Index

_

__call__() (shorttext.utils.textpreprocessing.StemmerSingleton method), [1], [2] __contains__() (shorttext.generators.bow.LatentTopicModeling.LatentTopicModeler method), [1] __getitem__() (shorttext.generators.bow.LatentTopicModeling.LatentTopicModeler method), [1] __init__() (shorttext.classifiers.bow.maxent.MaxEntClassification.MaxEntClassifier method), [1] (shorttext.classifiers.bow.topic.SkLearnClassification.TopicVectorSkLearnClassifier method), [1] (shorttext.classifiers.bow.topic.TopicVectorDistanceClassification.TopicVecCosineDistanceClassifier method), [1] (shorttext.classifiers.embed.nnlib.VarNNEmbedVecClassification.VarNNEmbeddedVecClassifier method), [1], [2] (shorttext.classifiers.embed.sumvec.SumEmbedVecClassification.SumEmbeddedVecClassifier method), [1] (shorttext.classifiers.embed.sumvec.VarNNSumEmbedVecClassification.VarNNSumEmbeddedVecClassifier method) (shorttext.generators.bow.GensimTopicModeling.GensimTopicModeler method), [1], [2] (shorttext.generators.bow.LatentTopicModeling.LatentTopicModeler method), [1] (shorttext.generators.charbase.char2vec.SentenceToCharVecEncoder method), [1], [2] (shorttext.generators.seq2seq.charbaseS2S.CharBasedSeq2SeqGenerator method), [1], [2] (shorttext.generators.seq2seq.s2skeras.Seq2SeqWithKeras method) (shorttext.spell.norvig.NorvigSpellCorrector method), [1] (shorttext.stack.stacking.StackedGeneralization method), [1] (shorttext.utils.compactmodel_io.CompactIOMachine method) (shorttext.utils.dtm.NumpyDocumentTermMatrix method), [1], [2] (shorttext.utils.wordembed.RESTfulKeyedVectors method), [1], [2], [3], [4]

__len__() (shorttext.generators.charbase.char2vec.SentenceToCharVecEncoder method), [1], [2]

A

AbstractScorer (class in shorttext.classifiers.base) add_classifier() (shorttext.stack.stacking.StackedGeneralization method), [1] advanced_text_tokenizer_1() (in module shorttext.utils.textpreprocessing), [1], [2]

AlgorithmNotExistException autoencoder (shorttext.schemas.models.AutoEncoderPackage attribute) AutoEncoderPackage (class in shorttext.schemas.models) AutoencodingTopicModeler (class in shorttext.generators.bow.AutoEncodingTopicModeling), [1]

C

calculate_prelim_vec() (shorttext.generators.charbase.char2vec.SentenceToCharVecEncoder method), [1], [2] candidates() (shorttext.spell.norvig.NorvigSpellCorrector method), [1] CharBasedSeq2SeqGenerator (class in shorttext.generators.seq2seq.charbaseS2S), [1], [2] classify() (shorttext.classifiers.bow.topic.SkLearnClassification.TopicVectorSkLearnClassifier method), [1] closer_than() (shorttext.utils.wordembed.RESTfulKeyedVectors method), [1], [2], [3], [4] CLSTMWordEmbed() (in module shorttext.classifiers.embed.nnlib.frameworks), [1] CNNWordEmbed() (in module shorttext.classifiers.embed.nnlib.frameworks), [1] CompactIOMachine (class in shorttext.utils.compactmodel_io) compile() (shorttext.generators.seq2seq.charbaseS2S.CharBasedSeq2SeqGenerator method), [1], [2] (shorttext.generators.seq2seq.s2skeras.Seq2SeqWithKeras method) compute_document_frequency() (in module shorttext.utils.dtm), [1]

