## ----setup, include = FALSE---------------------------------------------------
knitr::opts_chunk$set(
  collapse = TRUE,
  eval = any(dir.exists(c("working_example_data", "benchmark_data", "new_benchmark_data", "topic_data", "valid_data", "new_stage_data"))),
  comment = "#>",
  fig.width = 10,
  fig.height = 10,
  warning = FALSE
)

## ----results = FALSE, message=FALSE-------------------------------------------
#install.packages("CiteSource")
library(CiteSource)

## -----------------------------------------------------------------------------
file_path <- "../vignettes/new_stage_data/"
citation_files <- list.files(path = file_path, pattern = "\\.ris", full.names = TRUE)
citation_files

## -----------------------------------------------------------------------------
imported_tbl <- tibble::tribble(
  ~files,                ~cite_sources,       ~cite_labels,
  "wos_278.ris",         "WoS",               "search",
  "medline_84.ris",      "Medline",           "search",
  "econlit_3.ris",       "EconLit",           "search",
  "Dimensions_246.ris",  "Dimensions",        "search",
  "lens_343.ris",        "Lens.org",          "search",
  "envindex_100.ris",    "Environment Index", "search",
  "screened_128.ris",    NA,                  "screened",
  "final_24.ris",        NA,                  "final"
) |>
  dplyr::mutate(files = paste0(file_path, files))

raw_citations <- read_citations(metadata = imported_tbl)

## -----------------------------------------------------------------------------
unique_citations  <- dedup_citations(raw_citations)
n_unique          <- count_unique(unique_citations)
source_comparison <- compare_sources(unique_citations, comp_type = "sources")

## -----------------------------------------------------------------------------
initial_records <- calculate_initial_records(unique_citations, "search")
create_initial_record_table(initial_records)

## -----------------------------------------------------------------------------
plot_source_overlap_heatmap(source_comparison)
plot_source_overlap_heatmap(source_comparison, plot_type = "percentages")

## -----------------------------------------------------------------------------
plot_source_overlap_upset(source_comparison, decreasing = c(TRUE, TRUE))

## -----------------------------------------------------------------------------
plot_contributions(n_unique,
  center    = TRUE,
  bar_order = c("search", "screened", "final")
)

## -----------------------------------------------------------------------------
detailed_counts <- calculate_detailed_records(unique_citations, n_unique, "search")
create_detailed_record_table(detailed_counts)

## -----------------------------------------------------------------------------
phase_counts <- calculate_phase_records(unique_citations, n_unique, "cite_source")
create_precision_sensitivity_table(phase_counts)

## -----------------------------------------------------------------------------
unique_citations |>
  dplyr::filter(stringr::str_detect(cite_label, "final")) |>
  record_level_table(return = "DT")

## -----------------------------------------------------------------------------
#export_csv(unique_citations, filename = "citesource_export_phases.csv")
#export_ris(unique_citations, filename = "citesource_export_phases.ris", source_field = "DB", label_field = "C5")
#export_bib(unique_citations, filename = "citesource_export_phases.bib", include = c("sources", "labels", "strings"))

# Reimport a previously exported file
#unique_citations <- reimport_csv("citesource_export_phases.csv")
#unique_citations <- reimport_ris("citesource_export_phases.ris")