wine 001

# script that outputs a graph
library(tidyverse)

## ── Attaching packages ───────────────────────────────── tidyverse 1.2.1 ──

## ✔ ggplot2 3.2.1.9000     ✔ purrr   0.3.2     
## ✔ tibble  2.1.3          ✔ dplyr   0.8.1     
## ✔ tidyr   0.8.3          ✔ stringr 1.4.0     
## ✔ readr   1.3.1          ✔ forcats 0.4.0

## ── Conflicts ──────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()

library(firatheme)
wine <- read_delim("https://archive.ics.uci.edu/ml/machine-learning-databases/wine/wine.data", 
  delim = ",",
  col_names = c(
    "Cultivar", "Alcohol", "Malic acid", "Ash", "Alcalinity of ash", "Magnesium",
    "Total phenols", "Flavanoids", "Nonflavanoid phenols", "Proanthocyanins",
    "Color intensity", "Hue", "OD280/OD315", "Proline"
  )
)

## Parsed with column specification:
## cols(
##   Cultivar = col_double(),
##   Alcohol = col_double(),
##   `Malic acid` = col_double(),
##   Ash = col_double(),
##   `Alcalinity of ash` = col_double(),
##   Magnesium = col_double(),
##   `Total phenols` = col_double(),
##   Flavanoids = col_double(),
##   `Nonflavanoid phenols` = col_double(),
##   Proanthocyanins = col_double(),
##   `Color intensity` = col_double(),
##   Hue = col_double(),
##   `OD280/OD315` = col_double(),
##   Proline = col_double()
## )

wine_long <- 
  wine %>% 
  mutate(Cultivar = as_factor(Cultivar)) %>% 
  gather(key = "variable", value = "value", -Cultivar)

wine_long %>% 
  filter(variable != "Total phenols") %>% 
  ggplot(aes(x = value, fill = Cultivar, colour = Cultivar)) +
  geom_density(alpha = 0.8, colour = "black") +
  geom_rug() + theme_bw()+
  facet_wrap(~variable, scales = 'free')

  labs(
    x = "", 
    y = "", 
    title = "Chemical properties of three different wine cultivars"
  )

## $x
## [1] ""
## 
## $y
## [1] ""
## 
## $title
## [1] "Chemical properties of three different wine cultivars"
## 
## attr(,"class")
## [1] "labels"

## ggsave("wine_plot.pdf", device = cairo_pdf, width = 12, height = 8)

pca <- princomp(wine[,-1], cor = TRUE)$scores[,1:2]
as_tibble(pca) %>% 
  set_names("x", "y") %>% 
  mutate(Cultivar = as_factor(wine$Cultivar)) %>% 
  ggplot(aes(x = x, y = y, colour = Cultivar, fill = Cultivar)) +
  geom_polygon(stat = "density_2d", alpha = 0.1, colour = NA) +
  geom_point() +geom_smooth()+theme_bw()+
  coord_fixed() +
  xlim(-7, 7) +
  labs(x = "First principal component",
       y = "Second principal component")

## Warning: Computation failed in `stat_density2d()`:
## there is no package called 'isoband'

## `geom_smooth()` using method = 'loess' and formula 'y ~ x'

## ggsave("pca_plot.pdf", device = cairo_pdf, width = 12, height = 6)