openalexR

install.packages("remotes")
remotes::install_github("ropensci/openalexR")

install.packages("openalexR")

options(openalexR.mailto = "example@email.com")
options(openalexR.apikey = "EXAMPLE_APIKEY")

library(openalexR)
library(dplyr)
library(ggplot2)

works_from_dois <- oa_fetch(
  entity = "works",
  doi = c("10.1016/j.joi.2017.08.007", "https://doi.org/10.1007/s11192-013-1221-3"),
  verbose = TRUE
)
#> Requesting url: https://api.openalex.org/works?filter=doi%3A10.1016%2Fj.joi.2017.08.007%7Chttps%3A%2F%2Fdoi.org%2F10.1007%2Fs11192-013-1221-3
#> Getting 1 page of results with a total of 2 records...

# str(works_from_dois, max.level = 2)
# head(works_from_dois)
# show_works(works_from_dois)

works_from_dois |>
  show_works() |>
  knitr::kable()

works_from_orcids <- oa_fetch(
  entity = "works",
  author.orcid = c("0000-0001-6187-6610", "0000-0002-8517-9411"),
  verbose = TRUE
)
#> Requesting url: https://api.openalex.org/works?filter=author.orcid%3A0000-0001-6187-6610%7C0000-0002-8517-9411
#> Getting 2 pages of results with a total of 260 records...
#> Warning in oa_request(oa_query(filter = filter_i, multiple_id = multiple_id, : 
#> The following work(s) have truncated lists of authors: W4230863633.
#> Query each work separately by its identifier to get full list of authors.
#> For example:
#>   lapply(c("W4230863633"), \(x) oa_fetch(identifier = x))
#> Details at https://docs.openalex.org/api-entities/authors/limitations.

works_from_orcids |>
  show_works() |>
  knitr::kable()

works_search <- oa_fetch(
  entity = "works",
  title.search = c("bibliometric analysis", "science mapping"),
  cited_by_count = ">50",
  from_publication_date = "2020-01-01",
  to_publication_date = "2021-12-31",
  options = list(sort = "cited_by_count:desc"),
  verbose = TRUE
)
#> Requesting url: https://api.openalex.org/works?filter=title.search%3Abibliometric%20analysis%7Cscience%20mapping%2Ccited_by_count%3A%3E50%2Cfrom_publication_date%3A2020-01-01%2Cto_publication_date%3A2021-12-31&sort=cited_by_count%3Adesc
#> Getting 2 pages of results with a total of 258 records...

works_search |>
  show_works() |>
  knitr::kable()

authors_from_orcids <- oa_fetch(
  entity = "authors",
  orcid = c("0000-0001-6187-6610", "0000-0002-8517-9411")
)

authors_from_orcids |>
  show_authors() |>
  knitr::kable()

authors_from_names <- oa_fetch(
  entity = "authors",
  display_name = c("Massimo Aria", "Jason Priem"),
  has_orcid = TRUE
)
authors_from_names |>
  show_authors() |>
  knitr::kable()

my_arguments <- list(
  entity = "authors",
  last_known_institutions.id = "I71267560",
  works_count = ">499"
)

do.call(oa_fetch, c(my_arguments, list(count_only = TRUE)))
#>      count db_response_time_ms page per_page
#> [1,]    36                 177    1        1

if (do.call(oa_fetch, c(my_arguments, list(count_only = TRUE)))[1]>0){
do.call(oa_fetch, my_arguments) |>
  show_authors() |>
  knitr::kable()
}

library(gghighlight)
concept_df <- oa_fetch(
  entity = "concepts",
  level = 1,
  ancestors.id = "https://openalex.org/C86803240", # Biology
  works_count = ">1000000"
)

