data(flights)
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
set.seed(1234)
df <- tibble::tibble(
a = rnorm(10),
b = rnorm(10),
c = rnorm(10),
d = rnorm(10)
)
df$a <- (df$a - min(df$a, na.rm = TRUE)) /
(max(df$a, na.rm = TRUE) - min(df$a, na.rm = TRUE))
df$b <- (df$b - min(df$b, na.rm = TRUE)) /
(max(df$b, na.rm = TRUE) - min(df$b, na.rm = TRUE))
df$c <- (df$c - min(df$c, na.rm = TRUE)) /
(max(df$c, na.rm = TRUE) - min(df$c, na.rm = TRUE))
df$d <- (df$d - min(df$d, na.rm = TRUE)) /
(max(df$d, na.rm = TRUE) - min(df$d, na.rm = TRUE))
df
## # A tibble: 10 × 4
## a b c d
## <dbl> <dbl> <dbl> <dbl>
## 1 0.332 0.153 0.782 1
## 2 0.765 0 0.473 0.519
## 3 1 0.0651 0.498 0.448
## 4 0 0.311 0.943 0.511
## 5 0.809 0.573 0.373 0.168
## 6 0.831 0.260 0 0.308
## 7 0.516 0.143 1 0
## 8 0.524 0.0255 0.210 0.256
## 9 0.519 0.0472 0.708 0.575
## 10 0.424 1 0.253 0.522
rescale <- function(x) {
# body
x <- (x - min(x, na.rm = TRUE)) /
(max(x, na.rm = TRUE) - min(x, na.rm = TRUE))
# return values
return(x)
}
df$a <- rescale(df$a)
df$b <- rescale(df$b)
df$c <- rescale(df$c)
df$d <- rescale(df$d)
df
## # A tibble: 10 × 4
## a b c d
## <dbl> <dbl> <dbl> <dbl>
## 1 0.332 0.153 0.782 1
## 2 0.765 0 0.473 0.519
## 3 1 0.0651 0.498 0.448
## 4 0 0.311 0.943 0.511
## 5 0.809 0.573 0.373 0.168
## 6 0.831 0.260 0 0.308
## 7 0.516 0.143 1 0
## 8 0.524 0.0255 0.210 0.256
## 9 0.519 0.0472 0.708 0.575
## 10 0.424 1 0.253 0.522
nrow_num <- flights %>%
# filter rows that meet a condition
filter(carrier == "UA") %>%
# Count rows
nrow()
nrow_num
## [1] 58665
detect_sign <- function(x) {
if(x > 0) {
message("Value is positive")
print(x)
} else if(x == 0) {
warning("Value is not positive, but it can be accepted")
print(x)
} else {
stop("Value is negative, the function must stop")
print(x)
}
}
3 %>% detect_sign()
## Value is positive
## [1] 3
0 %>% detect_sign()
## Warning in detect_sign(.): Value is not positive, but it can be accepted
## [1] 0
# -1 %>% detect_sign()
?mean
x <- c(1:10, 100, NA)
x
## [1] 1 2 3 4 5 6 7 8 9 10 100 NA
x %>% mean()
## [1] NA
x %>% mean(na.rm = TRUE)
## [1] 14.09091
x %>% mean(na.rm = TRUE, trim = 0.1)
## [1] 6
mean_remove_na <- function(x, na.rm = TRUE, ...) {
avg <- mean(x, na.rm = na.rm, ...)
return(avg)
}
x %>% mean_remove_na()
## [1] 14.09091
x %>% mean_remove_na(na.rm = FALSE)
## [1] NA
x %>% mean_remove_na(trim = 0.1)
## [1] 6