ECCO multi-target split creation

library(tidyverse)

── Attaching core tidyverse packages ───────────────────────────────────────────────────────────────────────────────────────── tidyverse 2.0.0 ──
✔ dplyr     1.1.4     ✔ readr     2.1.5
✔ forcats   1.0.0     ✔ stringr   1.5.1
✔ ggplot2   3.5.1     ✔ tibble    3.2.1
✔ lubridate 1.9.3     ✔ tidyr     1.3.1
✔ purrr     1.0.2     
── Conflicts ─────────────────────────────────────────────────────────────────────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag()    masks stats::lag()
ℹ Use the ]8;;http://conflicted.r-lib.org/conflicted package]8;; to force all conflicts to become errors

library(eccor)
library(estcr)
ecco_core <- load_ecco_core()
estc_core <- load_estc_core()
estc_actor_links <- load_estc_actor_links()
estc_actors <- load_estc_actors()
works <- ecco_core %>% 
  left_join(estc_core, join_by(estc_id)) %>%
  replace_na(list(work_id="unknown work", publication_place="unknown place of publication")) %>%
  group_by(work_id) %>%
  summarise(
    earliest_publication_year=min(publication_year),
    ecco_parts=str_flatten(sort(unique(ecco_part)), collapse = "|"),
    ecco_languages=str_flatten(sort(unique(ecco_language)), collapse = "|"),
    has_prices=all(!is.na(total_price)),
    places_of_publication=str_flatten(sort(unique(publication_place)), collapse = "|"),
    ecco_modules=str_flatten(sort(unique(ecco_module)), collapse = "|"), .groups="drop") %>% 
  mutate(earliest_publication_decade=floor(earliest_publication_year/10)*10) %>%
  select(work_id, earliest_publication_decade, ecco_parts, ecco_modules, ecco_languages, places_of_publication, has_prices)

ecco_ids_to_works <- ecco_core %>% 
  left_join(estc_core, join_by(estc_id)) %>%
  replace_na(list(work_id="unknown work")) %>%
  select(ecco_id, work_id)

ecco_test <- works %>%
  group_by(ecco_parts, ecco_modules, earliest_publication_decade, ecco_languages, places_of_publication, has_prices) %>%
  slice_sample(prop=0.1) %>% # select at most 10% of the works
  slice_sample(n=5) %>% # filter down to max 5 per group
  group_by(ecco_modules, ecco_languages) %>%
  slice_sample(n=1000) %>%
  group_by(places_of_publication, ecco_languages) %>%
  slice_sample(n=1000) %>%
  group_by(has_prices, ecco_languages) %>%
  slice_sample(n=1000) %>%
  ungroup() %>%
  slice_sample(n=1000) %>% # iteratively pare down further
  inner_join(ecco_ids_to_works) %>%
  select(ecco_id, work_id)

Joining with `by = join_by(work_id)`

ecco_val <- works %>%
  anti_join(ecco_test) %>%
  group_by(ecco_parts, ecco_modules, earliest_publication_decade, ecco_languages, places_of_publication, has_prices) %>%
  slice_sample(prop=0.1) %>% # select at most 10% of the works
  slice_sample(n=5) %>% # filter down to max 5 per group
  group_by(ecco_modules, ecco_languages) %>%
  slice_sample(n=1000) %>%
  group_by(places_of_publication, ecco_languages) %>%
  slice_sample(n=1000) %>%
  group_by(has_prices, ecco_languages) %>%
  slice_sample(n=1000) %>%
  ungroup() %>%
  slice_sample(n=1000) %>% # iteratively pare down further
  inner_join(ecco_ids_to_works) %>%
  select(ecco_id, work_id)

Joining with `by = join_by(work_id)`
Joining with `by = join_by(work_id)`

ecco_train <- works %>%
  anti_join(ecco_test) %>%
  anti_join(ecco_val) %>%
  inner_join(ecco_ids_to_works) %>%
  select(ecco_id, work_id)

Joining with `by = join_by(work_id)`
Joining with `by = join_by(work_id)`
Joining with `by = join_by(work_id)`

library(here)

here() starts at /Users/jiemakel/tyo/r-scratch

ecco_test <- read_tsv(here("data/output/ecco_test_split_by_part_module_language_price_publication_place_and_decade.tsv"))

Rows: 1398 Columns: 2
── Column specification ─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
Delimiter: "\t"
chr (2): ecco_id, work_id

ℹ Use `spec()` to retrieve the full column specification for this data.
ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

ecco_val <- read_tsv(here("data/output/ecco_val_split_by_part_module_language_price_publication_place_and_decade.tsv"))

Rows: 1456 Columns: 2
── Column specification ─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
Delimiter: "\t"
chr (2): ecco_id, work_id

ℹ Use `spec()` to retrieve the full column specification for this data.
ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

ecco_train <- read_tsv(here("data/output/ecco_train_split_by_part_module_language_price_publication_place_and_decade.tsv"))

Rows: 204759 Columns: 2
── Column specification ─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
Delimiter: "\t"
chr (2): ecco_id, work_id

ℹ Use `spec()` to retrieve the full column specification for this data.
ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

targets <- ecco_core %>%
  left_join(estc_core, join_by(estc_id)) %>%
  left_join(estc_core %>% 
              group_by(work_id) %>% 
              filter(publication_year==min(publication_year)) %>%
              summarise(earliest_publication_year=min(publication_year), earliest_publication_year_definite = !any(uncertain | circa | range))
              , join_by(work_id)
            ) %>%
  transmute(ecco_id, ecco_part, ecco_module, publication_year, publication_year_definite = !(is.na(publication_year) | uncertain | circa | range), earliest_publication_year, earliest_publication_year_definite, primary_language, total_price, publication_place, publication_country, publication_place_deduced=org_260_a_square_brackets, pages=ecco_pages, estc_id)

ecco_test <- ecco_test %>% left_join(targets, join_by(ecco_id))
ecco_val <- ecco_val %>% left_join(targets, join_by(ecco_id))
ecco_train <- ecco_train %>% left_join(targets, join_by(ecco_id))
split <- ecco_test %>% 
  mutate(set="test") %>%
  union_all(
    ecco_val %>% 
      mutate(set="val")
  ) %>%
  union_all(
    ecco_train %>% 
      mutate(set="train")
  )

to_move_publication_year <- split %>% 
  filter(set=="train") %>% 
  group_by(publication_year_definite, publication_year) %>% 
  summarise(works=n_distinct(work_id), .groups="drop") %>%
  anti_join(split %>% 
              filter(set!="train") %>% 
              group_by(publication_year_definite, publication_year) %>% 
              summarise(works=n_distinct(work_id), .groups="drop") %>%
              filter(works>=5), join_by(publication_year_definite, publication_year)) %>%
  filter(works>=10) %>%
  inner_join(split %>% 
    filter(set=="train")) %>%
  distinct(publication_year_definite, publication_year, work_id) %>% 
  group_by(publication_year_definite, publication_year) %>%
  slice_sample(n=5)

Joining with `by = join_by(publication_year_definite, publication_year)`

to_move_publication_year_val <- to_move_publication_year %>%
  slice_sample(n=2) %>%
  mutate(new_set="val")

to_move_publication_year <- to_move_publication_year %>%
  anti_join(to_move_publication_year_val) %>%
  mutate(new_set="test") %>%
  union_all(to_move_publication_year_val) %>%
  ungroup() %>%
  select(work_id, new_set)

Joining with `by = join_by(publication_year_definite, publication_year, work_id)`

  
to_move_earliest_publication_year <- split %>% 
  filter(set=="train") %>% 
  group_by(earliest_publication_year_definite, earliest_publication_year) %>% 
  summarise(works=n_distinct(work_id), .groups="drop") %>%
  anti_join(split %>% 
              filter(set!="train") %>% 
              group_by(earliest_publication_year_definite, earliest_publication_year) %>% 
              summarise(works=n_distinct(work_id), .groups="drop") %>%
              filter(works>=5), join_by(earliest_publication_year_definite, earliest_publication_year)) %>%
  filter(works>=10) %>%
  inner_join(split %>% 
    filter(set=="train")) %>%
  distinct(earliest_publication_year_definite, earliest_publication_year, work_id) %>% 
  group_by(earliest_publication_year_definite, earliest_publication_year) %>%
  slice_sample(n=5)

Joining with `by = join_by(earliest_publication_year_definite, earliest_publication_year)`

to_move_earliest_publication_year_val <- to_move_earliest_publication_year %>%
  slice_sample(n=2) %>%
  mutate(new_set="val")

to_move_earliest_publication_year <- to_move_earliest_publication_year %>%
  anti_join(to_move_earliest_publication_year_val) %>%
  mutate(new_set="test") %>%
  union_all(to_move_earliest_publication_year_val) %>%
  ungroup() %>%
  select(work_id, new_set)

Joining with `by = join_by(earliest_publication_year_definite, earliest_publication_year, work_id)`

to_move_primary_language <- split %>% 
  filter(set=="train") %>% 
  group_by(primary_language) %>% 
  summarise(works=n_distinct(work_id), .groups="drop") %>%
  anti_join(split %>% 
              filter(set!="train") %>% 
              group_by(primary_language) %>% 
              summarise(works=n_distinct(work_id), .groups="drop") %>%
              filter(works>=5), join_by(primary_language)) %>%
  filter(works>=10) %>%
  inner_join(split %>% 
    filter(set=="train")) %>%
  distinct(primary_language, work_id) %>% 
  group_by(primary_language) %>%
  slice_sample(n=5)

Joining with `by = join_by(primary_language)`

to_move_primary_language_val <- to_move_primary_language %>%
  slice_sample(n=2) %>%
  mutate(new_set="val")

to_move_primary_language <- to_move_primary_language %>%
  anti_join(to_move_primary_language_val) %>%
  mutate(new_set="test") %>%
  union_all(to_move_primary_language_val) %>%
  ungroup() %>%
  select(work_id, new_set)

Joining with `by = join_by(primary_language, work_id)`

to_move_publication_place <- split %>% 
  filter(set=="train") %>% 
  group_by(publication_place_deduced,  publication_place) %>% 
  summarise(works=n_distinct(work_id), .groups="drop") %>%
  anti_join(split %>% 
              filter(set!="train") %>% 
              group_by(publication_place_deduced,  publication_place) %>% 
              summarise(works=n_distinct(work_id), .groups="drop") %>%
              filter(works>=5), join_by(publication_place_deduced,  publication_place)) %>%
  filter(works>=10) %>%
  inner_join(split %>% 
    filter(set=="train")) %>%
  distinct(publication_place_deduced,  publication_place, work_id) %>% 
  group_by(publication_place_deduced,  publication_place) %>%
  slice_sample(n=5) %>%
  ungroup() %>%
  select(work_id)

Joining with `by = join_by(publication_place_deduced, publication_place)`

to_move_publication_place_val <- to_move_publication_place %>%
  slice_sample(n=2) %>%
  mutate(new_set="val")

to_move_publication_place <- to_move_publication_place %>%
  anti_join(to_move_publication_place_val) %>%
  mutate(new_set="test") %>%
  union_all(to_move_publication_place_val) %>%
  ungroup() %>%
  select(work_id, new_set)

Joining with `by = join_by(work_id)`

d <- split %>% 
  left_join(estc_actor_links) %>% 
  select(set, work_id, actor_id, actor_roles_all) %>% 
  separate_rows(actor_roles_all, sep="; ") %>%
  distinct()

Joining with `by = join_by(estc_id)`

Warning in left_join(., estc_actor_links) :
  Detected an unexpected many-to-many relationship between `x` and `y`.
ℹ Row 2 of `x` matches multiple rows in `y`.
ℹ Row 399569 of `y` matches multiple rows in `x`.
ℹ If a many-to-many relationship is expected, set `relationship = "many-to-many"` to silence this warning.

to_move_actor <- d %>%
  filter(set=="train") %>% 
  group_by(actor_id,actor_roles_all) %>% 
  summarise(works=n_distinct(work_id), .groups="drop") %>%
  anti_join(d %>% 
              filter(set!="train") %>% 
              group_by(actor_roles_all, actor_id) %>% 
              summarise(works=n_distinct(work_id), .groups="drop") %>%
              filter(works>=5), join_by(actor_id)) %>%
  filter(works>=50) %>%
  inner_join(d %>% 
    filter(set=="train")) %>%
  distinct(actor_id, work_id) %>% 
  group_by(actor_id) %>%
  slice_sample(n=7)

Joining with `by = join_by(actor_id, actor_roles_all)`

to_move_actor_val <- to_move_actor %>%
  slice_sample(n=2) %>%
  mutate(new_set="val")

to_move_actor <- to_move_actor %>%
  anti_join(to_move_actor_val) %>%
  mutate(new_set="test") %>%
  union_all(to_move_actor_val) %>%
  ungroup() %>%
  select(work_id, new_set)

Joining with `by = join_by(actor_id, work_id)`

to_move <- to_move_earliest_publication_year %>% 
  union(to_move_publication_year) %>%
  union(to_move_primary_language) %>%
  union(to_move_publication_place) %>%
  union(to_move_actor) %>%
  group_by(work_id) %>%
  summarise(new_set=if_else(any(new_set=="test"),"test", "val"))

split <- split %>%
  left_join(to_move, join_by(work_id)) %>%
  mutate(set=coalesce(new_set,set)) %>%
  select(-new_set)

ssplit <- split
while (TRUE) {
  bad_test <- split %>%
    filter(set!="train", publication_year<1700 | publication_year>1800 | earliest_publication_year>1800) %>%
    union(split %>%
      filter(set!="train") %>% 
      anti_join(split %>% filter(set=="train"), join_by(publication_place))
    ) %>%
    union(split %>%
      filter(set!="train") %>% 
      anti_join(split %>% filter(set=="train"), join_by(publication_country))
    ) %>%
    union(split %>%
      filter(set!="train") %>% 
      anti_join(split %>% filter(set=="train"), join_by(primary_language))
    ) %>%
    union(split %>%
      filter(set!="train") %>% 
      anti_join(split %>% filter(set=="train"), join_by(publication_country))
    ) %>%
    distinct(work_id) %>%
    mutate(new_set="train")
  old_split <- split
  split <- split %>%
    left_join(bad_test, join_by(work_id)) %>%
    mutate(set=coalesce(new_set,set)) %>%
    select(-new_set)
  if (all(old_split$set==split$set)) break
}

major_primary_language <- split %>% 
  filter(set=="test") %>% 
  group_by(primary_language) %>% 
  summarise(works=n_distinct(work_id), documents=n(), pages=sum(pages)) %>%
  transmute(primary_language,major_primary_language=if_else(is.na(primary_language) | works>=10,primary_language, "Other"))

split <- split %>%
  left_join(major_primary_language)

Joining with `by = join_by(primary_language)`

major_publication_place <- split %>%
  filter(set=="test") %>% 
  group_by(publication_place) %>% 
  summarise(works=n_distinct(work_id), documents=n(), pages=sum(pages)) %>%
  transmute(publication_place,major_publication_place=if_else(is.na(publication_place) | works>=20,publication_place, "Other"))

split <- split %>%
  left_join(major_publication_place)

Joining with `by = join_by(publication_place)`

major_publication_country <- split %>%
  filter(set=="test") %>% 
  group_by(publication_country) %>% 
  summarise(works=n_distinct(work_id), documents=n(), pages=sum(pages)) %>%
  transmute(publication_country,major_publication_country=if_else(is.na(publication_country) | works>=10,publication_country, "Other"))

split <- split %>%
  left_join(major_publication_country)

Joining with `by = join_by(publication_country)`

actor_split <- split %>% 
  inner_join(estc_actor_links) %>% 
  select(set, work_id, actor_id, actor_roles_all) %>% 
  separate_rows(actor_roles_all, sep="; ") %>%
  mutate(actor_roles_all=if_else(actor_roles_all=="printer","publisher",actor_roles_all)) %>%
  distinct()

Joining with `by = join_by(estc_id)`

Warning in inner_join(., estc_actor_links) :
  Detected an unexpected many-to-many relationship between `x` and `y`.
ℹ Row 2 of `x` matches multiple rows in `y`.
ℹ Row 399569 of `y` matches multiple rows in `x`.
ℹ If a many-to-many relationship is expected, set `relationship = "many-to-many"` to silence this warning.

bad_test_actors <- actor_split %>%
  filter(set!="train") %>%
  anti_join(d %>% filter(set=="train"), join_by(actor_id, actor_roles_all)) %>%
  distinct(actor_roles_all, actor_id)

actor_split <- actor_split %>% 
  anti_join(bad_test_actors)

Joining with `by = join_by(actor_id, actor_roles_all)`

major_actor <- actor_split %>%
  filter(set=="test") %>% 
  group_by(actor_id, actor_roles_all) %>% 
  summarise(works=n(), .groups="drop") %>%
  transmute(actor_id, actor_roles_all, major_actor_id=if_else(is.na(actor_id) | works>=50,actor_id, "Other"))

major_actor_split <- actor_split %>%
  inner_join(major_actor %>% filter(major_actor_id!="Other")) %>%
  select(-actor_id)

Joining with `by = join_by(actor_id, actor_roles_all)`

actor_split <- actor_split %>% 
  inner_join(split %>% 
               select(ecco_id, work_id, pages)) %>% 
  inner_join(estc_actors %>% 
               select(actor_id, name_unified)) %>% 
  rename(actor_role=actor_roles_all)

Joining with `by = join_by(work_id)`

Warning in inner_join(., split %>% select(ecco_id, work_id, pages)) :
  Detected an unexpected many-to-many relationship between `x` and `y`.
ℹ Row 1 of `x` matches multiple rows in `y`.
ℹ Row 2 of `y` matches multiple rows in `x`.
ℹ If a many-to-many relationship is expected, set `relationship = "many-to-many"` to silence this warning.

