├── .DS_Store ├── .Rbuildignore ├── .gitignore ├── .travis.yml ├── DESCRIPTION ├── NAMESPACE ├── R ├── .DS_Store ├── ACMI_contribution.R ├── Data_Documentation.R ├── Package_Documentation.R ├── RcppExports.R ├── calculate_ACMI_R.R ├── calculate_document_pair_distances.R ├── check_directory_name.R ├── clean_document_text.R ├── color_word_table.R ├── color_words_by_frequency.R ├── combine_document_term_matrices.R ├── compare_tf_idf_scalings.R ├── contingency_table.R ├── convert_quanteda_to_slam.R ├── corenlp.R ├── corenlp_blocked.R ├── count_ngrams.R ├── count_words.R ├── dice_coefficient_diff_table.R ├── dice_coefficient_line_matching.R ├── distinct_words.R ├── document_similarities.R ├── download_corenlp.R ├── download_mallet.R ├── edit_metrics.R ├── estimate_plots.R ├── extract_jk.R ├── extract_ngrams.R ├── extract_verbs.R ├── feature_selection.R ├── fightin_words_plot.R ├── frequency_threshold.R ├── generate_blocked_document_term_vectors.R ├── generate_document_term_matrix.R ├── generate_document_term_vectors.R ├── get_file_paths.R ├── get_term_topics.R ├── get_unique_values_and_counts.R ├── kill_zombies.R ├── mallet_lda.R ├── multi_dice_coefficient_matching.R ├── multi_plot.R ├── mutual_information.R ├── ngram_sequence_matching.R ├── ngram_sequence_plot.R ├── ngrams.R ├── ngrams_single_block.R ├── ngrams_single_document.R ├── order_by_counts.R ├── output_ngrams.R ├── parallel_sequence_matching.R ├── pmi.R ├── reference_distribution_distance.R ├── sparse_doc_term_parallel.R ├── sparse_large_document_term_matrix.R ├── sparse_to_dense_matrix.R ├── speed_set_vocabulary.R ├── subsume_ngrams.R ├── tfidf.R ├── topic_coherence.R ├── unlist_and_concatenate.R └── zzz.R ├── README.md ├── SpeedReader.Rproj ├── data ├── .DS_Store ├── Processed_Text.rda ├── congress_bills.rda ├── document_term_count_list.rda ├── document_term_vector_list.rda └── sotu_corp.rda ├── inst ├── .DS_Store └── extdata │ ├── .DS_Store │ ├── Block_1.Rdata │ ├── Block_2.Rdata │ ├── bill1.phrases.tsv │ ├── bill2.phrases.tsv │ ├── bill3.phrases.tsv │ ├── bill4.phrases.tsv │ ├── bill5.phrases.tsv │ ├── speech_1.txt │ └── speech_2.txt ├── man ├── .DS_Store ├── .Rapp.history ├── ACMI_contribution.Rd ├── Processed_Text.Rd ├── SpeedReader.Rd ├── calculate_document_pair_distances.Rd ├── check_directory_name.Rd ├── clean_document_text.Rd ├── color_word_table.Rd ├── color_words_by_frequency.Rd ├── combine_document_term_matrices.Rd ├── compare_tf_idf_scalings.Rd ├── congress_bills.Rd ├── contingency_table.Rd ├── convert_quanteda_to_slam.Rd ├── corenlp.Rd ├── corenlp_blocked.Rd ├── count_ngrams.Rd ├── count_words.Rd ├── dice_coefficient_diff_table.Rd ├── dice_coefficient_line_matching.Rd ├── distinct_words.Rd ├── document_similarities.Rd ├── document_term_count_list.Rd ├── document_term_vector_list.Rd ├── download_corenlp.Rd ├── download_mallet.Rd ├── edit_metrics.Rd ├── estimate_plots.Rd ├── feature_selection.Rd ├── fightin_words_plot.Rd ├── frequency_threshold.Rd ├── generate_blocked_document_term_vectors.Rd ├── generate_document_term_matrix.Rd ├── generate_document_term_vectors.Rd ├── generate_sparse_large_document_term_matrix.Rd ├── get_file_paths.Rd ├── get_unique_values_and_counts.Rd ├── kill_zombies.Rd ├── mallet_lda.Rd ├── multi_dice_coefficient_matching.Rd ├── multi_plot.Rd ├── mutual_information.Rd ├── ngram_sequence_matching.Rd ├── ngram_sequnce_plot.Rd ├── ngrams.Rd ├── order_by_counts.Rd ├── pmi.Rd ├── reference_distribution_distance.Rd ├── sparse_doc_term_parallel.Rd ├── sparse_to_dense_matrix.Rd ├── speed_set_vocabulary.Rd ├── tfidf.Rd ├── topic_coherence.Rd └── unlist_and_concatenate.Rd ├── src ├── .DS_Store ├── Calculate_TFIDF.cpp ├── Col_and_Row_Sums.cpp ├── Combine_Document_Term_Matrices.cpp ├── Count_Words.cpp ├── Efficient_Block_Sequential_String_Set_Hash_Comparison.cpp ├── Fast_Mutual_Information.cpp ├── Fast_Sparse_Mutual_Information.cpp ├── Generate_Document_Word_Matrix.cpp ├── Generate_Sparse_Document_Word_Matrix.cpp ├── Generate_Sparse_Document_Word_Matrix_Stem_Vocabulary.cpp ├── LineWise_Dice_Coefficients.cpp ├── Makevars ├── Makevars.win ├── Mutual_Information.cpp ├── RcppExports.cpp ├── Sparse_Document_Frequencies.cpp ├── Sparse_PMI_Statistics.cpp ├── Variable_Dice_Coefficients.cpp ├── calculate_ACMI_contribution.cpp ├── calculate_document_frequency.cpp └── reference_dist_distance.cpp ├── tests ├── .DS_Store ├── testthat.R └── testthat │ ├── test_clean_document_text.R │ ├── test_corenlp.R │ ├── test_count_ngrams.R │ ├── test_document_similarities.R │ ├── test_document_similarities_2.R │ ├── test_generate_blocked_document_term_vectors.R │ ├── test_generate_contingency_table.R │ ├── test_generate_document_term_matrix.R │ ├── test_generate_document_term_vectors.R │ ├── test_mallet_lda.R │ ├── test_ngrams.R │ ├── test_pmi.R │ ├── test_sparse_doc_term_parallel.R │ ├── test_sparse_large_document_term_matrix.R │ ├── test_speed_set_vocabulary.R │ ├── test_tfidf.R │ └── test_word_counter.R └── vignettes └── getting_started_with_SpeedReader.Rmd /.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/.DS_Store -------------------------------------------------------------------------------- /.Rbuildignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/.Rbuildignore -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/.gitignore -------------------------------------------------------------------------------- /.travis.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/.travis.yml -------------------------------------------------------------------------------- /DESCRIPTION: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/DESCRIPTION -------------------------------------------------------------------------------- /NAMESPACE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/NAMESPACE -------------------------------------------------------------------------------- /R/.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/.DS_Store -------------------------------------------------------------------------------- /R/ACMI_contribution.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/ACMI_contribution.R -------------------------------------------------------------------------------- /R/Data_Documentation.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/Data_Documentation.R -------------------------------------------------------------------------------- /R/Package_Documentation.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/Package_Documentation.R -------------------------------------------------------------------------------- /R/RcppExports.