compute_set_edits1() (in module shorttext.spell.editor) compute_set_edits2() (in module shorttext.spell.editor) compute_tfidf_document_term_matrix() (in module shorttext.utils.dtm), [1] convert_classdict_to_corpus() (in module shorttext.utils.dtm), [1] convert_classdict_to_xy() (in module shorttext.utils.dtm), [1] convert_label_to_buckets() (shorttext.stack.stacking.StackedGeneralization method), [1] convert_traindata_embedvecs() (shorttext.classifiers.embed.sumvec.VarNNSumEmbedVecClassification.VarNNSumEmbeddedVecClassifier method) convert_traindata_matrix() (shorttext.stack.stacking.StackedGeneralization method), [1] convert_trainingdata_matrix() (shorttext.classifiers.embed.nnlib.VarNNEmbedVecClassification.VarNNEmbeddedVecClassifier method), [1], [2] correct() (shorttext.spell.basespellcorrector.SpellCorrector method) (shorttext.spell.norvig.NorvigSpellCorrector method), [1] cosine_similarity() (in module shorttext.utils.compute)

D

damerau_levenshtein() (in module shorttext.metrics.dynprog.dldist) decode() (shorttext.generators.seq2seq.charbaseS2S.CharBasedSeq2SeqGenerator method), [1], [2] decoder (shorttext.schemas.models.AutoEncoderPackage attribute) delete_classifier() (shorttext.stack.stacking.StackedGeneralization method), [1]

DenseWordEmbed() (in module shorttext.classifiers.embed.sumvec.frameworks) distance() (shorttext.utils.wordembed.RESTfulKeyedVectors method), [1], [2], [3], [4] distances() (shorttext.utils.wordembed.RESTfulKeyedVectors method), [1], [2], [3], [4] docids (shorttext.utils.dtm.NumpyDocumentTermMatrix property), [1], [2] DoubleCNNWordEmbed() (in module shorttext.classifiers.embed.nnlib.frameworks), [1]

E

encode_sentence() (shorttext.generators.charbase.char2vec.SentenceToCharVecEncoder method), [1], [2]

encode_sentences() (shorttext.generators.charbase.char2vec.SentenceToCharVecEncoder method), [1], [2] encoder (shorttext.schemas.models.AutoEncoderPackage attribute)

F

fit() (shorttext.generators.seq2seq.s2skeras.Seq2SeqWithKeras method) from_npdict_file() (shorttext.utils.dtm.NumpyDocumentTermMatrix class method), [1], [2] from_pretrained() (shorttext.classifiers.bow.maxent.MaxEntClassification.MaxEntClassifier class method), [1] (shorttext.classifiers.embed.nnlib.VarNNEmbedVecClassification.VarNNEmbeddedVecClassifier class method), [1], [2] (shorttext.classifiers.embed.sumvec.SumEmbedVecClassification.SumEmbeddedVecClassifier class method), [1] (shorttext.classifiers.embed.sumvec.VarNNSumEmbedVecClassification.VarNNSumEmbeddedVecClassifier class method) (shorttext.generators.bow.AutoEncodingTopicModeling.AutoencodingTopicModeler class method), [1] (shorttext.generators.bow.GensimTopicModeling.GensimTopicModeler class method), [1], [2] (shorttext.generators.charbase.char2vec.SentenceToCharVecEncoder class method), [1], [2] (shorttext.generators.seq2seq.charbaseS2S.CharBasedSeq2SeqGenerator class method), [1], [2] (shorttext.generators.seq2seq.s2skeras.Seq2SeqWithKeras class method)

from_pretrained_autoencoder() (shorttext.classifiers.bow.topic.TopicVectorDistanceClassification.TopicVecCosineDistanceClassifier class method), [1] from_pretrained_autoencoder_sklearnclassifier() (shorttext.classifiers.bow.topic.SkLearnClassification.TopicVectorSkLearnClassifier class method), [1] from_pretrained_gensimtopic() (shorttext.classifiers.bow.topic.TopicVectorDistanceClassification.TopicVecCosineDistanceClassifier class method), [1] from_pretrained_gensimtopic_sklearnclassifier() (shorttext.classifiers.bow.topic.SkLearnClassification.TopicVectorSkLearnClassifier class method), [1]

