Index

_

__add__() (podium.Vocab method) __call__() (podium.preproc.KeywordExtractor method) (podium.preproc.MosesNormalizer method) (podium.preproc.NLTKStemmer method) (podium.preproc.RegexReplace method) (podium.preproc.SpacyLemmatizer method) (podium.preproc.SpacySentencizer method) (podium.preproc.TextCleanUp method) __eq__() (podium.Vocab method) (podium.vocab.Special method) __getattr__() (podium.Dataset method) __getitem__() (podium.Dataset method) (podium.datasets.arrow.DiskBackedDataset method) (podium.Vocab method) __getstate__() (podium.Field method)

__hash__() (podium.vocab.Special method) __iadd__() (podium.Vocab method) __iter__() (podium.Dataset method) (podium.datasets.arrow.DiskBackedDataset method) (podium.datasets.hf.HFDatasetConverter method) (podium.datasets.Iterator method) (podium.Vocab method) __len__() (podium.Dataset method) (podium.datasets.arrow.DiskBackedDataset method) (podium.datasets.Iterator method) (podium.Vocab method) __new__() (podium.vocab.Special static method) __setstate__() (podium.Field method) _ARCHIVE_TYPE (podium.vectorizers.GloVe attribute) _BINARY (podium.vectorizers.GloVe attribute) _NAME_FILE_MAPPING (podium.vectorizers.GloVe attribute)

A

add_output_field() (podium.MultioutputField method) add_posttokenize_hook() (podium.Field method) add_pretokenize_hook() (podium.Field method) (podium.MultioutputField method) ANNOTATOR_LABELS_FIELD_NAME (podium.datasets.impl.SNLI attribute) apply() (podium.vocab.BOS method) (podium.vocab.EOS method) (podium.vocab.Special method)

ARCHIVE_TYPE (podium.datasets.impl.IMDB attribute) (podium.datasets.impl.SNLI attribute) (podium.datasets.impl.SST attribute) as_dataset() (podium.datasets.hf.HFDatasetConverter method) as_dict() (podium.Dataset method) as_posttokenize_hook() (in module podium.preproc)

B

batch() (podium.Dataset method) batch_size() (podium.datasets.Iterator property)

BOS (class in podium.vocab) BucketIterator (class in podium.datasets)

C

CAPTION_ID_FIELD_NAME (podium.datasets.impl.SNLI attribute) close() (podium.datasets.arrow.DiskBackedDataset method)

CoNLLUDataset (class in podium.datasets) CornellMovieDialogs (class in podium.datasets.impl)

D

Dataset (class in podium) DATASET_DIR (podium.datasets.impl.IMDB attribute) (podium.datasets.impl.SNLI attribute) (podium.datasets.impl.SST attribute)

delete_cache() (podium.datasets.arrow.DiskBackedDataset method) DEV_FILE_NAME (podium.datasets.impl.SNLI attribute) DiskBackedDataset (class in podium.datasets.arrow) dump_cache() (podium.datasets.arrow.DiskBackedDataset method)

E

eager() (podium.Field property) EOS (class in podium.vocab)

epoch() (podium.datasets.Iterator property) examples() (podium.Dataset property)

F

Field (class in podium) field() (podium.Dataset method) field_dict() (podium.Dataset property) fields() (podium.Dataset property) filter() (podium.Dataset method) filtered() (podium.Dataset method) finalize() (podium.Field method) (podium.MultilabelField method) (podium.Vocab method) finalize_fields() (podium.Dataset method)

fit() (podium.vectorizers.TfIdfVectorizer method) from_dataset() (podium.Dataset static method) (podium.datasets.arrow.DiskBackedDataset static method) from_dataset_dict() (podium.datasets.hf.HFDatasetConverter static method) from_examples() (podium.datasets.arrow.DiskBackedDataset static method) from_itos() (podium.Vocab class method) from_pandas() (podium.Dataset class method) (podium.datasets.arrow.DiskBackedDataset class method) from_stoi() (podium.Vocab class method) from_tabular_file() (podium.datasets.arrow.DiskBackedDataset static method)

G

get() (podium.Dataset method) get_dataset_splits() (podium.datasets.impl.IMDB static method) (podium.datasets.impl.SST static method) get_default_fields() (podium.datasets.CoNLLUDataset static method) (podium.datasets.impl.CornellMovieDialogs static method) (podium.datasets.impl.IMDB static method) (podium.datasets.impl.SNLI static method) (podium.datasets.impl.SST static method) get_default_value() (podium.Field method) get_freqs() (podium.Vocab method)

get_internal_random_state() (podium.datasets.Iterator method) get_numericalization_for_example() (podium.Field method) get_output_fields() (podium.Field method) (podium.MultioutputField method) get_padding_index() (podium.Vocab method) get_tokenizer() (in module podium.preproc) get_train_test_dev_dataset() (podium.datasets.impl.SNLI static method) GloVe (class in podium.vectorizers) GOLD_LABEL_FIELD_NAME (podium.datasets.impl.SNLI attribute) grid_search() (in module podium.experimental.model_selection.model_selection)