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/RcppExports.R -------------------------------------------------------------------------------- /R/calculate_ACMI_R.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/calculate_ACMI_R.R -------------------------------------------------------------------------------- /R/calculate_document_pair_distances.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/calculate_document_pair_distances.R -------------------------------------------------------------------------------- /R/check_directory_name.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/check_directory_name.R -------------------------------------------------------------------------------- /R/clean_document_text.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/clean_document_text.R -------------------------------------------------------------------------------- /R/color_word_table.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/color_word_table.R -------------------------------------------------------------------------------- /R/color_words_by_frequency.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/color_words_by_frequency.R -------------------------------------------------------------------------------- /R/combine_document_term_matrices.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/combine_document_term_matrices.R -------------------------------------------------------------------------------- /R/compare_tf_idf_scalings.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/compare_tf_idf_scalings.R -------------------------------------------------------------------------------- /R/contingency_table.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/contingency_table.R -------------------------------------------------------------------------------- /R/convert_quanteda_to_slam.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/convert_quanteda_to_slam.R -------------------------------------------------------------------------------- /R/corenlp.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/corenlp.R -------------------------------------------------------------------------------- /R/corenlp_blocked.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/corenlp_blocked.R -------------------------------------------------------------------------------- /R/count_ngrams.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/count_ngrams.R -------------------------------------------------------------------------------- /R/count_words.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/count_words.R -------------------------------------------------------------------------------- /R/dice_coefficient_diff_table.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/dice_coefficient_diff_table.R -------------------------------------------------------------------------------- /R/dice_coefficient_line_matching.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/dice_coefficient_line_matching.R -------------------------------------------------------------------------------- /R/distinct_words.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/distinct_words.R -------------------------------------------------------------------------------- /R/document_similarities.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/document_similarities.R -------------------------------------------------------------------------------- /R/download_corenlp.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/download_corenlp.R -------------------------------------------------------------------------------- /R/download_mallet.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/download_mallet.R -------------------------------------------------------------------------------- /R/edit_metrics.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/edit_metrics.R -------------------------------------------------------------------------------- /R/estimate_plots.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/estimate_plots.R -------------------------------------------------------------------------------- /R/extract_jk.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/extract_jk.R -------------------------------------------------------------------------------- /R/extract_ngrams.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/extract_ngrams.R -------------------------------------------------------------------------------- /R/extract_verbs.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/extract_verbs.R -------------------------------------------------------------------------------- /R/feature_selection.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/feature_selection.R -------------------------------------------------------------------------------- /R/fightin_words_plot.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/fightin_words_plot.R -------------------------------------------------------------------------------- /R/frequency_threshold.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/frequency_threshold.R -------------------------------------------------------------------------------- /R/generate_blocked_document_term_vectors.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/generate_blocked_document_term_vectors.R -------------------------------------------------------------------------------- /R/generate_document_term_matrix.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/generate_document_term_matrix.R -------------------------------------------------------------------------------- /R/generate_document_term_vectors.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/generate_document_term_vectors.R -------------------------------------------------------------------------------- /R/get_file_paths.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/get_file_paths.R -------------------------------------------------------------------------------- /R/get_term_topics.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/get_term_topics.R -------------------------------------------------------------------------------- /R/get_unique_values_and_counts.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/get_unique_values_and_counts.R -------------------------------------------------------------------------------- /R/kill_zombies.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/kill_zombies.R -------------------------------------------------------------------------------- /R/mallet_lda.