Import your data
data(flights)
flights %>% skimr::skim()
Data summary
| 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
| 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
| 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
| time_hour |
0 |
1 |
2013-01-01 05:00:00 |
2013-12-31 23:00:00 |
2013-07-03 10:00:00 |
6936 |
data <- read_excel("../00_data/MyData-Charts.xlsx")
data
## # A tibble: 1,222 × 11
## year months state colon…¹ colon…² colon…³ colon…⁴ colon…⁵ colon…⁶ colon…⁷
## <dbl> <chr> <chr> <dbl> <chr> <dbl> <dbl> <chr> <chr> <chr>
## 1 2015 January-… Alab… 7000 7000 1800 26 2800 250 4
## 2 2015 January-… Ariz… 35000 35000 4600 13 3400 2100 6
## 3 2015 January-… Arka… 13000 14000 1500 11 1200 90 1
## 4 2015 January-… Cali… 1440000 1690000 255000 15 250000 124000 7
## 5 2015 January-… Colo… 3500 12500 1500 12 200 140 1
## 6 2015 January-… Conn… 3900 3900 870 22 290 NA NA
## 7 2015 January-… Flor… 305000 315000 42000 13 54000 25000 8
## 8 2015 January-… Geor… 104000 105000 14500 14 47000 9500 9
## 9 2015 January-… Hawa… 10500 10500 380 4 3400 760 7
## 10 2015 January-… Idaho 81000 88000 3700 4 2600 8000 9
## # … with 1,212 more rows, 1 more variable: `Growth of colonies` <dbl>, and
## # abbreviated variable names ¹colony_n, ²colony_max, ³colony_lost,
## # ⁴colony_lost_pct, ⁵colony_added, ⁶colony_reno, ⁷colony_reno_pct
data_small <- read_excel("../00_data/Datasimpler.xlsx")
data %>% count(year)
## # A tibble: 7 × 2
## year n
## <dbl> <int>
## 1 2015 188
## 2 2016 188
## 3 2017 188
## 4 2018 188
## 5 2019 188
## 6 2020 188
## 7 2021 94
data %>% count(state)
## # A tibble: 47 × 2
## state n
## <chr> <int>
## 1 Alabama 26
## 2 Arizona 26
## 3 Arkansas 26
## 4 California 26
## 5 Colorado 26
## 6 Connecticut 26
## 7 Florida 26
## 8 Georgia 26
## 9 Hawaii 26
## 10 Idaho 26
## # … with 37 more rows
data %>% count(months)
## # A tibble: 4 × 2
## months n
## <chr> <int>
## 1 April-June 329
## 2 January-March 329
## 3 July-September 282
## 4 October-December 282
Create Data frame functions
Example 1: count columns
code snippets
ncol_num <- flights %>%
# Select a type of variables
select(where(is.numeric)) %>%
# Count columns
ncol()
ncol_num
## [1] 14
Turn them into a function
count_ncol_numeric <- function(.data) {
# Body of Function
ncol_num <- flights %>%
# Select a type of variables
select(where(is.numeric)) %>%
# Count columns
ncol()
ncol_num
#Return The New Variable
return(ncol_num)
}
flights %>% count_ncol_numeric()
## [1] 14
flights %>% .[1:10, -1:-13] %>% count_ncol_numeric()
## [1] 14
Adding arguments for details of operation
count_ncol_type <- function(.data, type_data = "numeric") {
#If Statement
if(type_data == "numeric") {
ncol_type <- .data %>%
# Select a type of variables
select(where(is.numeric)) %>%
# Count columns
ncol()
} else if (type_data == "character") {
# body
ncol_num <- flights %>%
# Select a type of variables
select(where(is.Charachter)) %>%
# Count columns
ncol()
}
#Return The New Variable
return(ncol_num)
}
flights %>% count_ncol_type()
## [1] 14
flights %>% count_ncol_type(type_data = "charachter")
## [1] 14
flights %>% .[1:10, 1:5] %>% count_ncol_type(type_data = "charachter")
## [1] 14
Example 2: count rows
code snippets
nrow_num <- flights %>%
# filter rows that meet a condition
filter(carrier == "DL") %>%
# Count rows
nrow()
nrow_num
## [1] 48110
Turn them into a function
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()
#Return New variable
return(nrow_num)
}
flights %>% .[1:10, "carrier"] %>%
count_num_flights_by_carrier(carrier_name = "AA")
## [1] 2
Example 3: count rows
code snippets
nrow_num <- data %>%
# filter rows that meet a condition
filter(state == "New York") %>%
# Count rows
nrow()
nrow_num
## [1] 26
Turn them into a function
count_num_states_by_New_York <- function(.data, state_name) {
# body
nrow_num <- data %>%
# filter rows that meet a condition
filter(state == "New York") %>%
# Count rows
nrow()
return(nrow_num)
}
data %>% .[1:10,1:5,"state"] %>%
count_num_states_by_New_York(state_name = "New York")
## [1] 26