Joining with `by = join_by(actor_id)`

major_actor_split <- major_actor_split %>% 
  inner_join(split %>% 
               select(ecco_id, work_id, pages)) %>% 
  inner_join(estc_actors %>% 
               select(major_actor_id=actor_id, name_unified)) %>% 
  rename(actor_role=actor_roles_all)

Joining with `by = join_by(work_id)`

Warning in inner_join(., split %>% select(ecco_id, work_id, pages)) :
  Detected an unexpected many-to-many relationship between `x` and `y`.
ℹ Row 1 of `x` matches multiple rows in `y`.
ℹ Row 8 of `y` matches multiple rows in `x`.
ℹ If a many-to-many relationship is expected, set `relationship = "many-to-many"` to silence this warning.

Joining with `by = join_by(major_actor_id)`

split %>% 
  write_tsv(here("data/output/ecco-multi-target-split.tsv"),quote="needed",na="")

actor_split %>%
  write_tsv(here("data/output/ecco-multi-target-actor-split.tsv"),quote="needed",na="")
major_actor_split %>%
  write_tsv(here("data/output/ecco-multi-target-major-actor-split.tsv"),quote="needed",na="")

Overall

library(gt)

Registered S3 methods overwritten by 'htmltools':
  method               from         
  print.html           tools:rstudio
  print.shiny.tag      tools:rstudio
  print.shiny.tag.list tools:rstudio

split %>%
    group_by(set) %>%
    summarise(pages=sum(pages),documents=n(),works=n_distinct(work_id), .groups="drop") %>%
    pivot_longer(pages:works) %>% 
    pivot_wider(names_from=set,values_from=value) %>%
    mutate(name=fct_relevel(name,"works","documents","pages")) %>%
    arrange(name) %>%
    gt(rowname_col = "name") %>%
    tab_header(title = "Overall") %>%
    fmt_integer(columns=c(test,val,train))

Overall
	test	train	val
works	5,970	107,740	2,530
documents	26,808	173,739	7,066
pages	6,587,400	24,788,273	1,537,513

split %>% 
  pivot_longer(c(ecco_part,ecco_module,primary_language,major_primary_language,publication_country,major_publication_country,publication_place,major_publication_place)) %>%
  select(name,set,value) %>%
  union_all(
    major_actor_split %>%
      transmute(name="major_actor_id",set,value=major_actor_id)
  ) %>%
  union_all(
    actor_split %>%
      transmute(name="actor_id",set,value=actor_id)
  ) %>%
  distinct(name,set,value) %>%
  count(set,name) %>%
  pivot_wider(names_from=set,values_from=n) %>%
  gt(rowname_col = "name") %>%
  tab_header(title = "Number of targets by task") %>%
  fmt_integer(columns=c(test,val,train))

Number of targets by task
	test	train	val
actor_id	10,698	60,856	4,452
ecco_module	8	8	8
ecco_part	2	2	2
major_actor_id	108	108	108
major_primary_language	9	9	9
major_publication_country	14	14	14
major_publication_place	40	40	40
primary_language	13	19	12
publication_country	19	38	15
publication_place	264	649	104

NA

• regression tasks: earliest_publication_year, publication_year, total_price

Single label targets

print_split <- function(split, group_var, group_var_name, major=FALSE, order_by_frequency=TRUE) {
  group_var = enquo(group_var)
  d <- split %>%
    group_by(set, !!group_var) %>%
    summarise(pages=sum(pages),documents=n(),works=n_distinct(work_id), .groups="drop") %>%
    pivot_longer(pages:works) %>% 
    pivot_wider(names_from=set,values_from=value) %>%
    mutate(name=fct_relevel(name,"works","documents","pages"))
  d <- if (order_by_frequency) d %>% mutate(group_var=fct_reorder(!!group_var, train, .desc=TRUE)) else d %>% mutate(group_var=!!group_var)
  d %>%
    select(-!!group_var) %>%
    arrange(name,group_var) %>%
    gt(groupname_col = "name", rowname_col="group_var") %>%
    tab_header(title = str_c("By ",group_var_name), subtitle=str_c("(", if (major) "major only, " else "", split %>% filter(set=="test") %>% distinct(!!group_var) %>% count() %>% pull(), " targets)")) %>%
    fmt_integer(columns=c(test,val,train))
}

ECCO part

split %>% 
  print_split(ecco_part, "ECCO part")

By ECCO part
(2 targets)
	test	train	val
works
ecco1	4,706	82,027	1,924
ecco2	2,468	33,930	1,010
documents
ecco1	19,950	129,702	5,272
ecco2	6,858	44,037	1,794
pages
ecco1	5,058,897	19,754,735	1,204,951
ecco2	1,528,503	5,033,538	332,562

ECCO module

split %>% 
  print_split(ecco_module, "ECCO module")

By ECCO module
(8 targets)
	test	train	val
works
Religion and Philosophy	1,968	29,403	771
Literature and Language	1,628	23,271	618
Social Sciences	1,517	29,885	641
History and Geography	565	8,001	244
Medicine, Science and Technology	468	8,916	217
Law	350	9,303	155
General Reference	236	3,203	79
Fine Arts	276	2,511	103
documents
Religion and Philosophy	6,309	44,113	1,754
Literature and Language	10,799	40,909	2,271
Social Sciences	3,067	39,485	1,061
History and Geography	2,629	15,031	663
Medicine, Science and Technology	1,487	13,713	464
Law	1,237	11,978	395
General Reference	489	4,532	201
Fine Arts	791	3,978	257
pages
Religion and Philosophy	1,444,519	6,313,356	365,012
Literature and Language	2,627,666	6,242,597	458,667
Social Sciences	492,522	3,296,537	141,209
History and Geography	970,297	4,095,770	231,541
Medicine, Science and Technology	427,364	2,626,252	125,229
Law	420,675	1,143,333	130,524
General Reference	128,449	713,606	61,683
Fine Arts	75,908	356,822	23,648

Primary language

split %>% 
  print_split(major_primary_language, "primary language", TRUE)

By primary language
(major only, 9 targets)
	test	train	val
works
English	5,641	102,414	2,367
French	198	2,457	86
Latin	210	2,812	94
Welsh	57	368	8
Italian	31	214	6
German	27	184	4
Other	20	76	10
Multiple languages	14	54	4
NA	3	22	2
documents
English	24,965	163,512	6,694
French	718	4,722	158
Latin	845	4,097	172
Welsh	82	460	10
Italian	95	392	11
German	35	251	4
Other	37	100	11
Multiple languages	28	69	4
NA	3	136	2
pages
English	6,028,016	22,498,845	1,449,460
French	223,017	1,205,902	31,991
Latin	260,398	789,051	47,719
Welsh	16,528	60,333	1,464
Italian	30,953	109,408	3,494
German	11,120	52,124	814
Other	9,752	31,309	1,608
Multiple languages	7,501	14,946	907
NA	115	26,355	56

split %>% 
  print_split(primary_language, "primary language")

By primary language
(13 targets)
	test	train	val
works
English	5,641	102,414	2,367
French	198	2,457	86
Latin	210	2,812	94
Welsh	57	368	8
Italian	31	214	6
German	27	184	4
Multiple languages	14	54	4
Spanish	5	30	3
Portuguese	2	22	2
Scottish Gaelic	9	13	3
Dutch	3	9	2
Manx	1	6	NA
Irish	NA	6	NA
Danish	NA	3	NA
Swedish	NA	3	NA
Algonquian (Other)	NA	1	NA
Mohawk	NA	1	NA
Romance (Other)	NA	1	NA
NA	3	7	2
documents
English	24,965	163,512	6,694
French	718	4,722	158
Latin	845	4,097	172
Welsh	82	460	10
Italian	95	392	11
German	35	251	4
Multiple languages	28	69	4
Spanish	10	35	3
Portuguese	2	23	2
Scottish Gaelic	21	17	4
Dutch	3	16	2
Manx	1	9	NA
Irish	NA	7	NA
Danish	NA	4	NA
Swedish	NA	3	NA
Algonquian (Other)	NA	1	NA
Mohawk	NA	1	NA
Romance (Other)	NA	1	NA
NA	3	119	2
pages
English	6,028,016	22,498,845	1,449,460
French	223,017	1,205,902	31,991
Latin	260,398	789,051	47,719
Welsh	16,528	60,333	1,464
Italian	30,953	109,408	3,494
German	11,120	52,124	814
Multiple languages	7,501	14,946	907
Spanish	2,831	11,091	123
Portuguese	396	5,091	144
Scottish Gaelic	5,683	5,104	741
Dutch	759	6,962	600
Manx	83	3,061	NA
Irish	NA	1,149	NA
Danish	NA	1,848	NA
Swedish	NA	915	NA
Algonquian (Other)	NA	97	NA
Mohawk	NA	206	NA
Romance (Other)	NA	162	NA
NA	115	21,978	56

Publication country

split %>% 
  print_split(major_publication_country, "publication country", TRUE)

By publication country
(major only, 14 targets)
	test	train	val
works
England	4,489	81,370	1,871
Scotland	807	12,073	335
Ireland	1,076	10,714	431
USA	797	6,997	226
France	96	1,047	34
Netherlands	76	325	15
Germany	48	176	9
Wales	50	271	7
Switzerland	26	87	1
Italy	18	88	1
India	11	123	2
Other	30	96	2
Belgium	10	43	1
NA	145	1,071	39
documents
England	18,541	128,352	5,007
Scotland	2,790	15,912	653
Ireland	3,140	15,448	910
USA	1,277	8,259	305
France	283	2,122	69
Netherlands	171	593	19
Germany	78	339	15
Wales	64	302	8
Switzerland	118	174	1
Italy	40	154	4
India	14	149	2
Other	48	129	6
Belgium	12	78	1
NA	232	1,728	66
pages
England	4,745,063	18,668,142	1,126,815
Scotland	673,838	1,937,308	145,205
Ireland	708,237	2,030,397	189,521
USA	167,405	735,190	29,935
France	89,436	577,826	16,538
Netherlands	48,799	164,539	4,013
Germany	25,858	121,346	2,542
Wales	10,055	25,057	810
Switzerland	43,643	55,515	454
Italy	13,783	43,683	1,455
India	2,506	27,788	265
Other	10,800	25,183	1,651
Belgium	2,163	15,540	8
NA	45,814	360,759	18,301

split %>% 
  print_split(publication_country, "publication country")

By publication country
(19 targets)
	test	train	val
works
England	4,489	81,370	1,871
Scotland	807	12,073	335
Ireland	1,076	10,714	431
USA	797	6,997	226
France	96	1,047	34
Netherlands	76	325	15
Germany	48	176	9
Wales	50	271	7
Switzerland	26	87	1
Italy	18	88	1
India	11	123	2
Belgium	10	43	1
Jamaica	9	32	1
Austria	8	12	1
Canada	8	27	NA
Sweden	2	12	NA
Denmark	6	11	NA
Saint Kitts and Nevis	NA	11	NA
Guernsey	NA	11	NA
Isle of Man	NA	8	NA
Barbados	NA	10	NA
Antigua	NA	8	NA
Haiti	NA	8	NA
Channel Islands	NA	8	NA
Malta	NA	7	NA
Portugal	NA	7	NA
Spain	NA	4	NA
Russia	NA	5	NA
Dominica	NA	3	NA
Grenada	1	3	NA
Poland	NA	2	NA
South Africa	NA	2	NA
Bahamas	NA	1	NA
Hungary	NA	1	NA
Netherlands Antilles	NA	1	NA
Northern Ireland	NA	1	NA
Saint-Domingue	NA	1	NA
NA	145	974	39
documents
England	18,541	128,352	5,007
Scotland	2,790	15,912	653
Ireland	3,140	15,448	910
USA	1,277	8,259	305
France	283	2,122	69
Netherlands	171	593	19
Germany	78	339	15
Wales	64	302	8
Switzerland	118	174	1
Italy	40	154	4
India	14	149	2
Belgium	12	78	1
Jamaica	13	38	4
Austria	13	31	2
Canada	11	28	NA
Sweden	2	16	NA
Denmark	8	13	NA
Saint Kitts and Nevis	NA	12	NA
Guernsey	NA	11	NA
Isle of Man	NA	11	NA
Barbados	NA	10	NA
Antigua	NA	9	NA
Haiti	NA	9	NA
Channel Islands	NA	8	NA
Malta	NA	8	NA
Portugal	NA	7	NA
Spain	NA	7	NA
Russia	NA	5	NA
Dominica	NA	3	NA
Grenada	1	3	NA
Poland	NA	3	NA
South Africa	NA	2	NA
Bahamas	NA	1	NA
Hungary	NA	1	NA
Netherlands Antilles	NA	1	NA
Northern Ireland	NA	1	NA
Saint-Domingue	NA	1	NA
NA	232	1,618	66
pages
England	4,745,063	18,668,142	1,126,815
Scotland	673,838	1,937,308	145,205
Ireland	708,237	2,030,397	189,521
USA	167,405	735,190	29,935
France	89,436	577,826	16,538
Netherlands	48,799	164,539	4,013
Germany	25,858	121,346	2,542
Wales	10,055	25,057	810
Switzerland	43,643	55,515	454
Italy	13,783	43,683	1,455
India	2,506	27,788	265
Belgium	2,163	15,540	8
Jamaica	2,627	4,453	1,468
Austria	4,937	8,508	183
Canada	1,146	3,264	NA
Sweden	234	5,110	NA
Denmark	1,852	3,644	NA
Saint Kitts and Nevis	NA	676	NA
Guernsey	NA	1,637	NA
Isle of Man	NA	916	NA
Barbados	NA	478	NA
Antigua	NA	372	NA
Haiti	NA	81	NA
Channel Islands	NA	1,792	NA
Malta	NA	2,428	NA
Portugal	NA	1,687	NA
Spain	NA	4,552	NA
Russia	NA	1,292	NA
Dominica	NA	31	NA
Grenada	4	204	NA
Poland	NA	1,238	NA
South Africa	NA	2	NA
Bahamas	NA	110	NA
Hungary	NA	240	NA
Netherlands Antilles	NA	164	NA
Northern Ireland	NA	46	NA
Saint-Domingue	NA	83	NA
NA	45,814	342,934	18,301

Publication place

split %>% 
  print_split(major_publication_place, "publication place", TRUE)