concept_df |>
  select(display_name, counts_by_year) |>
  tidyr::unnest(counts_by_year) |>
  filter(year < 2022) |>
  ggplot() +
  aes(x = year, y = works_count, color = display_name) +
  facet_wrap(~display_name) +
  geom_line(linewidth = 0.7) +
  scale_color_brewer(palette = "Dark2") +
  labs(
    x = NULL, y = "Works count",
    title = "Virology spiked in 2020."
  ) +
  guides(color = "none") +
  gghighlight(
    max(works_count) > 200000,
    min(works_count) < 400000,
    label_params = list(nudge_y = 10^5, segment.color = NA)
  )
#> label_key: display_name

italy_insts <- oa_fetch(
  entity = "institutions",
  country_code = "it",
  type = "education",
  verbose = TRUE
)
#> Requesting url: https://api.openalex.org/institutions?filter=country_code%3Ait%2Ctype%3Aeducation
#> Getting 2 pages of results with a total of 232 records...

italy_insts |>
  slice_max(cited_by_count, n = 8) |>
  mutate(display_name = forcats::fct_reorder(display_name, cited_by_count)) |>
  ggplot() +
  aes(x = cited_by_count, y = display_name, fill = display_name) +
  geom_col() +
  scale_fill_viridis_d(option = "E") +
  guides(fill = "none") +
  labs(
    x = "Total citations", y = NULL,
    title = "Italian references"
  ) +
  coord_cartesian(expand = FALSE)

# The package wordcloud needs to be installed to run this chunk
# library(wordcloud)

concept_cloud <- italy_insts |>
  select(inst_id = id, topics) |>
  tidyr::unnest(topics) |>
  filter(name == "field") |>
  select(display_name, count) |>
  group_by(display_name) |>
  summarise(score = sqrt(sum(count)))

pal <- c("black", scales::brewer_pal(palette = "Set1")(5))
set.seed(1)
wordcloud::wordcloud(
  concept_cloud$display_name,
  concept_cloud$score,
  scale = c(2, .4),
  colors = pal
)

# The package ggtext needs to be installed to run this chunk
# library(ggtext)

jours_all <- oa_fetch(
  entity = "sources",
  works_count = ">200000",
  verbose = TRUE
)

clean_journal_name <- function(x) {
  x |>
    gsub("\\(.*?\\)", "", x = _) |>
    gsub("Journal of the|Journal of", "J.", x = _) |>
    gsub("/.*", "", x = _)
}

jours <- jours_all |>
  filter(type == "journal") |>
  slice_max(cited_by_count, n = 9) |>
  distinct(display_name, .keep_all = TRUE) |>
  select(jour = display_name, topics) |>
  tidyr::unnest(topics) |>
  filter(name == "field") |>
  group_by(id, jour, display_name) |> 
  summarise(score = (sum(count))^(1/3), .groups = "drop") |> 
  left_join(concept_abbrev, by = join_by(id, display_name)) |>
  mutate(
    abbreviation = gsub(" ", "<br>", abbreviation),
    jour = clean_journal_name(jour),
  ) |>
  tidyr::complete(jour, abbreviation, fill = list(score = 0)) |>
  group_by(jour) |>
  mutate(
    color = if_else(score > 10, "#1A1A1A", "#D9D9D9"), # CCCCCC
    label = paste0("<span style='color:", color, "'>", abbreviation, "</span>")
  ) |>
  ungroup()

jours |>
  ggplot() +
  aes(fill = jour, y = score, x = abbreviation, group = jour) +
  facet_wrap(~jour) +
  geom_hline(yintercept = c(25, 50), colour = "grey90", linewidth = 0.2) +
  geom_segment(
    aes(x = abbreviation, xend = abbreviation, y = 0, yend = 55),
    color = "grey95"
  ) +
  geom_col(color = "grey20") +
  coord_polar(clip = "off") +
  theme_bw() +
  theme(
    plot.background = element_rect(fill = "transparent", colour = NA),
    panel.background = element_rect(fill = "transparent", colour = NA),
    panel.grid = element_blank(),
    panel.border = element_blank(),
    axis.text = element_blank(),
    axis.ticks.y = element_blank()
  ) +
  ggtext::geom_richtext(
    aes(y = 75, label = label),
    fill = NA, label.color = NA, size = 3
  ) +
  scale_fill_brewer(palette = "Set1", guide = "none") +
  labs(y = NULL, x = NULL, title = "Journal clocks")

