Homework7

Question 1: There are 150 observations and 5 variables in the iris dataset.

library(dplyr)
library(tidyverse)

## ── Attaching packages ──────────────────────────────────── tidyverse 1.3.2 ──
## ✔ tibble  3.2.1     ✔ stringr 1.5.1
## ✔ readr   2.1.5     ✔ forcats 0.5.2
## ✔ purrr   1.0.1     
## ── Conflicts ─────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()

iris <- iris

Question 2: There are 56 observations and 5 variables in the iris1 dataset.

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

Question 3: There are 56 observations and 3 variables in the iris2 dataset.

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

Question 4:

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: There are 56 observations and 4 variables in the iris4 dataset.

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

Question 6:

iris5 <- iris4 %>% 
  summarise(avgLength = mean(Sepal.Length),
            avgWidth = mean(Sepal.Width),
            sampleSize = n())

print(iris5)

##   avgLength avgWidth sampleSize
## 1  6.698214 3.041071         56

Question 7:

iris6 <- iris4 %>% 
  group_by(Species) %>% 
  summarise(avgLength = mean(Sepal.Length),
            avgWidth = mean(Sepal.Width),
            sampleSize = n())

print(iris6)

## # A tibble: 2 × 4
##   Species    avgLength avgWidth sampleSize
##   <fct>          <dbl>    <dbl>      <int>
## 1 versicolor      6.48     2.99         17
## 2 virginica       6.79     3.06         39

Question 8:

irisFinal <- iris %>% 
  filter(Species %in% c("versicolor", "virginica") & Sepal.Length > 6 & Sepal.Width > 2.5) %>% 
  select(Species, Sepal.Length, Sepal.Width) %>% 
  arrange(desc(Sepal.Length)) %>% 
  mutate(Sepal.Area = (Sepal.Length*Sepal.Width)) %>% 
  group_by(Species) %>% 
  summarise(avgLength = mean(Sepal.Length),
            avgWidth = mean(Sepal.Width),
            sampleSize = n())

print(irisFinal)

## # A tibble: 2 × 4
##   Species    avgLength avgWidth sampleSize
##   <fct>          <dbl>    <dbl>      <int>
## 1 versicolor      6.48     2.99         17
## 2 virginica       6.79     3.06         39

Question 9:

irisLong <- iris %>% 
  pivot_longer(cols = 1:4, names_to= "Measure", values_to= "Value")

print(irisLong)

## # 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

Homework7

2025-02-26