Index

A

adjust_summary_size() (src.preprocessing.extract_important_sentences.ExtractImportantSentences method)

B

build_graph_from_adj_list() (in module src.utils.construct_graph)

C

classes (dashapp.generate_graph_elements.EdgeElement attribute) (dashapp.generate_graph_elements.NodeElement attribute) (dashapp.generate_graph_elements.StoryElement attribute) cluster_members (dashapp.generate_graph_elements.ClusterNodeElementData attribute) ClusterDocuments (class in src.preprocessing.cluster_documents) ClusterExplainer (class in src.preprocessing.cluster_explainer) ClusterNodeElementData (class in dashapp.generate_graph_elements) ComputeLayout (class in src.preprocessing.compute_layout) create_graph() (in module dashapp.generate_graph_elements) create_story_element() (in module dashapp.generate_graph_elements) CreateEvents (class in src.preprocessing.create_events) custom_transform() (src.preprocessing.cluster_documents.ClusterDocuments method) (src.preprocessing.cluster_explainer.ClusterExplainer method) (src.preprocessing.compute_layout.ComputeLayout method) (src.preprocessing.compute_topical_distributions.TopicalDistribution method) (src.preprocessing.create_events.CreateEvents method) (src.preprocessing.extract_dates_regex.ExtractDatesRegex method) (src.preprocessing.extract_important_sentences.ExtractImportantSentences method) (src.preprocessing.filter_redundant_edges.FilterRedundantEdges method) (src.preprocessing.find_storylines.FindStorylines method) (src.preprocessing.generate_roberta_embedding.GenerateRobertaEmbedding method) (src.preprocessing.impute_dates.ImputeDates method) (src.preprocessing.linear_programming.LinearProgramming method) (src.preprocessing.pdf_to_text.PdfToText method)

D

dashapp module dashapp.conf module dashapp.generate_graph_elements module dashapp.pages module

dashapp.pages.home module data (dashapp.generate_graph_elements.EdgeElement attribute) (dashapp.generate_graph_elements.NodeElement attribute) (dashapp.generate_graph_elements.StoryElement attribute) dictionary_name_or_path (src.preprocessing.compute_topical_distributions.TopicalDistribution attribute) directed (dashapp.generate_graph_elements.EdgeElementData attribute) dossier_selected() (in module dashapp.pages.home)

E

edge_boundary() (in module src.utils.construct_graph) EdgeElement (class in dashapp.generate_graph_elements) EdgeElementData (class in dashapp.generate_graph_elements) extension (gz_extract.GzExtractConfig attribute) external_define_metric() (src.logging.logger.Logger method)

extract_date_regex() (src.preprocessing.extract_dates_regex.ExtractDatesRegex method) extract_important_sentences() (src.preprocessing.extract_important_sentences.ExtractImportantSentences method) extract_text_for_doc() (src.preprocessing.pdf_to_text.PdfToText method) ExtractDatesRegex (class in src.preprocessing.extract_dates_regex) ExtractImportantSentences (class in src.preprocessing.extract_important_sentences)

F

files (src.preprocessing.pdf_to_text.PdfToText attribute) filter_interstory_connections() (in module src.utils.construct_graph) FilterRedundantEdges (class in src.preprocessing.filter_redundant_edges)

find_most_similar() (src.preprocessing.create_events.CreateEvents method) find_storylines() (in module src.preprocessing.find_storylines) FindStorylines (class in src.preprocessing.find_storylines) fix_dtypes() (in module src.utils.fix_dtypes)

G

generate_edges() (in module dashapp.generate_graph_elements) generate_graph_elements() (in module dashapp.generate_graph_elements) generate_node_elements() (in module dashapp.generate_graph_elements) GenerateRobertaEmbedding (class in src.preprocessing.generate_roberta_embedding) get_cache_exists() (src.pipeline.verbose_transformation_pipeline.VerboseTransformationPipeline method)

get_topic_dist() (src.preprocessing.compute_topical_distributions.TopicalDistribution method) gz_extract module gz_extract() (in module gz_extract) GzExtractConfig (class in gz_extract)

I

id (dashapp.generate_graph_elements.ClusterNodeElementData attribute) (dashapp.generate_graph_elements.EdgeElementData attribute) (dashapp.generate_graph_elements.StoryElementData attribute)

ImputeDates (class in src.preprocessing.impute_dates)

K

K (src.preprocessing.linear_programming.LinearProgramming attribute)

L

label (dashapp.generate_graph_elements.ClusterNodeElementData attribute) (dashapp.generate_graph_elements.EdgeElementData attribute) LinearProgramming (class in src.preprocessing.linear_programming) load_dossier() (in module src.load_data) load_pdf_dossier() (in module src.load_data) log_exception() (in module src.logging.logger)

log_section_separator() (src.logging.logger.Logger method) log_to_debug() (src.logging.logger.Logger method) log_to_external() (src.logging.logger.Logger method) log_to_terminal() (src.logging.logger.Logger method) log_to_warning() (src.logging.logger.Logger method) Logger (class in src.logging.logger)