By publication place
(major only, 40 targets)
	test	train	val
works
London	3,518	70,105	1,656
Dublin	993	9,885	424
Edinburgh	583	10,234	268
Other	1,278	6,108	79
Boston Ma	276	3,041	118
Oxford	125	1,492	48
Glasgow	270	1,509	79
Philadelphia Pa	189	1,621	63
Paris	83	858	28
Cambridge	107	1,099	52
Newcastle	67	960	28
Bristol	69	761	28
York	64	600	22
Bath	32	534	9
New York Ny	69	597	24
Birmingham	51	512	9
Salisbury	27	412	4
Norwich	25	385	4
Manchester	57	388	16
Cork	46	344	10
Belfast	63	297	11
Leeds	24	278	10
Shrewsbury	30	244	8
Aberdeen	41	238	10
Liverpool	21	212	3
New London Ct	22	172	8
Northampton	26	199	4
Hartford Ct	38	176	9
Chester	23	184	1
Perth	43	98	5
Gloucester	26	134	3
Berwick-upon-Tweed	39	106	10
New Haven Ct	22	137	6
Coventry	23	137	2
Providence Ri	31	127	5
The Hague	42	63	4
Newburyport Ma	22	105	3
Paisley	20	78	3
Falkirk	27	79	2
NA	187	2,658	64
documents
London	16,294	111,914	4,562
Dublin	2,910	14,286	879
Edinburgh	1,746	12,887	489
Other	1,853	7,552	111
Boston Ma	396	3,387	153
Oxford	279	2,238	114
Glasgow	747	2,080	127
Philadelphia Pa	283	1,966	78
Paris	224	1,730	45
Cambridge	187	1,507	73
Newcastle	93	1,144	30
Bristol	153	1,008	39
York	106	751	30
Bath	48	748	13
New York Ny	104	696	28
Birmingham	86	641	12
Salisbury	41	461	5
Norwich	27	453	4
Manchester	68	448	16
Cork	57	383	10
Belfast	89	335	13
Leeds	30	333	13
Shrewsbury	40	307	9
Aberdeen	61	285	19
Liverpool	22	252	5
New London Ct	23	222	8
Northampton	27	213	4
Hartford Ct	51	211	10
Chester	25	205	1
Perth	88	175	6
Gloucester	32	161	3
Berwick-upon-Tweed	59	154	11
New Haven Ct	24	151	6
Coventry	30	150	6
Providence Ri	31	129	5
The Hague	67	122	6
Newburyport Ma	24	108	3
Paisley	20	97	3
Falkirk	35	88	2
NA	328	3,761	115
pages
London	4,401,845	16,671,741	1,051,211
Dublin	680,689	1,932,516	186,410
Edinburgh	440,701	1,434,837	106,727
Other	295,927	971,413	14,771
Boston Ma	40,900	223,443	12,197
Oxford	83,460	403,804	32,461
Glasgow	172,862	335,340	28,058
Philadelphia Pa	52,552	251,577	10,792
Paris	67,345	470,499	9,241
Cambridge	40,194	223,622	13,867
Newcastle	14,381	93,143	2,588
Bristol	10,748	97,172	2,968
York	20,242	93,607	4,144
Bath	5,953	113,802	1,114
New York Ny	21,011	87,543	3,340
Birmingham	19,295	94,109	1,948
Salisbury	6,201	23,115	19
Norwich	2,731	40,373	324
Manchester	7,501	41,732	585
Cork	8,839	43,061	1,608
Belfast	12,861	30,352	1,035
Leeds	4,570	36,159	2,515
Shrewsbury	6,581	46,468	1,660
Aberdeen	10,487	39,286	6,111
Liverpool	4,314	33,569	896
New London Ct	1,832	11,201	277
Northampton	1,604	6,902	4
Hartford Ct	4,337	18,042	755
Chester	2,853	18,904	24
Perth	20,406	57,043	1,413
Gloucester	3,724	16,206	571
Berwick-upon-Tweed	12,863	36,292	2,238
New Haven Ct	1,104	8,031	277
Coventry	4,573	12,196	1,738
Providence Ri	1,802	5,984	165
The Hague	13,049	39,586	1,196
Newburyport Ma	2,551	7,239	93
Paisley	3,980	18,204	467
Falkirk	5,957	11,285	382
NA	74,575	688,875	31,323

split %>% 
  print_split(publication_place, "publication place")

