Index

_

__dict__ (pythainlp.spell.NorvigSpellChecker attribute) __init__() (pythainlp.augment.lm.FastTextAug method) (pythainlp.augment.lm.Thai2transformersAug method) (pythainlp.augment.word2vec.bpemb_wv.BPEmbAug method) (pythainlp.augment.word2vec.LTW2VAug method) (pythainlp.augment.word2vec.Thai2fitAug method) (pythainlp.augment.word2vec.Word2VecAug method) (pythainlp.augment.WordNetAug method) (pythainlp.generate.Bigram method) (pythainlp.generate.Trigram method) (pythainlp.generate.Unigram method) (pythainlp.spell.NorvigSpellChecker method) (pythainlp.tag.NER method) (pythainlp.tag.NNER method) (pythainlp.tag.thainer.ThaiNameTagger method) (pythainlp.tokenize.attacut.AttacutTokenizer method), [1] (pythainlp.tokenize.longest.LongestMatchTokenizer method) (pythainlp.tokenize.multi_cut.LatticeString method) (pythainlp.tokenize.Tokenizer method) (pythainlp.translate.en_th.EnThTranslator method) (pythainlp.translate.en_th.ThEnTranslator method) (pythainlp.translate.th_fr.ThFrTranslator method) (pythainlp.translate.Translate method) (pythainlp.translate.zh_th.ThZhTranslator method) (pythainlp.translate.zh_th.ZhThTranslator method) (pythainlp.transliterate.wunsen.WunsenTransliterate method) (pythainlp.ulmfit.ThaiTokenizer method) (pythainlp.util.Trie method) (pythainlp.util.Trie.Node method) (pythainlp.wangchanberta.ThaiNameTagger method) (pythainlp.word_vector.WordVector method)

__module__ (pythainlp.spell.NorvigSpellChecker attribute)

A

add() (pythainlp.util.Trie method) add_special_cases() (pythainlp.ulmfit.ThaiTokenizer method) all_lemma_names() (in module pythainlp.corpus.wordnet) all_synsets() (in module pythainlp.corpus.wordnet) arabic_digit_to_thai_digit() (in module pythainlp.util) AttacutTokenizer (class in pythainlp.tokenize.attacut), [1]

augment() (pythainlp.augment.lm.FastTextAug method) (pythainlp.augment.lm.Thai2transformersAug method) (pythainlp.augment.word2vec.bpemb_wv.BPEmbAug method) (pythainlp.augment.word2vec.LTW2VAug method) (pythainlp.augment.word2vec.Thai2fitAug method) (pythainlp.augment.word2vec.Word2VecAug method) (pythainlp.augment.WordNetAug method)

B

bahttext() (in module pythainlp.util) benchmark() (in module pythainlp.benchmarks.word_tokenization)

Bigram (class in pythainlp.generate) bigram_word_freqs() (in module pythainlp.corpus.tnc) BPEmbAug (class in pythainlp.augment.word2vec.bpemb_wv)

C

children (pythainlp.util.Trie.Node attribute) chunk_parse() (in module pythainlp.tag) clause_tokenize() (in module pythainlp.tokenize) collate() (in module pythainlp.util) compute_stats() (in module pythainlp.benchmarks.word_tokenization)

correct() (in module pythainlp.spell) (pythainlp.spell.NorvigSpellChecker method) correct_sent() (in module pythainlp.spell) countries() (in module pythainlp.corpus) countthai() (in module pythainlp.util) custom_lemmas() (in module pythainlp.corpus.wordnet)

D

DEFAULT_SPELL_CHECKER (in module pythainlp.spell) dependency_parsing() (in module pythainlp.parse) dict_trie() (in module pythainlp.util) dictionary() (pythainlp.spell.NorvigSpellChecker method) digit_to_text() (in module pythainlp.util)

display_thai_char() (in module pythainlp.util) document_vector() (in module pythainlp.ulmfit) doesnt_match() (pythainlp.word_vector.WordVector method) download() (in module pythainlp.corpus) download_model_all() (in module pythainlp.translate.en_th)

E

edges() (in module pythainlp.corpus.conceptnet) emoji_to_thai() (in module pythainlp.util) end (pythainlp.util.Trie.Node attribute) eng_to_thai() (in module pythainlp.util)

EnThTranslator (class in pythainlp.translate.en_th) environment variable PYTHAINLP_DATA_DIR, [1] PYTHAINLP_READ_MODE extract_features() (in module pythainlp.tokenize.crfcut), [1]

