#Load tidyverse
library(tidyverse)
## ── 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)
#1. Examine 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.…
## $ 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.…
## $ 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.…
## $ 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.…
## $ Species <fct> setosa, setosa, setosa, setosa, setosa, setosa, setosa, s…
dim(iris) #Check the number of observations and variables
## [1] 150 5
#2. Create iris 1: filter for species "virginica" and "versicolor with Sepal.Length >6 and Sepal.Widths >2.5
iris1 <- iris%>%
filter(Species %in% c("virginica", "versicolor"),
Sepal.Length > 6,
Sepal.Width > 2.5)
dim(iris1) #check dimensions of iris1
## [1] 56 5
#3. Create iris2: select only Species, Sepal.Length, and Sepal. Width
iris2 <- iris1 %>%
select(Species, Sepal.Length, Sepal.Width)
dim(iris2) #check dimensions of iris2
## [1] 56 3
#4. Create iris3: arrange by Sepal.length in descending order
iris3 <- iris2 %>%
arrange(desc(Sepal.Length))
head(iris3) #display the first 6 rows
## 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
#5. Create iris4: Add a new colun Sepal.Area (Sepal.Length *Sepal.Width)
iris4 <- iris3 %>%
mutate(Sepal.Area = Sepal.Length * Sepal.Width)
dim(iris4) #Check dimensions of iris4
## [1] 56 4
#6. Creae iris5: Summarize to get mean Sepal.Length, mean Sepal. Width, and sample size
iris5 <- iris4 %>%
summarize(
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
#7. Create iris6: Group by species and summarize mean Sepal.Length, meanS epal.Width, and sample size
iris6 <- iris4 %>%
group_by(Species) %>%
summarize(
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
#8. rewrite steps using piping to create irisFinal
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(Septal.Area =Sepal.Length * Sepal.Width)
dim(irisFinal) #Check dimensions of irisFinal
## [1] 56 4
#9. Create a "longer" format data frame with three columns: Species, Measure, and Value
iris_long <- iris %>%
pivot_longer(cols = c(Sepal.Length, Sepal.Width, Petal.Length, Petal.Width),
names_to = "Measure",
values_to = "Value")
head(iris_long) #Display first 6 rows of the longer dataset
## # A tibble: 6 × 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