Homework 7

Homework 7

Question 1

library(tidyverse)

## Warning: package 'tidyverse' was built under R version 4.1.2

## -- Attaching packages --------------------------------------- tidyverse 1.3.1 --

## v ggplot2 3.3.5     v purrr   0.3.4
## v tibble  3.1.6     v dplyr   1.0.8
## v tidyr   1.2.0     v stringr 1.4.0
## v readr   2.1.2     v forcats 0.5.1

## Warning: package 'ggplot2' was built under R version 4.1.2

## Warning: package 'tibble' was built under R version 4.1.2

## Warning: package 'tidyr' was built under R version 4.1.2

## Warning: package 'readr' was built under R version 4.1.2

## Warning: package 'purrr' was built under R version 4.1.2

## Warning: package 'stringr' was built under R version 4.1.2

## Warning: package 'forcats' was built under R version 4.1.2

## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()

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 ...

Observation: 150 Variables: 5

Question 2

iris1 <- data.frame(filter(iris, 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.~
## $ 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~

Observations: 56 Variables: 5

Question 3

iris2 <- data.frame(select(iris1, Species, Sepal.Length, Sepal.Width))
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.~

Observations: 56 Variables: 3

Question 4

iris3 <- data.frame(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

Question 5

iris4 <- data.frame(mutate(iris3, Sepal.Area = Sepal.Length*Sepal.Width))
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~

Observations: 56 Variables: 4

Question 6

iris5 <- summarize(iris4, 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

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 x 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

iris %>%
  filter(Species %in% c("virginica","versicolor"), 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) %>%
  # summarize(Avg.Sepal.Length = mean(Sepal.Length), Avg.Sepal.Width = mean(Sepal.Width), Sample.Size = n()) %>%
  group_by(Species) %>%
  summarize(Avg.Sepal.Length = mean(Sepal.Length), Avg.Sepal.Width = mean(Sepal.Width), Sample.Size = n())

## # A tibble: 2 x 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 9

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

iris %>%
  pivot_longer(cols= 1:4,
               names_to = "Measure",
               values_to = "Value",
               values_drop_na = T)

## # A tibble: 600 x 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
## # ... with 590 more rows