F

FastTextAug (class in pythainlp.augment.lm) find_all_segment() (in module pythainlp.tokenize.multi_cut), [1] find_badwords() (in module pythainlp.corpus.util)

find_keyword() (in module pythainlp.util) find_synonyms() (pythainlp.augment.WordNetAug method) fix_html() (in module pythainlp.ulmfit) freq() (pythainlp.spell.NorvigSpellChecker method)

G

gen_sentence() (in module pythainlp.generate.thai2fit) (pythainlp.generate.Bigram method) (pythainlp.generate.Trigram method) (pythainlp.generate.Unigram method) generate() (pythainlp.augment.lm.Thai2transformersAug method) get_corpus() (in module pythainlp.corpus) get_corpus_db() (in module pythainlp.corpus) get_corpus_db_detail() (in module pythainlp.corpus)

get_corpus_default_db() (in module pythainlp.corpus) get_corpus_path() (in module pythainlp.corpus) get_full_data_path() (in module pythainlp.tools) get_model() (pythainlp.word_vector.WordVector method) get_ner() (in module pythainlp.tag.tltk) (pythainlp.tag.thainer.ThaiNameTagger method) (pythainlp.wangchanberta.ThaiNameTagger method) get_pythainlp_data_path() (in module pythainlp.tools) get_pythainlp_path() (in module pythainlp.tools)

I

is_native_thai() (in module pythainlp.util)

isthai() (in module pythainlp.util) isthaichar() (in module pythainlp.util)

K

known() (pythainlp.spell.NorvigSpellChecker method)

L

langs() (in module pythainlp.corpus.wordnet) LatticeString (class in pythainlp.tokenize.multi_cut) lch_similarity() (in module pythainlp.corpus.wordnet) lemma() (in module pythainlp.corpus.wordnet) lemma_from_key() (in module pythainlp.corpus.wordnet) lemmas() (in module pythainlp.corpus.wordnet) list_to_string() (in module pythainlp.tokenize.thaisumcut), [1] lk82() (in module pythainlp.soundex) load_dict() (in module pythainlp.tokenize.nlpo3), [1]

load_engine() (pythainlp.tag.NER method) (pythainlp.tag.NNER method) load_model() (pythainlp.translate.Translate method) load_w2v() (pythainlp.augment.word2vec.bpemb_wv.BPEmbAug method) (pythainlp.augment.word2vec.LTW2VAug method) (pythainlp.augment.word2vec.Thai2fitAug method) load_wordvector() (pythainlp.word_vector.WordVector method) LongestMatchTokenizer (class in pythainlp.tokenize.longest) lowercase_all() (in module pythainlp.ulmfit) LTW2VAug (class in pythainlp.augment.word2vec)

M

maiyamok() (in module pythainlp.util) merge_wgts() (in module pythainlp.ulmfit) metasound() (in module pythainlp.soundex) middle_cut() (in module pythainlp.tokenize.thaisumcut), [1] misspell() (in module pythainlp.tools) mmcut() (in module pythainlp.tokenize.multi_cut) modify_sent() (pythainlp.augment.lm.FastTextAug method) (pythainlp.augment.word2vec.Word2VecAug method) module pythainlp.tokenize.attacut pythainlp.tokenize.crfcut pythainlp.tokenize.deepcut pythainlp.tokenize.etcc pythainlp.tokenize.longest pythainlp.tokenize.multi_cut pythainlp.tokenize.nercut pythainlp.tokenize.newmm pythainlp.tokenize.nlpo3 pythainlp.tokenize.oskut pythainlp.tokenize.pyicu pythainlp.tokenize.sefr_cut pythainlp.tokenize.tcc pythainlp.tokenize.thaisumcut pythainlp.transliterate.ipa pythainlp.transliterate.iso_11940 pythainlp.transliterate.pyicu pythainlp.transliterate.royin.romanize pythainlp.transliterate.thai2rom.romanize pythainlp.transliterate.thaig2p.transliterate

morphy() (in module pythainlp.corpus.wordnet) most_similar_cosmul() (pythainlp.word_vector.WordVector method)

N

NER (class in pythainlp.tag) NNER (class in pythainlp.tag) normalize() (in module pythainlp.util)

NorvigSpellChecker (class in pythainlp.spell) now_reign_year() (in module pythainlp.util) num_to_thaiword() (in module pythainlp.util)

