R 的資料清理
Maggie Matsui
Content Developer @ DataCamp
character
integer
numeric
logical
factor
Date
sales <- read.csv("sales.csv") head(sales)
order_id revenue quantity 1 7432 5,454 494 2 7808 5,668 334 3 4893 4,062 259 4 6107 3,936 15 5 7661 1,067 307 6 5908 6,635 235
library(dplyr) glimpse(sales)
Observations: 100 Variables: 3 $ order_id <dbl> 7432, 7808, ... $ revenue <chr> "$5454", "$5668", ... $ quantity <dbl> 494, 334, ...
is.numeric(sales$revenue)
FALSE
library(assertive) assert_is_numeric(sales$revenue)
Error: is_numeric : sales$revenue is not of class 'numeric'; it has class 'character'.
assert_is_numeric(sales$quantity)
邏輯檢查－回傳 TRUE/FALSE
TRUE
is.character()
is.numeric()
is.logical()
is.factor()
is.Date()
assertive 檢查－為 FALSE 時拋錯
assertive
assert_is_character()
assert_is_numeric()
assert_is_logical()
assert_is_factor()
assert_is_date()
class(sales$revenue)
"character"
mean(sales$revenue)
NA Warning message: In mean.default(sales$revenue) : argument is not numeric or logical: returning NA
sales$revenue
"5,454" "5,668" "4,062" "3,936" "1,067" ...
library(stringr) revenue_trimmed = str_remove(sales$revenue, ",") revenue_trimmed
library(stringr) revenue_trimmed = str_remove(sales$revenue, ",")
revenue_trimmed
"5454" "5668" "4062" "3936" "1067" ...
as.numeric(revenue_trimmed)
5454 5668 4062 3936 1067 ...
sales %>% mutate(revenue_usd = as.numeric(str_remove(revenue, ",")))
# A tibble: 100 x 4 order_id revenue quantity revenue_usd <dbl> <chr> <dbl> <dbl> 1 7432 5,454 494 5454 2 7808 5,668 334 5668 3 4893 4,062 259 4062 4 6107 3,936 15 3936 5 7661 1,067 307 1067 # ... with 95 more rows
mean(sales$revenue_usd)
5361.4
as.character()
as.numeric()
as.logical()
as.factor()
as.Date()
product_type
1000 1000 3000 2000 3000 Levels: 1000 2000 3000
class(product_type)
"factor"
as.numeric(product_type)
1 1 3 2 3
as.numeric(as.character(product_type))
1000 1000 3000 2000 3000
Preparing Video For Download...
