.gitignore
LICENSE
MANIFEST.in
Pipfile
Pipfile.lock
README.md
pyproject.toml
setup.cfg
src/text_selection/__init__.py
src/text_selection/cover_applied.py
src/text_selection/cover_export.py
src/text_selection/cover_methods.py
src/text_selection/greedy_kld_applied.py
src/text_selection/greedy_kld_export.py
src/text_selection/greedy_kld_methods.py
src/text_selection/metrics_applied.py
src/text_selection/metrics_export.py
src/text_selection/metrics_methods.py
src/text_selection/random_applied.py
src/text_selection/random_export.py
src/text_selection/random_method.py
src/text_selection/selection.py
src/text_selection/utils.py
src/text_selection.egg-info/PKG-INFO
src/text_selection.egg-info/SOURCES.txt
src/text_selection.egg-info/dependency_links.txt
src/text_selection.egg-info/entry_points.txt
src/text_selection.egg-info/requires.txt
src/text_selection.egg-info/top_level.txt
src/text_selection/common/__init__.py
src/text_selection/common/durations_iterator.py
src/text_selection/common/filter_durations.py
src/text_selection/common/helper.py
src/text_selection/common/mapping_iterator.py
src/text_selection/common/ngram_extractor.py
src/text_selection/common/ngram_extractor2.py
src/text_selection/greedy/__init__.py
src/text_selection/greedy/greedy_N_epoch_iterator.py
src/text_selection/greedy/greedy_N_iterator.py
src/text_selection/greedy/greedy_applied.py
src/text_selection/greedy/greedy_epoch_iterator.py
src/text_selection/greedy/greedy_export.py
src/text_selection/greedy/greedy_iterator.py
src/text_selection/greedy/greedy_methods.py
src/text_selection/greedy/main.py
src/text_selection/greedy/optimized_greedy_N_iterator.py
src/text_selection/greedy/optimized_greedy_iterator.py
src/text_selection/kld/__init__.py
src/text_selection/kld/custom_kld_iterator.py
src/text_selection/kld/kld_iterator.py
src/text_selection/kld/main.py
src/text_selection/kld/optimized_kld_iterator.py
src/text_selection/random/__init__.py
src/text_selection/random/main.py
src/text_selection/random/random_iterator.py
src/text_selection_cli/__init__.py
src/text_selection_cli/argparse_helper.py
src/text_selection_cli/cli.py
src/text_selection_cli/datasets.py
src/text_selection_cli/default_args.py
src/text_selection_cli/export.py
src/text_selection_cli/filtering.py
src/text_selection_cli/globals.py
src/text_selection_cli/io_handling.py
src/text_selection_cli/logging_configuration.py
src/text_selection_cli/n_grams.py
src/text_selection_cli/selection.py
src/text_selection_cli/sorting.py
src/text_selection_cli/statistics.py
src/text_selection_cli/subset.py
src/text_selection_cli/subsets.py
src/text_selection_cli/validation.py
src/text_selection_cli/weights.py
src/text_selection_core/__init__.py
src/text_selection_core/common.py
src/text_selection_core/globals.py
src/text_selection_core/helper.py
src/text_selection_core/statistics.py
src/text_selection_core/subsets.py
src/text_selection_core/types.py
src/text_selection_core/validation.py
src/text_selection_core/algorithms/__init__.py
src/text_selection_core/algorithms/fifo.py
src/text_selection_core/algorithms/reverse.py
src/text_selection_core/exporting/__init__.py
src/text_selection_core/exporting/symbols_exporting.py
src/text_selection_core/filtering/__init__.py
src/text_selection_core/filtering/duplicates_filter.py
src/text_selection_core/filtering/line_nr_filter.py
src/text_selection_core/filtering/line_unit_frequency_filter.py
src/text_selection_core/filtering/nr_selection.py
src/text_selection_core/filtering/regex_filter.py