P

path_similarity() (in module pythainlp.corpus.wordnet) pos_tag() (in module pythainlp.tag) (in module pythainlp.wangchanberta) pos_tag_sents() (in module pythainlp.tag) prayut_and_somchaip() (in module pythainlp.soundex) prefixes() (pythainlp.util.Trie method) preprocessing() (in module pythainlp.benchmarks.word_tokenization) prob() (pythainlp.generate.Bigram method) (pythainlp.generate.Trigram method) (pythainlp.spell.NorvigSpellChecker method) process_thai() (in module pythainlp.ulmfit) pronunciate() (in module pythainlp.transliterate) provinces() (in module pythainlp.corpus) puan() (in module pythainlp.transliterate) pythainlp.tokenize.attacut module pythainlp.tokenize.crfcut module pythainlp.tokenize.deepcut module pythainlp.tokenize.etcc module pythainlp.tokenize.longest module pythainlp.tokenize.multi_cut module pythainlp.tokenize.nercut module

pythainlp.tokenize.newmm module pythainlp.tokenize.nlpo3 module pythainlp.tokenize.oskut module pythainlp.tokenize.pyicu module pythainlp.tokenize.sefr_cut module pythainlp.tokenize.tcc module pythainlp.tokenize.thaisumcut module pythainlp.transliterate.ipa module pythainlp.transliterate.iso_11940 module pythainlp.transliterate.pyicu module pythainlp.transliterate.royin.romanize module pythainlp.transliterate.thai2rom.romanize module pythainlp.transliterate.thaig2p.transliterate module PYTHAINLP_DATA_DIR

R

rank() (in module pythainlp.util) reign_year_to_ad() (in module pythainlp.util) remove() (in module pythainlp.corpus) (pythainlp.util.Trie method) remove_dangling() (in module pythainlp.util) remove_dup_spaces() (in module pythainlp.util) remove_repeat_vowels() (in module pythainlp.util) remove_space() (in module pythainlp.ulmfit) remove_tonemark() (in module pythainlp.util) remove_zw() (in module pythainlp.util) reorder_vowels() (in module pythainlp.util)

replace_rep_after() (in module pythainlp.ulmfit) replace_rep_nonum() (in module pythainlp.ulmfit) replace_wrep_post() (in module pythainlp.ulmfit) replace_wrep_post_nonum() (in module pythainlp.ulmfit) revise_newmm_default_wordset() (in module pythainlp.corpus.util) revise_wordset() (in module pythainlp.corpus.util) rm_brackets() (in module pythainlp.ulmfit) rm_useless_newlines() (in module pythainlp.ulmfit) rm_useless_spaces() (in module pythainlp.ulmfit) romanize() (in module pythainlp.transliterate) (in module pythainlp.transliterate.tltk)

S

segment() (in module pythainlp.tokenize.attacut) (in module pythainlp.tokenize.crfcut), [1] (in module pythainlp.tokenize.deepcut) (in module pythainlp.tokenize.etcc), [1] (in module pythainlp.tokenize.longest), [1] (in module pythainlp.tokenize.multi_cut), [1] (in module pythainlp.tokenize.nercut), [1] (in module pythainlp.tokenize.newmm), [1] (in module pythainlp.tokenize.nlpo3), [1] (in module pythainlp.tokenize.oskut) (in module pythainlp.tokenize.pyicu) (in module pythainlp.tokenize.sefr_cut) (in module pythainlp.tokenize.tcc), [1] (in module pythainlp.wangchanberta) sent_tokenize() (in module pythainlp.tokenize)

sentence_vectorizer() (pythainlp.word_vector.WordVector method) set_tokenize_engine() (pythainlp.tokenize.Tokenizer method) similarity() (pythainlp.word_vector.WordVector method) sound_syllable() (in module pythainlp.util) soundex() (in module pythainlp.soundex) spec_add_spaces() (in module pythainlp.ulmfit) spell() (in module pythainlp.spell) (pythainlp.spell.NorvigSpellChecker method) spell_sent() (in module pythainlp.spell) split_into_sentences() (pythainlp.tokenize.thaisumcut.ThaiSentenceSegmentor method), [1] subword_tokenize() (in module pythainlp.tokenize) summarize() (in module pythainlp.summarize) syllable_length() (in module pythainlp.util) syllable_open_close_detector() (in module pythainlp.util) synset() (in module pythainlp.corpus.wordnet) synsets() (in module pythainlp.corpus.wordnet)

