b1

library(dplyr)

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

library(ggplot2)

head(iris)

##   Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 1          5.1         3.5          1.4         0.2  setosa
## 2          4.9         3.0          1.4         0.2  setosa
## 3          4.7         3.2          1.3         0.2  setosa
## 4          4.6         3.1          1.5         0.2  setosa
## 5          5.0         3.6          1.4         0.2  setosa
## 6          5.4         3.9          1.7         0.4  setosa

str(iris)

## 'data.frame':    150 obs. of  5 variables:
##  $ Sepal.Length: num  5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
##  $ Sepal.Width : num  3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
##  $ Petal.Length: num  1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
##  $ Petal.Width : num  0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
##  $ Species     : Factor w/ 3 levels "setosa","versicolor",..: 1 1 1 1 1 1 1 1 1 1 ...

summary_petal <- iris %>%
  group_by(Species) %>%
  summarise(
    mean_petal = mean(Petal.Length),
    sd_petal   = sd(Petal.Length),
    max_petal  = max(Petal.Length)
  )

summary_petal

## # A tibble: 3 × 4
##   Species    mean_petal sd_petal max_petal
##   <fct>           <dbl>    <dbl>     <dbl>
## 1 setosa           1.46    0.174       1.9
## 2 versicolor       4.26    0.470       5.1
## 3 virginica        5.55    0.552       6.9

ggplot(iris, aes(x = Species, y = Sepal.Width, fill = Species)) +
  geom_violin() +
  labs(
    title = "Violin plot of Sepal Width by Species",
    x = "Species",
    y = "Sepal Width"
  ) +
  theme_minimal()