Package index
Corpus Preparation
Turn raw JSON filings into cleaned, tokenized quanteda corpora ready for downstream analysis.
-
from_json_to_df() - Convert JSON to data.table
-
define_corpus() - Generate a Quanteda Corpus from a Data Table
-
tokenize_corpus() - Fast Corpus Tokenization
-
singularize_tokens() - Fast Tokens Singularization
-
reshape_corpus() - Fast Corpus Reshape
-
lookup_tokens() - Fast Tokens Lookup
Token Preprocessing
Build n-grams, detect and compound collocations, stem or lemmatize tokens, and weight document-feature matrices.
-
ngram_tokens() - Construct Token N-Grams
-
detect_collocations() - Detect Candidate Multiword Expressions
-
compound_tokens() - Compound Multiword Expressions into Single Tokens
-
stem_tokens() - Stem Tokens
-
lemmatize_tokens() - Lemmatize Tokens
-
weight_dfm() - Weight a Document-Feature Matrix
Document-Level Analysis
Per-document summaries, readability scores, similarity, distance, and linguistic parsing.
-
summarize_corpus() - Fast Corpus Summarization
-
calculate_readability() - Fast Calculation of Readability Measures
-
calculate_similarity()calculate_distance() - Fast Calculation of Similarity and Distance Measures
-
parse_corpus() - Fast Corpus Parsing via spaCy
-
data_dictionary_BozanicRoulstoneVanBuskirk_FLS - Bozanic Roulstone VanBuskirk Forward Looking Statement Dictionary
-
data_dictionary_Cannon_Ling_Wang_Watanabe - Cannon, Ling, Wang, and Watanabe CSR Dictionary
-
data_dictionary_Li_FLS - Feng Li Forward Looking Statement Dictionary
-
data_dictionary_LoughranMcDonald_Complexity - Loughran and McDonald Firm Complexity Dictionary
-
data_dictionary_SDG - U.N. Sustainable Development Goals (SDG) Mapping Dictionary
Topic Model API
Engine-agnostic fit, adopt, extract, predict, evaluate, select-K, and stability workflows.
-
fit_topic_model() - Fit a Topic Model Via a Unified API
-
as_nlp_topic_fit() - Convert Existing Topic-Model Objects to
nlp_topic_fit -
get_dtw() - Extract Standardized Document Topic Weights
-
get_tww() - Extract Standardized Topic Word Weights
-
get_top_terms() - Extract Top Terms from Standardized TWW
-
predict_topic_model() - Predict Document Topic Weights for New Data
-
evaluate_topic_model() - Evaluate a Fitted Topic Model
-
select_k_topics() - Select the Number of Topics by Grid Search
-
summarize_k_selection() - Summarize Topic-Count Selection Results
-
assess_topic_stability() - Assess Topic Stability Across Repeated Fits
-
summarize_topics() - Summarize Topics for Interpretation
-
get_representative_candidates() - Extract Representative Topic Candidates
Topic Model Plots and Backends
Top-term and DTW plots plus STM-native labels, hyperparameters, and embedding helpers.
-
plot_top_terms() - Visualize Topic-Word Probabilities
-
plot_dtw() - Plot the Distribution of Document Topic Weights
-
get_stm_topic_labels() - Extract STM Topic Labels
-
summarize_stm_topics() - Summarize STM Topics
-
estimate_stm_topic_effects() - Estimate STM Topic Effects
-
get_topic_hyperparameters() - Extract Topic-Model Hyperparameters
-
get_topic_embeddings() - Extract ETM Topic Embeddings
-
get_term_embeddings() - Extract ETM Term Embeddings
-
plot_topic_embeddings() - Plot ETM Topic Embeddings
OpTop Interoperability
Convert NLPstudio DFMs and topic fits into inputs consumable by the OpTop package.
-
as_optop_weighted_dfm() - Prepare Weighted DFM Input for OpTop
-
as_optop_input() - Prepare NLPstudio Topic Models for OpTop
-
plot(<nlp_k_selection>) - Plot Topic-Count Selection Results
-
print(<nlp_k_selection>) - Print a Compact Summary of Topic-Count Selection Results
-
print(<nlp_k_selection_summary>) - Print K-selection summary
-
print(<nlp_optop_input>) - Print OpTop input summary
-
print(<nlp_topic_fit>) - Print a Compact Summary of a Topic-Model Fit
-
print(<nlp_topic_stability>) - Print Topic Stability Results