G

generate_corpus() (shorttext.generators.bow.GensimTopicModeling.GensimTopicModeler method), [1], [2] generate_dtm() (shorttext.utils.dtm.NumpyDocumentTermMatrix method), [1], [2] generate_gensim_corpora() (in module shorttext.utils.gensim_corpora) generate_npdict_document_term_matrix() (in module shorttext.utils.dtm), [1] GensimTopicModeler (class in shorttext.generators.bow.GensimTopicModeling), [1], [2] get_argparser() (in module shorttext.cli.categorization) get_autoencoder_models() (in module shorttext.generators.bow.AutoEncodingTopicModeling), [1] get_batch_cos_similarities() (shorttext.generators.bow.AutoEncodingTopicModeling.AutoencodingTopicModeler method), [1] (shorttext.generators.bow.GensimTopicModeling.GensimTopicModeler method), [1], [2] (shorttext.generators.bow.LatentTopicModeling.LatentTopicModeler method), [1] get_doc_frequency() (shorttext.utils.dtm.NumpyDocumentTermMatrix method), [1], [2] get_doc_tokens() (shorttext.utils.dtm.NumpyDocumentTermMatrix method), [1], [2] get_info() (shorttext.generators.bow.AutoEncodingTopicModeling.AutoencodingTopicModeler method), [1] (shorttext.generators.bow.GensimTopicModeling.GensimTopicModeler method), [1], [2] (shorttext.generators.bow.GensimTopicModeling.LDAModeler method), [1], [2] (shorttext.generators.bow.GensimTopicModeling.LSIModeler method), [1], [2] (shorttext.generators.bow.GensimTopicModeling.RPModeler method), [1], [2] (shorttext.generators.bow.LatentTopicModeling.LatentTopicModeler method), [1] (shorttext.utils.compactmodel_io.CompactIOMachine method)

get_model_classifier_name() (in module shorttext.utils.compactmodel_io) get_model_config_field() (in module shorttext.utils.compactmodel_io) get_or_download_data() (in module shorttext.data.data_retrieval), [1], [2], [3], [4] get_termfreq() (shorttext.utils.dtm.NumpyDocumentTermMatrix method), [1], [2] get_token_occurences() (shorttext.utils.dtm.NumpyDocumentTermMatrix method), [1], [2] get_total_termfreq() (shorttext.utils.dtm.NumpyDocumentTermMatrix method), [1], [2] get_vector() (shorttext.utils.wordembed.RESTfulKeyedVectors method), [1], [2], [3], [4] getargparser() (in module shorttext.cli.wordembedsim) getvector() (shorttext.classifiers.bow.topic.SkLearnClassification.TopicVectorSkLearnClassifier method), [1]

I

inaugural() (in module shorttext.data.data_retrieval), [1], [2], [3], [4] IncorrectClassificationModelFileException

initialize_SentenceToCharVecEncoder() (in module shorttext.generators.charbase.char2vec), [1], [2] initSentenceToCharVecEncoder() (in module shorttext.generators.charbase.char2vec), [1], [2]

J

jaccardscore_sents() (in module shorttext.metrics.embedfuzzy.jaccard), [1]

K

known() (shorttext.spell.norvig.NorvigSpellCorrector method), [1]

L

LatentTopicModeler (class in shorttext.generators.bow.LatentTopicModeling), [1] LDAModeler (class in shorttext.generators.bow.GensimTopicModeling), [1], [2] load_autoencoder_cosineClassifier() (in module shorttext.classifiers.bow.topic.TopicVectorDistanceClassification), [1] load_autoencoder_topic_sklearnclassifier() (in module shorttext.classifiers.bow.topic.SkLearnClassification), [1] load_autoencoder_topicmodel() (in module shorttext.generators.bow.AutoEncodingTopicModeling), [1] load_compact_model() (in module shorttext.utils.compactmodel_io) (shorttext.classifiers.bow.topic.SkLearnClassification.TopicVectorSkLearnClassifier method), [1] (shorttext.classifiers.bow.topic.TopicVectorDistanceClassification.TopicVecCosineDistanceClassifier method), [1] (shorttext.utils.compactmodel_io.CompactIOMachine method) load_corpus() (in module shorttext.utils.gensim_corpora) load_fasttext_model() (in module shorttext.utils.wordembed), [1], [2], [3], [4] load_gensim_topicvec_sklearnclassifier() (in module shorttext.classifiers.bow.topic.SkLearnClassification), [1] load_gensimtopicmodel() (in module shorttext.generators.bow.GensimTopicModeling), [1], [2] load_gensimtopicvec_cosineClassifier() (in module shorttext.classifiers.bow.topic.TopicVectorDistanceClassification), [1] load_maxent_classifier() (in module shorttext.classifiers.bow.maxent.MaxEntClassification), [1] load_model() (in module shorttext.utils.kerasmodel_io) load_numpy_documentmatrixmatrix() (in module shorttext.utils.dtm), [1] load_poincare_model() (in module shorttext.utils.wordembed), [1], [2], [3], [4] load_seq2seq_model() (in module shorttext.generators.seq2seq.s2skeras) load_sumword2vec_classifier() (in module shorttext.classifiers.embed.sumvec.SumEmbedVecClassification) load_varnnlibvec_classifier() (in module shorttext.classifiers.embed.nnlib.VarNNEmbedVecClassification), [1]

