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
data(iris)
class(iris)
## [1] "data.frame"

Problem 1: Examine the structure of the iris data set. How many observations and variables are in the data set?

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…

Answer: there are 150 rows i.e. observations and 5 columns i.e. variables

Problem 2: Create a new data frame iris1 that contains only the species virginica and versicolor with sepal lengths longer than 6 cm and sepal widths longer than 2.5 cm. How many observations and variables are in the data set?

iris1 <- filter(iris,Species %in% c("versicolor","virginica"),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.…
## $ 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.…
## $ 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.…
## $ 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.…
## $ Species      <fct> versicolor, versicolor, versicolor, versicolor, versicolo…

Answer: 56 observations, still 5 variables

Problem 3: Now, create a iris2 data frame from iris1 that contains only the columns for Species, Sepal.Length, and Sepal.Width. How many observations and variables are in the data set?

iris2 <- select(iris1, Species, Sepal.Length, Sepal.Width)
view(iris2)
glimpse(iris2)
## Rows: 56
## Columns: 3
## $ Species      <fct> versicolor, versicolor, versicolor, versicolor, versicolo…
## $ 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.…
## $ 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.…

Answer: still 56 observations, just the 3 variables specified

Problem 4: Create an iris3 data frame from iris2 that orders the observations from largest to smallest sepal length. Show the first 6 rows of this data set.

iris3 <- arrange(iris2,by=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

Problem 5:Create an iris4 data frame from iris3 that creates a column with a sepal area (length * width) value for each observation. How many observations and variables are in the data set?

iris4 <- mutate(iris3,Sepal.Area=Sepal.Length*Sepal.Width)
head(iris4)
##     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
glimpse(iris4)
## Rows: 56
## Columns: 4
## $ Species      <fct> virginica, virginica, virginica, virginica, virginica, vi…
## $ 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.…
## $ 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.…
## $ Sepal.Area   <dbl> 30.02, 29.26, 20.02, 21.56, 23.10, 22.80, 20.72, 21.17, 2…

Answer: there are still 56 observations and now 4 variables

Problem 6: Create iris5 that calculates the average sepal length, the average sepal width, and the sample size of the entire iris4 data frame and print iris5.

iris5 <- summarize(iris4, Average.Sepal.Length=mean(Sepal.Length, na.rn=TRUE), Average.Sepal.Width=mean(Sepal.Width, na.rn=TRUE), Sample.Size=n())
print(iris5)
##   Average.Sepal.Length Average.Sepal.Width Sample.Size
## 1             6.698214            3.041071          56

Problem 7: Finally, create iris6 that calculates the average sepal length, the average sepal width, and the sample size for each species of in the iris4 data frame and print iris6.

iris6 <- iris4 %>%
  group_by(Species) %>%
  summarize(Average.Sepal.Length=mean(Sepal.Length,na.rm=TRUE), Average.Sepal.Width=mean(Sepal.Width,na.rm=TRUE), Sample.Size=n())
print(iris6)
## # A tibble: 2 × 4
##   Species    Average.Sepal.Length Average.Sepal.Width Sample.Size
##   <fct>                     <dbl>               <dbl>       <int>
## 1 versicolor                 6.48                2.99          17
## 2 virginica                  6.79                3.06          39

In these exercises, you have successively modified different versions of the data frame iris1 iris2 iris3 iris4 iris5 iris6. At each stage, the output data frame from one operation serves as the input fro the next. A more efficient way to do this is to use the pipe operator %>% from the tidyr package. See if you can rework all of your previous statements (except for iris5) into an extended piping operation that uses iris as the input and generates irisFinal as the output.

irisFinal <- iris %>%
  filter(Species %in% c("versicolor","virginica"),Sepal.Length > 6, Sepal.Width > 2.5) %>%
  select(Species, Sepal.Length, Sepal.Width) %>%
  arrange(by=desc(Sepal.Length)) %>%
  mutate(Sepal.Area=Sepal.Length*Sepal.Width) %>%
  group_by(Species) %>%
  summarize(Average.Sepal.Length=mean(Sepal.Length,na.rm=TRUE), Average.Sepal.Width=mean(Sepal.Width,na.rm=TRUE), Sample.Size=n())
print(irisFinal)
## # A tibble: 2 × 4
##   Species    Average.Sepal.Length Average.Sepal.Width Sample.Size
##   <fct>                     <dbl>               <dbl>       <int>
## 1 versicolor                 6.48                2.99          17
## 2 virginica                  6.79                3.06          39

Create a ‘longer’ data frame using the original iris data set with three columns named “Species”, “Measure”, “Value”. The column “Species” will retain the species names of the data set. The column “Measure” will include whether the value corresponds to Sepal.Length, Sepal.Width, Petal.Length, or Petal.Width and the column “Value” will include the numerical values of those measurements.

view(iris)
longerIris <- iris %>% 
 pivot_longer(cols = Sepal.Length:Petal.Width,  names_to="Measure", values_to="Value")
head(longerIris)
## # 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