Wordle in Russian

knitr::opts_chunk$set(echo = TRUE)

This is my approach to solving/cheating at the Russian Wordle, mildly editing my English one over there.

Package(s)

First, get the {tidyverse} loaded:

library(tidyverse)

Registered S3 methods overwritten by 'dbplyr':
  method         from
  print.tbl_lazy     
  print.tbl_sql      
-- Attaching packages ------------------- tidyverse 1.3.1 --
v ggplot2 3.3.5     v purrr   0.3.4
v tibble  3.1.6     v dplyr   1.0.7
v tidyr   1.2.0     v stringr 1.4.0
v readr   2.1.2     v forcats 0.5.1
-- Conflicts ---------------------- tidyverse_conflicts() --
x dplyr::filter() masks stats::filter()
x dplyr::lag()    masks stats::lag()

Check that the basics are working:

str_detect("когда", "..гд.")

[1] TRUE

tolower("КОГДА")

[1] "когда"

Words

I’m using the Russian version of the word list previously discussed over here, directly from the GitHub repo:

words <-
  read.csv(
    "https://raw.githubusercontent.com/hermitdave/FrequencyWords/master/content/2016/ru/ru_full.txt",
    sep = " ",
    encoding="UTF-8",
    header = FALSE
  ) %>%
  as_tibble()
names(words) <- c("word", "freq")

head(words)

The words don’t display properly; however, printing the vector works okay:

head(words) %>%
  pull(word)

[1] "я"   "не"  "что" "в"   "и"   "ты" 

Make the wordles as before:

wordles <- words %>%
  filter(str_length(word) == 5) %>%
  mutate(word = str_to_lower(word)) %>%
  arrange(desc(freq))

wordles %>%
  slice_head(n = 500) %>%
  slice_sample(n = 5) %>%
  pull(word)

[1] "убьет" "штука" "моими" "мадам" "твоём"

Helpers

Tidyverse and base R already have all the functions I need to filter this word list as we learn more about what letters are and are not in a wordle. I just want some helper functions to make them easier to use.

All words that have particular letters somewhere

all_lets_somewhere <- Vectorize(function(str, lets) {
  all(str_detect(str, strsplit(lets, "")[[1]]))
}, vectorize.args = "str")

Here’s how it works – test whether “о” is in each word:

all_lets_somewhere(c("очень", "когда"), "о")

очень когда 
 TRUE  TRUE 

Test whether “о” and “ч” are in each word:

all_lets_somewhere(c("очень", "когда"), "оч")

очень когда 
 TRUE FALSE 

All words that don’t have particular letters anywhere

no_lets_anywhere <- Vectorize(function(str, lets) {
  !any(str_detect(str, strsplit(lets, "")[[1]]))
}, vectorize.args = "str")

Here’s how it works – test whether neither “д” nor “а” are in each word:

no_lets_anywhere(c("очень", "когда"), "да")

очень когда 
 TRUE FALSE 

Filter/keep words with letters in particular positions

Wordle’s feedback can tell us that a letter is there somewhere but not in the position we guessed. str_detect already does what we need easily enough: a “.” in a regex matches any letter, so we can negate that. This is a wrapper for ease of piping:

ditch_pattern <- function(data, match) {
  data %>%
    filter(!str_detect(word, match))
}

Here’s how to use it. First, here’s the top of the wordles data:

wordles %>%
  head() %>%
  pull(word)

[1] "чтобы" "когда" "здесь" "может" "будет" "очень"

Let’s remove the word with “гд” in their third and fourth characters:

wordles %>% 
  head() %>%
  ditch_pattern("..гд.") %>%
  pull(word)

[1] "чтобы" "здесь" "может" "будет" "очень"

keep_pattern works similarly:

keep_pattern <- function(data, match) {
  data %>%
    filter(str_detect(word, match))
}

Here’s an example:

wordles %>% 
  head() %>%
  keep_pattern("..гд.") %>%
  pull(word)

[1] "когда"

Final filter helpers

These functions just make it easier to use functions above in a pipe:

ditch_letters <- function(data, match) {
  data %>%
    filter(no_lets_anywhere(word, match))
}

keep_letters <- function(data, match) {
  data %>%
    filter(all_lets_somewhere(word, match))
}