load_varnnsumvec_classifier() (in module shorttext.classifiers.embed.sumvec.VarNNSumEmbedVecClassification) load_word2vec_model() (in module shorttext.utils.wordembed), [1], [2], [3], [4] loadCharBasedSeq2SeqGenerator() (in module shorttext.generators.seq2seq.charbaseS2S), [1] loadmodel() (shorttext.classifiers.bow.maxent.MaxEntClassification.MaxEntClassifier method), [1] (shorttext.classifiers.bow.topic.SkLearnClassification.TopicVectorSkLearnClassifier method), [1] (shorttext.classifiers.bow.topic.TopicVectorDistanceClassification.TopicVecCosineDistanceClassifier method), [1] (shorttext.classifiers.embed.nnlib.VarNNEmbedVecClassification.VarNNEmbeddedVecClassifier method), [1], [2] (shorttext.classifiers.embed.sumvec.SumEmbedVecClassification.SumEmbeddedVecClassifier method), [1] (shorttext.classifiers.embed.sumvec.VarNNSumEmbedVecClassification.VarNNSumEmbeddedVecClassifier method) (shorttext.generators.bow.AutoEncodingTopicModeling.AutoencodingTopicModeler method), [1] (shorttext.generators.bow.GensimTopicModeling.GensimTopicModeler method), [1], [2] (shorttext.generators.bow.LatentTopicModeling.LatentTopicModeler method), [1] (shorttext.generators.seq2seq.charbaseS2S.CharBasedSeq2SeqGenerator method), [1], [2] (shorttext.generators.seq2seq.s2skeras.Seq2SeqWithKeras method) (shorttext.stack.stacking.LogisticStackedGeneralization method), [1] (shorttext.utils.compactmodel_io.CompactIOMachine method) (shorttext.utils.dtm.NumpyDocumentTermMatrix method), [1], [2] loadSeq2SeqWithKeras() (in module shorttext.generators.seq2seq.s2skeras) logistic_framework() (in module shorttext.classifiers.bow.maxent.MaxEntClassification), [1] LogisticStackedGeneralization (class in shorttext.stack.stacking), [1] longest_common_prefix() (in module shorttext.metrics.dynprog.lcp) LSIModeler (class in shorttext.generators.bow.GensimTopicModeling), [1], [2]