By publication place
(264 targets)
	test	train	val
works
London	3,518	70,105	1,656
Dublin	993	9,885	424
Edinburgh	583	10,234	268
Boston Ma	276	3,041	118
Oxford	125	1,492	48
Glasgow	270	1,509	79
Philadelphia Pa	189	1,621	63
Paris	83	858	28
Cambridge	107	1,099	52
Newcastle	67	960	28
Bristol	69	761	28
York	64	600	22
Bath	32	534	9
New York Ny	69	597	24
Birmingham	51	512	9
Salisbury	27	412	4
Norwich	25	385	4
Manchester	57	388	16
Exeter	18	334	6
Cork	46	344	10
Belfast	63	297	11
Leeds	24	278	10
Shrewsbury	30	244	8
Aberdeen	41	238	10
Amsterdam	17	125	5
Liverpool	21	212	3
New London Ct	22	172	8
Northampton	26	199	4
Canterbury	14	168	NA
Hartford Ct	38	176	9
Chester	23	184	1
Nottingham	16	174	2
Worcester	17	173	2
Perth	43	98	5
Gloucester	26	134	3
Ipswich	15	142	1
Berwick-upon-Tweed	39	106	10
Warrington	19	126	2
New Haven Ct	22	137	6
Coventry	23	137	2
Sherborne	10	55	1
Reading	13	112	1
Rochester	19	106	3
Providence Ri	31	127	5
Eton	13	77	1
The Hague	42	63	4
Downpatrick	13	117	3
Hull	15	112	1
Newburyport Ma	22	105	3
Worcester Ma	16	105	2
Calcutta	11	86	1
Sheffield	13	96	1
Paisley	20	78	3
Basel	16	42	1
Newport Ri	14	90	2
Falkirk	27	79	2
Charleston Sc	11	81	NA
Leipzig	14	22	NA
Portsmouth Nh	13	71	NA
Bury	7	47	NA
Livorno	6	33	1
Leicester	11	65	NA
Salem Ma	12	68	1
Limerick	14	71	1
Southampton	12	65	1
Tewkesbury	15	67	3
Darlington	12	65	2
Colchester	11	67	1
Carlisle	5	56	NA
Lincoln	6	57	3
Plymouth	11	55	NA
Winchester	13	49	1
Dundee	8	55	NA
Preston	10	57	2
Hereford	11	51	NA
Newark	6	42	NA
Kings Lynn	11	50	NA
Baltimore Md	9	53	NA
Norwich Ct	6	53	1
Taunton	9	50	NA
Wilmington De	12	46	1
Stirling	9	49	NA
Aldershot	NA	1	NA
Derby	10	44	NA
Durham	10	45	1
Stamford	11	46	NA
Wolverhampton	8	45	NA
Chelmsford	10	35	1
Whitehaven	6	46	NA
Exeter Nh	6	45	1
Germantown Pa	6	27	1
Hamburg	12	29	NA
Twickenham	5	31	NA
Halifax	13	34	NA
Newry	11	39	2
Richmond Va	14	36	1
Portsmouth	7	40	3
Carmarthen	11	37	NA
Albany Ny	17	38	NA
Annapolis Md	14	25	NA
Kendal	6	35	NA
Waterford	9	34	NA
Williamsburg Va	5	27	NA
Lewes	10	34	NA
Huddersfield	9	27	NA
Lancaster Pa	10	32	NA
Ludlow	15	33	NA
Berlin	10	18	1
Brussels	7	12	NA
Geneva	7	17	NA
Windsor	11	19	NA
Wrexham	10	29	NA
Dresden	2	12	1
Vienna	8	12	1
Ayr	9	26	1
Brentford	7	25	1
Bury St Edmunds	5	28	NA
Dumfries	5	26	1
Trefeca	10	30	1
Cirencester	7	20	NA
Kingston	5	27	1
Alnwick	8	22	NA
Gainsborough	9	23	NA
Trefriw	5	15	NA
Kilmarnock	10	25	NA
Lustleigh	NA	2	NA
Stockton	5	24	NA
Peterborough	5	19	NA
Stockport	6	20	NA
Maidstone	6	21	NA
Concord Nh	6	21	NA
Guildford	6	18	NA
Wisbech	5	23	NA
Kidderminster	5	18	NA
Richmond	1	10	NA
Sunderland	11	22	NA
Warwick	10	18	1
Doncaster	11	21	NA
New York NY	10	19	NA
Penrith	6	21	NA
Aberhonddu	6	19	NA
Trenton Nj	11	19	NA
Watertown Ma	6	20	NA
Macclesfield	6	19	NA
Margate	5	16	NA
Newport	7	17	NA
Tunbridge Wells	5	12	NA
USA	7	19	NA
Windsor Vt	7	18	NA
Bradford	5	18	NA
Göttingen	6	13	NA
Portland Me	5	18	NA
Bedford	10	16	NA
Frankfurt	2	4	4
Springfield Ma	7	17	NA
Burlington Nj	6	15	NA
Chichester	6	15	NA
Florence	NA	13	NA
Litchfield Ct	5	16	NA
Rouen	NA	11	NA
Lancaster	5	15	NA
Rotterdam	6	12	NA
Trowbridge	NA	15	NA
Blackburn	6	12	1
Knaresborough	5	13	NA
Northampton Ma	13	14	NA
Quebec	6	13	NA
Venice	7	9	NA
Woodbridge NJ	5	14	NA
Amherst Nh	6	13	NA
Copenhagen	6	11	NA
Kelso	6	11	NA
Neuchatel	NA	5	NA
Stafford	NA	13	NA
Armagh	1	12	NA
Bruges	NA	9	NA
Devizes	5	9	NA
Dover Nh	6	11	1
Lausanne	1	7	NA
Leominster Ma	6	11	NA
Marlborough	5	10	NA
Newark Nj	NA	12	NA
Wakefield	5	12	NA
Altenburg	3	5	2
Banbury	5	11	NA
Buckingham	NA	7	NA
Douai	6	8	NA
Dudley	NA	9	NA
Egham	1	8	NA
Falmouth Me	4	11	1
Greenfield Ma	2	11	NA
Henley-on-Thames	5	10	NA
High Wycombe	NA	9	NA
Huntingdon	NA	11	NA
Leiden	NA	5	NA
Londonderry	5	10	NA
Lyon	2	8	NA
Monaghan	5	11	NA
Montrose	14	11	1
Pontefract	NA	11	NA
Ripon	1	11	NA
Sevenoaks	NA	10	NA
St Ives	5	10	NA
Sudbury	5	9	NA
Bennington Vt	1	10	NA
Boston	1	10	NA
Bridgetown	NA	10	NA
Chesterfield	5	8	NA
Congleton	1	9	NA
Deptford	2	10	NA
Dorchester	NA	10	NA
Douglas	NA	7	NA
Evesham	5	10	NA
Gosport	6	10	NA
New Bedford Ma	NA	10	NA
North Shields	5	10	NA
Savannah Ga	NA	10	NA
Spanish Town	5	7	NA
St Andrews	1	8	NA
Stourbridge	5	8	NA
Strabane	5	8	NA
Washington DC	5	10	NA
Weymouth	NA	6	NA
Whitby	7	9	NA
Wigan	7	9	NA
Alexandria Va	NA	9	NA
Basseterre Saint Kitts	NA	8	NA
Burslem	7	9	NA
Drogheda	2	8	NA
Gravesend	NA	9	NA
Haverhill Ma	NA	9	NA
Kilkenny	1	9	NA
Leominster NH	NA	9	NA
Liège	2	5	1
Madeley	NA	9	NA
Nantwich	1	9	NA
New Brunswick Nj	1	9	NA
Walpole Nh	3	7	NA
Antwerp	NA	6	NA
Bolton	7	8	1
Brunswick	NA	1	NA
Carlow	NA	8	NA
Ephrata Pa	5	8	NA
Halle	3	6	NA
Hamilton	5	8	NA
Market Harborough	1	8	NA
Middletown Ct	NA	8	NA
Monmouth	NA	8	NA
Northumberland Pa	NA	6	NA
Port-au-Prince	NA	7	NA
Poughkeepsie Ny	1	5	NA
Strood	NA	8	NA
Tamworth	NA	7	NA
Truru	NA	8	NA
Valletta	NA	7	NA
Windham Ct	5	7	NA
Brookfield Ma	NA	7	NA
Chippenham	NA	7	NA
Dedham Ma	5	7	NA
Dunbar	NA	7	NA
Fishkill Ny	NA	6	NA
Guernesey	NA	7	NA
Hertford	NA	6	NA
Oswestry	NA	6	NA
Padua	NA	3	NA
Rochdale	NA	7	NA
Stroud	NA	6	NA
the Hague	1	5	1
Utrecht	1	7	NA
Augusta Ga	NA	4	NA
Brighton	NA	5	NA
Caernarfon	NA	6	NA
Catskill Ny	1	5	NA
Elizabeth Nj	7	6	NA
Fersfield	NA	2	NA
Grantham	1	6	NA
Lexington Ky	NA	6	NA
Lisbon	NA	6	NA
Loughborough	1	6	NA
Montreal	NA	6	NA
Mullingar	1	6	1
Romsey	NA	6	NA
Scarborough	NA	6	NA
South Shields	1	6	NA
Suffield Ct	NA	6	1
Walsall	NA	4	NA
Wexford	5	6	NA
Woodbridge Nj	1	6	1
Abartawe	NA	5	NA
Abingdon	NA	5	NA
Berkhamsted	NA	5	NA
Bocking	NA	5	1
Bungay	NA	5	1
Chatham	1	5	NA
Chennai	NA	5	NA
Clipstone	7	4	NA
Danbury Ct	3	5	NA
Haarlem	NA	3	NA
Helston	1	5	NA
Keene Nh	1	4	NA
Liege	NA	1	NA
Lymington	NA	4	NA
Machynlleth	NA	5	1
Madrid	NA	2	NA
Medford Ma	NA	5	NA
New Bern Nc	5	5	NA
Peacham Vt	NA	5	NA
Reims	NA	2	NA
Rome	NA	5	NA
Saint-Omer	NA	5	1
Spalding	NA	5	NA
St Omer	NA	5	NA
Strasbourg	1	3	NA
Workington	NA	5	NA
Aylesbury	2	4	NA
Beverley	1	4	NA
Bishopstone	NA	3	NA
Bridport	NA	4	NA
Cambridge Ma	NA	4	NA
Cheltenham	2	2	NA
Cheshire Ct	NA	3	NA
Cheshunt	NA	4	NA
Clonmel	NA	4	NA
Cranbrook	NA	4	NA
Danvers Ma	NA	4	NA
Darmstadt	NA	1	NA
Ennis	NA	3	NA
Galway	NA	4	NA
Gouda	NA	1	NA
Hawick	NA	4	NA
Hillsborough NC	NA	4	NA
Hudson Ny	6	4	NA
Llanymddyfri	1	4	NA
Lyons	NA	3	NA
Newburgh Ny	NA	3	NA
Newmarket	NA	4	NA
Poole	NA	4	NA
Reading Pa	1	4	NA
Retford	NA	4	NA
Salem	NA	4	NA
St Peter Port	NA	4	NA
St Petersburg	NA	4	NA
Uppsala	2	3	NA
Uttoxeter	NA	3	NA
Warren Ri	NA	4	NA
Washington Pa	NA	4	NA
Windsor Ct	1	4	NA
Wotton-under-Edge	1	4	NA
Yverdon	NA	4	NA
Alston	1	3	NA
Ashford	NA	3	NA
Athlone	NA	3	NA
Bampton	NA	3	NA
Bern	1	3	NA
Blandford Va	NA	3	NA
Bridgewater	NA	3	NA
Bridlington	1	3	NA
Carlisle Pa	4	3	NA
Charleston SC	1	3	NA
Chelmsford Ma	NA	3	NA
Chesham	NA	2	NA
Coburg	NA	1	NA
Dereham	NA	3	NA
Dun Laoghaire	NA	2	NA
Greenock	1	3	NA
Hambourg	NA	1	NA
Harrisburg Pa	NA	2	NA
Harrogate	NA	3	NA
Hwlffordd	NA	3	NA
Jena	NA	1	NA
Kingston Ny	NA	2	NA
Launceston	NA	3	NA
Louvain	NA	3	NA
Lucca	NA	3	NA
Malton	NA	3	NA
Newfield Ct	NA	3	NA
Parma	3	3	NA
Peterhead	NA	3	NA
Ramsgate	NA	2	NA
Roseau Dominica	NA	3	NA
Rye	NA	3	NA
Schenectady Ny	1	3	NA
Stockholm	NA	3	NA
Stratford-upon-Avon	NA	3	NA
Tiverton	NA	3	NA
Toulouse	NA	2	NA
Treffynnon	NA	3	NA
Västerås	NA	2	NA
Adpar	NA	2	NA
America	NA	2	NA
Andover Ma	NA	2	NA
Avignon	NA	1	NA
Banff	NA	2	NA
Barnard Castle	NA	2	NA
Berne	1	1	NA
Bombay	NA	2	NA
Bontfaen	NA	2	NA
Boston England	NA	2	NA
Bouillon	NA	1	NA
Brattleboro Vt	NA	2	NA
Bremen	NA	2	NA
Bridgnorth	NA	2	NA
Burton	NA	2	NA
Cape Town	NA	2	NA
Castine Me	NA	2	NA
Chatham Nj	NA	2	NA
Chepstow	NA	2	NA
Chertsey	NA	2	NA
Cincinnati Oh	NA	2	NA
Concord Ma	NA	2	NA
Cooperstown Ny	NA	2	NA
Crewkerne	NA	2	NA
Dover De	NA	2	NA
Dungannon	NA	2	NA
Dunkirk	NA	1	NA
Edenton Nc	NA	2	NA
Enniskillen	NA	2	NA
Erlangen	NA	2	NA
Flensburg	NA	1	NA
Fredericktown Md	NA	2	NA
Fredericton	NA	2	NA
Frome	NA	2	NA
Georgetown Washington DC	NA	2	NA
Great Marlow	NA	2	NA
Haddington	NA	2	NA
Halifax Nc	NA	2	NA
Hannover Nh	NA	2	NA
Hemel Hempstead	NA	2	NA
Honiton	NA	2	NA
Horncastle	NA	2	NA
Horsham	NA	2	NA
Howden	NA	2	NA
Inverness	2	2	NA
Mannheim	NA	2	NA
Melton Mowbray	NA	2	NA
Middlewich	NA	2	NA
Montargis	NA	1	NA
Münster	NA	2	NA
Nancy	NA	2	NA
Newbury	1	2	1
Niagara	NA	2	NA
Norfolk Va	NA	2	NA
Northallerton	NA	2	NA
Nürnberg	NA	1	NA
Petersfield	NA	2	NA
Pisa	NA	2	NA
Potsdam	NA	1	NA
Prescot	NA	2	NA
Putney Vt	NA	2	NA
Rheims	NA	2	NA
Rome Ny	NA	2	NA
Shepton Mallet	NA	2	NA
South Molton	NA	2	NA
St Albans	NA	2	NA
St George	NA	2	NA
St Helier	NA	2	NA
Stonington Ct	NA	2	NA
Stowmarket	NA	2	NA
Szczecin	NA	1	NA
Troy Ny	NA	2	NA
Vergennes Vt	NA	2	NA
Watford	NA	2	NA
Wellingborough	NA	2	NA
Winterthur	NA	2	NA
York Pa	NA	2	NA
Zurich	NA	1	NA
Abbeville	NA	1	NA
Abermaw	NA	1	NA
Aberystwyth	NA	1	NA
Alcester	NA	1	NA
Ampthill	NA	1	NA
Arezzo	NA	1	NA
Ashby-de-la-Zouch	NA	1	NA
Atherstone	NA	1	NA
Bala	NA	1	NA
Balfron	NA	1	NA
Ballymena	NA	1	NA
Barnstaple	NA	1	NA
Barton-upon-Humber	NA	1	NA
Basingstoke	NA	1	NA
Bayreuth	NA	1	NA
Bedale	NA	1	NA
Beloeil	NA	1	NA
Besançon	NA	1	NA
Birr	NA	1	NA
Birstall	NA	1	NA
Bishop Castle	NA	1	NA
Bodedern	NA	1	NA
Bordeaux	NA	1	NA
Boulogne-sur-Mer	NA	1	NA
Brearley Hall	NA	1	1
Brigg	NA	1	NA
Budapest	NA	1	NA
Burlington NJ	NA	1	NA
Burnley	NA	1	NA
Caen	NA	1	NA
Caerdydd	NA	1	NA
Caerfyrddin	NA	1	NA
Caergybi	NA	1	NA
Calais	NA	1	NA
Carrickfergus	NA	1	NA
Castlebar	NA	1	NA
Castleford	NA	1	NA
Cavan	NA	1	NA
Chambersburg Pa	NA	1	NA
Ciutadella	NA	1	NA
Coimbra	NA	1	NA
Coleraine	NA	1	NA
Coxheath	NA	1	NA
Crieff	NA	1	NA
Cupar	NA	1	NA
Dampierre-sur-Boutonne	1	1	NA
Dartford	NA	1	NA
Dartmouth	NA	1	NA
Dessau	NA	1	NA
Dordrecht	NA	1	NA
Dover	NA	1	NA
Dunfermline	NA	1	NA
Dunkalk	NA	1	NA
Dunkeld	NA	1	NA
Duns	NA	1	NA
Düsseldorf	NA	1	NA
East Grinstead	NA	1	NA
Easton Md	NA	1	NA
Elie	NA	1	NA
Ellesmere	NA	1	NA
Essex	NA	1	NA
Faringdon	NA	1	NA
Featherstone	NA	1	NA
Fermoy	NA	1	NA
Fleet	NA	1	NA
Geneva Ny	NA	1	NA
Georgetown Washington Sc	NA	1	NA
Ghent	NA	1	NA
Gillingham	NA	1	NA
Gilmanton Nh	NA	1	NA
Goshen Ny	NA	1	NA
Gothenburg	NA	1	NA
Halesworth	NA	1	NA
Hallowell Me	NA	1	NA
Hanau	NA	1	NA
Hannover	NA	1	NA
Harbor Ny	NA	1	NA
Haverhill Nh	NA	1	NA
Hexham	NA	1	NA
Hildburghausen	NA	1	NA
Hinckley	NA	1	NA
Hitchin	NA	1	NA
Holt	NA	1	NA
Houghton Park	NA	1	NA
Hungerford	NA	1	NA
Karlskrona	NA	1	NA
Karlsruhe	NA	1	NA
Keene	NA	1	NA
Kenilworth	NA	1	NA
Keswick	NA	1	NA
Kinsale	NA	1	NA
Kirkbride	NA	1	NA
Knoxville Tn	NA	1	NA
Knutsford	NA	1	NA
Lanark	NA	1	NA
Leek	NA	1	NA
Lisburn	NA	1	NA
Long Buckby	NA	1	NA
Lugano	NA	1	NA
Lund	NA	1	NA
Mainz	NA	1	NA
Malda	NA	1	NA
Mantua	NA	1	NA
Marseilles	NA	1	NA
Middelburg	NA	1	NA
Milan	1	1	NA
Milborne Port	NA	1	NA
Môle-Saint-Nicolas	NA	1	NA
Monmouth Nj	NA	1	NA
Morristown Nj	NA	1	NA
Moscow	NA	1	NA
Naas	NA	1	NA
Nantes	NA	1	NA
Naples	1	1	NA
Nashville Tn	NA	1	NA
Nassau	NA	1	NA
Newbury Vt	NA	1	1
Nice	NA	1	NA
Nordhausen	NA	1	NA
Norfolk	NA	1	NA
Norristown Pa	NA	1	NA
Norrköping	NA	1	NA
Northwich	NA	1	NA
Nuremberg	NA	1	NA
Ormskirk	NA	1	NA
Osnabrück	NA	1	NA
Pattingham	NA	1	1
Pembroke	NA	1	NA
Perugia	NA	1	NA
Plymouth Ma	NA	1	NA
Pondicherry	NA	1	NA
Poughkeepsie NY	NA	1	NA
Poulton-le-Fylde	NA	1	NA
Princeton Nj	NA	1	NA
Providence RI	NA	1	NA
Raleigh Nc	NA	1	NA
Ramsey	NA	1	NA
Regensburg	NA	1	NA
Rhaglan	NA	1	NA
Saffron Walden	NA	1	NA
Saint Helier	NA	1	NA
Saint-Germain-en-Laye	NA	1	NA
Salisbury Nc	NA	1	NA
Sandhurst	NA	1	NA
Sandwich	NA	1	NA
Sanquhar	NA	1	NA
Schleswig	NA	1	NA
Sedbergh	NA	1	NA
Selby	NA	1	NA
Shepherdstown Wv	NA	1	NA
Siena	NA	1	NA
Sligo	1	1	NA
Southampton Pa	NA	1	NA
St Austell	NA	1	NA
St Eustatius	NA	1	NA
St Neots	NA	1	NA
Stoke-on-Trent	NA	1	NA
Stokesley	NA	1	NA
Stuttgart	NA	1	NA
Sulechow	NA	1	NA
Tetbury	NA	1	NA
Thirsk	NA	1	NA
Torrington	NA	1	NA
Totnes	NA	1	NA
Trenton	NA	1	NA
Trevoux	1	1	NA
Tuscany	NA	1	NA
Ulverston	NA	1	NA
Valencia	NA	1	NA
Verona	1	1	NA
Walpole NH	NA	1	NA
Wargrave	NA	1	NA
Warminster	NA	1	NA
Waterford Ny	NA	1	NA
Wells	NA	1	NA
Whitburn	1	1	NA
Whitchurch	1	1	NA
Wiscasset Me	NA	1	NA
Wittenberg	NA	1	NA
Yarm	NA	1	NA
Yeovil	NA	1	NA
Youghal	NA	1	NA
NA	187	1,691	58
documents
London	16,294	111,914	4,562
Dublin	2,910	14,286	879
Edinburgh	1,746	12,887	489
Boston Ma	396	3,387	153
Oxford	279	2,238	114
Glasgow	747	2,080	127
Philadelphia Pa	283	1,966	78
Paris	224	1,730	45
Cambridge	187	1,507	73
Newcastle	93	1,144	30
Bristol	153	1,008	39
York	106	751	30
Bath	48	748	13
New York Ny	104	696	28
Birmingham	86	641	12
Salisbury	41	461	5
Norwich	27	453	4
Manchester	68	448	16
Exeter	24	387	6
Cork	57	383	10
Belfast	89	335	13
Leeds	30	333	13
Shrewsbury	40	307	9
Aberdeen	61	285	19
Amsterdam	71	279	7
Liverpool	22	252	5
New London Ct	23	222	8
Northampton	27	213	4
Canterbury	21	212	NA
Hartford Ct	51	211	10
Chester	25	205	1
Nottingham	23	192	2
Worcester	19	189	2
Perth	88	175	6
