HW2

Jeeyoung Song, Scranton College Division of International Studies, 2169039

2021-03-17

Chapter 1 Prerequisites

# Code chunk 1 for HW1
# head() is a function in base-R that display only the first 6 observations
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

# Code chunk 2 for HW1
# tidying the raw data into the tidy data using `pivot_longer()` and `separate()` functions in the tidyr package
library(tidyverse)

## ── Attaching packages ────────────────────────────────────────────────────────── tidyverse 1.3.0 ──

## ✓ ggplot2 3.3.3     ✓ purrr   0.3.4
## ✓ tibble  3.1.0     ✓ dplyr   1.0.5
## ✓ tidyr   1.1.3     ✓ stringr 1.4.0
## ✓ readr   1.4.0     ✓ forcats 0.5.1

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

iris %>%
  pivot_longer(cols = -Species, names_to = "Part", values_to = "Value") %>%
  separate(col = "Part", into = c("Part", "Measure"))

## # A tibble: 600 x 4
##    Species Part  Measure Value
##    <fct>   <chr> <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

# Code chunk 3 for HW1
# transforming our data using `group_by()` and `summarize()` functions in the dplyr package
# Because we created the `Part` variable in our tidy data, 
# we can easily calculate the mean of the `Value` by `Species` and `Part`
iris %>%
  pivot_longer(cols = -Species, names_to = "Part", values_to = "Value") %>%
  separate(col = "Part", into = c("Part", "Measure")) %>%
  group_by(Species, Part) %>%
  summarize(m = mean(Value))

## # A tibble: 6 x 3
## # Groups:   Species [3]
##   Species    Part      m
##   <fct>      <chr> <dbl>
## 1 setosa     Petal 0.854
## 2 setosa     Sepal 4.22 
## 3 versicolor Petal 2.79 
## 4 versicolor Sepal 4.35 
## 5 virginica  Petal 3.79 
## 6 virginica  Sepal 4.78

# Code chunk 4 for HW1
# visualizing our data using `ggplot()` function in the `ggplot2` package
iris %>%
  pivot_longer(cols = -Species, names_to = "Part", values_to = "Value") %>%
  separate(col = "Part", into = c("Part", "Measure")) %>%
  ggplot(aes(x = Value, color = Part)) + geom_boxplot()