Import your data

data <- read_excel("../00_data/myData.xlsx")
data
## # A tibble: 236 × 20
##    TEAMID TEAM   PAKE PAKERANK  PASE PASERANK GAMES     W     L WINPERCENT   R64
##     <dbl> <chr> <dbl>    <dbl> <dbl>    <dbl> <dbl> <dbl> <dbl>      <dbl> <dbl>
##  1      1 Abil…   0.7       45   0.7       52     3     1     2      0.333     2
##  2      2 Akron  -0.9      179  -1.1      187     4     0     4      0         4
##  3      3 Alab…  -2.1      211  -2.9      220    10     5     5      0.5       5
##  4      4 Alba…  -0.4      147  -0.3      138     3     0     3      0         3
##  5      6 Amer…  -0.5      160  -0.4      150     3     0     3      0         3
##  6      8 Ariz…  -1.7      206  -2.5      216    28    17    11      0.607    11
##  7      9 Ariz…  -2        209  -1.9      206     5     1     4      0.2       4
##  8     10 Arka…   4.3       11   3.5       16    18    11     7      0.611     7
##  9     11 Arka…   0         76   0         78     1     0     1      0         1
## 10     12 Aubu…   0.6       53   1.4       30    11     7     4      0.636     4
## # ℹ 226 more rows
## # ℹ 9 more variables: R32 <dbl>, S16 <dbl>, E8 <dbl>, F4 <dbl>, F2 <dbl>,
## #   CHAMP <dbl>, TOP2 <dbl>, F4PERCENT <dbl>, CHAMPPERCENT <dbl>

Chapter 15

Create a factor

data %>% count(TEAM)
## # A tibble: 236 × 2
##    TEAM                    n
##    <chr>               <int>
##  1 Abilene Christian       1
##  2 Akron                   1
##  3 Alabama                 1
##  4 Albany                  1
##  5 American                1
##  6 Arizona                 1
##  7 Arizona St.             1
##  8 Arkansas                1
##  9 Arkansas Pine Bluff     1
## 10 Auburn                  1
## # ℹ 226 more rows
TEAM_levels <- c("Alabama", "Arkansas", "Auburn")

data_rev <- data %>%
    mutate(TEAM = TEAM %>% factor(levels = TEAM_levels))

Modify factor order

Make two bar charts here - one before ordering another after

Modify factor levels

data %>%
    mutate(TEAM = fct_recode(TEAM,
                             "Alabama" = "Albany",
                             "American" = "Arizona",
                             "Auburn" = "Arkansas")) %>% 
    count(TEAM)
## # A tibble: 233 × 2
##    TEAM                    n
##    <fct>               <int>
##  1 Abilene Christian       1
##  2 Akron                   1
##  3 Alabama                 2
##  4 American                2
##  5 Arizona St.             1
##  6 Auburn                  2
##  7 Arkansas Pine Bluff     1
##  8 Austin Peay             1
##  9 Baylor                  1
## 10 Belmont                 1
## # ℹ 223 more rows
data %>% 
    mutate(TEAM = fct_collapse(TEAM,
                              Alabama = "Albany",
                              Other   = "American", "Arizona")) %>%
    count(TEAM)
## # A tibble: 235 × 2
##    TEAM                      n
##    <fct>                 <int>
##  1 "Abilene Christian"       1
##  2 "Akron"                   1
##  3 "Alabama"                 2
##  4 "Other"                   1
##  5 ""                        1
##  6 "Arizona St."             1
##  7 "Arkansas"                1
##  8 "Arkansas Pine Bluff"     1
##  9 "Auburn"                  1
## 10 "Austin Peay"             1
## # ℹ 225 more rows
data %>% 
    mutate(TEAM = fct_lump(TEAM)) %>%
    count(TEAM)
## # A tibble: 236 × 2
##    TEAM                    n
##    <fct>               <int>
##  1 Abilene Christian       1
##  2 Akron                   1
##  3 Alabama                 1
##  4 Albany                  1
##  5 American                1
##  6 Arizona                 1
##  7 Arizona St.             1
##  8 Arkansas                1
##  9 Arkansas Pine Bluff     1
## 10 Auburn                  1
## # ℹ 226 more rows