M

main module max_date (src.preprocessing.extract_dates_regex.ExtractDatesRegex attribute) merge_whitespace() (src.preprocessing.extract_important_sentences.ExtractImportantSentences method) min_cover (src.preprocessing.linear_programming.LinearProgramming attribute) min_date (src.preprocessing.extract_dates_regex.ExtractDatesRegex attribute) modify_adjacency() (src.preprocessing.create_events.CreateEvents method) module dashapp dashapp.conf dashapp.generate_graph_elements dashapp.pages dashapp.pages.home gz_extract main split_woogle_dump_per_dossier src src.load_data src.logging src.logging.logger src.pipeline src.pipeline.setup_pipeline src.pipeline.verbose_transformation_pipeline src.preprocessing src.preprocessing.cluster_documents src.preprocessing.cluster_explainer src.preprocessing.compute_layout src.preprocessing.compute_topical_distributions src.preprocessing.create_events src.preprocessing.extract_dates_regex src.preprocessing.extract_important_sentences src.preprocessing.filter_redundant_edges src.preprocessing.find_storylines src.preprocessing.generate_roberta_embedding src.preprocessing.impute_dates src.preprocessing.linear_programming src.preprocessing.pdf_to_text src.utils src.utils.construct_graph src.utils.convert_rustworkx src.utils.fix_dtypes

N

NodeElement (class in dashapp.generate_graph_elements)

normalize_adj_weights() (in module src.utils.construct_graph) number (dashapp.generate_graph_elements.StoryElementData attribute)

P

parent (dashapp.generate_graph_elements.ClusterNodeElementData attribute) parse_float_list() (in module src.utils.fix_dtypes) parse_int_list() (in module src.utils.fix_dtypes) PdfToText (class in src.preprocessing.pdf_to_text) period (src.preprocessing.create_events.CreateEvents attribute)

periods (src.preprocessing.cluster_documents.ClusterDocuments attribute) Point (class in dashapp.generate_graph_elements) position (dashapp.generate_graph_elements.NodeElement attribute) preprocess_documents() (src.preprocessing.compute_topical_distributions.TopicalDistribution method) pretrained_model_name_or_path (src.preprocessing.compute_topical_distributions.TopicalDistribution attribute) (src.preprocessing.generate_roberta_embedding.GenerateRobertaEmbedding attribute)

R

rank_sentences() (src.preprocessing.cluster_explainer.ClusterExplainer method)

run_dossier_pipeline() (src.pipeline.verbose_transformation_pipeline.VerboseTransformationPipeline method) run_train() (in module main)

S

selectable (dashapp.generate_graph_elements.StoryElement attribute) setup_pipeline() (in module src.pipeline.setup_pipeline) source (dashapp.generate_graph_elements.EdgeElementData attribute) source_path (gz_extract.GzExtractConfig attribute) spacing_within_story (src.preprocessing.compute_layout.ComputeLayout attribute) split_woogle_dump_per_dossier module split_woogle_dump_per_dossier() (in module split_woogle_dump_per_dossier) src module src.load_data module src.logging module src.logging.logger module src.pipeline module src.pipeline.setup_pipeline module src.pipeline.verbose_transformation_pipeline module src.preprocessing module src.preprocessing.cluster_documents module src.preprocessing.cluster_explainer module src.preprocessing.compute_layout module src.preprocessing.compute_topical_distributions module

src.preprocessing.create_events module src.preprocessing.extract_dates_regex module src.preprocessing.extract_important_sentences module src.preprocessing.filter_redundant_edges module src.preprocessing.find_storylines module src.preprocessing.generate_roberta_embedding module src.preprocessing.impute_dates module src.preprocessing.linear_programming module src.preprocessing.pdf_to_text module src.utils module src.utils.construct_graph module src.utils.convert_rustworkx module src.utils.fix_dtypes module story (dashapp.generate_graph_elements.StoryElementData attribute) StoryElement (class in dashapp.generate_graph_elements) StoryElementData (class in dashapp.generate_graph_elements) summary (dashapp.generate_graph_elements.ClusterNodeElementData attribute)

T

target (dashapp.generate_graph_elements.EdgeElementData attribute) target_path (gz_extract.GzExtractConfig attribute) threshold (src.preprocessing.cluster_explainer.ClusterExplainer attribute) (src.preprocessing.linear_programming.LinearProgramming attribute)

to_networkx() (in module src.utils.convert_rustworkx) tokenize_sentences() (src.preprocessing.extract_important_sentences.ExtractImportantSentences method) TopicalDistribution (class in src.preprocessing.compute_topical_distributions) transitive_reduction() (in module src.utils.construct_graph) transpose (src.preprocessing.compute_layout.ComputeLayout attribute)

U

upload_files() (in module dashapp.pages.home)

V

VerboseTransformationPipeline (class in src.pipeline.verbose_transformation_pipeline)

W

weight (dashapp.generate_graph_elements.EdgeElementData attribute)

width (dashapp.generate_graph_elements.EdgeElementData attribute)

X

x (dashapp.generate_graph_elements.Point attribute)

Y

y (dashapp.generate_graph_elements.Point attribute)