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
count_ncol_numeric <- function(.data) {
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()
# return the new variable
return(nrow_num)
}
flights %>% .[1:10, "carrier"] %>% count_num_flights_by_carrier(carrier_name = "AA")
## [1] 2
Create your own.
Use the filter() function to select rows that meet a condition. Refer to Chapter 5.2 Filter rows with filter()
library(tidyverse)
library(tidyquant)
## Warning: package 'tidyquant' was built under R version 4.2.3
## Loading required package: PerformanceAnalytics
## Loading required package: xts
## Warning: package 'xts' was built under R version 4.2.3
## Loading required package: zoo
## Warning: package 'zoo' was built under R version 4.2.3
##
## Attaching package: 'zoo'
## The following objects are masked from 'package:base':
##
## as.Date, as.Date.numeric
##
## ################################### WARNING ###################################
## # We noticed you have dplyr installed. The dplyr lag() function breaks how #
## # base R's lag() function is supposed to work, which breaks lag(my_xts). #
## # #
## # Calls to lag(my_xts) that you enter or source() into this session won't #
## # work correctly. #
## # #
## # All package code is unaffected because it is protected by the R namespace #
## # mechanism. #
## # #
## # Set `options(xts.warn_dplyr_breaks_lag = FALSE)` to suppress this warning. #
## # #
## # You can use stats::lag() to make sure you're not using dplyr::lag(), or you #
## # can add conflictRules('dplyr', exclude = 'lag') to your .Rprofile to stop #
## # dplyr from breaking base R's lag() function. #
## ################################### WARNING ###################################
##
## Attaching package: 'xts'
## The following objects are masked from 'package:dplyr':
##
## first, last
##
## Attaching package: 'PerformanceAnalytics'
## The following object is masked from 'package:graphics':
##
## legend
## Loading required package: quantmod
## Warning: package 'quantmod' was built under R version 4.2.3
## Loading required package: TTR
## Registered S3 method overwritten by 'quantmod':
## method from
## as.zoo.data.frame zoo
symbols <- c("NVDA", "AAPL", "NFLX", "MSFT", "TSLA")
prices <- tq_get (x = symbols,
from = "2012-12-31")
prices %>%
filter(symbol == "AAPL", close > 150) %>%
nrow()
## [1] 241
prices %>%
filter(symbol == "NFLX", close > 200) %>%
nrow()
## [1] 1280
count_num_by_symbol_by_close <- function(.data, symbol_txt, close_dollar){
n_days <- .data %>%
filter(symbol == symbol_txt, close > close_dollar) %>%
nrow()
return(n_days)
}
count_num_by_symbol_by_close(.data = prices, symbol_txt = "NFLX", close_dollar = 250)
## [1] 1188
prices %>%
filter(close > 200) %>%
group_by(symbol) %>%
summarise(n_days = n()) %>%
ungroup()
## # A tibble: 4 × 2
## symbol n_days
## <chr> <int>
## 1 MSFT 707
## 2 NFLX 1280
## 3 NVDA 236
## 4 TSLA 481
get_nDays_above_close <- function(.data, closing_dollar){
new_variable <- .data %>%
filter(close > closing_dollar) %>%
group_by(symbol) %>%
summarise(n_days = n()) %>%
ungroup()
return(new_variable)
}
get_nDays_above_close(.data = prices, closing_dollar = 100)
## # A tibble: 5 × 2
## symbol n_days
## <chr> <int>
## 1 AAPL 682
## 2 MSFT 1217
## 3 NFLX 1788
## 4 NVDA 699
## 5 TSLA 684