arsenal (version 3.6.3)

formulize: formulize

Description

A shortcut to generate one-, two-, or many-sided formulas from vectors of variable names.

Usage

formulize(
  y = "",
  x = "",
  ...,
  data = NULL,
  collapse = "+",
  collapse.y = collapse,
  escape = FALSE
)

Arguments

y, x, ...

Character vectors, names, or calls to be collapsed (by "+") and put left-to-right in the formula. If data is supplied, these can also be numeric, denoting which column name to use. See examples.

data

An R object with non-null column names.

collapse

How should terms be collapsed? Default is addition.

collapse.y

How should the y-terms be collapsed? Default is addition. Also accepts the special string "list", which combines them into a multiple-left-hand-side formula, for use in other functions.

escape

A logical indicating whether character vectors should be coerced to names (that is, whether names with spaces should be surrounded with backticks or not)

See Also

reformulate

Examples

# NOT RUN {
## two-sided formula
f1 <- formulize("y", c("x1", "x2", "x3"))

## one-sided formula
f2 <- formulize(x = c("x1", "x2", "x3"))

## multi-sided formula
f3 <- formulize("y", c("x1", "x2", "x3"), c("z1", "z2"), "w1")

## can use numerics for column names
data(mockstudy)
f4 <- formulize(y = 1, x = 2:4, data = mockstudy)

## mix and match
f5 <- formulize(1, c("x1", "x2", "x3"), data = mockstudy)

## get an interaction
f6 <- formulize("y", c("x1*x2", "x3"))

## get only interactions
f7 <- formulize("y", c("x1", "x2", "x3"), collapse = "*")

## no intercept
f8 <- formulize("y", "x1 - 1")
f9 <- formulize("y", c("x1", "x2", "-1"))

## LHS as a list to use in arsenal functions
f10 <- formulize(c("y1", "y2", "y3"), c("x", "z"), collapse.y = "list")

## use in an lm
f11 <- formulize(2, 3:4, data = mockstudy)
summary(lm(f11, data = mockstudy))

## using non-syntactic names or calls (like reformulate example)
f12 <- formulize(as.name("+-"), c("`P/E`", "`% Growth`"))
f12 <- formulize("+-", c("P/E", "% Growth"), escape = TRUE)

f <- Surv(ft, case) ~ a + b
f13 <- formulize(f[[2]], f[[3]])

# }