abresler / markovifyr Goto Github PK

library(tidyverse)
library(gutenbergr)
library(markovifyR)

# system("pip install markovify")

# Step 1 -- Build the Corpus ----------------------------------------------
texts_emerson <- gutenberg_works(author == "Emerson, Ralph Waldo") %>% pull(gutenberg_id) %>% gutenberg_download(.)

texts <- texts_emerson %>% 
  sample_n(.,5000) %>% 
  pull(text) %>% 
  discard(. == "")

# Step 2 -- Build the Model -----------------------------------------------
markov_model <-
  generate_markovify_model(
    input_text = texts,
    markov_state_size = 2L,
    max_overlap_total = 25,
    max_overlap_ratio = .85
  )

library(tidyverse)
library(gutenbergr)
library(markovifyR)

# system("pip install markovify")

# Step 1 -- Build the Corpus ----------------------------------------------
texts_shake <- gutenberg_works(author == "Shakespeare, William") %>% pull(gutenberg_id) %>% gutenberg_download(.)

texts <-
  texts_shake %>% 
  sample_n(.,5000) %>% 
  pull(text) %>% 
  discard(. == "")


# Step 2 -- Build the Model -----------------------------------------------
markov_model <-
  generate_markovify_model(
    input_text = texts,
    markov_state_size = 2L,
    max_overlap_total = 25,
    max_overlap_ratio = .85
  )

R version 3.5.2 (2018-12-20)
Platform: x86_64-w64-mingw32/x64 (64-bit)
Running under: Windows >= 8 x64 (build 9200)

Matrix products: default

locale:
[1] LC_COLLATE=English_United States.1252 
[2] LC_CTYPE=English_United States.1252   
[3] LC_MONETARY=English_United States.1252
[4] LC_NUMERIC=C                          
[5] LC_TIME=English_United States.1252    

attached base packages:
[1] stats     graphics  grDevices utils     datasets 
[6] methods   base     

loaded via a namespace (and not attached):
[1] compiler_3.5.2 tools_3.5.2    yaml_2.1.19