yosuke-yasuda

# Path to your oh-my-zsh installation.
export ZSH=$HOME/.oh-my-zsh

# Set name of the theme to load.
# Look in ~/.oh-my-zsh/themes/
# Optionally, if you set this to "random", it'll load a random theme each
# time that oh-my-zsh is loaded.
ZSH_THEME="mortalscumbag"

# Uncomment the following line to use case-sensitive completion.

yosuke-yasuda

#' Get idf for terms
calc_idf <- function(document, term, log_scale = log, smooth_idf = FALSE){
  loadNamespace("Matrix")
  loadNamespace("text2vec")
  if(length(document)!=length(term)){
    stop("length of document and terms have to be the same")
  }
  doc_fact <- as.factor(document)
  term_fact <- as.factor(term)
  sparseMat <- Matrix::sparseMatrix(i = as.numeric(doc_fact), j = as.numeric(term_fact))

yosuke-yasuda

mecab_tokenize <- function(tbl, text_col, .drop=TRUE){
  loadNamespace("RMeCab")
  loadNamespace("tidyr")
  text_cname <- as.character(substitute(text_col))
  text <- tbl[[text_cname]]
  tokenize <- function(text){
    tokens <- unlist(RMeCab::RMeCabC(text))
    data.frame(.token = tokens, .pos = names(tokens))
  }
  if(.drop){