y <- get_count_vector(
corpus = "REUTERS", p_attribute = "word",
registry = get_tmp_registry()
)
df <- data.frame(token_id = 0:(length(y) - 1), count = y)
df[["token"]] <- cl_id2str(
"REUTERS", p_attribute = "word",
id = df[["token_id"]], registry = get_tmp_registry()
)
df <- df[,c("token", "token_id", "count")] # reorder columns
df <- df[order(df[["count"]], decreasing = TRUE),]
head(df)
Run the code above in your browser using DataLab