'BERTopic'-Style Topic Modeling Without 'Python'

Documentation for package ‘Rhobots’ version 0.1.10

Help Pages

agglomerative_clustering	Agglomerative (hierarchical) clustering
apply_mmr	Refine topic representations with Maximal Marginal Relevance (MMR)
build_dtm	Build a sparse document-term matrix from a character vector
classify_texts	Classify or label texts with a fine-tuned BERT-family model
classify_texts.default	Classify or label texts with a fine-tuned BERT-family model
classify_texts.hf_classifier	Classify or label texts with a fine-tuned BERT-family model
cls_pool	CLS-token pooling: extract the CLS hidden state as the sentence vector
cluster_docs	Fit a clustering model and return cluster labels
compare_topics	Compare topic prevalence across groups
cvalue_representation	Construct a C-value representation model
cvalue_terms	Compute C-value scores for candidate multi-word terms
c_tf_idf	Class-based TF-IDF (c-TF-IDF) for cluster-level topic terms
dim_project	Project new data using a fitted dimensionality-reduction model
dim_reduce	Fit a dimensionality-reduction model and return the reduced matrix
embed_texts	Embed a vector of texts to a numeric matrix
embed_texts.api_embedder	Embed a vector of texts to a numeric matrix
embed_texts.bert_encoder	Embed a vector of texts to a numeric matrix
embed_texts.default	Embed a vector of texts to a numeric matrix
embed_texts_cached	Compute or load document embeddings from a cache file
find_topics	Find topics most similar to a search term
fit_bertopic	Fit a BERTopic-style topic model
fit_topics_over_time	Fit independent BERTopic models per time period and align topics
get_document_info	Get document-level topic assignments as a data frame
get_representative_docs	Get representative documents for one or all topics
get_stopwords	Return the built-in stopword list for a language
get_topic	Get term-score representation for a single topic
get_topics	Get all topic-term representations
get_topic_info	Get topic-level metadata as a data frame
guided_fit_bertopic	Guided topic modeling with user-supplied seed words
hdbscan_clustering	HDBSCAN clustering
hierarchical_topics	Build a hierarchical topic tree from a fitted topic model
kmeans_clustering	K-means clustering
label_topics_llm	Label topics using a large language model
load_bertopic	Load a previously saved BERTopic model
load_bert_weights	Load BERT weights from a checkpoint into a constructed model
load_cohere_embedder	Load a Cohere embedding model
load_embeddings	Load an embedding matrix from disk
load_hf_bert	Load a BERT-family model from HuggingFace for use in R
load_hf_classifier	Load a fine-tuned BERT-family classifier from HuggingFace
load_openai_embedder	Load an OpenAI embedding model
load_specter2	Load a SPECTER2 model with a task-specific adapter
load_stopwords	Load a stopword list from a character vector, data frame, or file
make_wordpiece_tokenizer	Create a WordPiece tokenizer for BERT models that lack 'tokenizer.json'
mean_pool	Mean-pool token-level hidden states into a sentence vector
merge_topics	Manually merge a set of topics into one
no_reduction	Skip dimensionality reduction (identity pass-through)
pca_reduction	PCA dimensionality reduction
pos_dtm	Build a POS-filtered document-term matrix
pos_representation	Construct a POS-based representation model
predict.bertopic_fit	Predict topics for new documents using a fitted BERTopic model
print.bertopic_fit	Print method for bertopic_fit objects
print.bertopic_flow	Print method for bertopic_flow objects
print.bert_encoder	Print method for bert_encoder objects
print.hf_classifier	Print method for hf_classifier objects
print_topics	Pretty-print discovered topics
reduce_outliers	Reassign noise documents to the nearest real topic
reduce_topics	Reduce the number of topics by iteratively merging the most similar pair
rhobots_demo	Run a quick Rhobots demo using classic novels from Project Gutenberg
rhobots_install	Check Rhobots system dependencies and print setup instructions
save_bertopic	Save a fitted BERTopic model to disk
save_embeddings	Save an embedding matrix to disk
stability_analysis	Measure topic stability across multiple random seeds
sweep_topics	Sweep BERTopic hyperparameters and compare topic quality
topics_over_time	Compute how topic representations change over time
topic_coherence	Compute lexical coherence for discovered topics
topic_quality	Evaluate topic quality for a fitted BERTopic model
transform_bertopic	Predict topics for new documents (standalone alias)
umap_reduction	UMAP dimensionality reduction
visualize_barchart	Bar charts of top terms per topic
visualize_comparison	Interactive heatmap of topic - group associations
visualize_hierarchy	Visualise the hierarchical topic tree as a dendrogram
visualize_quality	Visualise topic quality metrics
visualize_stability	Interactive heatmap of pairwise ARI scores
visualize_sweep	Visualise the results of a parameter sweep
visualize_topics	Visualise documents in topic space
visualize_topics_over_time	Visualise topic frequency over time
visualize_topic_flow	Sankey diagram of topic flow across periods
zero_shot_topics	Zero-shot topic modeling with user-defined topic labels