M

main() (in module shorttext.cli.categorization) (in module shorttext.cli.wordembedsim) map() (shorttext.utils.misc.SinglePoolExecutor method) MaxEntClassifier (class in shorttext.classifiers.bow.maxent.MaxEntClassification), [1] merge_cv_dicts() (in module shorttext.data.data_retrieval), [1], [2], [3], [4] ModelNotTrainedException module shorttext shorttext.classifiers shorttext.classifiers.base shorttext.classifiers.bow shorttext.classifiers.bow.maxent.MaxEntClassification, [1] shorttext.classifiers.bow.topic.SkLearnClassification, [1] shorttext.classifiers.bow.topic.TopicVectorDistanceClassification, [1] shorttext.classifiers.embed shorttext.classifiers.embed.nnlib.frameworks, [1] shorttext.classifiers.embed.nnlib.VarNNEmbedVecClassification, [1] shorttext.classifiers.embed.sumvec.frameworks shorttext.classifiers.embed.sumvec.SumEmbedVecClassification shorttext.classifiers.embed.sumvec.VarNNSumEmbedVecClassification shorttext.cli shorttext.cli.categorization shorttext.cli.wordembedsim shorttext.data shorttext.data.data_retrieval, [1], [2], [3], [4] shorttext.generators shorttext.generators.bow shorttext.generators.bow.AutoEncodingTopicModeling, [1] shorttext.generators.bow.GensimTopicModeling, [1], [2] shorttext.generators.bow.LatentTopicModeling, [1] shorttext.generators.charbase shorttext.generators.charbase.char2vec, [1], [2] shorttext.generators.seq2seq shorttext.generators.seq2seq.charbaseS2S, [1] shorttext.generators.seq2seq.s2skeras shorttext.metrics shorttext.metrics.dynprog shorttext.metrics.dynprog.dldist shorttext.metrics.dynprog.jaccard, [1] shorttext.metrics.dynprog.lcp shorttext.metrics.embedfuzzy shorttext.metrics.embedfuzzy.jaccard, [1] shorttext.metrics.wasserstein shorttext.metrics.wasserstein.wordmoverdist, [1] shorttext.schemas shorttext.schemas.models shorttext.smartload shorttext.spell shorttext.spell.basespellcorrector shorttext.spell.editor shorttext.spell.norvig, [1] shorttext.stack shorttext.stack.stacking, [1] shorttext.utils shorttext.utils.classification_exceptions shorttext.utils.compactmodel_io shorttext.utils.compute shorttext.utils.dtm, [1] shorttext.utils.gensim_corpora shorttext.utils.kerasmodel_io shorttext.utils.misc shorttext.utils.textpreprocessing, [1], [2] shorttext.utils.wordembed, [1], [2], [3], [4]

most_similar() (shorttext.utils.wordembed.RESTfulKeyedVectors method), [1], [2], [3], [4] most_similar_to_given() (shorttext.utils.wordembed.RESTfulKeyedVectors method), [1], [2], [3], [4]

N

nbdocs (shorttext.utils.dtm.NumpyDocumentTermMatrix property), [1], [2] nbtokens (shorttext.utils.dtm.NumpyDocumentTermMatrix property), [1], [2] nihreports() (in module shorttext.data.data_retrieval), [1], [2], [3], [4]

NorvigSpellCorrector (class in shorttext.spell.norvig), [1] NotImplementedException() (in module shorttext.utils.classification_exceptions) NumpyDocumentTermMatrix (class in shorttext.utils.dtm), [1], [2]

O

oldschool_standard_text_preprocessor() (in module shorttext.utils.textpreprocessing), [1], [2]

OperationNotDefinedException

P

P() (shorttext.spell.norvig.NorvigSpellCorrector method), [1] precalculate_liststr_topicvec() (shorttext.generators.bow.AutoEncodingTopicModeling.AutoencodingTopicModeler method), [1]

prepare_model() (shorttext.generators.seq2seq.s2skeras.Seq2SeqWithKeras method) prepare_trainingdata() (shorttext.generators.seq2seq.charbaseS2S.CharBasedSeq2SeqGenerator method), [1], [2] preprocess_text() (in module shorttext.utils.textpreprocessing), [1], [2]

R

rank() (shorttext.utils.wordembed.RESTfulKeyedVectors method), [1], [2], [3], [4] register_classifiers() (shorttext.stack.stacking.StackedGeneralization method), [1] register_classlabels() (shorttext.stack.stacking.StackedGeneralization method), [1] removedir() (in module shorttext.utils.compactmodel_io) RESTfulKeyedVectors (class in shorttext.utils.wordembed), [1], [2], [3], [4] retrieve_bow() (shorttext.generators.bow.AutoEncodingTopicModeling.AutoencodingTopicModeler method), [1] (shorttext.generators.bow.GensimTopicModeling.GensimTopicModeler method), [1], [2] (shorttext.generators.bow.LatentTopicModeling.LatentTopicModeler method), [1] retrieve_bow_vector() (shorttext.generators.bow.AutoEncodingTopicModeling.AutoencodingTopicModeler method), [1] (shorttext.generators.bow.GensimTopicModeling.GensimTopicModeler method), [1], [2] (shorttext.generators.bow.LatentTopicModeling.LatentTopicModeler method), [1]

