R/data.R

In pridiltal/stray: Anomaly Detection in High Dimensional and Temporal Data

#' wheel data set with inlier and outlier.
#'
#' A bivariate dataset with an inlier and  anoutlier
#'
#' @format A data frame with 1002 rows and 3 variables:
#'  \describe{
#' \item{x }{numerical variable}
#' \item{y }{numerical variable}
#' \item{type}{Type of a data point : Typical or Outlier}}
"wheel1"


#' A dataset with an outlier
#'
#' A bivariate dataset with an outlier
#'
#' @format A data frame with 1001 rows and 3 variables:
#'  \describe{
#' \item{x }{numerical variable}
#' \item{y }{numerical variable}
#' \item{type}{Type of a data point : Typical or Outlier}}
"data_a"



#' A bimodal dataset with a micro cluster
#'
#' A bivariate dataset with two typical classes and a micor cluster
#'
#' @format A data frame with 2003 rows and 3 variables:
#'  \describe{
#' \item{x }{numerical variable}
#' \item{y }{numerical variable}
#' \item{type}{Type of a data point : Typical or Outlier}}
"data_b"


#' A dataset with local anomalies and  micro clusters
#'
#' A bivariate dataset with local anomalies and two  micro clusters
#'
#' @format A data frame with 1009 rows and 3 variables:
#'  \describe{
#' \item{x }{numerical variable}
#' \item{y }{numerical variable}
#' \item{type}{Type of a data point : Typical or Outlier}}
"data_c"



#' A wheel dataset with  two inliers
#'
#' A bivariate dataset with  two inliers. The inliers are very close to one another
#'
#' @format A data frame with 1002 rows and 3 variables:
#'  \describe{
#' \item{x }{numerical variable}
#' \item{y }{numerical variable}
#' \item{type}{Type of a data point : Typical or Outlier}}
"data_d"


#' A bimodal dataset with  an inlier
#'
#' A bimodal dataset with  an inlier. one typical class is a very dense  cluster,
#'
#' @format A data frame with 2001 rows and 3 variables:
#'  \describe{
#' \item{x }{numerical variable}
#' \item{y }{numerical variable}
#' \item{type}{Type of a data point : Typical or Outlier}}
"data_e"


#' A dataset with  an outlier
#'
#' A dataset with  an outlier. The typical class is a very dense cluster.
#'
#' @format A data frame with 2001 rows and 3 variables:
#'  \describe{
#' \item{x }{numerical variable}
#' \item{y }{numerical variable}
#' \item{type}{Type of a data point : Typical or Outlier}}
"data_f"


#' Dataset with pedestrian counts
#'
#' A dataset with  hourly pedestrian counts at 43 locations in the
#' city Melbourne, australia, from 1 December, 2018 to 1, January, 2019.
#'
#' @format A data frame with 33024 rows and 5 variables:
#'  \describe{
#' \item{Sensor }{Sensor location}
#' \item{Date_Time }{Time and date }
#' \item{Date}{Date}
#' \item{Time}{Time}
#' \item{Count}{Pedestrian count}}
"ped_data"