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/mallet_lda.R -------------------------------------------------------------------------------- /R/multi_dice_coefficient_matching.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/multi_dice_coefficient_matching.R -------------------------------------------------------------------------------- /R/multi_plot.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/multi_plot.R -------------------------------------------------------------------------------- /R/mutual_information.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/mutual_information.R -------------------------------------------------------------------------------- /R/ngram_sequence_matching.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/ngram_sequence_matching.R -------------------------------------------------------------------------------- /R/ngram_sequence_plot.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/ngram_sequence_plot.R -------------------------------------------------------------------------------- /R/ngrams.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/ngrams.R -------------------------------------------------------------------------------- /R/ngrams_single_block.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/ngrams_single_block.R -------------------------------------------------------------------------------- /R/ngrams_single_document.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/ngrams_single_document.R -------------------------------------------------------------------------------- /R/order_by_counts.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/order_by_counts.R -------------------------------------------------------------------------------- /R/output_ngrams.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/output_ngrams.R -------------------------------------------------------------------------------- /R/parallel_sequence_matching.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/parallel_sequence_matching.R -------------------------------------------------------------------------------- /R/pmi.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/pmi.R -------------------------------------------------------------------------------- /R/reference_distribution_distance.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/reference_distribution_distance.R -------------------------------------------------------------------------------- /R/sparse_doc_term_parallel.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/sparse_doc_term_parallel.R -------------------------------------------------------------------------------- /R/sparse_large_document_term_matrix.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/sparse_large_document_term_matrix.R -------------------------------------------------------------------------------- /R/sparse_to_dense_matrix.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/sparse_to_dense_matrix.R -------------------------------------------------------------------------------- /R/speed_set_vocabulary.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/speed_set_vocabulary.R -------------------------------------------------------------------------------- /R/subsume_ngrams.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/subsume_ngrams.R -------------------------------------------------------------------------------- /R/tfidf.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/tfidf.R -------------------------------------------------------------------------------- /R/topic_coherence.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/topic_coherence.R -------------------------------------------------------------------------------- /R/unlist_and_concatenate.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/unlist_and_concatenate.R -------------------------------------------------------------------------------- /R/zzz.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/R/zzz.R -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/README.md -------------------------------------------------------------------------------- /SpeedReader.Rproj: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/SpeedReader.Rproj -------------------------------------------------------------------------------- /data/.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/data/.DS_Store -------------------------------------------------------------------------------- /data/Processed_Text.rda: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/data/Processed_Text.rda -------------------------------------------------------------------------------- /data/congress_bills.rda: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/data/congress_bills.rda -------------------------------------------------------------------------------- /data/document_term_count_list.rda: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/data/document_term_count_list.rda -------------------------------------------------------------------------------- /data/document_term_vector_list.rda: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/data/document_term_vector_list.rda -------------------------------------------------------------------------------- /data/sotu_corp.rda: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/data/sotu_corp.rda -------------------------------------------------------------------------------- /inst/.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/inst/.DS_Store -------------------------------------------------------------------------------- /inst/extdata/.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/inst/extdata/.DS_Store -------------------------------------------------------------------------------- /inst/extdata/Block_1.Rdata: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/inst/extdata/Block_1.Rdata -------------------------------------------------------------------------------- /inst/extdata/Block_2.Rdata: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/inst/extdata/Block_2.Rdata -------------------------------------------------------------------------------- /inst/extdata/bill1.phrases.tsv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/inst/extdata/bill1.phrases.tsv -------------------------------------------------------------------------------- /inst/extdata/bill2.phrases.tsv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/inst/extdata/bill2.phrases.tsv -------------------------------------------------------------------------------- /inst/extdata/bill3.phrases.tsv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/inst/extdata/bill3.phrases.tsv -------------------------------------------------------------------------------- /inst/extdata/bill4.phrases.tsv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/inst/extdata/bill4.phrases.tsv -------------------------------------------------------------------------------- /inst/extdata/bill5.phrases.tsv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/inst/extdata/bill5.phrases.tsv -------------------------------------------------------------------------------- /inst/extdata/speech_1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/inst/extdata/speech_1.txt -------------------------------------------------------------------------------- /inst/extdata/speech_2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/inst/extdata/speech_2.txt -------------------------------------------------------------------------------- /man/.