agricolamz

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 |> 

agricolamz

library(tidyverse)

input <- "Мой друг, которого я давно не видел, крепко спит."

tmp_input <- tempfile(fileext = ".txt")
tmp_output <- tempfile(fileext = ".txt")
write_lines(input, tmp_input)

str_c("mystem -cdni --eng-gr ", tmp_input, " ", tmp_output) |> 
  system()

agricolamz

library(tidyverse)
df <- read_csv("https://raw.githubusercontent.com/LingConLab/rutul_dialectology/master/data/database.csv")
df |> 
  select(feature_title, feature_lexeme, value, settlement, value) |> 
  filter(!is.na(value),
         value != "NO DATA",
         value != "OTHER",
         value != "\\?",
         !(settlement %in% c("Tsudik", "Borch"))) |> 
  mutate(value = str_split(value, ";")) |> 

agricolamz

library(tidyverse)
df <- read_csv("https://raw.githubusercontent.com/LingConLab/rutul_dialectology/master/data/database.csv")
df |> 
  select(feature_title, feature_lexeme, value, settlement, value) |> 
  filter(!is.na(value),
         value != "NO DATA",
         value != "OTHER",
         value != "\\?",
         !(settlement %in% c("Tsudik", "Borch"))) |> 
  mutate(value = str_split(value, ";")) |> 

agricolamz

library(tidyverse)
df <- read_csv("https://raw.githubusercontent.com/LingConLab/rutul_dialectology/master/data/database.csv")
df |> 
  select(feature_title, feature_lexeme, value, settlement, value) |> 
  filter(!is.na(value),
         value != "NO DATA",
         value != "OTHER",
         value != "\\?",
         !(settlement %in% c("Tsudik", "Borch"))) |> 
  mutate(value = str_split(value, ";")) |> 

agricolamz

library(tidyverse)
library(lingtypology)

df <- tribble(
  ~lang, ~label,
  "Andi", "андийский",
  "Northern Akhvakh", "ахвахский",
  "Chamalal", "чамалинский",
  "Godoberi", "годоберинский",
  "Botlikh", "ботлихский",

agricolamz

library(tidyverse)
read_csv("https://raw.githubusercontent.com/Timofeidedov/thesis_paper_2023/refs/heads/main/%D1%82%D0%B0%D0%B1%D0%BB%D0%B8%D1%86%D0%B0_%D1%80%D0%B0%D1%81%D0%BF%D1%80%D0%B5%D0%B4%D0%B5%D0%BB%D0%B5%D0%BD%D0%B8%D1%8F_%D0%BF%D0%BE_%D1%81%D0%BB%D0%BE%D0%B2%D0%B0%D0%BC%20-%20%D0%9B%D0%B8%D1%81%D1%821.csv") |> 
  slice(-c(35, 36)) ->
  df

df |> 
  mutate(alienable = if_else(alienable == 0, 0.9, alienable),
         inal = if_else(inal == 0, 0.9, inal)) |> 
  ggplot(aes(alienable, inal, label = перевод, color = `количество с посс`))+
  geom_point()+

agricolamz

library(tidyverse)
library(tidytext)
avar <- read_csv("avar_dict.csv")

avar |> 
  select(lemma) |> 
  unnest_characters(input = "lemma", output = "chars") |> 
  distinct(chars) |> 
  arrange(chars) |> 
  pull(chars)

agricolamz

library("asciify")
"~/Desktop/1.png" |> 
  ascii_map() |> 
  ascii_plot(charsize = 2)

agricolamz

setwd("...")
library(tidyverse)
library(lubridate)

files <- list.files(pattern = "razdel_.*txt")

walk(files, function(file){
  read_lines(file) |> 
    enframe() |> 
    filter(value != "") |>