R/RcppExports.R

Defines functions C_tokenize C_ngram_weights C_wordgram C_is_ascii C_tcm C_tdm C_dtm C_corpus2ixmat C_corpus2ixdf C_corpus2ixseq C_rehash_vocab C_prune_embeddings C_vocab murmur3hash

# Generated by using Rcpp::compileAttributes() -> do not edit by hand
# Generator token: 10BE3573-1514-4C36-9D1C-5A225CD40393

murmur3hash <- function(x) {
    .Call(`_mlvocab_murmur3hash`, x)
}

C_vocab <- function(corpus0, oldvocab) {
    .Call(`_mlvocab_C_vocab`, corpus0, oldvocab)
}

C_prune_embeddings <- function(vocabdf, embeddings, by_row, nbuckets, min_to_average) {
    .Call(`_mlvocab_C_prune_embeddings`, vocabdf, embeddings, by_row, nbuckets, min_to_average)
}

C_rehash_vocab <- function(pruned_vocabdf, orig_vocabdf, nbuckets) {
    .Call(`_mlvocab_C_rehash_vocab`, pruned_vocabdf, orig_vocabdf, nbuckets)
}

C_corpus2ixseq <- function(corpus0, vocabdf, keep_unknown, nbuckets, reverse) {
    .Call(`_mlvocab_C_corpus2ixseq`, corpus0, vocabdf, keep_unknown, nbuckets, reverse)
}

C_corpus2ixdf <- function(corpus0, vocabdf, keep_unknown, nbuckets, reverse, asfactor) {
    .Call(`_mlvocab_C_corpus2ixdf`, corpus0, vocabdf, keep_unknown, nbuckets, reverse, asfactor)
}

C_corpus2ixmat <- function(corpus0, vocabdf, maxlen, pad_right, trunc_right, keep_unknown, nbuckets, reverse) {
    .Call(`_mlvocab_C_corpus2ixmat`, corpus0, vocabdf, maxlen, pad_right, trunc_right, keep_unknown, nbuckets, reverse)
}

C_dtm <- function(corpus0, vocabdf, term_weights, nbuckets, output, ngram_min, ngram_max) {
    .Call(`_mlvocab_C_dtm`, corpus0, vocabdf, term_weights, nbuckets, output, ngram_min, ngram_max)
}

C_tdm <- function(corpus0, vocabdf, term_weights, nbuckets, output, ngram_min, ngram_max) {
    .Call(`_mlvocab_C_tdm`, corpus0, vocabdf, term_weights, nbuckets, output, ngram_min, ngram_max)
}

C_tcm <- function(corpus0, vocabdf, term_weights, nbuckets, output, window_size, window_weights, context, ngram_min, ngram_max) {
    .Call(`_mlvocab_C_tcm`, corpus0, vocabdf, term_weights, nbuckets, output, window_size, window_weights, context, ngram_min, ngram_max)
}

C_is_ascii <- function(vec) {
    .Call(`_mlvocab_C_is_ascii`, vec)
}

C_wordgram <- function(vec, ngram_min, ngram_max, sep) {
    .Call(`_mlvocab_C_wordgram`, vec, ngram_min, ngram_max, sep)
}

C_ngram_weights <- function(weights, ngram_min, ngram_max) {
    .Call(`_mlvocab_C_ngram_weights`, weights, ngram_min, ngram_max)
}

C_tokenize <- function(input, rx) {
    .Call(`_mlvocab_C_tokenize`, input, rx)
}

Try the mlvocab package in your browser

Any scripts or data that you put into this service are public.

mlvocab documentation built on Sept. 21, 2018, 6:35 p.m.