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/.DS_Store -------------------------------------------------------------------------------- /man/.Rapp.history: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /man/ACMI_contribution.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/ACMI_contribution.Rd -------------------------------------------------------------------------------- /man/Processed_Text.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/Processed_Text.Rd -------------------------------------------------------------------------------- /man/SpeedReader.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/SpeedReader.Rd -------------------------------------------------------------------------------- /man/calculate_document_pair_distances.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/calculate_document_pair_distances.Rd -------------------------------------------------------------------------------- /man/check_directory_name.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/check_directory_name.Rd -------------------------------------------------------------------------------- /man/clean_document_text.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/clean_document_text.Rd -------------------------------------------------------------------------------- /man/color_word_table.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/color_word_table.Rd -------------------------------------------------------------------------------- /man/color_words_by_frequency.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/color_words_by_frequency.Rd -------------------------------------------------------------------------------- /man/combine_document_term_matrices.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/combine_document_term_matrices.Rd -------------------------------------------------------------------------------- /man/compare_tf_idf_scalings.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/compare_tf_idf_scalings.Rd -------------------------------------------------------------------------------- /man/congress_bills.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/congress_bills.Rd -------------------------------------------------------------------------------- /man/contingency_table.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/contingency_table.Rd -------------------------------------------------------------------------------- /man/convert_quanteda_to_slam.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/convert_quanteda_to_slam.Rd -------------------------------------------------------------------------------- /man/corenlp.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/corenlp.Rd -------------------------------------------------------------------------------- /man/corenlp_blocked.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/corenlp_blocked.Rd -------------------------------------------------------------------------------- /man/count_ngrams.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/count_ngrams.Rd -------------------------------------------------------------------------------- /man/count_words.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/count_words.Rd -------------------------------------------------------------------------------- /man/dice_coefficient_diff_table.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/dice_coefficient_diff_table.Rd -------------------------------------------------------------------------------- /man/dice_coefficient_line_matching.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/dice_coefficient_line_matching.Rd -------------------------------------------------------------------------------- /man/distinct_words.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/distinct_words.Rd -------------------------------------------------------------------------------- /man/document_similarities.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/document_similarities.Rd -------------------------------------------------------------------------------- /man/document_term_count_list.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/document_term_count_list.Rd -------------------------------------------------------------------------------- /man/document_term_vector_list.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/document_term_vector_list.Rd -------------------------------------------------------------------------------- /man/download_corenlp.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/download_corenlp.Rd -------------------------------------------------------------------------------- /man/download_mallet.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/download_mallet.Rd -------------------------------------------------------------------------------- /man/edit_metrics.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/edit_metrics.Rd -------------------------------------------------------------------------------- /man/estimate_plots.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/estimate_plots.Rd -------------------------------------------------------------------------------- /man/feature_selection.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/feature_selection.Rd -------------------------------------------------------------------------------- /man/fightin_words_plot.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/fightin_words_plot.Rd -------------------------------------------------------------------------------- /man/frequency_threshold.