src/text_selection_core/filtering/string_filter.py
src/text_selection_core/filtering/unit_frequency_filter.py
src/text_selection_core/filtering/vocabulary_filtering.py
src/text_selection_core/filtering/weights_filter.py
src/text_selection_core/preparation/n_grams.py
src/text_selection_core/selection/__init__.py
src/text_selection_core/selection/all_selection.py
src/text_selection_core/selection/fifo_selection.py
src/text_selection_core/selection/greedy_selection.py
src/text_selection_core/selection/kld_selection.py
src/text_selection_core/selection/symbol_extractor.py
src/text_selection_core/sorting/__init__.py
src/text_selection_core/sorting/fifo_sorting.py
src/text_selection_core/sorting/random.py
src/text_selection_core/sorting/reverse_sorting.py
src/text_selection_core/sorting/text_sorting.py
src/text_selection_core/sorting/weights_sorting.py
src/text_selection_core/weights/__init__.py
src/text_selection_core/weights/calculation.py
src/text_selection_core/weights/weights_iterator.py
src/text_selection_core_tests/__init__.py
src/text_selection_core_tests/filtering/__init__.py
src/text_selection_core_tests/filtering/duplicates_filter_py/__init__.py
src/text_selection_core_tests/filtering/duplicates_filter_py/test_filter_duplicats.py
src/text_selection_core_tests/filtering/regex_filter_py/__init__.py
src/text_selection_core_tests/filtering/regex_filter_py/test_filter_regex_pattern.py
src/text_selection_core_tests/filtering/unit_frequency_filter_py/test_filter_lines_with_unit_frequencies.py
src/text_selection_core_tests/selection/__init__.py
src/text_selection_core_tests/selection/fifo_selection_py/__init__.py
src/text_selection_core_tests/selection/fifo_selection_py/test_select_fifo.py
src/text_selection_core_tests/selection/greedy_selection_py/__init__.py
src/text_selection_core_tests/selection/greedy_selection_py/test_select_greedy.py
src/text_selection_core_tests/selection/greedy_selection_py/test_select_greedy_epochs.py
src/text_selection_core_tests/selection/kld_selection_py/__init__.py
src/text_selection_core_tests/selection/kld_selection_py/test_select_kld.py
src/text_selection_core_tests/selection/symbol_extractor_py/__init__.py
src/text_selection_core_tests/selection/symbol_extractor_py/generate_test_data.py
src/text_selection_core_tests/selection/symbol_extractor_py/test_get_array.py
src/text_selection_core_tests/selection/symbol_extractor_py/test_get_array_mp.py
src/text_selection_core_tests/types_py/__init__.py
src/text_selection_core_tests/types_py/test_Dataset.py
src/text_selection_core_tests/types_py/test_get_line_nrs.py
src/text_selection_core_tests/weights/__init__.py
src/text_selection_core_tests/weights/calculation_py/__init__.py
src/text_selection_core_tests/weights/calculation_py/test_convert_weights_to_percent_inplace.py
src/text_selection_core_tests/weights/calculation_py/test_get_from_lines.py
src/text_selection_tests/__init__.py
src/text_selection_tests/test_cover_export.py
src/text_selection_tests/test_greedy_export.py
src/text_selection_tests/test_greedy_kld_export.py
src/text_selection_tests/test_greedy_kld_methods.py
src/text_selection_tests/test_metrics_export.py
src/text_selection_tests/test_random_export.py
src/text_selection_tests/test_selection.py
src/text_selection_tests/test_utils.py
src/text_selection_tests/common/__init__.py
src/text_selection_tests/common/filter_durations_py/__init__.py
src/text_selection_tests/common/filter_durations_py/test_get_indices_in_duration_boundary.py
src/text_selection_tests/common/helper_py/__init__.py
