Index

C

clean() (TextCleaner method) compute_balanced_sample_weights() (in module pewanalytics.stats.sampling) compute_hdbscan_clusters() (in module pewanalytics.stats.clustering) compute_kmeans_clusters() (in module pewanalytics.stats.clustering) compute_mutual_info() (in module pewanalytics.stats.mutual_info)

compute_overall_scores() (in module pewanalytics.stats.irr) compute_overall_scores_multivariate() (in module pewanalytics.stats.irr) compute_sample_weights_from_frame() (in module pewanalytics.stats.sampling) compute_scores() (in module pewanalytics.stats.irr) correspondence_analysis() (in module pewanalytics.stats.dimensionality_reduction)

D

DateFinder (class in pewanalytics.text.dates)

E

extract() (NamedEntityExtractor method) (SampleExtractor method)

extract_corpus_fragments() (TextDataFrame method)

F

filter_parts_of_speech() (in module pewanalytics.text.__init__) find_dates() (DateFinder method)

find_duplicates() (TextDataFrame method) find_related_keywords() (TextDataFrame method) fit() (TopicModel method)

G

get_document_topics() (TopicModel method) get_features() (TopicModel method) get_fit_params() (TopicModel method) get_fuzzy_partial_ratio() (in module pewanalytics.text.__init__) get_fuzzy_ratio() (in module pewanalytics.text.__init__) get_largest_overlap() (TextOverlapExtractor method)

get_lsa() (in module pewanalytics.stats.dimensionality_reduction) get_pca() (in module pewanalytics.stats.dimensionality_reduction) get_score() (TopicModel method) get_text_overlaps() (TextOverlapExtractor method) get_top_documents() (TextDataFrame method) get_topics() (TopicModel method)

H

has_fragment() (in module pewanalytics.text.__init__)

hdbscan_clusters() (TextDataFrame method)

I

is_probable_stopword() (in module pewanalytics.text.__init__)

K

kappa_sample_size_CI() (in module pewanalytics.stats.irr)

kappa_sample_size_power() (in module pewanalytics.stats.irr) kmeans_clusters() (TextDataFrame method)

L

lsa_components() (TextDataFrame method)

M

make_document_cooccurrence_matrix() (TextDataFrame method) make_word_cooccurrence_matrix() (TextDataFrame method) match_text_to_corpus() (TextDataFrame method) module pewanalytics.stats.clustering pewanalytics.stats.dimensionality_reduction pewanalytics.stats.irr pewanalytics.stats.mutual_info pewanalytics.stats.sampling pewanalytics.text.__init__ pewanalytics.text.dates pewanalytics.text.ner pewanalytics.text.topics

mutual_info() (TextDataFrame method) mutual_info_bar_plot() (in module pewanalytics.stats.mutual_info) mutual_info_scatter_plot() (in module pewanalytics.stats.mutual_info)

N

NamedEntityExtractor (class in pewanalytics.text.ner)

P

pca_components() (TextDataFrame method) pewanalytics.stats.clustering module pewanalytics.stats.dimensionality_reduction module pewanalytics.stats.irr module pewanalytics.stats.mutual_info module pewanalytics.stats.sampling module

pewanalytics.text.__init__ module pewanalytics.text.dates module pewanalytics.text.ner module pewanalytics.text.topics module print_topics() (TopicModel method)

R

remove_fragments() (in module pewanalytics.text.__init__)

S

SampleExtractor (class in pewanalytics.stats.sampling)

search_corpus() (TextDataFrame method) SentenceTokenizer (class in pewanalytics.text.__init__)

T

TextCleaner (class in pewanalytics.text.__init__) TextDataFrame (class in pewanalytics.text.__init__) TextOverlapExtractor (class in pewanalytics.text.__init__)

tokenize() (SentenceTokenizer method) top_cluster_terms() (TextDataFrame method) TopicModel (class in pewanalytics.text.topics)