Configuration Utils

BaseConfig

`prokbert.config_utils.BaseConfig`()	Base class for managing and validating configurations.
`prokbert.config_utils.BaseConfig.cast_to_expected_type`(...)	Cast the given value to the expected type.
`prokbert.config_utils.BaseConfig.get_parameter`(...)	Retrieve the default value of a specified parameter.
`prokbert.config_utils.BaseConfig.validate_type`(...)	Validate the type of a given value against the expected type.
`prokbert.config_utils.BaseConfig.validate_value`(...)	Validate the value of a parameter against its constraints.
`prokbert.config_utils.BaseConfig.validate`(...)	Validate both the type and value of a parameter.
`prokbert.config_utils.BaseConfig.describe`(...)	Retrieve the description of a parameter.

class prokbert.config_utils.BaseConfig

Base class for managing and validating configurations.

cast_to_expected_type(parameter_class: str, parameter_name: str, value: any) → any

Cast the given value to the expected type.

Parameters

parameter_class (str) – The class/category of the parameter.
parameter_name (str) – The name of the parameter.
value (any) – The value to be casted.

Returns

Value casted to the expected type.

Return type

any

Raises

ValueError – If casting fails.

describe(parameter_class: str, parameter_name: str) → str

Retrieve the description of a parameter.

Parameters

parameter_class (str) – The class/category of the parameter.
parameter_name (str) – The name of the parameter.

Returns

Description of the parameter.

Return type

str

get_parameter(parameter_class: str, parameter_name: str) → any

Retrieve the default value of a specified parameter.

Parameters

parameter_class (str) – The class/category of the parameter (e.g., ‘segmentation’).
parameter_name (str) – The name of the parameter.

Returns

Default value of the parameter, casted to the expected type.

Return type

any

validate(parameter_class: str, parameter_name: str, value: any)

Validate both the type and value of a parameter.

Parameters

parameter_class (str) – The class/category of the parameter.
parameter_name (str) – The name of the parameter.
value (any) – The value to be validated.

Raises

TypeError – If the value is not of the expected type.
ValueError – If the value does not meet the parameter’s constraints.

validate_type(parameter_class: str, parameter_name: str, value: any) → bool

Validate the type of a given value against the expected type.

Parameters

parameter_class (str) – The class/category of the parameter.
parameter_name (str) – The name of the parameter.
value (any) – The value to be validated.

Returns

True if the value is of the expected type, otherwise False.

Return type

bool

validate_value(parameter_class: str, parameter_name: str, value: any) → bool

Validate the value of a parameter against its constraints.

Parameters

parameter_class (str) – The class/category of the parameter.
parameter_name (str) – The name of the parameter.
value (any) – The value to be validated.

Returns

True if the value meets the constraints, otherwise False.

Return type

bool

SeqConfig

`prokbert.config_utils.SeqConfig`()	Class to manage and validate sequence processing configurations.
`prokbert.config_utils.SeqConfig._get_default_sequence_processing_config_file`()	Retrieve the default sequence processing configuration file.
`prokbert.config_utils.SeqConfig.get_and_set_segmentation_parameters`([...])	Retrieve and validate the provided parameters for segmentation.
`prokbert.config_utils.SeqConfig.get_and_set_tokenization_parameters`([...])
`prokbert.config_utils.SeqConfig.get_and_set_computational_parameters`([...])	Reading and validating the computational paramters
`prokbert.config_utils.SeqConfig.get_maximum_segment_length_from_token_count_from_params`()	Calculating the maximum length of the segment from the token count
`prokbert.config_utils.SeqConfig.get_maximum_segment_length_from_token_count`(...)	Calcuates how long sequence can be covered
`prokbert.config_utils.SeqConfig.get_maximum_token_count_from_max_length`(...)	Calcuates how long sequence can be covered

class prokbert.config_utils.SeqConfig

Bases: BaseConfig

Class to manage and validate sequence processing configurations.

get_and_set_computational_parameters(parameters: dict = {}) → dict: Reading and validating the computational paramters

get_and_set_segmentation_parameters(parameters: dict = {}) → dict

Retrieve and validate the provided parameters for segmentation.

Parameters: parameters (dict) – A dictionary of parameters to be validated.
Returns: A dictionary of validated segmentation parameters.
Return type: dict
Raises: ValueError – If an invalid segmentation parameter is provided.

static get_maximum_segment_length_from_token_count(max_token_counts, shift, kmer): Calcuates how long sequence can be covered

get_maximum_segment_length_from_token_count_from_params(): Calculating the maximum length of the segment from the token count

static get_maximum_token_count_from_max_length(max_segment_length, shift, kmer): Calcuates how long sequence can be covered

get_maximum_token_count_from_max_length_from_params(): Calculating the maximum length of the segment from the token count

ProkBERTConfig

`prokbert.config_utils.ProkBERTConfig`()	Class to manage and validate pretraining configurations.
`prokbert.config_utils.ProkBERTConfig._get_default_pretrain_config_file`()	Retrieve the default pretraining configuration file.
`prokbert.config_utils.ProkBERTConfig.get_set_parameters`(...)	Retrieve and validate the provided parameters for a given parameter class.
`prokbert.config_utils.ProkBERTConfig.get_and_set_model_parameters`([...])	Setting the model parameters
`prokbert.config_utils.ProkBERTConfig.get_and_set_dataset_parameters`([...])	Setting the dataset parameters
`prokbert.config_utils.ProkBERTConfig.get_and_set_pretraining_parameters`([...])	Setting the model parameters
`prokbert.config_utils.ProkBERTConfig.get_and_set_datacollator_parameters`([...])	Setting the model parameters
`prokbert.config_utils.ProkBERTConfig.get_and_set_segmentation_parameters`([...])
`prokbert.config_utils.ProkBERTConfig.get_and_set_tokenization_parameters`([...])
`prokbert.config_utils.ProkBERTConfig.get_and_set_computation_params`([...])

class prokbert.config_utils.ProkBERTConfig

Bases: BaseConfig

Class to manage and validate pretraining configurations.

get_and_set_datacollator_parameters(parameters: dict = {}) → dict: Setting the model parameters

get_and_set_dataset_parameters(parameters: dict = {}) → dict: Setting the dataset parameters

get_and_set_model_parameters(parameters: dict = {}) → dict: Setting the model parameters

get_and_set_pretraining_parameters(parameters: dict = {}) → dict: Setting the model parameters

get_set_parameters(parameter_class: str, parameters: dict = {}) → dict

Retrieve and validate the provided parameters for a given parameter class.

Parameters

parameter_class (str) – The class/category of the parameter (e.g., ‘data_collator’).
parameters (dict) – A dictionary of parameters to be validated.

Returns

A dictionary of validated parameters.

Return type

dict

Raises

ValueError – If an invalid parameter is provided.