goout).
library(e1071)## Warning: package 'e1071' was built under R version 4.2.3library(caret)## Warning: package 'caret' was built under R version 4.2.3## Loading required package: ggplot2## Warning: package 'ggplot2' was built under R version 4.2.3## Loading required package: lattice## Warning: package 'lattice' was built under R version 4.2.3fitsvm1<-svm(Train.higher$higher~.,data=Train.higher,kernel= "sigmoid" )
summary(fitsvm1)##
## Call:
## svm(formula = Train.higher$higher ~ ., data = Train.higher, kernel = "sigmoid")
##
##
## Parameters:
## SVM-Type: C-classification
## SVM-Kernel: sigmoid
## cost: 1
## coef.0: 0
##
## Number of Support Vectors: 118
##
## ( 57 61 )
##
##
## Number of Classes: 2
##
## Levels:
## no yespredictedSVM <- predict(fitsvm1, Val.higher)
matrizSVM <- confusionMatrix(Val.higher$higher, predictedSVM)
matrizSVM## Confusion Matrix and Statistics
##
## Reference
## Prediction no yes
## no 1 11
## yes 0 183
##
## Accuracy : 0.9436
## 95% CI : (0.9013, 0.9715)
## No Information Rate : 0.9949
## P-Value [Acc > NIR] : 1.000000
##
## Kappa : 0.1458
##
## Mcnemar's Test P-Value : 0.002569
##
## Sensitivity : 1.000000
## Specificity : 0.943299
## Pos Pred Value : 0.083333
## Neg Pred Value : 1.000000
## Prevalence : 0.005128
## Detection Rate : 0.005128
## Detection Prevalence : 0.061538
## Balanced Accuracy : 0.971649
##
## 'Positive' Class : no
## Interpretación: El modelo de predicción indica que el 94.36% de los estudiantes se espera que continúen sus estudios universitarios, mientras que solo el 0.51% no seguirá estudiando según las predicciones realizadas.
##Random Forest
library(caret)
library(randomForest)## Warning: package 'randomForest' was built under R version 4.2.3## randomForest 4.7-1.1## Type rfNews() to see new features/changes/bug fixes.##
## Attaching package: 'randomForest'## The following object is masked from 'package:ggplot2':
##
## margin## The following object is masked from 'package:dplyr':
##
## combinefitRF <- randomForest(higher ~., data = Train.higher, ntree = 500)
summary(fitRF)## Length Class Mode
## call 4 -none- call
## type 1 -none- character
## predicted 454 factor numeric
## err.rate 1500 -none- numeric
## confusion 6 -none- numeric
## votes 908 matrix numeric
## oob.times 454 -none- numeric
## classes 2 -none- character
## importance 10 -none- numeric
## importanceSD 0 -none- NULL
## localImportance 0 -none- NULL
## proximity 0 -none- NULL
## ntree 1 -none- numeric
## mtry 1 -none- numeric
## forest 14 -none- list
## y 454 factor numeric
## test 0 -none- NULL
## inbag 0 -none- NULL
## terms 3 terms call#Predict Output
predictedRF <- predict(fitRF, Val.higher)
matrizRF <- confusionMatrix(Val.higher$higher, predictedRF)
matrizRF## Confusion Matrix and Statistics
##
## Reference
## Prediction no yes
## no 1 11
## yes 3 180
##
## Accuracy : 0.9282
## 95% CI : (0.8825, 0.9602)
## No Information Rate : 0.9795
## P-Value [Acc > NIR] : 0.99999
##
## Kappa : 0.0972
##
## Mcnemar's Test P-Value : 0.06137
##
## Sensitivity : 0.250000
## Specificity : 0.942408
## Pos Pred Value : 0.083333
## Neg Pred Value : 0.983607
## Prevalence : 0.020513
## Detection Rate : 0.005128
## Detection Prevalence : 0.061538
## Balanced Accuracy : 0.596204
##
## 'Positive' Class : no
## El modelo Random Forest tiene una precisión del 92.82% en predecir qué estudiantes continuarán estudiando en la universidad específicamente, el modelo identifica correctamente al 25% de los casos que no continuarán (sensibilidad) y al 94.24% de los casos que sí continuarán (especificidad). La tasa de prevalencia de estudiantes que no continuarán es del 2.05%.
###Conclusion:
El modelo SVM con kernel sigmoidal muestra una especificidad más alta (94.33%), lo que significa que identifica bien a los estudiantes que continuarán en la universidad. En contraste, el Random Forest tiene una sensibilidad algo mayor (25%) para detectar a los estudiantes que no continuarán, pero una especificidad ligeramente menor (94.24%). En resumen, el SVM con kernel sigmoidal es mejor en identificar correctamente a los estudiantes que continuarán según estos resultados específicos.