Gloucester	32	161	3
Ipswich	16	156	1
Berwick-upon-Tweed	59	154	11
Warrington	27	152	2
New Haven Ct	24	151	6
Coventry	30	150	6
Sherborne	10	138	4
Reading	14	137	2
Rochester	29	132	4
Providence Ri	31	129	5
Eton	27	128	1
The Hague	67	122	6
Downpatrick	13	120	3
Hull	17	116	1
Newburyport Ma	24	108	3
Worcester Ma	17	108	2
Calcutta	14	106	1
Sheffield	14	101	1
Paisley	20	97	3
Basel	76	96	1
Newport Ri	14	91	2
Falkirk	35	88	2
Charleston Sc	13	83	NA
Leipzig	26	79	NA
Portsmouth Nh	13	78	NA
Bury	10	77	NA
Livorno	15	76	4
Leicester	11	73	NA
Salem Ma	18	72	1
Limerick	14	71	1
Southampton	19	70	1
Tewkesbury	15	70	3
Darlington	13	69	2
Colchester	12	68	1
Carlisle	5	65	NA
Lincoln	6	61	3
Plymouth	11	61	NA
Winchester	13	61	1
Dundee	11	60	NA
Preston	10	58	2
Hereford	12	57	NA
Newark	7	57	NA
Kings Lynn	13	55	NA
Baltimore Md	10	54	NA
Norwich Ct	7	53	1
Taunton	10	53	NA
Wilmington De	12	53	1
Stirling	9	50	NA
Aldershot	NA	49	NA
Derby	11	49	NA
Durham	10	49	1
Stamford	11	49	NA
Wolverhampton	10	49	NA
Chelmsford	11	48	1
Whitehaven	6	48	NA
Exeter Nh	6	46	1
Germantown Pa	8	44	1
Hamburg	17	44	NA
Twickenham	6	43	NA
Halifax	13	42	NA
Newry	14	41	2
Richmond Va	15	41	1
Portsmouth	7	40	3
Carmarthen	11	39	NA
Albany Ny	19	38	NA
Annapolis Md	15	37	NA
Kendal	6	37	NA
Waterford	10	37	NA
Williamsburg Va	6	37	NA
Lewes	10	36	NA
Huddersfield	9	35	NA
Lancaster Pa	11	35	NA
Ludlow	16	35	NA
Berlin	15	33	1
Brussels	9	33	NA
Geneva	36	33	NA
Windsor	12	32	NA
Wrexham	10	32	NA
Dresden	2	31	1
Vienna	13	31	2
Ayr	9	30	1
Brentford	10	30	1
Bury St Edmunds	5	30	NA
Dumfries	5	30	1
Trefeca	11	30	2
Cirencester	7	29	NA
Kingston	9	29	4
Alnwick	8	28	NA
Gainsborough	10	28	NA
Trefriw	5	28	NA
Kilmarnock	11	27	NA
Lustleigh	NA	27	NA
Stockton	5	26	NA
Peterborough	6	25	NA
Stockport	6	25	NA
Maidstone	7	24	NA
Concord Nh	6	23	NA
Guildford	6	23	NA
Wisbech	6	23	NA
Kidderminster	6	22	NA
Richmond	1	22	NA
Sunderland	13	22	NA
Warwick	10	22	1
Doncaster	12	21	NA
New York NY	11	21	NA
Penrith	6	21	NA
Aberhonddu	7	20	NA
Trenton Nj	11	20	NA
Watertown Ma	6	20	NA
Macclesfield	6	19	NA
Margate	6	19	NA
Newport	12	19	NA
Tunbridge Wells	7	19	NA
USA	7	19	NA
Windsor Vt	7	19	NA
Bradford	5	18	NA
Göttingen	6	18	NA
Portland Me	5	18	NA
Bedford	10	17	NA
Frankfurt	3	17	4
Springfield Ma	8	17	NA
Burlington Nj	6	16	NA
Chichester	9	16	NA
Florence	NA	16	NA
Litchfield Ct	5	16	NA
Rouen	NA	16	NA
Lancaster	5	15	NA
Rotterdam	6	15	NA
Trowbridge	NA	15	NA
Blackburn	6	14	1
Knaresborough	6	14	NA
Northampton Ma	14	14	NA
Quebec	9	14	NA
Venice	16	14	NA
Woodbridge NJ	6	14	NA
Amherst Nh	6	13	NA
Copenhagen	8	13	NA
Kelso	6	13	NA
Neuchatel	NA	13	NA
Stafford	NA	13	NA
Armagh	1	12	NA
Bruges	NA	12	NA
Devizes	5	12	NA
Dover Nh	6	12	1
Lausanne	1	12	NA
Leominster Ma	6	12	NA
Marlborough	5	12	NA
Newark Nj	NA	12	NA
Wakefield	7	12	NA
Altenburg	3	11	8
Banbury	5	11	NA
Buckingham	NA	11	NA
Douai	6	11	NA
Dudley	NA	11	NA
Egham	1	11	NA
Falmouth Me	4	11	1
Greenfield Ma	2	11	NA
Henley-on-Thames	7	11	NA
High Wycombe	NA	11	NA
Huntingdon	NA	11	NA
Leiden	NA	11	NA
Londonderry	5	11	NA
Lyon	6	11	NA
Monaghan	5	11	NA
Montrose	29	11	3
Pontefract	NA	11	NA
Ripon	1	11	NA
Sevenoaks	NA	11	NA
St Ives	5	11	NA
Sudbury	5	11	NA
Bennington Vt	1	10	NA
Boston	2	10	NA
Bridgetown	NA	10	NA
Chesterfield	5	10	NA
Congleton	1	10	NA
Deptford	2	10	NA
Dorchester	NA	10	NA
Douglas	NA	10	NA
Evesham	7	10	NA
Gosport	6	10	NA
New Bedford Ma	NA	10	NA
North Shields	7	10	NA
Savannah Ga	NA	10	NA
Spanish Town	5	10	NA
St Andrews	1	10	NA
Stourbridge	5	10	NA
Strabane	5	10	NA
Washington DC	5	10	NA
Weymouth	NA	10	NA
Whitby	7	10	NA
Wigan	7	10	NA
Alexandria Va	NA	9	NA
Basseterre Saint Kitts	NA	9	NA
Burslem	8	9	NA
Drogheda	2	9	NA
Gravesend	NA	9	NA
Haverhill Ma	NA	9	NA
Kilkenny	2	9	NA
Leominster NH	NA	9	NA
Liège	2	9	1
Madeley	NA	9	NA
Nantwich	1	9	NA
New Brunswick Nj	1	9	NA
Walpole Nh	3	9	NA
Antwerp	NA	8	NA
Bolton	8	8	1
Brunswick	NA	8	NA
Carlow	NA	8	NA
Ephrata Pa	5	8	NA
Halle	3	8	NA
Hamilton	5	8	NA
Market Harborough	1	8	NA
Middletown Ct	NA	8	NA
Monmouth	NA	8	NA
Northumberland Pa	NA	8	NA
Port-au-Prince	NA	8	NA
Poughkeepsie Ny	2	8	NA
Strood	NA	8	NA
Tamworth	NA	8	NA
Truru	NA	8	NA
Valletta	NA	8	NA
Windham Ct	5	8	NA
Brookfield Ma	NA	7	NA
Chippenham	NA	7	NA
Dedham Ma	5	7	NA
Dunbar	NA	7	NA
Fishkill Ny	NA	7	NA
Guernesey	NA	7	NA
Hertford	NA	7	NA
Oswestry	NA	7	NA
Padua	NA	7	NA
Rochdale	NA	7	NA
Stroud	NA	7	NA
the Hague	1	7	1
Utrecht	1	7	NA
Augusta Ga	NA	6	NA
Brighton	NA	6	NA
Caernarfon	NA	6	NA
Catskill Ny	1	6	NA
Elizabeth Nj	7	6	NA
Fersfield	NA	6	NA
Grantham	1	6	NA
Lexington Ky	NA	6	NA
Lisbon	NA	6	NA
Loughborough	1	6	NA
Montreal	NA	6	NA
Mullingar	1	6	1
Romsey	NA	6	NA
Scarborough	NA	6	NA
South Shields	1	6	NA
Suffield Ct	NA	6	1
Walsall	NA	6	NA
Wexford	6	6	NA
Woodbridge Nj	1	6	1
Abartawe	NA	5	NA
Abingdon	NA	5	NA
Berkhamsted	NA	5	NA
Bocking	NA	5	1
Bungay	NA	5	2
Chatham	1	5	NA
Chennai	NA	5	NA
Clipstone	9	5	NA
Danbury Ct	3	5	NA
Haarlem	NA	5	NA
Helston	1	5	NA
Keene Nh	1	5	NA
Liege	NA	5	NA
Lymington	NA	5	NA
Machynlleth	NA	5	1
Madrid	NA	5	NA
Medford Ma	NA	5	NA
New Bern Nc	6	5	NA
Peacham Vt	NA	5	NA
Reims	NA	5	NA
Rome	NA	5	NA
Saint-Omer	NA	5	2
Spalding	NA	5	NA
St Omer	NA	5	NA
Strasbourg	2	5	NA
Workington	NA	5	NA
Aylesbury	2	4	NA
Beverley	1	4	NA
Bishopstone	NA	4	NA
Bridport	NA	4	NA
Cambridge Ma	NA	4	NA
Cheltenham	3	4	NA
Cheshire Ct	NA	4	NA
Cheshunt	NA	4	NA
Clonmel	NA	4	NA
Cranbrook	NA	4	NA
Danvers Ma	NA	4	NA
Darmstadt	NA	4	NA
Ennis	NA	4	NA
Galway	NA	4	NA
Gouda	NA	4	NA
Hawick	NA	4	NA
Hillsborough NC	NA	4	NA
Hudson Ny	6	4	NA
Llanymddyfri	2	4	NA
Lyons	NA	4	NA
Newburgh Ny	NA	4	NA
Newmarket	NA	4	NA
Poole	NA	4	NA
Reading Pa	1	4	NA
Retford	NA	4	NA
Salem	NA	4	NA
St Peter Port	NA	4	NA
St Petersburg	NA	4	NA
Uppsala	2	4	NA
Uttoxeter	NA	4	NA
Warren Ri	NA	4	NA
Washington Pa	NA	4	NA
Windsor Ct	1	4	NA
Wotton-under-Edge	1	4	NA
Yverdon	NA	4	NA
Alston	1	3	NA
Ashford	NA	3	NA
Athlone	NA	3	NA
Bampton	NA	3	NA
Bern	1	3	NA
Blandford Va	NA	3	NA
Bridgewater	NA	3	NA
Bridlington	1	3	NA
Carlisle Pa	4	3	NA
Charleston SC	1	3	NA
Chelmsford Ma	NA	3	NA
Chesham	NA	3	NA
Coburg	NA	3	NA
Dereham	NA	3	NA
Dun Laoghaire	NA	3	NA
Greenock	1	3	NA
Hambourg	NA	3	NA
Harrisburg Pa	NA	3	NA
Harrogate	NA	3	NA
Hwlffordd	NA	3	NA
Jena	NA	3	NA
Kingston Ny	NA	3	NA
Launceston	NA	3	NA
Louvain	NA	3	NA
Lucca	NA	3	NA
Malton	NA	3	NA
Newfield Ct	NA	3	NA
Parma	3	3	NA
Peterhead	NA	3	NA
Ramsgate	NA	3	NA
Roseau Dominica	NA	3	NA
Rye	NA	3	NA
Schenectady Ny	1	3	NA
Stockholm	NA	3	NA
Stratford-upon-Avon	NA	3	NA
Tiverton	NA	3	NA
Toulouse	NA	3	NA
Treffynnon	NA	3	NA
Västerås	NA	3	NA
Adpar	NA	2	NA
America	NA	2	NA
Andover Ma	NA	2	NA
Avignon	NA	2	NA
Banff	NA	2	NA
Barnard Castle	NA	2	NA
Berne	2	2	NA
Bombay	NA	2	NA
Bontfaen	NA	2	NA
Boston England	NA	2	NA
Bouillon	NA	2	NA
Brattleboro Vt	NA	2	NA
Bremen	NA	2	NA
Bridgnorth	NA	2	NA
Burton	NA	2	NA
Cape Town	NA	2	NA
Castine Me	NA	2	NA
Chatham Nj	NA	2	NA
Chepstow	NA	2	NA
Chertsey	NA	2	NA
Cincinnati Oh	NA	2	NA
Concord Ma	NA	2	NA
Cooperstown Ny	NA	2	NA
Crewkerne	NA	2	NA
Dover De	NA	2	NA
Dungannon	NA	2	NA
Dunkirk	NA	2	NA
Edenton Nc	NA	2	NA
Enniskillen	NA	2	NA
Erlangen	NA	2	NA
Flensburg	NA	2	NA
Fredericktown Md	NA	2	NA
Fredericton	NA	2	NA
Frome	NA	2	NA
Georgetown Washington DC	NA	2	NA
Great Marlow	NA	2	NA
Haddington	NA	2	NA
Halifax Nc	NA	2	NA
Hannover Nh	NA	2	NA
Hemel Hempstead	NA	2	NA
Honiton	NA	2	NA
Horncastle	NA	2	NA
Horsham	NA	2	NA
Howden	NA	2	NA
Inverness	2	2	NA
Mannheim	NA	2	NA
Melton Mowbray	NA	2	NA
Middlewich	NA	2	NA
Montargis	NA	2	NA
Münster	NA	2	NA
Nancy	NA	2	NA
Newbury	2	2	1
Niagara	NA	2	NA
Norfolk Va	NA	2	NA
Northallerton	NA	2	NA
Nürnberg	NA	2	NA
Petersfield	NA	2	NA
Pisa	NA	2	NA
Potsdam	NA	2	NA
Prescot	NA	2	NA
Putney Vt	NA	2	NA
Rheims	NA	2	NA
Rome Ny	NA	2	NA
Shepton Mallet	NA	2	NA
South Molton	NA	2	NA
St Albans	NA	2	NA
St George	NA	2	NA
St Helier	NA	2	NA
Stonington Ct	NA	2	NA
Stowmarket	NA	2	NA
Szczecin	NA	2	NA
Troy Ny	NA	2	NA
Vergennes Vt	NA	2	NA
Watford	NA	2	NA
Wellingborough	NA	2	NA
Winterthur	NA	2	NA
York Pa	NA	2	NA
Zurich	NA	2	NA
Abbeville	NA	1	NA
Abermaw	NA	1	NA
Aberystwyth	NA	1	NA
Alcester	NA	1	NA
Ampthill	NA	1	NA
Arezzo	NA	1	NA
Ashby-de-la-Zouch	NA	1	NA
Atherstone	NA	1	NA
Bala	NA	1	NA
Balfron	NA	1	NA
Ballymena	NA	1	NA
Barnstaple	NA	1	NA
Barton-upon-Humber	NA	1	NA
Basingstoke	NA	1	NA
Bayreuth	NA	1	NA
Bedale	NA	1	NA
Beloeil	NA	1	NA
Besançon	NA	1	NA
Birr	NA	1	NA
Birstall	NA	1	NA
Bishop Castle	NA	1	NA
Bodedern	NA	1	NA
Bordeaux	NA	1	NA
Boulogne-sur-Mer	NA	1	NA
Brearley Hall	NA	1	1
Brigg	NA	1	NA
Budapest	NA	1	NA
Burlington NJ	NA	1	NA
Burnley	NA	1	NA
Caen	NA	1	NA
Caerdydd	NA	1	NA
Caerfyrddin	NA	1	NA
Caergybi	NA	1	NA
Calais	NA	1	NA
Carrickfergus	NA	1	NA
Castlebar	NA	1	NA
Castleford	NA	1	NA
Cavan	NA	1	NA
Chambersburg Pa	NA	1	NA
Ciutadella	NA	1	NA
Coimbra	NA	1	NA
Coleraine	NA	1	NA
Coxheath	NA	1	NA
Crieff	NA	1	NA
Cupar	NA	1	NA
Dampierre-sur-Boutonne	2	1	NA
Dartford	NA	1	NA
Dartmouth	NA	1	NA
Dessau	NA	1	NA
Dordrecht	NA	1	NA
Dover	NA	1	NA
Dunfermline	NA	1	NA
Dunkalk	NA	1	NA
Dunkeld	NA	1	NA
Duns	NA	1	NA
Düsseldorf	NA	1	NA
East Grinstead	NA	1	NA
Easton Md	NA	1	NA
Elie	NA	1	NA
Ellesmere	NA	1	NA
Essex	NA	1	NA
Faringdon	NA	1	NA
Featherstone	NA	1	NA
Fermoy	NA	1	NA
Fleet	NA	1	NA
Geneva Ny	NA	1	NA
Georgetown Washington Sc	NA	1	NA
Ghent	NA	1	NA
Gillingham	NA	1	NA
Gilmanton Nh	NA	1	NA
Goshen Ny	NA	1	NA
Gothenburg	NA	1	NA
Halesworth	NA	1	NA
Hallowell Me	NA	1	NA
Hanau	NA	1	NA
Hannover	NA	1	NA
Harbor Ny	NA	1	NA
Haverhill Nh	NA	1	NA
Hexham	NA	1	NA
Hildburghausen	NA	1	NA
Hinckley	NA	1	NA
Hitchin	NA	1	NA
Holt	NA	1	NA
Houghton Park	NA	1	NA
Hungerford	NA	1	NA
Karlskrona	NA	1	NA
Karlsruhe	NA	1	NA
Keene	NA	1	NA
Kenilworth	NA	1	NA
Keswick	NA	1	NA
Kinsale	NA	1	NA
Kirkbride	NA	1	NA
Knoxville Tn	NA	1	NA
Knutsford	NA	1	NA
Lanark	NA	1	NA
Leek	NA	1	NA
Lisburn	NA	1	NA
Long Buckby	NA	1	NA
Lugano	NA	1	NA
Lund	NA	1	NA
Mainz	NA	1	NA
Malda	NA	1	NA
Mantua	NA	1	NA
Marseilles	NA	1	NA
Middelburg	NA	1	NA
Milan	2	1	NA
Milborne Port	NA	1	NA
Môle-Saint-Nicolas	NA	1	NA
Monmouth Nj	NA	1	NA
Morristown Nj	NA	1	NA
Moscow	NA	1	NA
Naas	NA	1	NA
Nantes	NA	1	NA
Naples	1	1	NA
Nashville Tn	NA	1	NA
Nassau	NA	1	NA
Newbury Vt	NA	1	1
Nice	NA	1	NA
Nordhausen	NA	1	NA
Norfolk	NA	1	NA
Norristown Pa	NA	1	NA
Norrköping	NA	1	NA
Northwich	NA	1	NA
Nuremberg	NA	1	NA
Ormskirk	NA	1	NA
Osnabrück	NA	1	NA
Pattingham	NA	1	1
Pembroke	NA	1	NA
Perugia	NA	1	NA
Plymouth Ma	NA	1	NA
Pondicherry	NA	1	NA
Poughkeepsie NY	NA	1	NA
Poulton-le-Fylde	NA	1	NA
Princeton Nj	NA	1	NA
Providence RI	NA	1	NA
Raleigh Nc	NA	1	NA
Ramsey	NA	1	NA
Regensburg	NA	1	NA
Rhaglan	NA	1	NA
Saffron Walden	NA	1	NA
Saint Helier	NA	1	NA
Saint-Germain-en-Laye	NA	1	NA
Salisbury Nc	NA	1	NA
Sandhurst	NA	1	NA
Sandwich	NA	1	NA
Sanquhar	NA	1	NA
Schleswig	NA	1	NA
Sedbergh	NA	1	NA
Selby	NA	1	NA
Shepherdstown Wv	NA	1	NA
Siena	NA	1	NA
Sligo	1	1	NA
Southampton Pa	NA	1	NA
St Austell	NA	1	NA
St Eustatius	NA	1	NA
St Neots	NA	1	NA
Stoke-on-Trent	NA	1	NA
Stokesley	NA	1	NA
Stuttgart	NA	1	NA
Sulechow	NA	1	NA
Tetbury	NA	1	NA
Thirsk	NA	1	NA
Torrington	NA	1	NA
Totnes	NA	1	NA
Trenton	NA	1	NA
Trevoux	6	1	NA
Tuscany	NA	1	NA
Ulverston	NA	1	NA
Valencia	NA	1	NA
Verona	2	1	NA
Walpole NH	NA	1	NA
Wargrave	NA	1	NA
Warminster	NA	1	NA
Waterford Ny	NA	1	NA
Wells	NA	1	NA
Whitburn	1	1	NA
Whitchurch	1	1	NA
Wiscasset Me	NA	1	NA
Wittenberg	NA	1	NA
Yarm	NA	1	NA
Yeovil	NA	1	NA
Youghal	NA	1	NA
NA	328	2,557	105
pages
London	4,401,845	16,671,741	1,051,211
Dublin	680,689	1,932,516	186,410
Edinburgh	440,701	1,434,837	106,727
Boston Ma	40,900	223,443	12,197
Oxford	83,460	403,804	32,461
Glasgow	172,862	335,340	28,058
Philadelphia Pa	52,552	251,577	10,792
Paris	67,345	470,499	9,241
Cambridge	40,194	223,622	13,867
Newcastle	14,381	93,143	2,588
Bristol	10,748	97,172	2,968
York	20,242	93,607	4,144
Bath	5,953	113,802	1,114
New York Ny	21,011	87,543	3,340
Birmingham	19,295	94,109	1,948
Salisbury	6,201	23,115	19
Norwich	2,731	40,373	324
Manchester	7,501	41,732	585
Exeter	3,019	38,360	343
Cork	8,839	43,061	1,608
Belfast	12,861	30,352	1,035
Leeds	4,570	36,159	2,515
Shrewsbury	6,581	46,468	1,660
Aberdeen	10,487	39,286	6,111
Amsterdam	27,101	84,430	1,529
Liverpool	4,314	33,569	896
New London Ct	1,832	11,201	277
Northampton	1,604	6,902	4
Canterbury	4,162	25,371	NA
Hartford Ct	4,337	18,042	755
Chester	2,853	18,904	24
Nottingham	2,723	12,058	74
Worcester	604	8,498	22
Perth	20,406	57,043	1,413
Gloucester	3,724	16,206	571
Ipswich	1,168	9,790	17
Berwick-upon-Tweed	12,863	36,292	2,238
Warrington	5,962	25,387	340
New Haven Ct	1,104	8,031	277
Coventry	4,573	12,196	1,738
Sherborne	1,243	54,914	1,115
Reading	832	20,729	110
Rochester	2,571	7,116	4
Providence Ri	1,802	5,984	165
Eton	4,928	24,089	72
The Hague	13,049	39,586	1,196
Downpatrick	18	197	8
Hull	3,235	8,267	21
Newburyport Ma	2,551	7,239	93