T

tag() (pythainlp.tag.NER method) (pythainlp.tag.NNER method) tag_provinces() (in module pythainlp.tag) tcc() (in module pythainlp.tokenize.tcc), [1] tcc_pos() (in module pythainlp.tokenize.tcc), [1] text_to_arabic_digit() (in module pythainlp.util) text_to_num() (in module pythainlp.util) text_to_thai_digit() (in module pythainlp.util) Thai2fitAug (class in pythainlp.augment.word2vec) Thai2transformersAug (class in pythainlp.augment.lm) thai_digit_to_arabic_digit() (in module pythainlp.util) thai_family_names() (in module pythainlp.corpus) thai_female_names() (in module pythainlp.corpus) thai_male_names() (in module pythainlp.corpus) thai_negations() (in module pythainlp.corpus) thai_stopwords() (in module pythainlp.corpus) thai_strftime() (in module pythainlp.util) thai_syllables() (in module pythainlp.corpus) thai_to_eng() (in module pythainlp.util) thai_word_tone_detector() (in module pythainlp.util) thai_words() (in module pythainlp.corpus) ThaiNameTagger (class in pythainlp.tag.thainer) (class in pythainlp.wangchanberta) ThaiSentenceSegmentor (class in pythainlp.tokenize.thaisumcut), [1] ThaiTokenizer (class in pythainlp.ulmfit) thaiword_to_date() (in module pythainlp.util) thaiword_to_num() (in module pythainlp.util) thaiword_to_time() (in module pythainlp.util) ThEnTranslator (class in pythainlp.translate.en_th) ThFrTranslator (class in pythainlp.translate.th_fr)

ThZhTranslator (class in pythainlp.translate.zh_th) time_to_thaiword() (in module pythainlp.util) tltk_g2p() (in module pythainlp.transliterate.tltk) tltk_ipa() (in module pythainlp.transliterate.tltk) tokenize() (pythainlp.augment.lm.FastTextAug method) (pythainlp.tokenize.attacut.AttacutTokenizer method), [1] (pythainlp.tokenize.longest.LongestMatchTokenizer method) Tokenizer (class in pythainlp.tokenize) tokenizer() (pythainlp.augment.word2vec.bpemb_wv.BPEmbAug method) (pythainlp.augment.word2vec.LTW2VAug method) (pythainlp.augment.word2vec.Thai2fitAug method) (pythainlp.ulmfit.ThaiTokenizer static method) tone_detector() (in module pythainlp.util) trans_list() (in module pythainlp.transliterate.ipa), [1] Translate (class in pythainlp.translate) translate() (pythainlp.translate.en_th.EnThTranslator method) (pythainlp.translate.en_th.ThEnTranslator method) (pythainlp.translate.th_fr.ThFrTranslator method) (pythainlp.translate.Translate method) (pythainlp.translate.zh_th.ThZhTranslator method) (pythainlp.translate.zh_th.ZhThTranslator method) transliterate() (in module pythainlp.transliterate) (in module pythainlp.transliterate.ipa), [1] (in module pythainlp.transliterate.iso_11940) (in module pythainlp.transliterate.pyicu), [1] (in module pythainlp.transliterate.thaig2p) (pythainlp.transliterate.wunsen.WunsenTransliterate method) Trie (class in pythainlp.util) Trie.Node (class in pythainlp.util) Trigram (class in pythainlp.generate) trigram_word_freqs() (in module pythainlp.corpus.tnc)

U

udom83() (in module pythainlp.soundex) ungroup_emoji() (in module pythainlp.ulmfit) Unigram (class in pythainlp.generate)

unigram_word_freqs() (in module pythainlp.corpus.oscar) (in module pythainlp.corpus.tnc) (in module pythainlp.corpus.ttc)

W

Word2VecAug (class in pythainlp.augment.word2vec) word_detokenize() (in module pythainlp.tokenize) word_freqs() (in module pythainlp.corpus.oscar) (in module pythainlp.corpus.tnc) (in module pythainlp.corpus.ttc) word_tokenize() (in module pythainlp.tokenize) (pythainlp.tokenize.Tokenizer method)

WordNetAug (class in pythainlp.augment) words_to_num() (in module pythainlp.util) WordVector (class in pythainlp.word_vector) WunsenTransliterate (class in pythainlp.transliterate.wunsen) wup_similarity() (in module pythainlp.corpus.wordnet)

X

xsampa_list() (in module pythainlp.transliterate.ipa), [1]

Z

ZhThTranslator (class in pythainlp.translate.zh_th)