feat: add p2p_data_sim

New method for simulating p2p data

NAMESPACE

@@ -118,6 +118,7 @@ export(one2one_rank)
 export(one2one_sum)
 export(one2one_summary)
 export(one2one_trend)
+export(p2p_data_sim)
 export(pairwise_count)
 export(period_change)
 export(personas_hclust)
@@ -171,6 +172,7 @@ importFrom(dplyr,mutate_if)
 importFrom(grDevices,rainbow)
 importFrom(htmltools,HTML)
 importFrom(igraph,graph_from_data_frame)
+importFrom(igraph,layout_with_mds)
 importFrom(igraph,plot.igraph)
 importFrom(magrittr,"%>%")
 importFrom(markdown,markdownToHTML)

R/p2p_data_sim.R

@@ -0,0 +1,73 @@
+#' @title Simulate a person-to-person query using a Watts-Strogatz model
+#'
+#' @description Generate an person-to-person query / edgelist based on the graph
+#' according to the Watts-Strogatz small-world network model. Organizational data
+#' fields are also simulated for `Organization`, `LevelDesignation`, and `City`.
+#'
+#' @param dim Integer constant, the dimension of the starting lattice.
+#' @param size Integer constant, the size of the lattice along each dimension.
+#' @param nei Integer constant, the neighborhood within which the vertices of
+#'  the lattice will be connected.
+#' @param p Real constant between zero and one, the rewiring probability.
+#'
+#' @details
+#' This is a wrapper around `igraph::watts.strogatz.game()`. See igraph documentation
+#' for details on methodology. Loop edges and multiple edges are disabled. Size of the
+#' network can be changing the arguments `size` and `nei`.
+#'
+#' @examples
+#' # Simulate a p2p dataset with 800 edges
+#' p2p_data_sim(size = 200, nei = 4)
+#'
+#' @export
+p2p_data_sim <- function(dim = 1,
+                         size = 300,
+                         nei = 5,
+                         p = 0.05){
+
+  igraph::watts.strogatz.game(dim = dim,
+                              size = 300,
+                              nei = 5,
+                              p = 0.05) %>%
+    igraph::as_edgelist() %>%
+    as.data.frame() %>%
+    dplyr::rename(TieOrigin_PersonId = "V1",
+           TieDestination_PersonId = "V2") %>%
+    dplyr::mutate(TieOrigin_Organization = add_cat(TieOrigin_PersonId, "Organization"),
+           TieDestination_Organization = add_cat(TieDestination_PersonId, "Organization"),
+           TieOrigin_LevelDesignation = add_cat(TieOrigin_PersonId, "LevelDesignation"),
+           TieDestination_LevelDesignation = add_cat(TieDestination_PersonId, "LevelDesignation"),
+           TieOrigin_City = add_cat(TieOrigin_PersonId, "City"),
+           TieDestination_City = add_cat(TieDestination_PersonId, "City")) %>%
+    dplyr::mutate_at(dplyr::vars(dplyr::ends_with("PersonId")),
+                     ~paste0("SIM_ID_", .)) %>%
+    dplyr::mutate(StrongTieScore = 1)
+}
+
+#' Add organizational data to the simulated p2p data
+
+add_cat <- function(x, type){
+
+  if(type == "Organization"){
+
+    dplyr::case_when((x %% 7 == 0) ~ "Org A",
+                     (x %% 6 == 0) ~ "Org B",
+                     (x %% 5 == 0) ~ "Org C",
+                     (x %% 4 == 0) ~ "Org D",
+                     (x %% 3 == 0) ~ "Org E",
+                     x < 100 ~ "Org F",
+                     (x %% 2 == 0) ~ "Org G", # Even number
+                     TRUE ~ "Org H")
+
+  } else if(type == "LevelDesignation"){
+
+    paste("Level", substr(x, 1, 1)) # Extract first digit
+
+  } else if(type == "City"){
+
+    dplyr::case_when((x %% 3 == 0) ~ "City A", # Divisible by 3
+                     (x %% 2 == 0) ~ "City B",
+                     TRUE ~ "City C")
+
+  }
+}

man/add_cat.Rd

@@ -0,0 +1,11 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/p2p_data_sim.R
+\name{add_cat}
+\alias{add_cat}
+\title{Add organizational data to the simulated p2p data}
+\usage{
+add_cat(x, type)
+}
+\description{
+Add organizational data to the simulated p2p data
+}

man/p2p_data_sim.Rd

@@ -0,0 +1,33 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/p2p_data_sim.R
+\name{p2p_data_sim}
+\alias{p2p_data_sim}
+\title{Simulate a person-to-person query using a Watts-Strogatz model}
+\usage{
+p2p_data_sim(dim = 1, size = 300, nei = 5, p = 0.05)
+}
+\arguments{
+\item{dim}{Integer constant, the dimension of the starting lattice.}
+
+\item{size}{Integer constant, the size of the lattice along each dimension.}
+
+\item{nei}{Integer constant, the neighborhood within which the vertices of
+the lattice will be connected.}
+
+\item{p}{Real constant between zero and one, the rewiring probability.}
+}
+\description{
+Generate an person-to-person query / edgelist based on the graph
+according to the Watts-Strogatz small-world network model. Organizational data
+fields are also simulated for \code{Organization}, \code{LevelDesignation}, and \code{City}.
+}
+\details{
+This is a wrapper around \code{igraph::watts.strogatz.game()}. See igraph documentation
+for details on methodology. Loop edges and multiple edges are disabled. Size of the
+network can be changing the arguments \code{size} and \code{nei}.
+}
+\examples{
+# Simulate a p2p dataset with 800 edges
+p2p_data_sim(size = 200, nei = 4)
+
+}