russian_borrowings_in_andic.R

library(tidyverse)

read_csv("andic_russian_bor2.csv")  |> 
  mutate(language_material = str_count(ipa_comparison, "-"),
         russian_material = str_count(russian_ipa_comparison, "-"),
         diff = if_else(russian_material == language_material, "", "problem")) |> 
  filter(diff != "problem") ->
  df

df |> 
  mutate(ipa_comparison = str_c(ipa_comparison, "#")) |> 
  select(language, meaning_ru, ipa_comparison) |> 
  mutate(language_material = str_split(ipa_comparison, "-")) |> 
  unnest(language_material) ->
  language_material
  
df |> 
  select(language, meaning_ru, russian_ipa_comparison) |> 
  mutate(russian_material = str_split(russian_ipa_comparison, "-")) |> 
  unnest(russian_material) ->
  russian_material

language_material |> 
  bind_cols(russian_material |> 
              select(russian_ipa_comparison, russian_material)) ->
  merged

merged |> 
  filter(str_detect(language_material, "\\#"),
         str_detect(russian_material, "0"),
         language == "Botlikh") |> 
  distinct(meaning_ru) |> 
  pull(meaning_ru) ->
  botlikh_lemma

merged |> 
  filter(str_detect(language_material, "\\#"),
         str_detect(russian_material, "0")) |> 
  select(-ipa_comparison, -russian_material, -russian_ipa_comparison) |> 
  distinct() |>
  add_count(meaning_ru) |> 
  pivot_wider(names_from = language, values_from = language_material) |> 
  View()