data(flights)
MyData <- read_csv("../00_data/MyData.csv")
## New names:
## Rows: 380 Columns: 23
## ── Column specification
## ──────────────────────────────────────────────────────── Delimiter: "," chr
## (6): Date, HomeTeam, AwayTeam, FTR, HTR, Referee dbl (17): ...1, FTHG, FTAG,
## HTHG, HTAG, HS, AS, HST, AST, HF, AF, HC, AC, HY...
## 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.
## • `` -> `...1`
flights %>% skimr::skim()
Name | Piped data |
Number of rows | 336776 |
Number of columns | 19 |
_______________________ | |
Column type frequency: | |
character | 4 |
numeric | 14 |
POSIXct | 1 |
________________________ | |
Group variables | None |
Variable type: character
skim_variable | n_missing | complete_rate | min | max | empty | n_unique | whitespace |
---|---|---|---|---|---|---|---|
carrier | 0 | 1.00 | 2 | 2 | 0 | 16 | 0 |
tailnum | 2512 | 0.99 | 5 | 6 | 0 | 4043 | 0 |
origin | 0 | 1.00 | 3 | 3 | 0 | 3 | 0 |
dest | 0 | 1.00 | 3 | 3 | 0 | 105 | 0 |
Variable type: numeric
skim_variable | n_missing | complete_rate | mean | sd | p0 | p25 | p50 | p75 | p100 | hist |
---|---|---|---|---|---|---|---|---|---|---|
year | 0 | 1.00 | 2013.00 | 0.00 | 2013 | 2013 | 2013 | 2013 | 2013 | ▁▁▇▁▁ |
month | 0 | 1.00 | 6.55 | 3.41 | 1 | 4 | 7 | 10 | 12 | ▇▆▆▆▇ |
day | 0 | 1.00 | 15.71 | 8.77 | 1 | 8 | 16 | 23 | 31 | ▇▇▇▇▆ |
dep_time | 8255 | 0.98 | 1349.11 | 488.28 | 1 | 907 | 1401 | 1744 | 2400 | ▁▇▆▇▃ |
sched_dep_time | 0 | 1.00 | 1344.25 | 467.34 | 106 | 906 | 1359 | 1729 | 2359 | ▁▇▇▇▃ |
dep_delay | 8255 | 0.98 | 12.64 | 40.21 | -43 | -5 | -2 | 11 | 1301 | ▇▁▁▁▁ |
arr_time | 8713 | 0.97 | 1502.05 | 533.26 | 1 | 1104 | 1535 | 1940 | 2400 | ▁▃▇▇▇ |
sched_arr_time | 0 | 1.00 | 1536.38 | 497.46 | 1 | 1124 | 1556 | 1945 | 2359 | ▁▃▇▇▇ |
arr_delay | 9430 | 0.97 | 6.90 | 44.63 | -86 | -17 | -5 | 14 | 1272 | ▇▁▁▁▁ |
flight | 0 | 1.00 | 1971.92 | 1632.47 | 1 | 553 | 1496 | 3465 | 8500 | ▇▃▃▁▁ |
air_time | 9430 | 0.97 | 150.69 | 93.69 | 20 | 82 | 129 | 192 | 695 | ▇▂▂▁▁ |
distance | 0 | 1.00 | 1039.91 | 733.23 | 17 | 502 | 872 | 1389 | 4983 | ▇▃▂▁▁ |
hour | 0 | 1.00 | 13.18 | 4.66 | 1 | 9 | 13 | 17 | 23 | ▁▇▇▇▅ |
minute | 0 | 1.00 | 26.23 | 19.30 | 0 | 8 | 29 | 44 | 59 | ▇▃▆▃▅ |
Variable type: POSIXct
skim_variable | n_missing | complete_rate | min | max | median | n_unique |
---|---|---|---|---|---|---|
time_hour | 0 | 1 | 2013-01-01 05:00:00 | 2013-12-31 23:00:00 | 2013-07-03 10:00:00 | 6936 |
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 the new variable
return(ncol_num)
}
flights %>% count_ncol_numeric()
## [1] 14
flights %>% .[1:10, -1:-13] %>% count_ncol_numeric()
## [1] 4
count_ncol_type <- function(.data, type_data = "numeric") {
# if statement for type of variables
if(type_data == "numeric") {
# body
ncol_type <- .data %>%
# Select a type of variables
select(where(is.numeric)) %>%
# Count columns
ncol()
} else if(type_data == "character") {
# body
ncol_type <- .data %>%
# Select a type of variables
select(where(is.character)) %>%
# Count columns
ncol()
}
# Return the new variable
return(ncol_type)
}
flights %>% count_ncol_type()
## [1] 14
flights %>% count_ncol_type(type_data = "character")
## [1] 4
flights %>% .[1:10, 1:5] %>% count_ncol_type(type_data = "character")
## [1] 0
nrow_num <- flights %>%
# filter rows that meet a condition
filter(carrier == "UA") %>%
# Count rows
nrow()
nrow_num
## [1] 58665
count_num_flights_by_carrier <- function(.data, carrier_name) {
# body
nrow_num <- .data %>%
# filter rows that meet a condition
filter(carrier == carrier_name) %>%
# Count rows
nrow()
}
flights %>% .[1:10, "carrier"] %>%
count_num_flights_by_carrier(carrier_name = "AA")
Create your own.
nrow_num <- MyData %>%
filter(FTR == "H") %>%
nrow()
nrow_num
## [1] 163
Use the filter() function to select rows that meet a condition. Refer to Chapter 5.2 Filter rows with filter()
count_num_wins_by_ftr <- function(MyData, FTR) {
nrow_num <- MyData %>%
filter(FTR == "H") %>%
nrow()
return(nrow_num)
}
MyData %>% .[1:10, "FTR"] %>%
count_num_wins_by_ftr(FTR = "H")
## [1] 7