Compare ee925e4 ... +0 ... 13b3b3c

#' Cluster pairs of items into groups using hierarchical clustering

#'

#' Reshape a table that represents pairwise distances into hierarchical clusters,

#' returning a table with \code{item} and \code{cluster} columns.

#'

#' @param tbl Table

#' @param item1 First item

#' @param item2 Second item

#' @param distance Distance column

#' @param k The desired number of groups

#' @param h Height at which to cut the hierarchically clustered tree

#'

#' @examples

#'

#' library(gapminder)

#' library(dplyr)

#'

#' # Construct Euclidean distances between countries based on life

#' # expectancy over time

#' country_distances <- gapminder %>%

#'   pairwise_dist(country, year, lifeExp)

#'

#' country_distances

#'

#' # Turn this into 5 hierarchical clusters

#' clusters <- country_distances %>%

#'   widely_hclust(item1, item2, distance, k = 8)

#'

#' # Examine a few such clusters

#' clusters %>% filter(cluster == 1)

#' clusters %>% filter(cluster == 2)

#'

#' @seealso \link{cutree}

#'

#' @export

widely_hclust <- function(tbl, item1, item2, distance, k = NULL, h = NULL) {

}

#' Cluster items based on k-means across features

#'

#' Given a tidy table of features describing each item, perform k-means

#' clustering using \code{\link{kmeans}} and retidy the data into

#' one-row-per-cluster.

#'

#' @param tbl Table

#' @param item Item to cluster (as a bare column name)

#' @param feature Feature column (dimension in clustering)

#' @param value Value column

#' @param k Number of clusters

#' @param fill What to fill in for missing values

#' @param ... Other arguments passed on to \code{\link{kmeans}}

#'

#' @seealso \code{\link{widely_hclust}}

#'

#' @importFrom rlang :=

#'

#' @examples

#'

#' library(gapminder)

#' library(dplyr)

#'

#' clusters <- gapminder %>%

#'   widely_kmeans(country, year, lifeExp, k = 5)

#'

#' clusters

#'

#' clusters %>%

#'   count(cluster)

#'

#' # Examine a few clusters

#' clusters %>% filter(cluster == 1)

#' clusters %>% filter(cluster == 2)

#'

#' @export

widely_kmeans <- function(tbl, item, feature, value, k, fill = 0, ...) {

  # Add the clusters to the original table

}