La regresión logística es un modelo estadístico de clasificación binaria, que estima la probabilidad de que ocurra un evento (valor 1) frente a que no ocurra (valor 0), en función de variables independientes.
# library(tidyverse)df <- read.csv("/Users/marceloreyesp/Desktop/Negocios/6to Semestre LIT/Clase Codigos/Clase Codigo R/heart.csv")summary(df)## age sex cp trestbps
## Min. :29.00 Min. :0.0000 Min. :0.0000 Min. : 94.0
## 1st Qu.:48.00 1st Qu.:0.0000 1st Qu.:0.0000 1st Qu.:120.0
## Median :56.00 Median :1.0000 Median :1.0000 Median :130.0
## Mean :54.43 Mean :0.6956 Mean :0.9424 Mean :131.6
## 3rd Qu.:61.00 3rd Qu.:1.0000 3rd Qu.:2.0000 3rd Qu.:140.0
## Max. :77.00 Max. :1.0000 Max. :3.0000 Max. :200.0
## chol fbs restecg thalach
## Min. :126 Min. :0.0000 Min. :0.0000 Min. : 71.0
## 1st Qu.:211 1st Qu.:0.0000 1st Qu.:0.0000 1st Qu.:132.0
## Median :240 Median :0.0000 Median :1.0000 Median :152.0
## Mean :246 Mean :0.1493 Mean :0.5298 Mean :149.1
## 3rd Qu.:275 3rd Qu.:0.0000 3rd Qu.:1.0000 3rd Qu.:166.0
## Max. :564 Max. :1.0000 Max. :2.0000 Max. :202.0
## exang oldpeak slope ca
## Min. :0.0000 Min. :0.000 Min. :0.000 Min. :0.0000
## 1st Qu.:0.0000 1st Qu.:0.000 1st Qu.:1.000 1st Qu.:0.0000
## Median :0.0000 Median :0.800 Median :1.000 Median :0.0000
## Mean :0.3366 Mean :1.072 Mean :1.385 Mean :0.7541
## 3rd Qu.:1.0000 3rd Qu.:1.800 3rd Qu.:2.000 3rd Qu.:1.0000
## Max. :1.0000 Max. :6.200 Max. :2.000 Max. :4.0000
## thal target
## Min. :0.000 Min. :0.0000
## 1st Qu.:2.000 1st Qu.:0.0000
## Median :2.000 Median :1.0000
## Mean :2.324 Mean :0.5132
## 3rd Qu.:3.000 3rd Qu.:1.0000
## Max. :3.000 Max. :1.0000str(df)## 'data.frame': 1025 obs. of 14 variables:
## $ age : int 52 53 70 61 62 58 58 55 46 54 ...
## $ sex : int 1 1 1 1 0 0 1 1 1 1 ...
## $ cp : int 0 0 0 0 0 0 0 0 0 0 ...
## $ trestbps: int 125 140 145 148 138 100 114 160 120 122 ...
## $ chol : int 212 203 174 203 294 248 318 289 249 286 ...
## $ fbs : int 0 1 0 0 1 0 0 0 0 0 ...
## $ restecg : int 1 0 1 1 1 0 2 0 0 0 ...
## $ thalach : int 168 155 125 161 106 122 140 145 144 116 ...
## $ exang : int 0 1 1 0 0 0 0 1 0 1 ...
## $ oldpeak : num 1 3.1 2.6 0 1.9 1 4.4 0.8 0.8 3.2 ...
## $ slope : int 2 0 0 2 1 1 0 1 2 1 ...
## $ ca : int 2 0 0 1 3 0 3 1 0 2 ...
## $ thal : int 3 3 3 3 2 2 1 3 3 2 ...
## $ target : int 0 0 0 0 0 1 0 0 0 0 ...df <- df[, c("target", "age", "sex", "cp")]
df <- na.omit(df)
df$target <- as.factor(df$target)
df$sex <- as.factor(df$sex)
df$cp <- as.factor(df$cp)modelo <- glm(target ~ ., data=df, family=binomial)
summary(modelo)##
## Call:
## glm(formula = target ~ ., family = binomial, data = df)
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 3.739627 0.573892 6.516 7.21e-11 ***
## age -0.066961 0.009559 -7.005 2.47e-12 ***
## sex1 -1.791697 0.189715 -9.444 < 2e-16 ***
## cp1 2.561954 0.239299 10.706 < 2e-16 ***
## cp2 2.411452 0.192865 12.503 < 2e-16 ***
## cp3 2.274265 0.287080 7.922 2.34e-15 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 1420.24 on 1024 degrees of freedom
## Residual deviance: 989.79 on 1019 degrees of freedom
## AIC: 1001.8
##
## Number of Fisher Scoring iterations: 5prueba <- data.frame(age=c(55, 45), sex=as.factor(c(1, 0)), cp=as.factor(c(0, 2)))
probabilidad <- predict(modelo, newdata=prueba, type="response")
cbind(prueba, Probabilidad_Enfermedad=probabilidad)## age sex cp Probabilidad_Enfermedad
## 1 55 1 0 0.1499607
## 2 45 0 2 0.9584272```