# The packages ggraph and tidygraph need to be installed to run this chunk
library(ggraph)
library(tidygraph)
#> 
#> Attaching package: 'tidygraph'
#> The following object is masked from 'package:stats':
#> 
#>     filter

snowball_docs <- oa_snowball(
  identifier = c("W1964141474", "W1963991285"),
  verbose = TRUE
)
#> Requesting url: https://api.openalex.org/works?filter=openalex%3AW1964141474%7CW1963991285
#> Getting 1 page of results with a total of 2 records...
#> Collecting all documents citing the target papers...
#> Requesting url: https://api.openalex.org/works?filter=cites%3AW1963991285%7CW1964141474
#> Getting 3 pages of results with a total of 540 records...
#> Collecting all documents cited by the target papers...
#> Requesting url: https://api.openalex.org/works?filter=cited_by%3AW1963991285%7CW1964141474
#> Getting 1 page of results with a total of 91 records...

ggraph(graph = as_tbl_graph(snowball_docs), layout = "stress") +
  geom_edge_link(aes(alpha = after_stat(index)), show.legend = FALSE) +
  geom_node_point(aes(fill = oa_input, size = cited_by_count), shape = 21, color = "white") +
  geom_node_label(aes(filter = oa_input, label = id), nudge_y = 0.2, size = 3) +
  scale_edge_width(range = c(0.1, 1.5), guide = "none") +
  scale_size(range = c(3, 10), guide = "none") +
  scale_fill_manual(values = c("#a3ad62", "#d46780"), na.value = "grey", name = "") +
  theme_graph() +
  theme(
    plot.background = element_rect(fill = "transparent", colour = NA),
    panel.background = element_rect(fill = "transparent", colour = NA),
    legend.position = "bottom"
  ) +
  guides(fill = "none")

ngrams_data <- oa_ngrams(
  works_identifier = c("W1964141474", "W1963991285"),
  verbose = TRUE
)

ngrams_data
#> # A tibble: 2 × 4
#>   id                               doi                              count ngrams
#>   <chr>                            <chr>                            <int> <list>
#> 1 https://openalex.org/W1964141474 https://doi.org/10.1016/j.conb.…  2733 <df>  
#> 2 https://openalex.org/W1963991285 https://doi.org/10.1126/science…  2338 <df>

lapply(ngrams_data$ngrams, head, 3)
#> [[1]]
#>                                        ngram ngram_count ngram_tokens
#> 1                 brain basis and core cause           2            5
#> 2                     cause be not yet fully           2            5
#> 3 include structural and functional magnetic           2            5
#>   term_frequency
#> 1   0.0006637902
#> 2   0.0006637902
#> 3   0.0006637902
#> 
#> [[2]]
#>                                          ngram ngram_count ngram_tokens
#> 1          intact but less accessible phonetic           1            5
#> 2 accessible phonetic representation in Adults           1            5
#> 3       representation in Adults with Dyslexia           1            5
#>   term_frequency
#> 1   0.0003756574
#> 2   0.0003756574
#> 3   0.0003756574

ngrams_data |>
  tidyr::unnest(ngrams) |>
  filter(ngram_tokens == 2) |>
  select(id, ngram, ngram_count) |>
  group_by(id) |>
  slice_max(ngram_count, n = 10, with_ties = FALSE) |>
  ggplot(aes(ngram_count, forcats::fct_reorder(ngram, ngram_count))) +
  geom_col(aes(fill = id), show.legend = FALSE) +
  facet_wrap(~id, scales = "free_y") +
  labs(
    title = "Top 10 fulltext bigrams",
    x = "Count",
    y = NULL
  )