Last updated on 2025-10-09 20:04:25 CEST.
Flavor | Version | Tinstall | Tcheck | Ttotal | Status | Flags |
---|---|---|---|---|---|---|
r-devel-linux-x86_64-debian-clang | 0.1.0 | 8.75 | 225.05 | 233.80 | NOTE | |
r-devel-linux-x86_64-debian-gcc | 0.1.0 | 10.09 | 201.99 | 212.08 | NOTE | |
r-devel-linux-x86_64-fedora-clang | 0.1.0 | 361.87 | NOTE | |||
r-devel-linux-x86_64-fedora-gcc | 0.1.0 | 336.79 | NOTE | |||
r-devel-windows-x86_64 | 0.1.0 | 16.00 | 111.00 | 127.00 | ERROR | |
r-patched-linux-x86_64 | 0.1.0 | 10.99 | 217.77 | 228.76 | NOTE | |
r-release-linux-x86_64 | 0.1.0 | 10.01 | 219.18 | 229.19 | NOTE | |
r-release-macos-arm64 | 0.1.0 | 103.00 | NOTE | |||
r-release-macos-x86_64 | 0.1.0 | 208.00 | NOTE | |||
r-release-windows-x86_64 | 0.1.0 | 12.00 | 111.00 | 123.00 | ERROR | |
r-oldrel-macos-arm64 | 0.1.0 | 47.00 | NOTE | |||
r-oldrel-macos-x86_64 | 0.1.0 | 65.00 | NOTE | |||
r-oldrel-windows-x86_64 | 0.1.0 | 15.00 | 139.00 | 154.00 | ERROR |
Version: 0.1.0
Check: CRAN incoming feasibility
Result: NOTE
Maintainer: ‘Jan Wijffels <jwijffels@bnosac.be>’
The Description field contains
David M. Blei (2019), available at <arXiv:1907.04907>.
Please refer to arXiv e-prints via their arXiv DOI <doi:10.48550/arXiv.YYMM.NNNNN>.
Flavors: r-devel-linux-x86_64-debian-clang, r-devel-linux-x86_64-debian-gcc
Version: 0.1.0
Check: Rd files
Result: NOTE
checkRd: (-1) ETM.Rd:33: Lost braces in \itemize; \value handles \item{}{} directly
checkRd: (-1) ETM.Rd:34: Lost braces in \itemize; \value handles \item{}{} directly
checkRd: (-1) ETM.Rd:35: Lost braces in \itemize; \value handles \item{}{} directly
checkRd: (-1) ETM.Rd:36: Lost braces in \itemize; \value handles \item{}{} directly
checkRd: (-1) ETM.Rd:37: Lost braces in \itemize; \value handles \item{}{} directly
Flavors: r-devel-linux-x86_64-debian-clang, r-devel-linux-x86_64-debian-gcc, r-devel-linux-x86_64-fedora-clang, r-devel-linux-x86_64-fedora-gcc, r-devel-windows-x86_64, r-patched-linux-x86_64, r-release-linux-x86_64, r-release-macos-arm64, r-release-macos-x86_64, r-release-windows-x86_64, r-oldrel-macos-arm64, r-oldrel-macos-x86_64, r-oldrel-windows-x86_64
Version: 0.1.0
Check: examples
Result: ERROR
Running examples in 'topicmodels.etm-Ex.R' failed
The error most likely occurred in:
> ### Name: ETM
> ### Title: Topic Modelling in Semantic Embedding Spaces
> ### Aliases: ETM
>
> ### ** Examples
>
> library(torch)
> library(topicmodels.etm)
> library(word2vec)
> library(udpipe)
> data(brussels_reviews_anno, package = "udpipe")
> ##
> ## Toy example with pretrained embeddings
> ##
>
> ## a. build word2vec model
> x <- subset(brussels_reviews_anno, language %in% "nl")
> x <- paste.data.frame(x, term = "lemma", group = "doc_id")
> set.seed(4321)
> w2v <- word2vec(x = x$lemma, dim = 15, iter = 20, type = "cbow", min_count = 5)
> embeddings <- as.matrix(w2v)
>
> ## b. build document term matrix on nouns + adjectives, align with the embedding terms