Letter frequencies

long_wordles <- function(wordles) {
  wordle_chars <- sapply(str_split(wordles$word, ""),
                         c) %>% 
  t()
  
  colnames(wordle_chars) <- paste("c", 1:5, sep = "_")
  
  bind_cols(wordles, wordle_chars %>% as_tibble()) %>%
  pivot_longer(cols = c_1:c_5,
               names_prefix = "c_",
               names_to = "pos",
               values_to = "let")
}

letter_freqs <- function(wordles) {
  n_words <- nrow(wordles)
  
  wordles %>%
    long_wordles() %>%
    group_by(word, freq, let) %>%
    summarise(n = n()) %>%
    mutate(b = as.numeric(n > 0)) %>%
    ungroup() %>%
    group_by(let) %>%
    summarise(n = n()) %>%
    ungroup() %>%
    mutate(perc = 100*n/n_words) %>%
    arrange(desc(n))    
}

Get letter frequencies for 1000 most frequent words:

wordles %>%
  head(1000) %>%
  letter_freqs() %>%
  pull(let)

`summarise()` has grouped output by 'word', 'freq'. You can override using the `.groups` argument.
 [1] "о" "а" "е" "и" "т" "л" "н" "р" "м" "с" "у" "д" "в" "к"
[15] "п" "б" "й" "ы" "ь" "з" "ж" "ш" "г" "ч" "я" "х" "ю" "ц"
[29] "ф" "э" "ё" "щ" "e" "h" "r" "t"

The most frequent letters are “о”, “а”, “е”, “и”, and “т”. Let’s find a word with as many as possible of those letters…

wordles %>%
  keep_letters("оае") %>%
  head() %>%
  pull(word)

[1] "такое" "самое" "какое" "обеда" "океан" "озера"

I’ll spare you all the steps - this was the final one:

wordles %>%
  keep_letters("ам") %>%
  keep_pattern("ма...") %>%
  ditch_letters("ткоепрняд") %>%
  ditch_pattern("...а.") %>%
  pull(word)

  [1] "малыш" "магии" "майлз" "масла" "магию" "малый"
  [7] "масса" "мафии" "майлс" "массу" "массы" "маслу"
 [13] "малым" "малых" "майли" "малую" "мафию" "мауса"
 [19] "мамма" "мамба" "масси" "мазью" "маффи" "майма"
 [25] "маюми" "магма" "малли" "магмы" "маззи" "малла"
 [31] "малум" "малии" "маймы" "мауча" "майми" "маюсь"
 [37] "мамбу" "мамчу" "магги" "малус" "маэль" "мамьi"
 [43] "мауси" "малию" "майму" "магму" "маиса" "мамми"
 [49] "мавис" "малул" "мамбы" "мааса" "маусу" "мамцы"
 [55] "мамoй" "малви" "мальц" "малэм" "маилс" "маилз"
 [61] "магси" "мафий" "маглы" "маггл" "майла" "маучу"
 [67] "малуа" "майлο" "малва" "майбл" "маглс" "маглз"
 [73] "маэла" "магли" "мацуи" "малюй" "мачли" "малюю"
 [79] "магий" "мамул" "магзи" "мамзи" "мамфи" "мацис"
 [85] "мальм" "маама" "малву" "магус" "маэза" "маммс"
 [91] "массé" "мацца" "маэлю" "майлc" "малиа" "маасу"
 [97] "мамии" "масли" "магла" "маухи" "майлу" "малха"
[103] "машиу" "маэлз" "масуи" "маббс" "мамьы" "мацуu"
[109] "малчш" "майлы" "маазы" "малйз" "мамси" "мамша"
[115] "мацзу" "маучи" "мафиг" "махis" "маблс" "маллы"
[121] "малль" "маццу" "магжи" "маcлa" "массю" "масуа"
[127] "мальы" "маcлo" "магис" "машуа" "мамбл" "массл"
[133] "маисы" "маига" "майус" "маллз" "майзл" "малуф"
[139] "маиша" "маммы" "малми" "мальй" "магсl" "машиы"
[145] "маgiс" "малич" "маггз" "мамуз" "маиии" "мазуи"
[151] "майзи" "малиш" "мазль" "маллу" "малыф" "маусы"
[157] "малфи" "мальш" "маусс" "малёх" "малуш" "магич"
[163] "мафуз"

Here’s the route I took: