data <- readxl::read_xlsx("../00_data/Pokemon Data.xlsx")
data %>% skimr::skim()
| Name | Piped data |
| Number of rows | 949 |
| Number of columns | 22 |
| _______________________ | |
| Column type frequency: | |
| character | 10 |
| numeric | 12 |
| ________________________ | |
| Group variables | None |
Variable type: character
| skim_variable | n_missing | complete_rate | min | max | empty | n_unique | whitespace |
|---|---|---|---|---|---|---|---|
| pokemon | 0 | 1 | 3 | 23 | 0 | 949 | 0 |
| type_1 | 0 | 1 | 3 | 8 | 0 | 18 | 0 |
| type_2 | 0 | 1 | 2 | 8 | 0 | 19 | 0 |
| color_1 | 0 | 1 | 7 | 7 | 0 | 18 | 0 |
| color_2 | 0 | 1 | 2 | 7 | 0 | 19 | 0 |
| color_f | 0 | 1 | 2 | 7 | 0 | 156 | 0 |
| egg_group_1 | 0 | 1 | 3 | 13 | 0 | 15 | 0 |
| egg_group_2 | 0 | 1 | 2 | 13 | 0 | 13 | 0 |
| url_icon | 0 | 1 | 2 | 55 | 0 | 722 | 0 |
| url_image | 0 | 1 | 83 | 85 | 0 | 949 | 0 |
Variable type: numeric
| skim_variable | n_missing | complete_rate | mean | sd | p0 | p25 | p50 | p75 | p100 | hist |
|---|---|---|---|---|---|---|---|---|---|---|
| id | 0 | 1.00 | 1899.77 | 3507.95 | 1.0 | 238.0 | 475.0 | 712.0 | 10147.0 | ▇▁▁▁▂ |
| species_id | 0 | 1.00 | 400.13 | 239.95 | 1.0 | 191.0 | 395.0 | 615.0 | 802.0 | ▇▇▇▆▇ |
| height | 0 | 1.00 | 1.23 | 1.27 | 0.1 | 0.5 | 1.0 | 1.5 | 14.5 | ▇▁▁▁▁ |
| weight | 0 | 1.00 | 66.21 | 119.95 | 0.1 | 8.5 | 28.8 | 66.6 | 999.9 | ▇▁▁▁▁ |
| base_experience | 0 | 1.00 | 150.48 | 76.39 | 36.0 | 68.0 | 157.0 | 184.0 | 608.0 | ▇▇▂▁▁ |
| hp | 0 | 1.00 | 68.95 | 25.93 | 1.0 | 50.0 | 65.0 | 80.0 | 255.0 | ▃▇▁▁▁ |
| attack | 0 | 1.00 | 79.47 | 31.95 | 5.0 | 55.0 | 75.0 | 100.0 | 190.0 | ▂▇▆▂▁ |
| defense | 0 | 1.00 | 74.07 | 30.76 | 5.0 | 50.0 | 70.0 | 90.0 | 230.0 | ▃▇▃▁▁ |
| special_attack | 0 | 1.00 | 72.81 | 32.63 | 10.0 | 50.0 | 65.0 | 95.0 | 194.0 | ▅▇▅▂▁ |
| special_defense | 0 | 1.00 | 72.22 | 27.68 | 20.0 | 50.0 | 70.0 | 90.0 | 230.0 | ▇▇▂▁▁ |
| speed | 0 | 1.00 | 69.02 | 29.21 | 5.0 | 45.0 | 65.0 | 90.0 | 180.0 | ▃▇▆▂▁ |
| generation_id | 147 | 0.85 | 3.69 | 1.93 | 1.0 | 2.0 | 4.0 | 5.0 | 7.0 | ▇▅▃▅▅ |
ncol_num <- flights %>%
# Select a type of variables
select(where(is.numeric)) %>%
# Count columns
ncol()
ncol_num
## [1] 14
count_ncol_numeric <- function(.data) {
#Body
ncol_num <- .data %>%
# Select a type of variables
select(where(is.numeric)) %>%
# Count columns
ncol()
return(ncol_num)
}
data %>% count_ncol_numeric()
## [1] 12
data %>% .[1:10, -1:-10] %>% count_ncol_numeric()
## [1] 5
count_ncol_type <- function(.data, type_of_data = "numeric") {
if(type_of_data == "numeric") {
#Body
ncol_num <- .data %>%
# Select a type of variables
select(where(is.numeric)) %>%
# Count columns
ncol()
} else if(type_of_data == "character") {
#Body
ncol_num <- .data %>%
# Select a type of variables
select(where(is.character)) %>%
# Count columns
ncol()
}
return(ncol_num)
}
data %>% count_ncol_type()
## [1] 12
data %>% count_ncol_type(type_of_data = "character")
## [1] 10
data %>% .[1:10, 1:5] %>% count_ncol_type(type_of_data = "character")
## [1] 1
nrow_num <- flights %>%
# filter rows that meet a condition
filter(carrier == "DL") %>%
# Count rows
nrow()
nrow_num
## [1] 48110
count_num_poke_type1 <- function(.data, type_1) {
# body
nrow_num <- .data %>%
# filter rows that meet a condition
filter(type_1 == type_1) %>%
# Count rows
nrow()
# return the new variable
return(nrow_num)
}
data %>% .[1:10, "type_1", drop = FALSE] %>%
count_num_poke_type1(type_1 = "fire")
## [1] 10
Create your own.
Use the filter() function to select rows that meet a condition. Refer to Chapter 5.2 Filter rows with filter()