arules (version 0.1-3)

Income: Income Data Set

Description

The Income data set originates from an example in the book The Elements of Statistical Learning (see Section source). The data set is an extract from this survey. It consists of 8993 instances (obtained from the original data set with 9409 instances, by removing those observations with the annual income missing) with 14 demographic attributes. The data set is a good mixture of categorical and continuous variables with a lot of missing data. This is characteristic of data mining applications. The Income_transactions data set contains the data already prepared and coerced to transactions.

Usage

data("Income")
data("Income_transactions")

source

Impact Resources, Inc., Columbus, OH (1987).

Obtained from the web site of the book: Hastie, T., Tibshirani, R. & Friedman, J. (2001). The Elements of Statistical Learning. Springer-Verlag. (http://www-stat.stanford.edu/~tibs/ElemStatLearn/; called Marketing)

Details

To create Income_transactions, the original data frame in Income prepared in a similar way as described in The Elements of Statistical Learning. We removed cases with missing values and cut each ordinal variable (age, education, income, years in bay area, number in household, and number of children) at its median into two values (see Section examples).

Examples

data("Income")
Income[1:3, ]

### remove incomplete cases
Income <- Income[complete.cases(Income), ]

### preparing the data set
Income[["income"]] <- factor((as.numeric(Income[["income"]]) > 6) +1,
      levels = 1 : 2 , labels = c("$0-$40,000", "$40,000+"))
	  
Income[["age"]] <- factor((as.numeric(Income[["age"]]) > 3) +1,
    levels = 1 : 2 , labels = c("14-34", "35+"))

Income[["education"]] <- factor((as.numeric(Income[["education"]]) > 4) +1,
    levels = 1 : 2 , labels = c("no college graduate", "college graduate"))

Income[["years in bay area"]] <- factor(
	(as.numeric(Income[["years in bay area"]]) > 4) +1,
	levels = 1 : 2 , labels = c("1-9", "10+"))

Income[["number in household"]] <- factor(
	(as.numeric(Income[["number in household"]]) > 3) +1,
    levels = 1 : 2 , labels = c("1", "2+"))

Income[["number of children"]] <- factor(
     (as.numeric(Income[["number of children"]]) > 1) +0,
     levels = 0 : 1 , labels = c("0", "1+"))
	
##  creating transactions
Income_transactions <- as(Income, "transactions")
Income_transactions