Load required libraries

library(tidyverse)
## Warning: package 'tidyverse' was built under R version 4.3.3
## Warning: package 'ggplot2' was built under R version 4.3.3
## Warning: package 'lubridate' was built under R version 4.3.3
## ── Attaching core tidyverse packages ───────────────────────────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ ggplot2   3.5.1     ✔ tibble    3.2.1
## ✔ lubridate 1.9.4     ✔ tidyr     1.3.1
## ✔ purrr     1.0.2     
## ── Conflicts ─────────────────────────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

Load the iris dataset

data(iris)

Question 1. Examine the structure of the iris dataset

glimpse(iris) 
## Rows: 150
## Columns: 5
## $ Sepal.Length <dbl> 5.1, 4.9, 4.7, 4.6, 5.0, 5.4, 4.6, 5.0, 4.4, 4.9, 5.4, 4.8, 4.8, 4.3, 5.8, 5.7…
## $ Sepal.Width  <dbl> 3.5, 3.0, 3.2, 3.1, 3.6, 3.9, 3.4, 3.4, 2.9, 3.1, 3.7, 3.4, 3.0, 3.0, 4.0, 4.4…
## $ Petal.Length <dbl> 1.4, 1.4, 1.3, 1.5, 1.4, 1.7, 1.4, 1.5, 1.4, 1.5, 1.5, 1.6, 1.4, 1.1, 1.2, 1.5…
## $ Petal.Width  <dbl> 0.2, 0.2, 0.2, 0.2, 0.2, 0.4, 0.3, 0.2, 0.2, 0.1, 0.2, 0.2, 0.1, 0.1, 0.2, 0.4…
## $ Species      <fct> setosa, setosa, setosa, setosa, setosa, setosa, setosa, setosa, setosa, setosa…

Question 2. Create iris1: Filter for species Virginica and Versicolor with Sepal.Length > 6 and Sepal.Width > 2.5

iris1 <- iris %>%
  filter(Species %in% c("virginica", "versicolor"),
         Sepal.Length > 6,
         Sepal.Width > 2.5)

glimpse(iris1)
## Rows: 56
## Columns: 5
## $ Sepal.Length <dbl> 7.0, 6.4, 6.9, 6.5, 6.3, 6.6, 6.1, 6.7, 6.1, 6.1, 6.4, 6.6, 6.8, 6.7, 6.7, 6.1…
## $ Sepal.Width  <dbl> 3.2, 3.2, 3.1, 2.8, 3.3, 2.9, 2.9, 3.1, 2.8, 2.8, 2.9, 3.0, 2.8, 3.0, 3.1, 3.0…
## $ Petal.Length <dbl> 4.7, 4.5, 4.9, 4.6, 4.7, 4.6, 4.7, 4.4, 4.0, 4.7, 4.3, 4.4, 4.8, 5.0, 4.7, 4.6…
## $ Petal.Width  <dbl> 1.4, 1.5, 1.5, 1.5, 1.6, 1.3, 1.4, 1.4, 1.3, 1.2, 1.3, 1.4, 1.4, 1.7, 1.5, 1.4…
## $ Species      <fct> versicolor, versicolor, versicolor, versicolor, versicolor, versicolor, versic…

Question 3. Create iris2: Select only Species, Sepal.Length, and Sepal.Width

iris2 <- iris1 %>%
  select(Species, Sepal.Length, Sepal.Width)

glimpse(iris2)
## Rows: 56
## Columns: 3
## $ Species      <fct> versicolor, versicolor, versicolor, versicolor, versicolor, versicolor, versic…
## $ Sepal.Length <dbl> 7.0, 6.4, 6.9, 6.5, 6.3, 6.6, 6.1, 6.7, 6.1, 6.1, 6.4, 6.6, 6.8, 6.7, 6.7, 6.1…
## $ Sepal.Width  <dbl> 3.2, 3.2, 3.1, 2.8, 3.3, 2.9, 2.9, 3.1, 2.8, 2.8, 2.9, 3.0, 2.8, 3.0, 3.1, 3.0…

