Man pages for activetext/activeR
a semi-supervised active learning algorithm for text classification.
| active_initial_messages | Prints initial messages for active sampling, if needed. |
| active_label | Active Learning EM Algorithm |
| active_label_from_saved | Active Learning EM Algorithm |
| active_label_wrapper | Active Learning EM Algorithm |
| agg_helper_convert | Aggregation Helper |
| aggregate_model_predictions | Aggregate Model Predictions |
| balancing_data | Create a (un)balanced dataset with specified size and ratio... |
| check_extreme_words_inlabel | Check how often the extreme words are in the labeled... |
| check_lr_convergence | check for convergence if using log-ratio sampling |
| choose_best_model | Choose best model. |
| classification_gui | GUI to select labels. |
| clean_data | Structure Data |
| EM | EM algorithm |
| E_step | E step of the EM algorithm |
| E_step_multi | E step with multiple cluster |
| generate_lambda_vec | Creates a vector of lambdas depending on decay value |
| gen_results_tbl | Generate Results Table |
| get_alpha_m | Get alpha_m |
| get_classes | Get Classes |
| get_class_matrix | Get Document Class Probability Matrix |
| get_class_prob | get weighted log of class probability |
| get_class_prob_log | get weighted log of class probability |
| get_class_prob_NB | NB step, class probability |
| get_clusters | Get Clusters |
| get_conf_matrix_weight | Obtain weighted False negative and false positive in the... |
| get_dfm | Get Document Feature Matrix |
| get_empirical_dist | Get True Empirical Word Distributions. |
| get_entropy | Get Entropy Value |
| get_fixed_words_mtx | Get a Matrix of Fixed Words and Class Probabilities. |
| get_index | Get Index |
| get_initial_documents | gets initial documents for active learning algorithm |
| get_keywords | Get Keywords |
| get_label_prop_fig | Get Label Proportion Figure |
| get_maximand | get maximand. Use this to check if the EM keeps incrasing... |
| get_mean_mpe | Get Mean Prediction Error Singular |
| get_mean_mpes | Get Mean Prediction Error |
| get_model_diff | Get Difference Between Model Parameters |
| get_model_weights | Get Model Weights |
| get_predict_prop_fig | Get Prediction Probability Figure |
| get_results_matrix | Get Results Matrix for active_EM Output. |
| get_tune_lambda_fig | Gets Tune Lambda Figure |
| get_uncertain_docs | Get Uncertain Documents |
| get_weighted_prediction | Get Weighted Prediction |
| get_word_prob | get log likelihood of a document |
| get_word_prob_log | get log likelihood of a document |
| get_word_prob_NB | Get Word Probability (Naive Bayes) |
| initialize_beta_tbl | initializes a table of prior values for eta |
| KL | KL Divergence Function |
| log_ratio_sample | Log-Ratio Sampling |
| match_clusters_to_docs | Match Multicluster EM Output to Document Matrix |
| match_EM_to_docs | Match EM Output to Document Matrix |
| multiEM | EM algorithm |
| process_metadata | Process Model Metadata |
| query_eta | Query Eta |
| query_label | Label Query |
| region_sample | Log-Ratio Region Sampling |
| region_sample_edge | Log-Ratio Region Sampling |
| reshapedocs | reshape docs object such that the prediction at each... |
| reshapedocs_helper | (helper) reshape docs object such that the prediction at each... |
| run_unsupervised_EM | Run Unsupervised EM |
| sample_data | get a sample of dataset with a specific proportion of... |
| split_dfm | Splits Document Term Matrix into two parts. |
| split_sparsemat | Split DTM into positive and negative label areas Extract... |
| tune_lambda | Tune Lambda Weight and Number of Clusters |
| tune_lambda_helper | Helper Function for 'Tune_Lambda()' |
| tune_lambda_in_active | Tunes lambda value at each iteraction, if enabled |
| tuning_algorithm | Active EM Parameter Tuning Algorithm |
| update_results | Update model results. |
