Module 11: Apply it to your data 10

Import your data

data <- read_csv("../Desktop/PSU_DAT3000_IntroToDA/00_data/Mydata.csv")

## New names:
## Rows: 41152 Columns: 17
## ── Column specification
## ──────────────────────────────────────────────────────── Delimiter: "," chr
## (11): Name, Sex, Event, Equiptment, Age Class, Division, Weight Class KG... dbl
## (5): Age, Bodyweight, Best Sqaut KG, Best Bench KG, Best Deadlifting lgl (1):
## ...17
## 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.
## • `` -> `...17`

Chapter 15

Create a factor

Modify factor order

Make two bar charts here - one before ordering another after

# Plot Before
data %>%
    
    ggplot(aes(x = Sex , y = `Weight Class KG`)) +
    geom_point()

# Plot After

Modify factor levels

Show examples of three functions:

• fct_recode
• fct_collapse
• fct_lump

data %>% count(Event)

## # A tibble: 3 × 2
##   Event     n
##   <chr> <int>
## 1 B     12564
## 2 SB        2
## 3 SBD   28586

data %>%
    mutate(Event_Rev = fct_recode(Event,
                                  "Bench" = "B",
                                  "SquatBench" = "SB",
                                  "SquatBenchDeadlift" = "SBD")) %>%
    select(Event, Event_Rev) %>%
    sample_n(10)

## # A tibble: 10 × 2
##    Event Event_Rev         
##    <chr> <fct>             
##  1 SBD   SquatBenchDeadlift
##  2 B     Bench             
##  3 SBD   SquatBenchDeadlift
##  4 B     Bench             
##  5 B     Bench             
##  6 SBD   SquatBenchDeadlift
##  7 B     Bench             
##  8 B     Bench             
##  9 SBD   SquatBenchDeadlift
## 10 B     Bench

data %>%
    mutate(Event_col = fct_collapse(Event,
                                    lift_heavy = c("SB", "SBD"),
                                    lift_light = c("B"))
           ) %>%
    select(Event, Event_col) %>%
    sample_n(3)

## # A tibble: 3 × 2
##   Event Event_col 
##   <chr> <fct>     
## 1 SBD   lift_heavy
## 2 SBD   lift_heavy
## 3 SBD   lift_heavy

data %>% count(Event, sort = T)

## # A tibble: 3 × 2
##   Event     n
##   <chr> <int>
## 1 SBD   28586
## 2 B     12564
## 3 SB        2

data%>%
    mutate(Event_lump = fct_lump(Event, n = 2)) %>%
    select(Event, Event_lump)

## # A tibble: 41,152 × 2
##    Event Event_lump
##    <chr> <fct>     
##  1 B     B         
##  2 B     B         
##  3 B     B         
##  4 B     B         
##  5 B     B         
##  6 B     B         
##  7 B     B         
##  8 B     B         
##  9 B     B         
## 10 B     B         
## # … with 41,142 more rows

Chapter 16

No need to do anything here.