Question 4. Create iris3: Arrange by Sepal.Length in descending order

iris3 <- iris2 %>%
  arrange(desc(Sepal.Length))

head(iris3)
##     Species Sepal.Length Sepal.Width
## 1 virginica          7.9         3.8
## 2 virginica          7.7         3.8
## 3 virginica          7.7         2.6
## 4 virginica          7.7         2.8
## 5 virginica          7.7         3.0
## 6 virginica          7.6         3.0

Question 5. Create iris4: Add a column for Sepal.Area (Sepal.Length * Sepal.Width)

iris4 <- iris3 %>%
  mutate(Sepal.Area = Sepal.Length * Sepal.Width)

glimpse(iris4)
## Rows: 56
## Columns: 4
## $ Species      <fct> virginica, virginica, virginica, virginica, virginica, virginica, virginica, v…
## $ Sepal.Length <dbl> 7.9, 7.7, 7.7, 7.7, 7.7, 7.6, 7.4, 7.3, 7.2, 7.2, 7.2, 7.1, 7.0, 6.9, 6.9, 6.9…
## $ Sepal.Width  <dbl> 3.8, 3.8, 2.6, 2.8, 3.0, 3.0, 2.8, 2.9, 3.6, 3.2, 3.0, 3.0, 3.2, 3.1, 3.2, 3.1…
## $ Sepal.Area   <dbl> 30.02, 29.26, 20.02, 21.56, 23.10, 22.80, 20.72, 21.17, 25.92, 23.04, 21.60, 2…

Question 6. Create iris5: Compute overall mean Sepal.Length, mean Sepal.Width, and sample size

iris5 <- iris4 %>%
  summarise(Avg.Sepal.Length = mean(Sepal.Length),
            Avg.Sepal.Width = mean(Sepal.Width),
            Sample.Size = n())

print(iris5)
##   Avg.Sepal.Length Avg.Sepal.Width Sample.Size
## 1         6.698214        3.041071          56

Question 7. Create iris6: Compute mean Sepal.Length, mean Sepal.Width, and sample size grouped by Species

iris6 <- iris4 %>%
  group_by(Species) %>%
  summarise(Avg.Sepal.Length = mean(Sepal.Length),
            Avg.Sepal.Width = mean(Sepal.Width),
            Sample.Size = n())

print(iris6)
## # A tibble: 2 × 4
##   Species    Avg.Sepal.Length Avg.Sepal.Width Sample.Size
##   <fct>                 <dbl>           <dbl>       <int>
## 1 versicolor             6.48            2.99          17
## 2 virginica              6.79            3.06          39

Question 8. Use piping to create irisFinal in one pipeline

irisFinal <- iris %>%
  filter(Species %in% c("virginica", "versicolor"),
         Sepal.Length > 6,
         Sepal.Width > 2.5) %>%
  select(Species, Sepal.Length, Sepal.Width) %>%
  arrange(desc(Sepal.Length)) %>%
  mutate(Sepal.Area = Sepal.Length * Sepal.Width)

head(irisFinal)
##     Species Sepal.Length Sepal.Width Sepal.Area
## 1 virginica          7.9         3.8      30.02
## 2 virginica          7.7         3.8      29.26
## 3 virginica          7.7         2.6      20.02
## 4 virginica          7.7         2.8      21.56
## 5 virginica          7.7         3.0      23.10
## 6 virginica          7.6         3.0      22.80

Question 9. Create a longer data frame with columns: Species, Measure, Value

iris_long <- iris %>%
  pivot_longer(cols = -Species, names_to = "Measure", values_to = "Value")

print(iris_long)
## # A tibble: 600 × 3
##    Species Measure      Value
##    <fct>   <chr>        <dbl>
##  1 setosa  Sepal.Length   5.1
##  2 setosa  Sepal.Width    3.5
##  3 setosa  Petal.Length   1.4
##  4 setosa  Petal.Width    0.2
##  5 setosa  Sepal.Length   4.9
##  6 setosa  Sepal.Width    3  
##  7 setosa  Petal.Length   1.4
##  8 setosa  Petal.Width    0.2
##  9 setosa  Sepal.Length   4.7
## 10 setosa  Sepal.Width    3.2
## # ℹ 590 more rows