Worcester Ma	1,781	10,134	60
Calcutta	2,556	22,248	197
Sheffield	445	9,044	138
Paisley	3,980	18,204	467
Basel	31,800	32,875	454
Newport Ri	1,425	5,482	16
Falkirk	5,957	11,285	382
Charleston Sc	570	5,093	NA
Leipzig	12,919	44,339	NA
Portsmouth Nh	882	3,940	NA
Bury	708	22,733	NA
Livorno	5,973	29,061	1,455
Leicester	737	7,471	NA
Salem Ma	3,341	6,027	1
Limerick	575	3,781	65
Southampton	1,741	6,600	1
Tewkesbury	192	2,410	129
Darlington	619	2,367	6
Colchester	682	3,274	36
Carlisle	1,062	9,878	NA
Lincoln	336	2,094	61
Plymouth	592	3,903	NA
Winchester	1,065	11,798	42
Dundee	883	10,705	NA
Preston	971	3,643	298
Hereford	1,198	3,759	NA
Newark	1,135	8,233	NA
Kings Lynn	1,661	5,302	NA
Baltimore Md	679	6,328	NA
Norwich Ct	494	3,013	41
Taunton	1,254	3,967	NA
Wilmington De	2,581	5,650	323
Stirling	196	1,023	NA
Aldershot	NA	28,656	NA
Derby	501	2,613	NA
Durham	519	2,397	218
Stamford	294	2,633	NA
Wolverhampton	1,325	5,186	NA
Chelmsford	700	6,035	23
Whitehaven	264	7,233	NA
Exeter Nh	184	1,816	148
Germantown Pa	1,998	12,628	98
Hamburg	4,752	13,046	NA
Twickenham	498	4,844	NA
Halifax	1,310	5,066	NA
Newry	1,136	2,938	64
Richmond Va	796	3,844	16
Portsmouth	698	2,708	417
Carmarthen	1,258	3,018	NA
Albany Ny	3,559	4,094	NA
Annapolis Md	2,494	3,011	NA
Kendal	541	3,245	NA
Waterford	1,679	3,823	NA
Williamsburg Va	199	5,309	NA
Lewes	310	1,918	NA
Huddersfield	803	3,196	NA
Lancaster Pa	1,189	2,168	NA
Ludlow	792	2,992	NA
Berlin	3,404	7,536	162
Brussels	1,240	5,744	NA
Geneva	10,522	9,399	NA
Windsor	1,592	5,549	NA
Wrexham	680	3,317	NA
Dresden	845	10,355	303
Vienna	4,937	8,508	183
Ayr	2,013	6,343	327
Brentford	804	3,463	12
Bury St Edmunds	209	714	NA
Dumfries	490	4,130	323
Trefeca	1,876	3,121	73
Cirencester	411	4,527	NA
Kingston	1,753	2,905	1,468
Alnwick	703	797	NA
Gainsborough	1,821	3,570	NA
Trefriw	40	264	NA
Kilmarnock	2,110	4,347	NA
Lustleigh	NA	13,776	NA
Stockton	313	3,251	NA
Peterborough	352	871	NA
Stockport	101	1,734	NA
Maidstone	703	560	NA
Concord Nh	168	640	NA
Guildford	363	871	NA
Wisbech	219	1,168	NA
Kidderminster	987	2,971	NA
Richmond	370	2,263	NA
Sunderland	1,411	2,130	NA
Warwick	806	1,219	167
Doncaster	614	1,311	NA
New York NY	532	1,632	NA
Penrith	59	1,091	NA
Aberhonddu	666	1,210	NA
Trenton Nj	2,662	2,289	NA
Watertown Ma	80	92	NA
Macclesfield	2,769	2,277	NA
Margate	272	1,194	NA
Newport	932	2,705	NA
Tunbridge Wells	509	3,645	NA
USA	329	501	NA
Windsor Vt	576	773	NA
Bradford	349	681	NA
Göttingen	850	4,819	NA
Portland Me	199	609	NA
Bedford	214	1,082	NA
Frankfurt	1,126	8,821	1,183
Springfield Ma	1,016	1,041	NA
Burlington Nj	1,176	1,521	NA
Chichester	627	1,471	NA
Florence	NA	2,941	NA
Litchfield Ct	641	924	NA
Rouen	NA	4,796	NA
Lancaster	151	750	NA
Rotterdam	1,931	3,836	NA
Trowbridge	NA	1,299	NA
Blackburn	2,500	3,547	88
Knaresborough	9	219	NA
Northampton Ma	1,749	886	NA
Quebec	1,080	1,917	NA
Venice	4,783	4,788	NA
Woodbridge NJ	549	236	NA
Amherst Nh	294	639	NA
Copenhagen	1,852	3,644	NA
Kelso	695	1,817	NA
Neuchatel	NA	4,202	NA
Stafford	NA	413	NA
Armagh	66	336	NA
Bruges	NA	2,574	NA
Devizes	315	1,201	NA
Dover Nh	298	1,268	124
Lausanne	150	3,915	NA
Leominster Ma	471	707	NA
Marlborough	192	492	NA
Newark Nj	NA	2,203	NA
Wakefield	828	821	NA
Altenburg	693	2,823	797
Banbury	197	315	NA
Buckingham	NA	565	NA
Douai	1,662	3,907	NA
Dudley	NA	1,313	NA
Egham	297	1,561	NA
Falmouth Me	248	292	70
Greenfield Ma	334	1,386	NA
Henley-on-Thames	1,154	1,190	NA
High Wycombe	NA	1,639	NA
Huntingdon	NA	248	NA
Leiden	NA	1,412	NA
Londonderry	256	1,526	NA
Lyon	3,646	3,920	NA
Monaghan	135	207	NA
Montrose	11,342	2,185	999
Pontefract	NA	285	NA
Ripon	1	36	NA
Sevenoaks	NA	272	NA
St Ives	207	577	NA
Sudbury	310	2,557	NA
Bennington Vt	333	1,157	NA
Boston	271	205	NA
Bridgetown	NA	478	NA
Chesterfield	92	628	NA
Congleton	24	802	NA
Deptford	49	857	NA
Dorchester	NA	1,041	NA
Douglas	NA	494	NA
Evesham	1,949	1,318	NA
Gosport	607	824	NA
New Bedford Ma	NA	499	NA
North Shields	1,581	1,406	NA
Savannah Ga	NA	242	NA
Spanish Town	917	1,764	NA
St Andrews	76	2,190	NA
Stourbridge	428	1,055	NA
Strabane	168	1,734	NA
Washington DC	160	227	NA
Weymouth	NA	872	NA
Whitby	442	670	NA
Wigan	1,727	1,606	NA
Alexandria Va	NA	452	NA
Basseterre Saint Kitts	NA	468	NA
Burslem	245	258	NA
Drogheda	436	505	NA
Gravesend	NA	766	NA
Haverhill Ma	NA	302	NA
Kilkenny	393	549	NA
Leominster NH	NA	722	NA
Liège	637	2,433	8
Madeley	NA	706	NA
Nantwich	96	761	NA
New Brunswick Nj	204	1,529	NA
Walpole Nh	280	964	NA
Antwerp	NA	1,954	NA
Bolton	1,712	1,262	74
Brunswick	NA	3,932	NA
Carlow	NA	142	NA
Ephrata Pa	1,707	1,878	NA
Halle	568	5,199	NA
Hamilton	122	254	NA
Market Harborough	338	1,342	NA
Middletown Ct	NA	240	NA
Monmouth	NA	804	NA
Northumberland Pa	NA	894	NA
Port-au-Prince	NA	47	NA
Poughkeepsie Ny	45	482	NA
Strood	NA	68	NA
Tamworth	NA	1,349	NA
Truru	NA	535	NA
Valletta	NA	2,428	NA
Windham Ct	153	1,131	NA
Brookfield Ma	NA	434	NA
Chippenham	NA	134	NA
Dedham Ma	274	906	NA
Dunbar	NA	98	NA
Fishkill Ny	NA	251	NA
Guernesey	NA	1,234	NA
Hertford	NA	411	NA
Oswestry	NA	265	NA
Padua	NA	914	NA
Rochdale	NA	678	NA
Stroud	NA	10	NA
the Hague	95	1,657	100
Utrecht	192	1,237	NA
Augusta Ga	NA	246	NA
Brighton	NA	375	NA
Caernarfon	NA	82	NA
Catskill Ny	76	404	NA
Elizabeth Nj	1,624	957	NA
Fersfield	NA	4,573	NA
Grantham	41	263	NA
Lexington Ky	NA	156	NA
Lisbon	NA	1,272	NA
Loughborough	35	252	NA
Montreal	NA	772	NA
Mullingar	24	677	190
Romsey	NA	766	NA
Scarborough	NA	102	NA
South Shields	83	403	NA
Suffield Ct	NA	136	144
Walsall	NA	435	NA
Wexford	12	33	NA
Woodbridge Nj	16	669	136
Abartawe	NA	65	NA
Abingdon	NA	342	NA
Berkhamsted	NA	766	NA
Bocking	NA	201	168
Bungay	NA	563	666
Chatham	22	213	NA
Chennai	NA	387	NA
Clipstone	603	1,202	NA
Danbury Ct	558	101	NA
Haarlem	NA	974	NA
Helston	117	1,089	NA
Keene Nh	11	142	NA
Liege	NA	620	NA
Lymington	NA	1,228	NA
Machynlleth	NA	645	60
Madrid	NA	4,161	NA
Medford Ma	NA	216	NA
New Bern Nc	1,104	1,402	NA
Peacham Vt	NA	126	NA
Reims	NA	1,125	NA
Rome	NA	484	NA
Saint-Omer	NA	1,983	874
Spalding	NA	159	NA
St Omer	NA	928	NA
Strasbourg	710	637	NA
Workington	NA	182	NA
Aylesbury	24	312	NA
Beverley	4	150	NA
Bishopstone	NA	1,015	NA
Bridport	NA	185	NA
Cambridge Ma	NA	110	NA
Cheltenham	239	193	NA
Cheshire Ct	NA	236	NA
Cheshunt	NA	4	NA
Clonmel	NA	111	NA
Cranbrook	NA	296	NA
Danvers Ma	NA	82	NA
Darmstadt	NA	828	NA
Ennis	NA	141	NA
Galway	NA	312	NA
Gouda	NA	126	NA
Hawick	NA	758	NA
Hillsborough NC	NA	27	NA
Hudson Ny	856	304	NA
Llanymddyfri	1,108	384	NA
Lyons	NA	694	NA
Newburgh Ny	NA	551	NA
Newmarket	NA	289	NA
Poole	NA	130	NA
Reading Pa	218	476	NA
Retford	NA	312	NA
Salem	NA	413	NA
St Peter Port	NA	403	NA
St Petersburg	NA	1,117	NA
Uppsala	234	892	NA
Uttoxeter	NA	666	NA
Warren Ri	NA	327	NA
Washington Pa	NA	339	NA
Windsor Ct	177	235	NA
Wotton-under-Edge	24	96	NA
Yverdon	NA	852	NA
Alston	44	95	NA
Ashford	NA	194	NA
Athlone	NA	4	NA
Bampton	NA	28	NA
Bern	277	717	NA
Blandford Va	NA	61	NA
Bridgewater	NA	545	NA
Bridlington	87	371	NA
Carlisle Pa	791	393	NA
Charleston SC	28	181	NA
Chelmsford Ma	NA	59	NA
Chesham	NA	55	NA
Coburg	NA	430	NA
Dereham	NA	32	NA
Dun Laoghaire	NA	17	NA
Greenock	24	103	NA
Hambourg	NA	1,598	NA
Harrisburg Pa	NA	547	NA
Harrogate	NA	50	NA
Hwlffordd	NA	40	NA
Jena	NA	1,810	NA
Kingston Ny	NA	339	NA
Launceston	NA	33	NA
Louvain	NA	556	NA
Lucca	NA	629	NA
Malton	NA	878	NA
Newfield Ct	NA	199	NA
Parma	668	62	NA
Peterhead	NA	54	NA
Ramsgate	NA	287	NA
Roseau Dominica	NA	31	NA
Rye	NA	31	NA
Schenectady Ny	144	423	NA
Stockholm	NA	1,252	NA
Stratford-upon-Avon	NA	113	NA
Tiverton	NA	211	NA
Toulouse	NA	936	NA
Treffynnon	NA	173	NA
Västerås	NA	903	NA
Adpar	NA	589	NA
America	NA	119	NA
Andover Ma	NA	75	NA
Avignon	NA	1,205	NA
Banff	NA	21	NA
Barnard Castle	NA	13	NA
Berne	308	650	NA
Bombay	NA	277	NA
Bontfaen	NA	207	NA
Boston England	NA	80	NA
Bouillon	NA	528	NA
Brattleboro Vt	NA	56	NA
Bremen	NA	1,132	NA
Bridgnorth	NA	8	NA
Burton	NA	42	NA
Cape Town	NA	2	NA
Castine Me	NA	59	NA
Chatham Nj	NA	103	NA
Chepstow	NA	133	NA
Chertsey	NA	170	NA
Cincinnati Oh	NA	61	NA
Concord Ma	NA	59	NA
Cooperstown Ny	NA	154	NA
Crewkerne	NA	209	NA
Dover De	NA	33	NA
Dungannon	NA	26	NA
Dunkirk	NA	763	NA
Edenton Nc	NA	1,021	NA
Enniskillen	NA	2	NA
Erlangen	NA	495	NA
Flensburg	NA	937	NA
Fredericktown Md	NA	173	NA
Fredericton	NA	48	NA
Frome	NA	105	NA
Georgetown Washington DC	NA	75	NA
Great Marlow	NA	18	NA
Haddington	NA	8	NA
Halifax Nc	NA	223	NA
Hannover Nh	NA	307	NA
Hemel Hempstead	NA	20	NA
Honiton	NA	506	NA
Horncastle	NA	59	NA
Horsham	NA	174	NA
Howden	NA	130	NA
Inverness	450	2	NA
Mannheim	NA	100	NA
Melton Mowbray	NA	18	NA
Middlewich	NA	86	NA
Montargis	NA	457	NA
Münster	NA	394	NA
Nancy	NA	676	NA
Newbury	48	88	22
Niagara	NA	41	NA
Norfolk Va	NA	43	NA
Northallerton	NA	115	NA
Nürnberg	NA	485	NA
Petersfield	NA	11	NA
Pisa	NA	53	NA
Potsdam	NA	552	NA
Prescot	NA	49	NA
Putney Vt	NA	85	NA
Rheims	NA	866	NA
Rome Ny	NA	54	NA
Shepton Mallet	NA	11	NA
South Molton	NA	51	NA
St Albans	NA	41	NA
St George	NA	73	NA
St Helier	NA	239	NA
Stonington Ct	NA	30	NA
Stowmarket	NA	5	NA
Szczecin	NA	885	NA
Troy Ny	NA	194	NA
Vergennes Vt	NA	56	NA
Watford	NA	15	NA
Wellingborough	NA	30	NA
Winterthur	NA	408	NA
York Pa	NA	46	NA
Zurich	NA	964	NA
Abbeville	NA	259	NA
Abermaw	NA	1	NA
Aberystwyth	NA	1	NA
Alcester	NA	30	NA
Ampthill	NA	1	NA
Arezzo	NA	332	NA
Ashby-de-la-Zouch	NA	31	NA
Atherstone	NA	20	NA
Bala	NA	6	NA
Balfron	NA	15	NA
Ballymena	NA	2	NA
Barnstaple	NA	51	NA
Barton-upon-Humber	NA	42	NA
Basingstoke	NA	2	NA
Bayreuth	NA	276	NA
Bedale	NA	28	NA
Beloeil	NA	137	NA
Besançon	NA	144	NA
Birr	NA	296	NA
Birstall	NA	11	NA
Bishop Castle	NA	1	NA
Bodedern	NA	16	NA
Bordeaux	NA	236	NA
Boulogne-sur-Mer	NA	110	NA
Brearley Hall	NA	100	265
Brigg	NA	9	NA
Budapest	NA	240	NA
Burlington NJ	NA	372	NA
Burnley	NA	15	NA
Caen	NA	26	NA
Caerdydd	NA	25	NA
Caerfyrddin	NA	44	NA
Caergybi	NA	17	NA
Calais	NA	209	NA
Carrickfergus	NA	59	NA
Castlebar	NA	1	NA
Castleford	NA	68	NA
Cavan	NA	68	NA
Chambersburg Pa	NA	84	NA
Ciutadella	NA	57	NA
Coimbra	NA	415	NA
Coleraine	NA	40	NA
Coxheath	NA	36	NA
Crieff	NA	271	NA
Cupar	NA	263	NA
Dampierre-sur-Boutonne	872	506	NA
Dartford	NA	60	NA
Dartmouth	NA	1	NA
Dessau	NA	103	NA
Dordrecht	NA	618	NA
Dover	NA	53	NA
Dunfermline	NA	15	NA
Dunkalk	NA	49	NA
Dunkeld	NA	1	NA
Duns	NA	22	NA
Düsseldorf	NA	191	NA
East Grinstead	NA	225	NA
Easton Md	NA	19	NA
Elie	NA	34	NA
Ellesmere	NA	8	NA
Essex	NA	76	NA
Faringdon	NA	24	NA
Featherstone	NA	72	NA
Fermoy	NA	60	NA
Fleet	NA	12	NA
Geneva Ny	NA	24	NA
Georgetown Washington Sc	NA	22	NA
Ghent	NA	8	NA
Gillingham	NA	27	NA
Gilmanton Nh	NA	15	NA
Goshen Ny	NA	136	NA
Gothenburg	NA	391	NA
Halesworth	NA	3	NA
Hallowell Me	NA	21	NA
Hanau	NA	151	NA
Hannover	NA	210	NA
Harbor Ny	NA	27	NA
Haverhill Nh	NA	34	NA
Hexham	NA	91	NA
Hildburghausen	NA	498	NA
Hinckley	NA	1	NA
Hitchin	NA	1	NA
Holt	NA	91	NA
Houghton Park	NA	1	NA
Hungerford	NA	12	NA
Karlskrona	NA	32	NA
Karlsruhe	NA	15	NA
Keene	NA	23	NA
Kenilworth	NA	32	NA
Keswick	NA	1	NA
Kinsale	NA	8	NA
Kirkbride	NA	291	NA
Knoxville Tn	NA	31	NA
Knutsford	NA	2	NA
Lanark	NA	15	NA
Leek	NA	1	NA
Lisburn	NA	1	NA
Long Buckby	NA	39	NA
Lugano	NA	93	NA
Lund	NA	312	NA
Mainz	NA	295	NA
Malda	NA	182	NA
Mantua	NA	46	NA
Marseilles	NA	47	NA
Middelburg	NA	95	NA
Milan	556	131	NA
Milborne Port	NA	21	NA
Môle-Saint-Nicolas	NA	34	NA
Monmouth Nj	NA	468	NA
Morristown Nj	NA	328	NA
Moscow	NA	175	NA
Naas	NA	1	NA
Nantes	NA	383	NA
Naples	374	191	NA
Nashville Tn	NA	26	NA
Nassau	NA	110	NA
Newbury Vt	NA	190	148
Nice	NA	195	NA
Nordhausen	NA	114	NA
Norfolk	NA	34	NA
Norristown Pa	NA	157	NA
Norrköping	NA	8	NA
Northwich	NA	1	NA
Nuremberg	NA	596	NA
Ormskirk	NA	32	NA
Osnabrück	NA	95	NA
Pattingham	NA	19	422
Pembroke	NA	33	NA
Perugia	NA	87	NA
Plymouth Ma	NA	45	NA
Pondicherry	NA	155	NA
Poughkeepsie NY	NA	161	NA
Poulton-le-Fylde	NA	1	NA
Princeton Nj	NA	229	NA
Providence RI	NA	31	NA
Raleigh Nc	NA	16	NA
Ramsey	NA	63	NA
Regensburg	NA	173	NA
Rhaglan	NA	73	NA
Saffron Walden	NA	1	NA
Saint Helier	NA	414	NA
Saint-Germain-en-Laye	NA	376	NA
Salisbury Nc	NA	40	NA
Sandhurst	NA	10	NA
Sandwich	NA	1	NA
Sanquhar	NA	8	NA
Schleswig	NA	523	NA
Sedbergh	NA	20	NA
Selby	NA	16	NA
Shepherdstown Wv	NA	332	NA
Siena	NA	186	NA
Sligo	41	18	NA
Southampton Pa	NA	8	NA
St Austell	NA	23	NA
St Eustatius	NA	164	NA
St Neots	NA	24	NA
Stoke-on-Trent	NA	7	NA
Stokesley	NA	27	NA
Stuttgart	NA	48	NA
Sulechow	NA	353	NA
Tetbury	NA	10	NA
Thirsk	NA	8	NA
Torrington	NA	34	NA
Totnes	NA	34	NA
Trenton	NA	36	NA
Trevoux	3,193	337	NA
Tuscany	NA	128	NA
Ulverston	NA	640	NA
Valencia	NA	334	NA
Verona	1,223	21	NA
Walpole NH	NA	51	NA
Wargrave	NA	15	NA
Warminster	NA	1	NA
Waterford Ny	NA	127	NA
Wells	NA	51	NA
Whitburn	182	225	NA
Whitchurch	122	24	NA
Wiscasset Me	NA	24	NA
Wittenberg	NA	303	NA
Yarm	NA	47	NA
Yeovil	NA	139	NA
Youghal	NA	146	NA
NA	74,575	516,172	28,576