> dtm <- subset(brussels_reviews_anno, language %in% "nl" & upos %in% c("NOUN", "ADJ"))
> dtm <- document_term_frequencies(dtm, document = "doc_id", term = "lemma")
> dtm <- document_term_matrix(dtm)
> dtm <- dtm_conform(dtm, columns = rownames(embeddings))
> dtm <- dtm[dtm_rowsums(dtm) > 0, ]
>
> ## create and fit an embedding topic model - 8 topics, theta 100-dimensional
> if (torch::torch_is_installed()) {
+
+ set.seed(4321)
+ torch_manual_seed(4321)
+ model <- ETM(k = 8, dim = 100, embeddings = embeddings, dropout = 0.5)
+ optimizer <- optim_adam(params = model$parameters, lr = 0.005, weight_decay = 0.0000012)
+ overview <- model$fit(data = dtm, optimizer = optimizer, epoch = 40, batch_size = 1000)
+ scores <- predict(model, dtm, type = "topics")
+
+ lastbatch <- subset(overview$loss, overview$loss$batch_is_last == TRUE)
+ plot(lastbatch$epoch, lastbatch$loss)
+ plot(overview$loss_test)
+
+ ## show top words in each topic
+ terminology <- predict(model, type = "terms", top_n = 7)
+ terminology
+
+ ##
+ ## Toy example without pretrained word embeddings
+ ##
+ set.seed(4321)
+ torch_manual_seed(4321)
+ model <- ETM(k = 8, dim = 100, embeddings = 15, dropout = 0.5, vocab = colnames(dtm))
+ optimizer <- optim_adam(params = model$parameters, lr = 0.005, weight_decay = 0.0000012)
+ overview <- model$fit(data = dtm, optimizer = optimizer, epoch = 40, batch_size = 1000)
+ terminology <- predict(model, type = "terms", top_n = 7)
+ terminology
+
+
+
+ ## Don't show:
+ ##
+ ## Another example using fit_original
+ ##
+ data(ng20, package = "topicmodels.etm")
+ vocab <- ng20$vocab
+ tokens <- ng20$bow_tr$tokens
+ counts <- ng20$bow_tr$counts
+
+ torch_manual_seed(123456789)
+ model <- ETM(k = 4, vocab = vocab, dim = 5, embeddings = 25)
+ model
+ optimizer <- optim_adam(params = model$parameters, lr = 0.005, weight_decay = 0.0000012)
+
+ traindata <- list(tokens = tokens, counts = counts, vocab = vocab)
+ test1 <- list(tokens = ng20$bow_ts_h1$tokens, counts = ng20$bow_ts_h1$counts, vocab = vocab)
+ test2 <- list(tokens = ng20$bow_ts_h2$tokens, counts = ng20$bow_ts_h2$counts, vocab = vocab)
+
+ out <- model$fit_original(data = traindata, test1 = test1, test2 = test2, epoch = 4,
+ optimizer = optimizer, batch_size = 1000,
+ lr_anneal_factor = 4, lr_anneal_nonmono = 10)
+ test <- subset(out$loss, out$loss$batch_is_last == TRUE)
+ plot(test$epoch, test$loss)
+
+ topic.centers <- as.matrix(model, type = "embedding", which = "topics")
+ word.embeddings <- as.matrix(model, type = "embedding", which = "words")
+ topic.terminology <- as.matrix(model, type = "beta")
+
+ terminology <- predict(model, type = "terms", top_n = 4)
+ terminology
+ ## End(Don't show)
+
+ }
Flavors: r-devel-windows-x86_64, r-release-windows-x86_64, r-oldrel-windows-x86_64
These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.
Health stats visible at Monitor.