Module 11: Apply it to your data 10

Import your data

# csv file
mydata <- read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/main/data/2025/2025-07-01/weekly_gas_prices.csv')

## Rows: 22360 Columns: 5
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr  (3): fuel, grade, formulation
## dbl  (1): price
## date (1): date
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

Chapter 15

Create a factor

mydata %>% count(grade)

## # A tibble: 6 × 2
##   grade                n
##   <chr>            <int>
## 1 all               6506
## 2 low_sulfur          96
## 3 midgrade          4788
## 4 premium           4788
## 5 regular           5222
## 6 ultra_low_sulfur   960

grade_levels <- c("all","regular","midgrade","premium","ultra_low_sulfur","low_sulfur")

mydata_rev <- mydata %>% 
    mutate(grade = grade %>% factor(levels = grade_levels))

mydata_rev %>% count(grade)

## # A tibble: 6 × 2
##   grade                n
##   <fct>            <int>
## 1 all               6506
## 2 regular           5222
## 3 midgrade          4788
## 4 premium           4788
## 5 ultra_low_sulfur   960
## 6 low_sulfur          96

Modify factor order

Make two bar charts here - one before ordering another after

mydata %>%
  count(grade) %>%
  ggplot(aes(x = grade, y = n)) +
  geom_bar(stat = "identity") +
  labs(x = "Grade", y = "Amount of Values", title = "Amount of Values per version of Grade") +
    theme(axis.text.x = element_text(angle = 45, hjust = 1))

mydata_rev %>%
    count(grade) %>%
  ggplot(aes(x = grade, y = n)) +
  geom_bar(stat = "identity") +
  labs(x = "Grade", y = "Amount of Values", title = "Amount of Values per version of Grade") +
    theme(axis.text.x = element_text(angle = 45, hjust = 1))

Modify factor levels

Show examples of three functions:

• fct_recode

mydata %>%
  mutate(grade = fct_recode(grade,
    "Total" = "all",
  "87" = "regular",
  "89" = "midgrade",
  "92" = "premium",
  "Diesel" = "ultra_low_sulfur",
  "Low sulfer Diesel" = "low_sulfur",
  )) %>%
  count(grade)

## # A tibble: 6 × 2
##   grade                 n
##   <fct>             <int>
## 1 Total              6506
## 2 Low sulfer Diesel    96
## 3 89                 4788
## 4 92                 4788
## 5 87                 5222
## 6 Diesel              960

• fct_collapse

mydata %>%
    
mutate(grade = fct_collapse(grade,
  Gasoline = c("regular","midgrade","premium"),
  Diesel = "ultra_low_sulfur","low_sulfur",
  All = "all")) %>%
    count(grade)

## # A tibble: 4 × 2
##   grade          n
##   <fct>      <int>
## 1 "All"       6506
## 2 ""            96
## 3 "Gasoline" 14798
## 4 "Diesel"     960

• fct_lump

mydata %>%
    mutate(grade = fct_lump(grade)) %>%
    count(grade)

## # A tibble: 5 × 2
##   grade        n
##   <fct>    <int>
## 1 all       6506
## 2 midgrade  4788
## 3 premium   4788
## 4 regular   5222
## 5 Other     1056

Chapter 16

No need to do anything here.