Wine Data

Cargar datos

library(readr)
redwine <- read_csv("winequality-red.csv")
redwine <- as.data.frame(lapply(redwine, as.numeric))

Limpiar nombres y vista inicial de data

redwine <- clean_names(redwine)
str(redwine)

## 'data.frame':    1599 obs. of  12 variables:
##  $ fixed_acidity       : num  7.4 7.8 7.8 11.2 7.4 7.4 7.9 7.3 7.8 7.5 ...
##  $ volatile_acidity    : num  0.7 0.88 0.76 0.28 0.7 0.66 0.6 0.65 0.58 0.5 ...
##  $ citric_acid         : num  0 0 0.04 0.56 0 0 0.06 0 0.02 0.36 ...
##  $ residual_sugar      : num  1.9 2.6 2.3 1.9 1.9 1.8 1.6 1.2 2 6.1 ...
##  $ chlorides           : num  0.076 0.098 0.092 0.075 0.076 0.075 0.069 0.065 0.073 0.071 ...
##  $ free_sulfur_dioxide : num  11 25 15 17 11 13 15 15 9 17 ...
##  $ total_sulfur_dioxide: num  34 67 54 60 34 40 59 21 18 102 ...
##  $ density             : num  0.998 0.997 0.997 0.998 0.998 ...
##  $ p_h                 : num  3.51 3.2 3.26 3.16 3.51 3.51 3.3 3.39 3.36 3.35 ...
##  $ sulphates           : num  0.56 0.68 0.65 0.58 0.56 0.56 0.46 0.47 0.57 0.8 ...
##  $ alcohol             : num  9.4 9.8 9.8 9.8 9.4 9.4 9.4 10 9.5 10.5 ...
##  $ quality             : num  5 5 5 6 5 5 5 7 7 5 ...

summary(redwine)

##  fixed_acidity   volatile_acidity  citric_acid    residual_sugar  
##  Min.   : 4.60   Min.   :0.1200   Min.   :0.000   Min.   : 0.900  
##  1st Qu.: 7.10   1st Qu.:0.3900   1st Qu.:0.090   1st Qu.: 1.900  
##  Median : 7.90   Median :0.5200   Median :0.260   Median : 2.200  
##  Mean   : 8.32   Mean   :0.5278   Mean   :0.271   Mean   : 2.539  
##  3rd Qu.: 9.20   3rd Qu.:0.6400   3rd Qu.:0.420   3rd Qu.: 2.600  
##  Max.   :15.90   Max.   :1.5800   Max.   :1.000   Max.   :15.500  
##    chlorides       free_sulfur_dioxide total_sulfur_dioxide    density      
##  Min.   :0.01200   Min.   : 1.00       Min.   :  6.00       Min.   :0.9901  
##  1st Qu.:0.07000   1st Qu.: 7.00       1st Qu.: 22.00       1st Qu.:0.9956  
##  Median :0.07900   Median :14.00       Median : 38.00       Median :0.9968  
##  Mean   :0.08747   Mean   :15.87       Mean   : 46.47       Mean   :0.9967  
##  3rd Qu.:0.09000   3rd Qu.:21.00       3rd Qu.: 62.00       3rd Qu.:0.9978  
##  Max.   :0.61100   Max.   :72.00       Max.   :289.00       Max.   :1.0037  
##       p_h          sulphates         alcohol         quality     
##  Min.   :2.740   Min.   :0.3300   Min.   : 8.40   Min.   :3.000  
##  1st Qu.:3.210   1st Qu.:0.5500   1st Qu.: 9.50   1st Qu.:5.000  
##  Median :3.310   Median :0.6200   Median :10.20   Median :6.000  
##  Mean   :3.311   Mean   :0.6581   Mean   :10.42   Mean   :5.636  
##  3rd Qu.:3.400   3rd Qu.:0.7300   3rd Qu.:11.10   3rd Qu.:6.000  
##  Max.   :4.010   Max.   :2.0000   Max.   :14.90   Max.   :8.000

Histogramas de cada variable

columnas <- dim(redwine)[2]

par(mfrow=c(3,columnas/3))
for (i in 1:columnas) {
  if (is.numeric(redwine[,i])==TRUE)
  {
    hist(redwine[,i], 
       main = names(redwine)[i],   # ← aquí le dices el título
       xlab = names(redwine)[i],   # opcional: etiqueta del eje X
       col = "steelblue",
       border = "white")
  }
  else
  {
    pie(table(redwine[,i]))
  }
}

Gráficos Calidad vs …

variables <- names(redwine)[names(redwine) != "quality"]

for (var in variables) {
  
  p <- ggplot(redwine, aes(x = quality, y = .data[[var]])) +
  geom_point(color = "green", alpha = 0.6) +
  geom_smooth(method = "lm",     color = "red",    se = FALSE, linetype = "dashed") +
  geom_smooth(method = "loess",  color = "blue",   se = TRUE) +
  geom_smooth(method = "gam",    color = "darkgreen", formula = y ~ s(x), se = FALSE) +
  labs(title = paste("Calidad vs", var),
       x = "Calidad", y = var) +
  theme_minimal()
  
  print(p)
}