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/frequency_threshold.Rd -------------------------------------------------------------------------------- /man/generate_blocked_document_term_vectors.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/generate_blocked_document_term_vectors.Rd -------------------------------------------------------------------------------- /man/generate_document_term_matrix.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/generate_document_term_matrix.Rd -------------------------------------------------------------------------------- /man/generate_document_term_vectors.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/generate_document_term_vectors.Rd -------------------------------------------------------------------------------- /man/generate_sparse_large_document_term_matrix.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/generate_sparse_large_document_term_matrix.Rd -------------------------------------------------------------------------------- /man/get_file_paths.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/get_file_paths.Rd -------------------------------------------------------------------------------- /man/get_unique_values_and_counts.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/get_unique_values_and_counts.Rd -------------------------------------------------------------------------------- /man/kill_zombies.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/kill_zombies.Rd -------------------------------------------------------------------------------- /man/mallet_lda.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/mallet_lda.Rd -------------------------------------------------------------------------------- /man/multi_dice_coefficient_matching.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/multi_dice_coefficient_matching.Rd -------------------------------------------------------------------------------- /man/multi_plot.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/multi_plot.Rd -------------------------------------------------------------------------------- /man/mutual_information.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/mutual_information.Rd -------------------------------------------------------------------------------- /man/ngram_sequence_matching.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/ngram_sequence_matching.Rd -------------------------------------------------------------------------------- /man/ngram_sequnce_plot.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/ngram_sequnce_plot.Rd -------------------------------------------------------------------------------- /man/ngrams.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/ngrams.Rd -------------------------------------------------------------------------------- /man/order_by_counts.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/order_by_counts.Rd -------------------------------------------------------------------------------- /man/pmi.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/pmi.Rd -------------------------------------------------------------------------------- /man/reference_distribution_distance.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/reference_distribution_distance.Rd -------------------------------------------------------------------------------- /man/sparse_doc_term_parallel.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/sparse_doc_term_parallel.Rd -------------------------------------------------------------------------------- /man/sparse_to_dense_matrix.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/sparse_to_dense_matrix.Rd -------------------------------------------------------------------------------- /man/speed_set_vocabulary.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/speed_set_vocabulary.Rd -------------------------------------------------------------------------------- /man/tfidf.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/tfidf.Rd -------------------------------------------------------------------------------- /man/topic_coherence.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/topic_coherence.Rd -------------------------------------------------------------------------------- /man/unlist_and_concatenate.Rd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/man/unlist_and_concatenate.Rd -------------------------------------------------------------------------------- /src/.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/src/.DS_Store -------------------------------------------------------------------------------- /src/Calculate_TFIDF.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/src/Calculate_TFIDF.cpp -------------------------------------------------------------------------------- /src/Col_and_Row_Sums.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/src/Col_and_Row_Sums.cpp -------------------------------------------------------------------------------- /src/Combine_Document_Term_Matrices.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/src/Combine_Document_Term_Matrices.cpp -------------------------------------------------------------------------------- /src/Count_Words.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/src/Count_Words.cpp -------------------------------------------------------------------------------- /src/Efficient_Block_Sequential_String_Set_Hash_Comparison.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/src/Efficient_Block_Sequential_String_Set_Hash_Comparison.cpp -------------------------------------------------------------------------------- /src/Fast_Mutual_Information.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/src/Fast_Mutual_Information.cpp -------------------------------------------------------------------------------- /src/Fast_Sparse_Mutual_Information.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/src/Fast_Sparse_Mutual_Information.cpp -------------------------------------------------------------------------------- /src/Generate_Document_Word_Matrix.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/src/Generate_Document_Word_Matrix.cpp -------------------------------------------------------------------------------- /src/Generate_Sparse_Document_Word_Matrix.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/src/Generate_Sparse_Document_Word_Matrix.cpp -------------------------------------------------------------------------------- /src/Generate_Sparse_Document_Word_Matrix_Stem_Vocabulary.