H

HFDatasetConverter (class in podium.datasets.hf)

HierarchicalIterator (class in podium.datasets)

I

IMDB (class in podium.datasets.impl) is_finalized (podium.Vocab attribute) is_finalized() (podium.Field property)

iterations() (podium.datasets.Iterator property) Iterator (class in podium.datasets) itos (podium.Vocab attribute)

K

KeywordExtractor (class in podium.preproc)

L

LABEL_FIELD_NAME (podium.datasets.impl.IMDB attribute) (podium.datasets.impl.SST attribute)

LabelField (class in podium) load_cache() (podium.datasets.arrow.DiskBackedDataset static method)

M

matrix_class() (podium.datasets.Iterator property) module podium.experimental.model_selection.model_selection podium.experimental.models podium.experimental.models.impl podium.experimental.models.impl.pytorch podium.experimental.pipeline podium.experimental.validation

MosesNormalizer (class in podium.preproc) MultilabelField (class in podium) MultioutputField (class in podium)

N

NAME (podium.datasets.impl.IMDB attribute) (podium.datasets.impl.SNLI attribute) (podium.datasets.impl.SST attribute) name() (podium.Field property) NAME_DIM_MAPPING (podium.vectorizers.GloVe attribute) NAME_URL_MAPPING (podium.vectorizers.GloVe attribute) NEGATIVE_LABEL (podium.datasets.impl.IMDB attribute) (podium.datasets.impl.SST attribute)

NEGATIVE_LABEL_DIR (podium.datasets.impl.IMDB attribute) NlplVectorizer (class in podium.vectorizers) NLTKStemmer (class in podium.preproc) numericalize() (podium.Field method) (podium.MultilabelField method) (podium.Vocab method) numericalize_examples() (podium.Dataset method)

P

PAD (class in podium.vocab) PAIR_ID_FIELD_NAME (podium.datasets.impl.SNLI attribute) podium.experimental.model_selection.model_selection module podium.experimental.models module podium.experimental.models.impl module podium.experimental.models.impl.pytorch module

podium.experimental.pipeline module podium.experimental.validation module POSITIVE_LABEL (podium.datasets.impl.IMDB attribute) (podium.datasets.impl.SST attribute) POSITIVE_LABEL_DIR (podium.datasets.impl.IMDB attribute) preprocess() (podium.Field method) (podium.MultioutputField method)

R

random_normal_default_vector() (in module podium.vectorizers) RegexReplace (class in podium.preproc) remove_posttokenize_hooks() (podium.Field method) remove_pretokenize_hooks() (podium.Field method) (podium.MultioutputField method)

remove_stopwords() (in module podium.preproc) reset() (podium.datasets.Iterator method) reverse_numericalize() (podium.Vocab method)

S

SENTENCE1_BINARY_PARSE_FIELD_NAME (podium.datasets.impl.SNLI attribute) SENTENCE1_FIELD_NAME (podium.datasets.impl.SNLI attribute) SENTENCE1_PARSE_FIELD_NAME (podium.datasets.impl.SNLI attribute) SENTENCE2_BINARY_PARSE_FIELD_NAME (podium.datasets.impl.SNLI attribute) SENTENCE2_FIELD_NAME (podium.datasets.impl.SNLI attribute) SENTENCE2_PARSE_FIELD_NAME (podium.datasets.impl.SNLI attribute) set_dataset() (podium.datasets.HierarchicalIterator method) (podium.datasets.Iterator method) (podium.datasets.SingleBatchIterator method) set_internal_random_state() (podium.datasets.Iterator method)

shuffle_examples() (podium.Dataset method) shuffled() (podium.Dataset method) SingleBatchIterator (class in podium.datasets) SNLI (class in podium.datasets.impl) sorted() (podium.Dataset method) SpacyLemmatizer (class in podium.preproc) SpacySentencizer (class in podium.preproc) Special (class in podium.vocab) split() (podium.Dataset method) SST (class in podium.datasets.impl) stoi (podium.Vocab attribute)

T

TabularDataset (class in podium.datasets) TEST_DIR (podium.datasets.impl.IMDB attribute) TEST_FILE_NAME (podium.datasets.impl.SNLI attribute) TEXT_FIELD_NAME (podium.datasets.impl.IMDB attribute) (podium.datasets.impl.SST attribute) TextCleanUp (class in podium.preproc)

TfIdfVectorizer (class in podium.vectorizers) to_pandas() (podium.Dataset method) TRAIN_DIR (podium.datasets.impl.IMDB attribute) TRAIN_FILE_NAME (podium.datasets.impl.SNLI attribute) transform() (podium.vectorizers.TfIdfVectorizer method) truecase() (in module podium.preproc)

U

UNK (class in podium.vocab) update_vocab() (podium.Field method) URL (podium.datasets.impl.IMDB attribute) (podium.datasets.impl.SNLI attribute) (podium.datasets.impl.SST attribute)

use_vocab() (podium.Field property)

V

Vocab (class in podium)

vocab() (podium.Field property)

Z

zeros_default_vector() (in module podium.vectorizers)