R/kc_house_data.R

In MAVE: Methods for Dimension Reduction

#' House price in King County, USA
#'
#' A data set contains 21613 obervations with 19 features plus house price. The names of the columns are given below.
#' \itemize{
#'   \item id
#'   \item date: Date house was sold(String)
#'   \item price: Price of the sold house
#'   \item bedrooms: Numer of Bedrooms
#'   \item bathrooms: Numer of bathrooms
#'   \item sqft_living: Square footage of the living room
#'   \item sqrt_log: Square footage of the log
#'   \item floors: Total floors in the house
#'   \item waterfront: Whether the house has a view a waterfront(1: yes, 0: not)
#'   \item view: unknown
#'   \item condtion: Condition of the house
#'   \item grade: unknown
#'   \item sqft_above: Square footage of house apart from basement
#'   \item sqft_basement: Square footage of the basement
#'   \item yr_built: Built year
#'   \item yr_renovated: Year when the house was renovated
#'   \item zipcode: zipcode of the house
#'   \item lat: Latitude coordinate
#'   \item long Longitude coordinate
#'   \item sqft_living15: Living room area in 2015(implies some renovations)
#'   \item sqrt_lot15: Lot area in 2015(implies some renovations)
#' }
#'
#'
#' @docType data
#' @keywords datasets
#' @format A data frame with 21613 rows and 19 variables
#' @source \url{https://www.kaggle.com/harlfoxem/housesalesprediction}
#' @name kc_house_data
#' @examples
#' data(kc_house_data)
#' #convert date in string to date in numeric value
#' kc_house_data[,2]=sapply(kc_house_data[,2],as.double)
#' train = sample(1:21613)[1:1000]
#' x.train = as.matrix(kc_house_data[train,c(2,4:21)]) #exclude id, house price
#' y.train = as.matrix(kc_house_data[train,3]) # house price
#' x.test  = as.matrix(kc_house_data[-train,c(2,4:21)])
#' y.test  = as.matrix(kc_house_data[-train,3])
#
# dr = mave.compute(x.train,y.train, method='meanopg',max.dim=5)
# dr.dim = mave.dim(dr,max.dim=5)
# y.pred = predict(dr.dim,x.test)
# #estimation error
# mean(abs(y.pred-y.test)/y.test)
NULL