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/src/Generate_Sparse_Document_Word_Matrix_Stem_Vocabulary.cpp -------------------------------------------------------------------------------- /src/LineWise_Dice_Coefficients.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/src/LineWise_Dice_Coefficients.cpp -------------------------------------------------------------------------------- /src/Makevars: -------------------------------------------------------------------------------- 1 | CXX_STD = CXX11 -------------------------------------------------------------------------------- /src/Makevars.win: -------------------------------------------------------------------------------- 1 | CXX_STD = CXX11 -------------------------------------------------------------------------------- /src/Mutual_Information.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/src/Mutual_Information.cpp -------------------------------------------------------------------------------- /src/RcppExports.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/src/RcppExports.cpp -------------------------------------------------------------------------------- /src/Sparse_Document_Frequencies.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/src/Sparse_Document_Frequencies.cpp -------------------------------------------------------------------------------- /src/Sparse_PMI_Statistics.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/src/Sparse_PMI_Statistics.cpp -------------------------------------------------------------------------------- /src/Variable_Dice_Coefficients.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/src/Variable_Dice_Coefficients.cpp -------------------------------------------------------------------------------- /src/calculate_ACMI_contribution.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/src/calculate_ACMI_contribution.cpp -------------------------------------------------------------------------------- /src/calculate_document_frequency.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/src/calculate_document_frequency.cpp -------------------------------------------------------------------------------- /src/reference_dist_distance.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/src/reference_dist_distance.cpp -------------------------------------------------------------------------------- /tests/.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/tests/.DS_Store -------------------------------------------------------------------------------- /tests/testthat.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/tests/testthat.R -------------------------------------------------------------------------------- /tests/testthat/test_clean_document_text.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/tests/testthat/test_clean_document_text.R -------------------------------------------------------------------------------- /tests/testthat/test_corenlp.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/tests/testthat/test_corenlp.R -------------------------------------------------------------------------------- /tests/testthat/test_count_ngrams.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/tests/testthat/test_count_ngrams.R -------------------------------------------------------------------------------- /tests/testthat/test_document_similarities.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/tests/testthat/test_document_similarities.R -------------------------------------------------------------------------------- /tests/testthat/test_document_similarities_2.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/tests/testthat/test_document_similarities_2.R -------------------------------------------------------------------------------- /tests/testthat/test_generate_blocked_document_term_vectors.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/tests/testthat/test_generate_blocked_document_term_vectors.R -------------------------------------------------------------------------------- /tests/testthat/test_generate_contingency_table.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/tests/testthat/test_generate_contingency_table.R -------------------------------------------------------------------------------- /tests/testthat/test_generate_document_term_matrix.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/tests/testthat/test_generate_document_term_matrix.R -------------------------------------------------------------------------------- /tests/testthat/test_generate_document_term_vectors.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/tests/testthat/test_generate_document_term_vectors.R -------------------------------------------------------------------------------- /tests/testthat/test_mallet_lda.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/tests/testthat/test_mallet_lda.R -------------------------------------------------------------------------------- /tests/testthat/test_ngrams.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/tests/testthat/test_ngrams.R -------------------------------------------------------------------------------- /tests/testthat/test_pmi.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/tests/testthat/test_pmi.R -------------------------------------------------------------------------------- /tests/testthat/test_sparse_doc_term_parallel.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/tests/testthat/test_sparse_doc_term_parallel.R -------------------------------------------------------------------------------- /tests/testthat/test_sparse_large_document_term_matrix.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/tests/testthat/test_sparse_large_document_term_matrix.R -------------------------------------------------------------------------------- /tests/testthat/test_speed_set_vocabulary.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/tests/testthat/test_speed_set_vocabulary.R -------------------------------------------------------------------------------- /tests/testthat/test_tfidf.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/tests/testthat/test_tfidf.R -------------------------------------------------------------------------------- /tests/testthat/test_word_counter.R: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/tests/testthat/test_word_counter.R -------------------------------------------------------------------------------- /vignettes/getting_started_with_SpeedReader.Rmd: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewjdenny/SpeedReader/HEAD/vignettes/getting_started_with_SpeedReader.Rmd --------------------------------------------------------------------------------