Data cleaning

# dplyr::filter()
df |> filter(age > 30 & city == "New York City")

# bracket subsetting
df[df$age > 30 & df$city == "New York City", ]

df |> 
  group_by(age) |>
  summarize(income = mean(income))

ceiling(x)
floor(x)
round(x, 3)     # number of decimal places
signif(x, 3)    # number of significant digits

activities <- c("running", "dancing", "reading")
pattern <- "read"
str_subset(activities, pattern)   # return strings that match this pattern
str_detect(activities, pattern)   # return a logical vector
str_which(activities, pattern)    # return indice(s)

string <- "Contact: string@gmail.com or character@gmail.com",
pattern <- "[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+"
str_extract()                     # extract the first match
str_extract_all()                 # extract all matches