inst/doc/comparing-topics.R

In scopusflow: A Reproducible Workflow Layer for 'Scopus' Bibliographic Searches

## ----include = FALSE----------------------------------------------------------
knitr::opts_chunk$set(collapse = TRUE, comment = "#>")
# The plotting chunks below need ggplot2 (a suggested package); skip them
# gracefully when it is not installed.
has_ggplot2 <- requireNamespace("ggplot2", quietly = TRUE)

## ----setup--------------------------------------------------------------------
library(scopusflow)

## ----eval = FALSE-------------------------------------------------------------
# cmp <- scopus_compare_topics(
#   reference_query  = "deep learning",
#   comparison_terms = c("computer vision", "natural language processing",
#                        "medical imaging", "drug discovery"),
#   years            = 2013:2021,
#   field            = "TITLE-ABS-KEY"
# )

## -----------------------------------------------------------------------------
years <- 2013:2021
ref_n <- round(seq(400, 1600, length.out = length(years)))
mk <- function(from, to) round(seq(from, to, length.out = length(years)))
counts <- list(
  "computer vision" = mk(140, 720),
  "natural language processing" = mk(90, 540),
  "medical imaging" = mk(15, 260),
  "drug discovery" = mk(8, 170)
)
cmp <- tibble::tibble(
  query = "q",
  query_type = c(rep("reference", length(years)),
                 rep("comparison", length(counts) * length(years))),
  abridged_query = c(rep("deep learning", length(years)),
                     rep(names(counts), each = length(years))),
  year = rep(years, length(counts) + 1),
  n = c(ref_n, unlist(counts, use.names = FALSE)),
  reference_n = rep(ref_n, length(counts) + 1),
  comparison_percentage = 100 * c(ref_n, unlist(counts, use.names = FALSE)) /
    rep(ref_n, length(counts) + 1),
  average_comparison_percentage = c(rep(100, length(years)),
                                    rep(c(40, 33, 15, 9), each = length(years)))
)
class(cmp) <- c("scopus_comparison", class(cmp))
cmp

## ----eval = has_ggplot2, fig.alt = "Four application areas' share of the deep-learning literature from 2013 to 2021, with shaded uncertainty bands", fig.width = 8, fig.height = 4.6----
plot_scopus_comparison(cmp)

## ----eval = has_ggplot2, fig.alt = "The same chart with the medical-imaging topic highlighted against the others in grey", fig.width = 8, fig.height = 4.6----
plot_scopus_comparison(cmp, highlight = "medical imaging")

## ----eval = has_ggplot2, fig.alt = "The comparison chart without record counts or bands", fig.width = 8, fig.height = 4.6----
plot_scopus_comparison(cmp, pub_count_in_legend = FALSE, interval = FALSE)

## -----------------------------------------------------------------------------
comp <- cmp[cmp$query_type == "comparison", ]
unique(comp[, c("abridged_query", "average_comparison_percentage")])