Index

_

__getitem__() (prokbert.prok_datasets.IterableProkBERTPretrainingDataset method)

__init__() (prokbert.prok_datasets.IterableProkBERTPretrainingDataset method)

B

BaseConfig (class in prokbert.config_utils) batch_decode() (prokbert.prokbert_tokenizer.ProkBERTTokenizer method)

batch_encode_plus() (prokbert.prokbert_tokenizer.ProkBERTTokenizer method) batch_tokenize_segments_with_ids() (in module prokbert.sequtils)

C

cast_to_expected_type() (prokbert.config_utils.BaseConfig method) check_expected_columns() (in module prokbert.general_utils) check_file_exists() (in module prokbert.general_utils) convert_ids_to_tokens() (prokbert.prokbert_tokenizer.ProkBERTTokenizer method)

count_gpus() (in module prokbert.general_utils) create_directory_for_filepath() (in module prokbert.general_utils) create_hard_links() (in module prokbert.general_utils) create_selected_hard_links() (in module prokbert.general_utils)

D

decode() (prokbert.prokbert_tokenizer.ProkBERTTokenizer method)

depr_convert_ids_to_tokens() (prokbert.prokbert_tokenizer.ProkBERTTokenizer method) describe() (prokbert.config_utils.BaseConfig method)

E

encode() (prokbert.prokbert_tokenizer.ProkBERTTokenizer method)

encode_plus() (prokbert.prokbert_tokenizer.ProkBERTTokenizer method)

F

from_pretrained() (prokbert.prokbert_tokenizer.ProkBERTTokenizer class method)

G

generate_kmers() (in module prokbert.sequtils) get_and_set_computational_parameters() (prokbert.config_utils.SeqConfig method) get_and_set_datacollator_parameters() (prokbert.config_utils.ProkBERTConfig method) get_and_set_dataset_parameters() (prokbert.config_utils.ProkBERTConfig method) get_and_set_model_parameters() (prokbert.config_utils.ProkBERTConfig method) get_and_set_pretraining_parameters() (prokbert.config_utils.ProkBERTConfig method) get_and_set_segmentation_parameters() (prokbert.config_utils.SeqConfig method) get_maximum_segment_length_from_token_count() (prokbert.config_utils.SeqConfig static method)

get_maximum_segment_length_from_token_count_from_params() (prokbert.config_utils.SeqConfig method) get_maximum_token_count_from_max_length() (prokbert.config_utils.SeqConfig static method) get_maximum_token_count_from_max_length_from_params() (prokbert.config_utils.SeqConfig method) get_non_empty_files() (in module prokbert.general_utils) get_parameter() (prokbert.config_utils.BaseConfig method) get_positions_tokens() (prokbert.prokbert_tokenizer.ProkBERTTokenizer method) get_rectangular_array_from_tokenized_dataset() (in module prokbert.sequtils) get_set_parameters() (prokbert.config_utils.ProkBERTConfig method)

I

is_valid_primary_key() (in module prokbert.general_utils)

IterableProkBERTPretrainingDataset (class in prokbert.prok_datasets)

L

lca_tokenize_segment() (in module prokbert.sequtils)

load_contigs() (in module prokbert.sequtils) load_vocab() (in module prokbert.prokbert_tokenizer)

P

pretty_print_overlapping_sequence() (in module prokbert.sequtils) process_batch_tokenize_segments_with_ids() (in module prokbert.sequtils)

ProkBERTConfig (class in prokbert.config_utils) ProkBERTTokenizer (class in prokbert.prokbert_tokenizer)

R

remove_hidden_files() (in module prokbert.general_utils)

S

save_to_hdf() (in module prokbert.sequtils) save_vocabulary() (prokbert.prokbert_tokenizer.ProkBERTTokenizer method) segment_sequence_contiguous() (in module prokbert.sequtils)

segment_sequences() (in module prokbert.sequtils) segment_sequences_random() (in module prokbert.sequtils) SeqConfig (class in prokbert.config_utils)

T

tokenize() (prokbert.prokbert_tokenizer.ProkBERTTokenizer method)

tokenize_kmerized_segment_list() (in module prokbert.sequtils) truncate_zero_columns() (in module prokbert.general_utils)

V

validate() (prokbert.config_utils.BaseConfig method)

validate_type() (prokbert.config_utils.BaseConfig method) validate_value() (prokbert.config_utils.BaseConfig method)