Year of earliest publication

split %>%
  count(set,earliest_publication_year_definite) %>%
  ggplot(aes(x=set,y=n,fill=earliest_publication_year_definite)) +
  geom_col(position='dodge') +
  theme_hsci_discrete() +
  coord_flip() +
  ylab("ECCO documents") +
  xlab("Set") +
  labs(fill="Date certain") +
  theme(legend.position="bottom") + 
  ggtitle("Uncertainty/certainty of dating the earliest year of publication")

split %>%
  count(set,earliest_publication_year,earliest_publication_year_definite) %>%
  ggplot(aes(x=earliest_publication_year,y=n,fill=earliest_publication_year_definite)) +
  geom_col(position='stack',width=1) +
  theme_hsci_discrete() +
  ylab("ECCO documents") +
  xlab("Year") +
  labs(fill="Date certain") +    
  theme(legend.position="bottom") + 
  facet_wrap(~set, scales="free") +
  ggtitle("Earliest year of publication")

Warning: Removed 3 rows containing missing values or values outside the scale range (`geom_col()`).

split %>% 
  mutate(earliest_publication_decade=floor(earliest_publication_year/10)*10) %>%
  print_split(earliest_publication_decade, "earliest publication decade", order_by_frequency=FALSE)

By earliest publication decade
(32 targets)
	test	train	val
works
1470	NA	4	NA
1480	3	2	NA
1490	1	NA	NA
1500	1	4	NA
1510	2	3	NA
1520	NA	5	NA
1530	1	15	NA
1540	NA	10	3
1550	5	13	NA
1560	8	16	2
1570	6	33	1
1580	7	20	NA
1590	10	41	5
1600	10	40	2
1610	12	57	5
1620	18	46	2
1630	14	72	7
1640	36	113	20
1650	37	157	27
1660	47	144	22
1670	74	267	28
1680	80	387	34
1690	91	559	35
1700	403	7,322	195
1710	433	9,689	216
1720	368	7,322	191
1730	369	7,281	180
1740	414	8,361	194
1750	453	8,894	241
1760	504	10,436	214
1770	579	10,919	220
1780	666	13,164	270
1790	1,163	19,437	361
1800	143	2,732	51
1810	NA	3	NA
1820	NA	4	NA
1830	NA	1	NA
1840	NA	3	NA
1850	NA	2	NA
1860	NA	1	NA
1910	NA	1	NA
1970	NA	1	NA
NA	12	159	4
documents
1470	NA	36	NA
1480	179	4	NA
1490	8	NA	NA
1500	18	24	NA
1510	150	26	NA
1520	NA	8	NA
1530	5	873	NA
1540	NA	34	53
1550	132	108	NA
1560	202	51	43
1570	210	301	1
1580	282	97	NA
1590	179	161	54
1600	215	146	10
1610	586	307	101
1620	220	127	2
1630	106	190	75
1640	172	300	72
1650	224	559	138
1660	466	482	89
1670	695	957	153
1680	920	1,168	151
1690	906	1,926	146
1700	2,495	11,847	542
1710	2,657	15,088	554
1720	1,880	11,649	512
1730	1,621	11,868	765
1740	1,938	13,519	465
1750	1,983	14,855	751
1760	2,421	17,046	635
1770	1,802	17,964	497
1780	1,745	20,663	564
1790	2,178	27,727	623
1800	160	3,246	63
1810	NA	4	NA
1820	NA	4	NA
1830	NA	2	NA
1840	NA	3	NA
1850	NA	2	NA
1860	NA	3	NA
1910	NA	1	NA
1970	NA	1	NA
NA	53	362	7
pages
1470	NA	9,319	NA
1480	49,929	516	NA
1490	930	NA	NA
1500	7,880	7,062	NA
1510	51,574	6,505	NA
1520	NA	2,069	NA
1530	1,073	213,027	NA
1540	NA	7,579	13,010
1550	39,495	42,466	NA
1560	53,735	22,764	17,841
1570	86,806	81,647	275
1580	101,179	51,640	NA
1590	47,526	44,963	9,023
1600	68,197	19,923	1,697
1610	182,677	53,157	32,642
1620	52,997	34,979	186
1630	33,582	46,923	13,682
1640	46,536	64,841	17,869
1650	68,046	138,277	33,852
1660	148,658	123,139	29,926
1670	211,283	185,238	35,698
1680	195,203	218,114	27,574
1690	289,121	484,589	25,493
1700	647,072	1,440,561	143,111
1710	705,390	1,517,773	128,145
1720	469,041	1,639,046	93,166
1730	362,280	1,660,011	208,046
1740	431,489	1,764,350	90,533
1750	479,900	2,202,399	155,707
1760	637,262	2,336,543	142,475
1770	381,855	2,833,902	90,506
1780	345,723	3,216,681	101,333
1790	366,658	3,839,644	117,823
1800	18,832	384,543	5,689
1810	NA	902	NA
1820	NA	196	NA
1830	NA	582	NA
1840	NA	399	NA
1850	NA	189	NA
1860	NA	978	NA
1910	NA	4	NA
1970	NA	16	NA
NA	5,471	90,817	2,211

Year of publication

split %>%
  count(set,publication_year_definite) %>%
  ggplot(aes(x=set,y=n,fill=publication_year_definite)) +
  geom_col(position='dodge') +
  theme_hsci_discrete() +
  ylab("ECCO documents") +
  xlab("Set") +
  labs(fill="Date certain") +    
  theme(legend.position="bottom") + 
  coord_flip() +
  ggtitle("Uncertainty/certainty of dating the year of publication")

split %>%
  count(set,publication_year,publication_year_definite) %>%
  ggplot(aes(x=publication_year,y=n,fill=publication_year_definite)) +
  geom_col(position='stack',width=1) +
  theme_hsci_discrete() +
  ylab("ECCO documents") +
  xlab("Year") +
  labs(fill="Date certain") +    
  theme(legend.position="bottom") + 
  facet_wrap(~set, scales="free") +
  ggtitle("Year of publication")

Warning: Removed 3 rows containing missing values or values outside the scale range (`geom_col()`).

split %>% 
  mutate(publication_decade=floor(publication_year/10)*10) %>%
  print_split(publication_decade, "publication decade", order_by_frequency=FALSE)

By publication decade
(12 targets)
	test	train	val
works
1600	NA	2	NA
1610	NA	2	NA
1620	NA	1	NA
1630	NA	1	NA
1640	NA	5	NA
1650	NA	5	NA
1660	NA	4	NA
1670	NA	8	NA
1680	NA	16	NA
1690	NA	28	NA
1700	606	7,873	270
1710	725	10,618	315
1720	742	8,466	291
1730	750	8,398	287
1740	766	9,560	285
1750	867	10,233	353
1760	985	12,126	376
1770	1,135	12,883	369
1780	1,205	15,186	426
1790	1,840	22,418	542
1800	358	3,598	93
1810	NA	4	NA
1820	NA	4	NA
1830	NA	1	NA
1840	NA	3	NA
1850	NA	2	NA
1860	NA	1	NA
1910	NA	1	NA
1970	NA	1	NA
NA	11	158	4
documents
1600	NA	2	NA
1610	NA	3	NA
1620	NA	1	NA
1630	NA	1	NA
1640	NA	5	NA
1650	NA	5	NA
1660	NA	4	NA
1670	NA	10	NA
1680	NA	31	NA
1690	NA	31	NA
1700	1,055	10,382	426
1710	1,565	14,240	505
1720	1,731	11,360	487
1730	2,006	11,528	537
1740	1,934	13,093	496
1750	2,438	14,608	715
1760	3,086	17,239	941
1770	3,553	19,420	841
1780	3,432	22,904	882
1790	5,426	34,004	1,094
1800	571	4,486	135
1810	NA	5	NA
1820	NA	4	NA
1830	NA	2	NA
1840	NA	3	NA
1850	NA	2	NA
1860	NA	3	NA
1910	NA	1	NA
1970	NA	1	NA
NA	11	361	7
pages
1600	NA	116	NA
1610	NA	95	NA
1620	NA	24	NA
1630	NA	76	NA
1640	NA	138	NA
1650	NA	103	NA
1660	NA	78	NA
1670	NA	1,139	NA
1680	NA	13,698	NA
1690	NA	3,858	NA
1700	246,446	1,142,136	90,012
1710	363,694	1,359,129	90,880
1720	453,674	1,540,902	100,492
1730	517,969	1,560,180	123,819
1740	478,001	1,716,975	113,898
1750	597,839	2,121,366	163,770
1760	769,405	2,450,668	220,321
1770	860,137	3,131,800	185,863
1780	834,338	3,708,766	175,588
1790	1,347,900	5,318,060	246,041
1800	116,740	624,915	24,618
1810	NA	918	NA
1820	NA	196	NA
1830	NA	582	NA
1840	NA	399	NA
1850	NA	189	NA
1860	NA	978	NA
1910	NA	4	NA
1970	NA	16	NA
NA	1,257	90,769	2,211

Price

split %>% 
  mutate(has_price=!is.na(total_price)) %>%
  count(set,has_price) %>%
  pivot_wider(names_from=set,values_from=n) %>%
  gt(rowname_col = "set") %>%
    tab_header(title = "Price information availability") %>%
    fmt_integer(columns=c(test,val,train))

Price information availability
has_price	test	train	val
FALSE	24,346	147,906	6,088
TRUE	2,462	25,833	978

split %>%
  count(set,total_price) %>%
  ggplot(aes(x=total_price,y=n)) +
  geom_col(width=1) +
  theme_hsci_discrete() +
  ylab("ECCO documents") +
  xlab("Price") +
  theme(legend.position="bottom") + 
  facet_wrap(~set, scales="free", ncol=1) +
  ggtitle("Prices")

Warning: `position_stack()` requires non-overlapping x intervals.
Warning: `position_stack()` requires non-overlapping x intervals.
Warning: `position_stack()` requires non-overlapping x intervals.
Warning: Removed 3 rows containing missing values or values outside the scale range (`geom_col()`).

Multi-label targets

Actors

library(gghsci)
major_actor_split %>%
  filter(set=="test") %>%
  count(ecco_id) %>%
  count(n) %>%
  ggplot(aes(x=n,y=nn)) +
  geom_col() +
  theme_hsci_discrete() +
  ylab("ECCO documents") +
  xlab("Number of actors attached") +
  ggtitle("Test set label count distribution (major only)")

Storing counts in `nn`, as `n` already present in input
ℹ Use `name = "new_name"` to pick a new name.

major_actor_split %>% 
  group_by(set, major_actor_id, actor_role, name_unified) %>%
  summarise(pages=sum(pages),documents=n(),works=n_distinct(work_id), .groups="drop") %>%
  pivot_longer(pages:works) %>% 
  pivot_wider(names_from=set,values_from=value) %>%
  mutate(name=fct_relevel(name,"works","documents","pages")) %>%
  mutate(major_actor_id=fct_reorder(major_actor_id, train, .desc=TRUE)) %>%
  arrange(name,major_actor_id) %>%
  select(-major_actor_id) %>%
  gt(groupname_col = "name", rowname_col="name_unified") %>%
  tab_header(title = "By actor", subtitle=str_c("(major only, ", major_actor_split %>% filter(set=="test") %>% distinct(major_actor_id) %>% count() %>% pull(), " targets)")) %>%
  fmt_integer(columns=c(test,val,train))