src/text_selection_tests/common/helper_py/test_get_empty_columns.py
src/text_selection_tests/common/ngram_extractor2_py/__init__.py
src/text_selection_tests/common/ngram_extractor2_py/test_NGramExtractor2.py
src/text_selection_tests/common/ngram_extractor2_py/test_get_all_ngrams_iterator2.py
src/text_selection_tests/common/ngram_extractor2_py/test_get_count_array2.py
src/text_selection_tests/common/ngram_extractor2_py/test_get_ngrams_generator2.py
src/text_selection_tests/common/ngram_extractor2_py/test_get_numerated_ngrams2.py
src/text_selection_tests/common/ngram_extractor_py/__init__.py
src/text_selection_tests/common/ngram_extractor_py/test_NGramExtractor.py
src/text_selection_tests/common/ngram_extractor_py/test_get_all_ngrams_iterator.py
src/text_selection_tests/common/ngram_extractor_py/test_get_count_array.py
src/text_selection_tests/common/ngram_extractor_py/test_get_ngrams_generator.py
src/text_selection_tests/common/ngram_extractor_py/test_get_numerated_ngrams.py
src/text_selection_tests/core/__init__.py
src/text_selection_tests/greedy/__init__.py
src/text_selection_tests/greedy/greedy_epoch_iterator_py/__init__.py
src/text_selection_tests/greedy/greedy_epoch_iterator_py/test_GreedyEpochIterator.py
src/text_selection_tests/greedy/greedy_iterator_N_py/__init__.py
src/text_selection_tests/greedy/greedy_iterator_N_py/test_greedy_iterator_N.py
src/text_selection_tests/greedy/greedy_iterator_py/__init__.py
src/text_selection_tests/greedy/greedy_iterator_py/test_get_indicies_with_most_new.py
src/text_selection_tests/greedy/greedy_iterator_py/test_get_keys_with_most_new.py
src/text_selection_tests/greedy/greedy_iterator_py/test_get_maximum_indices.py
src/text_selection_tests/greedy/greedy_iterator_py/test_get_uncovered_amounts.py
src/text_selection_tests/greedy/greedy_iterator_py/test_greedy_iterator.py
src/text_selection_tests/greedy/main_py/__init__.py
src/text_selection_tests/greedy/main_py/test_greedy_uniform_ngrams_seconds_with_preselection_perf.py
src/text_selection_tests/greedy/optimized_greedy_iterator_py/__init__.py
src/text_selection_tests/greedy/optimized_greedy_iterator_py/test_OptimizedGreedyIterator.py
src/text_selection_tests/kld/__init__.py
src/text_selection_tests/kld/kld_iterator_py/__init__.py
src/text_selection_tests/kld/kld_iterator_py/test_KldIterator.py
src/text_selection_tests/kld/kld_iterator_py/test_get_distribution.py
src/text_selection_tests/kld/kld_iterator_py/test_get_distributions_from_weights.py
src/text_selection_tests/kld/kld_iterator_py/test_get_kullback_leibler_divergence.py
src/text_selection_tests/kld/kld_iterator_py/test_get_minimum_kld.py
src/text_selection_tests/kld/kld_iterator_py/test_get_minimum_kld_keys.py
src/text_selection_tests/kld/kld_iterator_py/test_get_minimun_indices.py
src/text_selection_tests/kld/kld_iterator_py/test_get_uniform_weights.py
src/text_selection_tests/kld/kld_iterator_py/test_is_valid_counts_or_weights.py
src/text_selection_tests/kld/kld_iterator_py/test_is_valid_distribution.py
src/text_selection_tests/kld/kld_iterator_py/test_remove_nan_rows.py
src/text_selection_tests/kld/main_py/__init__.py
src/text_selection_tests/kld/main_py/test_greedy_kld_uniform_ngrams_seconds_with_preselection_perf.py
src/text_selection_tests/random/__init__.py
src/text_selection_tests/random/main_py/__init__.py
src/text_selection_tests/random/main_py/test_random_seconds_perf.py
src/text_selection_tests/random/random_iterator_py/__init__.py
src/text_selection_tests/random/random_iterator_py/test_RandomIterator.py