R
!!!relativeFrequency 相対頻度について
{{outline}}

!!サンプルデータ　１００万語
http://www.thegrammarlab.com/?nor-portfolio=1000000-word-sample-corpora
http://micusp.elicorpora.info/
MICUSP Sample
http://www.thegrammarlab.com/?nor-portfolio=1000000-word-sample-corpora#
{{pre
#　サンプルデータを読み込む
install.packages("readtext", dependencies = T)
library(readtext)

sample100 <- readtext(choose.files())

sample100
str(sample100)

install.packages("quanteda")
library(quanteda)


sample100.corpus <- corpus(sample100)

summary(sample100.corpus)

sample100.dfm <- dfm(sample100.corpus)

summary(sample100.dfm)


sample100.tokens <- tokens(sample100orpus)
.c#サンプリング

tokens_chunk(sample100.tokens, 100)