R-dummy-R生成哑变量的三种方法

library("nnet")
	dummy_income <- class.ind(hairPre$income)
	head(dummy_income) #Display the head 6 lines
	class(hairPre$income)
	#Do not have to as.factor() the variable

library(dummies)
	#to create dummies for specific variable
	#Do not have to as.factor() the variable
	d1 <- hairPre
	d1 <- cbind(d1, dummy(d1$income, sep = "."))
	#dummy.data.frame() call for the function model.matrix()
	class(d1$income)
	names(d1)

#Have to as.factor() the variable first
	hairPre$income <- as.factor(hairPre$income)
	dum_income <- model.matrix(~income, hairPre)
	class(hairPre$income)
	head(cbind(dum_income, hairPre$income))

caret包可以很简便地生成dummies
两种方式：

The function dummyVars can be used to generate a complete (less than full rank parameterized) set of dummy variables from one or more factors. The function takes a formula and a data set and outputs an object that can be used to create the dummy variables using the predict method.

For example, the etitanic data set in the earth package includes two factors: pclass (passenger class, with levels 1st, 2nd, 3rd) and sex (with levels female, male).

The base R function model.matrix would generate the following variables:

library(earth)
data(etitanic)
head(model.matrix(survived ~ ., data = etitanic))

Using dummyVars:

dummies <- dummyVars(survived ~ ., data = etitanic)
head(predict(dummies, newdata = etitanic))

Note there is no intercept and each factor has a dummy variable for each level, so this parameterization may not be useful for some model functions, such as lm.