retrieve_corpus_topicdist() (shorttext.generators.bow.GensimTopicModeling.GensimTopicModeler method), [1], [2] retrieve_csvdata_as_dict() (in module shorttext.data.data_retrieval), [1], [2], [3], [4] retrieve_jsondata_as_dict() (in module shorttext.data.data_retrieval), [1], [2], [3], [4] retrieve_topicvec() (shorttext.generators.bow.AutoEncodingTopicModeling.AutoencodingTopicModeler method), [1] (shorttext.generators.bow.GensimTopicModeling.GensimTopicModeler method), [1], [2] (shorttext.generators.bow.LatentTopicModeling.LatentTopicModeler method), [1] RPModeler (class in shorttext.generators.bow.GensimTopicModeling), [1], [2]

S

save() (shorttext.utils.wordembed.RESTfulKeyedVectors method), [1], [2], [3], [4] save_compact_model() (in module shorttext.utils.compactmodel_io) (shorttext.classifiers.bow.topic.SkLearnClassification.TopicVectorSkLearnClassifier method), [1] (shorttext.classifiers.bow.topic.TopicVectorDistanceClassification.TopicVecCosineDistanceClassifier method), [1] (shorttext.utils.compactmodel_io.CompactIOMachine method) save_corpus() (in module shorttext.utils.gensim_corpora) save_model() (in module shorttext.utils.kerasmodel_io) savemodel() (shorttext.classifiers.bow.maxent.MaxEntClassification.MaxEntClassifier method), [1] (shorttext.classifiers.bow.topic.SkLearnClassification.TopicVectorSkLearnClassifier method), [1] (shorttext.classifiers.bow.topic.TopicVectorDistanceClassification.TopicVecCosineDistanceClassifier method), [1] (shorttext.classifiers.embed.nnlib.VarNNEmbedVecClassification.VarNNEmbeddedVecClassifier method), [1], [2] (shorttext.classifiers.embed.sumvec.SumEmbedVecClassification.SumEmbeddedVecClassifier method), [1] (shorttext.classifiers.embed.sumvec.VarNNSumEmbedVecClassification.VarNNSumEmbeddedVecClassifier method) (shorttext.generators.bow.AutoEncodingTopicModeling.AutoencodingTopicModeler method), [1] (shorttext.generators.bow.GensimTopicModeling.GensimTopicModeler method), [1], [2] (shorttext.generators.bow.LatentTopicModeling.LatentTopicModeler method), [1] (shorttext.generators.seq2seq.charbaseS2S.CharBasedSeq2SeqGenerator method), [1], [2] (shorttext.generators.seq2seq.s2skeras.Seq2SeqWithKeras method) (shorttext.stack.stacking.LogisticStackedGeneralization method), [1] (shorttext.utils.compactmodel_io.CompactIOMachine method) (shorttext.utils.dtm.NumpyDocumentTermMatrix method), [1], [2] score() (shorttext.classifiers.base.AbstractScorer method) (shorttext.classifiers.bow.maxent.MaxEntClassification.MaxEntClassifier method), [1] (shorttext.classifiers.bow.topic.SkLearnClassification.TopicVectorSkLearnClassifier method), [1] (shorttext.classifiers.bow.topic.TopicVectorDistanceClassification.TopicVecCosineDistanceClassifier method), [1] (shorttext.classifiers.embed.nnlib.VarNNEmbedVecClassification.VarNNEmbeddedVecClassifier method), [1], [2] (shorttext.classifiers.embed.sumvec.SumEmbedVecClassification.SumEmbeddedVecClassifier method), [1] (shorttext.classifiers.embed.sumvec.VarNNSumEmbedVecClassification.VarNNSumEmbeddedVecClassifier method) (shorttext.stack.stacking.LogisticStackedGeneralization method), [1] (shorttext.stack.stacking.StackedGeneralization method), [1] SentenceToCharVecEncoder (class in shorttext.generators.charbase.char2vec), [1], [2] Seq2SeqWithKeras (class in shorttext.generators.seq2seq.s2skeras) shorttext module shorttext.classifiers module shorttext.classifiers.base module shorttext.classifiers.bow module shorttext.classifiers.bow.maxent.MaxEntClassification module, [1] shorttext.classifiers.bow.topic.SkLearnClassification module, [1] shorttext.classifiers.bow.topic.TopicVectorDistanceClassification module, [1] shorttext.classifiers.embed module shorttext.classifiers.embed.nnlib.frameworks module, [1] shorttext.classifiers.embed.nnlib.VarNNEmbedVecClassification module, [1] shorttext.classifiers.embed.sumvec.frameworks module shorttext.classifiers.embed.sumvec.SumEmbedVecClassification module shorttext.classifiers.embed.sumvec.VarNNSumEmbedVecClassification module shorttext.cli module shorttext.cli.categorization module shorttext.cli.wordembedsim module shorttext.data module shorttext.data.data_retrieval module, [1], [2], [3], [4] shorttext.generators module shorttext.generators.bow module shorttext.generators.bow.AutoEncodingTopicModeling module, [1] shorttext.generators.bow.GensimTopicModeling module, [1], [2] shorttext.generators.bow.LatentTopicModeling module, [1] shorttext.generators.charbase module shorttext.generators.charbase.char2vec module, [1], [2]