By actor
(major only, 108 targets)
	actor_role	test	train	val
works
Robinson, George I	publisher	145	698	36
Cadell, Thomas	publisher	160	849	41
Strahan, William	publisher	153	493	38
Longman, Thomas	publisher	209	330	46
Baldwin, Robert I	publisher	192	527	37
Johnston, William	publisher	148	255	30
Law, Bedwell	publisher	167	299	33
Caslon, Thomas	publisher	162	167	31
Millar, Andrew	publisher	102	501	23
Cadell, Thomas Ii	publisher	99	495	24
F. and C. Rivington	publisher	76	372	27
Rivington, John	publisher	150	294	39
Hitch, Charles	publisher	182	357	45
Johnson, John	publisher	78	527	15
Roberts, James	publisher	57	1,569	36
Dodsley, James	publisher	57	451	22
J. and F. Rivington	publisher	112	203	23
Becket, Thomas	publisher	105	504	20
Crowder, Stanley	publisher	118	265	23
Smith, W.	publisher	69	179	16
Faulkner, George	publisher	55	568	22
Hawes, Lacy	publisher	140	199	23
Byrne, P.	publisher	79	512	27
J. Exshaw	publisher	129	331	28
Lowndes, Thomas	publisher	102	165	26
Bettesworth, Arthur	publisher	152	380	45
Dilly, Charles	publisher	110	555	33
Williams, J.	publisher	87	285	23
Powell, S.	publisher	69	235	15
G. G. and J. Robinson	publisher	75	402	27
Strahan, Andrew	publisher	62	264	11
Wogan, P.	publisher	100	347	24
Innys, William	publisher	81	391	20
J. and P. Knapton	publisher	127	256	29
Moore, J.	publisher	66	362	23
Risk, George	publisher	76	135	15
E. and C. Dilly	publisher	52	215	11
Bell, John	publisher	88	293	18
Cooper, Mary Mrs	publisher	70	938	24
Potts, J.	publisher	76	219	24
Hodges, James Sir	publisher	73	239	20
Tonson, Jacob I	publisher	121	419	16
Crowder, Samuel	publisher	95	103	17
Jones, W.	publisher	76	292	25
J. and R. Tonson	publisher	83	168	17
Lowndes, William	publisher	86	108	16
Wilson, P.	publisher	83	246	19
Sleater, W.	publisher	73	277	22
Davies, Thomas	publisher	82	208	16
Powell, S.	publisher	53	396	19
Bladon, Samuel	publisher	111	326	27
Nichols, John	publisher	58	424	18
Osborne, Thomas Ii	publisher	58	169	12
Donaldson, A.	publisher	73	165	8
Johnson, John	publisher	62	328	11
Richardson, Joseph	publisher	53	105	11
Birt, Samuel	publisher	99	171	20
J. F. and C. Rivington	publisher	95	215	17
Ware, Richard I	publisher	75	117	16
Walker, T.	publisher	61	211	14
Harrison and Co	publisher	62	130	13
Nicoll, William	publisher	84	200	16
Gosling, Robert	publisher	59	241	14
Chamberlaine, D.	publisher	59	177	10
Buckland, James	publisher	67	515	23
Midwinter, Daniel	publisher	106	202	27
Ware, Catherine Mrs	publisher	67	55	9
Wilson, W.	publisher	52	187	14
Longman, Thomas	publisher	107	154	23
Lintott, Barnaby Bernard	publisher	58	298	14
Davis, Lockyer John	publisher	61	249	14
Rivington, Charles	publisher	62	229	14
Mears, William	publisher	61	223	16
Vernor and Hood	publisher	52	185	10
Wilkie, John	publisher	50	343	12
Walthoe, John I	publisher	67	136	21
Richardson, William	publisher	58	207	9
G. and T. Wilkie	publisher	69	170	13
Kearsley, George	publisher	69	351	16
Keith, George	publisher	78	272	16
Walker, John	publisher	58	117	9
Saunders, H.	publisher	55	130	11
Clarke, William	publisher	58	119	11
Davies, William	publisher	52	269	12
Payne, Thomas	publisher	54	181	13
Goldsmith, William	publisher	60	84	9
Nicholson, John	publisher	50	88	21
Motte, Benjamin	publisher	61	92	10
Bew, John	publisher	64	368	17
Robinson, Ranew	publisher	50	89	10
Clarke, John	publisher	70	232	18
Bathurst, Charles	publisher	81	128	12
Ward, John	publisher	78	145	14
Browne, Daniel Ii	publisher	60	148	14
Newbery, Elizabeth Mrs	publisher	50	141	7
Grierson, George	publisher	53	188	14
Lintot, Henry	publisher	70	141	8
Hinton, John	publisher	52	82	10
Hett, Richard	publisher	64	392	20
Scatcherd, James	publisher	56	70	10
Ward, Aaron	publisher	96	206	26
Horsfield, Robert	publisher	57	80	9
Pemberton, John	publisher	58	206	16
Woodfall, Henry	publisher	70	94	8
Osborn, John Ii	publisher	54	119	14
Brindley, John	publisher	53	130	11
Clay, Francis	publisher	83	99	25
Darby, John	publisher	64	133	19
documents
Robinson, George I	publisher	5,186	5,441	462
Cadell, Thomas	publisher	5,474	5,139	1,115
Strahan, William	publisher	6,605	4,869	1,098
Longman, Thomas	publisher	6,283	3,990	1,086
Baldwin, Robert I	publisher	6,193	3,769	874
Johnston, William	publisher	5,505	3,623	744
Law, Bedwell	publisher	5,365	3,564	591
Caslon, Thomas	publisher	5,676	3,540	672
Millar, Andrew	publisher	3,018	3,537	351
Cadell, Thomas Ii	publisher	4,226	3,492	309
F. and C. Rivington	publisher	3,379	3,454	294
Rivington, John	publisher	4,675	3,299	903
Hitch, Charles	publisher	4,659	3,162	967
Johnson, John	publisher	2,971	3,075	143
Roberts, James	publisher	1,297	3,030	92
Dodsley, James	publisher	1,569	2,785	560
J. and F. Rivington	publisher	5,223	2,775	685
Becket, Thomas	publisher	3,307	2,751	428
Crowder, Stanley	publisher	3,912	2,712	442
Smith, W.	publisher	2,348	2,708	253
Faulkner, George	publisher	1,798	2,694	548
Hawes, Lacy	publisher	4,370	2,683	803
Byrne, P.	publisher	1,659	2,680	164
J. Exshaw	publisher	3,704	2,557	437
Lowndes, Thomas	publisher	3,751	2,528	517
Bettesworth, Arthur	publisher	3,520	2,508	361
Dilly, Charles	publisher	3,382	2,483	310
Williams, J.	publisher	2,754	2,469	618
Powell, S.	publisher	1,951	2,418	201
G. G. and J. Robinson	publisher	3,260	2,417	395
Strahan, Andrew	publisher	2,049	2,401	217
Wogan, P.	publisher	2,794	2,385	251
Innys, William	publisher	1,737	2,332	110
J. and P. Knapton	publisher	3,254	2,234	204
Moore, J.	publisher	1,600	2,115	171
Risk, George	publisher	2,617	2,090	262
E. and C. Dilly	publisher	1,958	2,067	125
Bell, John	publisher	2,352	2,067	320
Cooper, Mary Mrs	publisher	2,232	2,057	232
Potts, J.	publisher	2,268	2,043	325
Hodges, James Sir	publisher	2,488	2,042	167
Tonson, Jacob I	publisher	4,284	1,987	172
Crowder, Samuel	publisher	4,154	1,982	439
Jones, W.	publisher	1,534	1,976	382
J. and R. Tonson	publisher	3,773	1,881	223
Lowndes, William	publisher	3,160	1,878	352
Wilson, P.	publisher	2,590	1,876	272
Sleater, W.	publisher	1,700	1,861	250
Davies, Thomas	publisher	3,571	1,857	361
Powell, S.	publisher	1,758	1,835	192
Bladon, Samuel	publisher	3,138	1,826	588
Nichols, John	publisher	2,171	1,810	610
Osborne, Thomas Ii	publisher	1,566	1,808	493
Donaldson, A.	publisher	4,550	1,808	514
Johnson, John	publisher	2,205	1,803	211
Richardson, Joseph	publisher	2,035	1,794	277
Birt, Samuel	publisher	2,769	1,775	140
J. F. and C. Rivington	publisher	3,414	1,749	480
Ware, Richard I	publisher	2,148	1,733	144
Walker, T.	publisher	1,874	1,733	281
Harrison and Co	publisher	2,263	1,714	241
Nicoll, William	publisher	2,624	1,707	323
Gosling, Robert	publisher	1,090	1,705	86
Chamberlaine, D.	publisher	1,297	1,685	158
Buckland, James	publisher	1,494	1,683	352
Midwinter, Daniel	publisher	2,146	1,651	235
Ware, Catherine Mrs	publisher	2,478	1,649	137
Wilson, W.	publisher	2,283	1,607	119
Longman, Thomas	publisher	2,707	1,600	184
Lintott, Barnaby Bernard	publisher	2,022	1,588	328
Davis, Lockyer John	publisher	1,753	1,570	365
Rivington, Charles	publisher	1,295	1,544	95
Mears, William	publisher	1,783	1,541	59
Vernor and Hood	publisher	1,709	1,538	59
Wilkie, John	publisher	1,133	1,533	73
Walthoe, John I	publisher	1,533	1,484	107
Richardson, William	publisher	2,513	1,466	170
G. and T. Wilkie	publisher	2,831	1,455	202
Kearsley, George	publisher	1,933	1,426	295
Keith, George	publisher	2,167	1,389	144
Walker, John	publisher	2,572	1,325	182
Saunders, H.	publisher	1,225	1,305	227
Clarke, William	publisher	1,934	1,300	180
Davies, William	publisher	1,516	1,298	153
Payne, Thomas	publisher	3,130	1,298	131
Goldsmith, William	publisher	2,454	1,274	254
Nicholson, John	publisher	1,080	1,229	142
Motte, Benjamin	publisher	1,754	1,222	52
Bew, John	publisher	2,464	1,218	200
Robinson, Ranew	publisher	1,083	1,181	59
Clarke, John	publisher	1,525	1,088	132
Bathurst, Charles	publisher	3,115	1,071	463
Ward, John	publisher	2,554	1,049	205
Browne, Daniel Ii	publisher	1,793	1,000	113
Newbery, Elizabeth Mrs	publisher	2,309	942	137
Grierson, George	publisher	2,664	936	73
Lintot, Henry	publisher	2,613	924	132
Hinton, John	publisher	1,326	924	365
Hett, Richard	publisher	1,032	907	145
Scatcherd, James	publisher	2,419	904	184
Ward, Aaron	publisher	1,716	865	189
Horsfield, Robert	publisher	2,275	839	204
Pemberton, John	publisher	1,496	802	109
Woodfall, Henry	publisher	2,741	790	150
Osborn, John Ii	publisher	1,724	785	87
Brindley, John	publisher	1,508	626	95
Clay, Francis	publisher	2,276	374	181
Darby, John	publisher	1,570	348	170
pages
Robinson, George I	publisher	1,852,735	1,703,202	152,990
Cadell, Thomas	publisher	1,923,035	1,533,797	374,947
Strahan, William	publisher	2,223,762	1,482,405	366,644
Longman, Thomas	publisher	2,151,570	1,290,462	376,116
Baldwin, Robert I	publisher	2,198,299	1,205,681	295,838
Johnston, William	publisher	2,022,684	1,154,143	269,345
Law, Bedwell	publisher	1,898,245	1,168,379	202,881
Caslon, Thomas	publisher	1,746,599	1,019,840	169,876
Millar, Andrew	publisher	1,106,781	1,019,811	103,630
Cadell, Thomas Ii	publisher	1,532,521	1,077,625	102,436
F. and C. Rivington	publisher	1,200,125	848,237	62,670
Rivington, John	publisher	1,677,519	952,599	315,955
Hitch, Charles	publisher	1,679,834	924,538	356,793
Johnson, John	publisher	1,083,707	810,070	45,961
Roberts, James	publisher	330,035	284,872	14,946
Dodsley, James	publisher	475,991	769,746	155,973
J. and F. Rivington	publisher	1,958,067	850,270	244,827
Becket, Thomas	publisher	1,071,697	677,106	109,737
Crowder, Stanley	publisher	1,308,686	868,411	156,221
Smith, W.	publisher	563,190	607,392	46,378
Faulkner, George	publisher	414,395	468,661	155,032
Hawes, Lacy	publisher	1,593,319	797,761	268,217
Byrne, P.	publisher	566,915	695,175	45,822
J. Exshaw	publisher	912,365	634,780	104,280
Lowndes, Thomas	publisher	1,125,863	625,525	94,955
Bettesworth, Arthur	publisher	1,312,172	680,405	121,995
Dilly, Charles	publisher	1,193,246	718,456	97,386
Williams, J.	publisher	798,596	655,527	216,092
Powell, S.	publisher	342,657	427,827	30,268
G. G. and J. Robinson	publisher	1,262,298	817,240	145,616
Strahan, Andrew	publisher	751,719	783,093	78,600
Wogan, P.	publisher	793,709	628,096	71,225
Innys, William	publisher	706,273	669,912	50,797
J. and P. Knapton	publisher	1,257,675	715,857	88,938
Moore, J.	publisher	577,855	622,757	68,884
Risk, George	publisher	641,645	408,317	46,347
E. and C. Dilly	publisher	726,445	529,597	41,533
Bell, John	publisher	359,019	339,855	43,276
Cooper, Mary Mrs	publisher	772,444	375,228	71,223
Potts, J.	publisher	588,490	498,298	84,973
Hodges, James Sir	publisher	876,704	552,919	51,409
Tonson, Jacob I	publisher	1,289,964	408,729	25,401
Crowder, Samuel	publisher	1,511,266	686,205	152,022
Jones, W.	publisher	460,346	494,068	100,237
J. and R. Tonson	publisher	1,154,142	444,654	19,641
Lowndes, William	publisher	958,062	474,887	78,275
Wilson, P.	publisher	594,576	419,824	45,390
Sleater, W.	publisher	459,521	443,016	66,073
Davies, Thomas	publisher	1,218,264	500,029	92,530
Powell, S.	publisher	390,958	296,485	40,135
Bladon, Samuel	publisher	782,157	391,761	141,788
Nichols, John	publisher	731,427	501,098	206,078
Osborne, Thomas Ii	publisher	669,777	615,210	200,673
Donaldson, A.	publisher	1,311,705	554,213	155,068
Johnson, John	publisher	822,874	580,469	70,063
Richardson, Joseph	publisher	740,391	546,232	102,450
Birt, Samuel	publisher	1,078,551	519,378	60,110
J. F. and C. Rivington	publisher	1,150,623	461,222	158,276
Ware, Richard I	publisher	772,511	501,768	52,429
Walker, T.	publisher	546,668	464,911	98,672
Harrison and Co	publisher	514,512	404,144	48,300
Nicoll, William	publisher	670,204	377,237	49,154
Gosling, Robert	publisher	433,197	542,626	41,792
Chamberlaine, D.	publisher	301,094	411,884	23,820
Buckland, James	publisher	525,912	411,005	106,942
Midwinter, Daniel	publisher	937,940	484,980	107,569
Ware, Catherine Mrs	publisher	822,709	517,758	60,864
Wilson, W.	publisher	647,210	423,109	29,152
Longman, Thomas	publisher	1,100,557	476,036	82,036
Lintott, Barnaby Bernard	publisher	631,004	313,009	100,418
Davis, Lockyer John	publisher	653,280	455,108	132,591
Rivington, Charles	publisher	595,882	422,355	47,805
Mears, William	publisher	653,958	413,807	24,410
Vernor and Hood	publisher	612,979	491,474	22,078
Wilkie, John	publisher	395,362	401,079	15,329
Walthoe, John I	publisher	588,401	451,991	56,240
Richardson, William	publisher	945,329	482,125	62,001
G. and T. Wilkie	publisher	1,005,105	430,375	60,045
Kearsley, George	publisher	618,931	303,646	51,288
Keith, George	publisher	808,693	438,661	39,557
Walker, John	publisher	958,726	461,104	57,629
Saunders, H.	publisher	295,874	312,485	64,222
Clarke, William	publisher	680,662	350,073	63,118
Davies, William	publisher	557,528	452,652	61,664
Payne, Thomas	publisher	1,205,284	450,713	36,690
Goldsmith, William	publisher	881,412	465,133	80,952
Nicholson, John	publisher	415,342	373,346	64,306
Motte, Benjamin	publisher	658,914	312,949	24,067
Bew, John	publisher	813,582	288,182	52,396
Robinson, Ranew	publisher	444,847	317,830	26,649
Clarke, John	publisher	550,145	325,767	46,256
Bathurst, Charles	publisher	1,113,717	316,166	188,003
Ward, John	publisher	936,219	362,393	68,545
Browne, Daniel Ii	publisher	681,391	353,489	53,637
Newbery, Elizabeth Mrs	publisher	783,393	295,656	39,809
Grierson, George	publisher	723,733	164,831	8,649
Lintot, Henry	publisher	890,530	323,730	43,163
Hinton, John	publisher	609,489	316,167	139,366
Hett, Richard	publisher	407,236	207,572	56,082
Scatcherd, James	publisher	807,026	284,784	59,147
Ward, Aaron	publisher	759,068	275,274	73,603
Horsfield, Robert	publisher	868,257	263,991	60,757
Pemberton, John	publisher	714,359	230,766	53,810
Woodfall, Henry	publisher	934,687	325,876	51,640
Osborn, John Ii	publisher	585,892	266,273	37,537
Brindley, John	publisher	495,443	166,988	14,033
Clay, Francis	publisher	875,395	128,369	58,600
Darby, John	publisher	585,774	88,820	55,938

In total, 19 roles, 10698 actors.

library(gghsci)
actor_split %>%
  filter(set=="test") %>%
  count(actor_role, ecco_id) %>%
  count(actor_role, n) %>%
  ggplot(aes(x=n,y=nn)) +
  geom_col() +
  theme_hsci_discrete() +
  ylab("ECCO documents") +
  xlab("Number of actors attached") +
  ggtitle("Test set label count distribution by actor role") +
  facet_wrap(~actor_role, scales="free")

Storing counts in `nn`, as `n` already present in input
ℹ Use `name = "new_name"` to pick a new name.