shorttext.generators.seq2seq module shorttext.generators.seq2seq.charbaseS2S module, [1] shorttext.generators.seq2seq.s2skeras module shorttext.metrics module shorttext.metrics.dynprog module shorttext.metrics.dynprog.dldist module shorttext.metrics.dynprog.jaccard module, [1] shorttext.metrics.dynprog.lcp module shorttext.metrics.embedfuzzy module shorttext.metrics.embedfuzzy.jaccard module, [1] shorttext.metrics.wasserstein module shorttext.metrics.wasserstein.wordmoverdist module, [1] shorttext.schemas module shorttext.schemas.models module shorttext.smartload module shorttext.spell module shorttext.spell.basespellcorrector module shorttext.spell.editor module shorttext.spell.norvig module, [1] shorttext.stack module shorttext.stack.stacking module, [1] shorttext.utils module shorttext.utils.classification_exceptions module shorttext.utils.compactmodel_io module shorttext.utils.compute module shorttext.utils.dtm module, [1] shorttext.utils.gensim_corpora module shorttext.utils.kerasmodel_io module shorttext.utils.misc module shorttext.utils.textpreprocessing module, [1], [2] shorttext.utils.wordembed module, [1], [2], [3], [4] shorttext_to_avgvec() (in module shorttext.utils.wordembed), [1], [2], [3], [4] shorttext_to_embedvec() (shorttext.classifiers.embed.sumvec.SumEmbedVecClassification.SumEmbeddedVecClassifier method), [1] (shorttext.classifiers.embed.sumvec.VarNNSumEmbedVecClassification.VarNNSumEmbeddedVecClassifier method) shorttext_to_matrix() (shorttext.classifiers.embed.nnlib.VarNNEmbedVecClassification.VarNNEmbeddedVecClassifier method), [1], [2] shorttext_to_vec() (shorttext.classifiers.bow.maxent.MaxEntClassification.MaxEntClassifier method), [1] similarity() (in module shorttext.metrics.dynprog.jaccard), [1] (shorttext.utils.wordembed.RESTfulKeyedVectors method), [1], [2], [3], [4] SinglePoolExecutor (class in shorttext.utils.misc) smartload_compact_model() (in module shorttext.smartload) soft_intersection_list() (in module shorttext.metrics.dynprog.jaccard), [1] soft_jaccard_score() (in module shorttext.metrics.dynprog.jaccard), [1] SpellCorrector (class in shorttext.spell.basespellcorrector) StackedGeneralization (class in shorttext.stack.stacking), [1] standard_text_preprocessor_1() (in module shorttext.utils.textpreprocessing), [1], [2] standard_text_preprocessor_2() (in module shorttext.utils.textpreprocessing), [1], [2] StemmerSingleton (class in shorttext.utils.textpreprocessing), [1], [2] stemword() (in module shorttext.utils.textpreprocessing), [1], [2] subjectkeywords() (in module shorttext.data.data_retrieval), [1], [2], [3], [4] SumEmbeddedVecClassifier (class in shorttext.classifiers.embed.sumvec.SumEmbedVecClassification), [1]

T

text_preprocessor() (in module shorttext.utils.textpreprocessing), [1], [2] textfile_generator() (in module shorttext.utils.misc) tokenize() (in module shorttext.utils.textpreprocessing), [1], [2] tokenize_text() (in module shorttext.utils.textpreprocessing), [1], [2] tokens (shorttext.utils.dtm.NumpyDocumentTermMatrix property), [1], [2] tokens_to_fracdict() (in module shorttext.utils.gensim_corpora) TopicVecCosineDistanceClassifier (class in shorttext.classifiers.bow.topic.TopicVectorDistanceClassification), [1] TopicVectorSkLearnClassifier (class in shorttext.classifiers.bow.topic.SkLearnClassification), [1] train() (shorttext.classifiers.bow.maxent.MaxEntClassification.MaxEntClassifier method), [1] (shorttext.classifiers.bow.topic.SkLearnClassification.TopicVectorSkLearnClassifier method), [1] (shorttext.classifiers.embed.nnlib.VarNNEmbedVecClassification.VarNNEmbeddedVecClassifier method), [1], [2] (shorttext.classifiers.embed.sumvec.SumEmbedVecClassification.SumEmbeddedVecClassifier method), [1] (shorttext.classifiers.embed.sumvec.VarNNSumEmbedVecClassification.VarNNSumEmbeddedVecClassifier method) (shorttext.generators.bow.AutoEncodingTopicModeling.AutoencodingTopicModeler method), [1] (shorttext.generators.bow.GensimTopicModeling.GensimTopicModeler method), [1], [2] (shorttext.generators.bow.LatentTopicModeling.LatentTopicModeler method), [1] (shorttext.generators.seq2seq.charbaseS2S.CharBasedSeq2SeqGenerator method), [1], [2] (shorttext.spell.basespellcorrector.SpellCorrector method) (shorttext.spell.norvig.NorvigSpellCorrector method), [1] (shorttext.stack.stacking.LogisticStackedGeneralization method), [1] (shorttext.stack.stacking.StackedGeneralization method), [1]

train_autoencoder_cosineClassifier() (in module shorttext.classifiers.bow.topic.TopicVectorDistanceClassification), [1] train_autoencoder_topic_sklearnclassifier() (in module shorttext.classifiers.bow.topic.SkLearnClassification), [1] train_gensim_topicvec_sklearnclassifier() (in module shorttext.classifiers.bow.topic.SkLearnClassification), [1] train_gensimtopicvec_cosineClassifier() (in module shorttext.classifiers.bow.topic.TopicVectorDistanceClassification), [1] translate_shorttext_intfeature_matrix() (shorttext.stack.stacking.StackedGeneralization method), [1]

U

UnequalArrayLengthsException

update() (shorttext.generators.bow.GensimTopicModeling.GensimTopicModeler method), [1], [2] update_corpus_labels() (in module shorttext.utils.gensim_corpora)

V

VarNNEmbeddedVecClassifier (class in shorttext.classifiers.embed.nnlib.VarNNEmbedVecClassification), [1], [2]

VarNNSumEmbeddedVecClassifier (class in shorttext.classifiers.embed.sumvec.VarNNSumEmbedVecClassification)

W

word_mover_distance() (in module shorttext.metrics.wasserstein.wordmoverdist), [1] word_mover_distance_linprog() (in module shorttext.metrics.wasserstein.wordmoverdist), [1]

word_to_embedvec() (shorttext.classifiers.embed.nnlib.VarNNEmbedVecClassification.VarNNEmbeddedVecClassifier method), [1], [2] (shorttext.classifiers.embed.sumvec.VarNNSumEmbedVecClassification.VarNNSumEmbeddedVecClassifier method) WordEmbeddingModelNotExistException

Y

yield_crossvalidation_classdicts() (in module shorttext.data.data_retrieval), [1], [2], [3], [4]