unitxt.processors module

class unitxt.processors.AddPrefix(data_classification_policy: List[str] = None, _requirements_list: List[str] | Dict[str, str] = [], requirements: List[str] | Dict[str, str] = [], caching: bool = None, apply_to_streams: List[str] = None, dont_apply_to_streams: List[str] = None, field: str | NoneType = None, to_field: str | NoneType = None, field_to_field: List[List[str]] | Dict[str, str] | NoneType = None, use_query: bool | NoneType = None, process_every_value: bool = False, get_default: Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False, prefix: str = __required__)

Bases: FieldOperator

class unitxt.processors.Capitalize(data_classification_policy: List[str] = None, _requirements_list: List[str] | Dict[str, str] = [], requirements: List[str] | Dict[str, str] = [], caching: bool = None, apply_to_streams: List[str] = None, dont_apply_to_streams: List[str] = None, field: str | NoneType = None, to_field: str | NoneType = None, field_to_field: List[List[str]] | Dict[str, str] | NoneType = None, use_query: bool | NoneType = None, process_every_value: bool = False, get_default: Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False)

Bases: FieldOperator

class unitxt.processors.ConvertToBoolean(data_classification_policy: List[str] = None, _requirements_list: List[str] | Dict[str, str] = [], requirements: List[str] | Dict[str, str] = [], caching: bool = None, apply_to_streams: List[str] = None, dont_apply_to_streams: List[str] = None, field: str | NoneType = None, to_field: str | NoneType = None, field_to_field: List[List[str]] | Dict[str, str] | NoneType = None, use_query: bool | NoneType = None, process_every_value: bool = False, get_default: Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False)

Bases: FieldOperator

class unitxt.processors.DictOfListsToPairs(data_classification_policy: List[str] = None, _requirements_list: List[str] | Dict[str, str] = [], requirements: List[str] | Dict[str, str] = [], caching: bool = None, apply_to_streams: List[str] = None, dont_apply_to_streams: List[str] = None, field: str | NoneType = None, to_field: str | NoneType = None, field_to_field: List[List[str]] | Dict[str, str] | NoneType = None, use_query: bool | NoneType = None, process_every_value: bool = False, get_default: Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False, position_key_before_value: bool = True)

Bases: FieldOperator

class unitxt.processors.ExtractArenaHardNumericalJudgment(data_classification_policy: List[str] = None, _requirements_list: List[str] | Dict[str, str] = [], requirements: List[str] | Dict[str, str] = [], caching: bool = None, apply_to_streams: List[str] = None, dont_apply_to_streams: List[str] = None, field: str | NoneType = None, to_field: str | NoneType = None, field_to_field: List[List[str]] | Dict[str, str] | NoneType = None, use_query: bool | NoneType = None, process_every_value: bool = False, get_default: Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False)

Bases: FieldOperator

class unitxt.processors.ExtractHarmRatingJudgement(data_classification_policy: List[str] = None, _requirements_list: List[str] | Dict[str, str] = [], requirements: List[str] | Dict[str, str] = [], caching: bool = None, apply_to_streams: List[str] = None, dont_apply_to_streams: List[str] = None, field: str | NoneType = None, to_field: str | NoneType = None, field_to_field: List[List[str]] | Dict[str, str] | NoneType = None, use_query: bool | NoneType = None, process_every_value: bool = False, get_default: Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False)

Bases: FieldOperator

class unitxt.processors.ExtractMtBenchLabelJudgment(data_classification_policy: List[str] = None, _requirements_list: List[str] | Dict[str, str] = [], requirements: List[str] | Dict[str, str] = [], caching: bool = None, apply_to_streams: List[str] = None, dont_apply_to_streams: List[str] = None, field: str | NoneType = None, to_field: str | NoneType = None, field_to_field: List[List[str]] | Dict[str, str] | NoneType = None, use_query: bool | NoneType = None, process_every_value: bool = False, get_default: Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False)

Bases: FieldOperator

class unitxt.processors.ExtractMtBenchRatingJudgment(data_classification_policy: List[str] = None, _requirements_list: List[str] | Dict[str, str] = [], requirements: List[str] | Dict[str, str] = [], caching: bool = None, apply_to_streams: List[str] = None, dont_apply_to_streams: List[str] = None, field: str | NoneType = None, to_field: str | NoneType = None, field_to_field: List[List[str]] | Dict[str, str] | NoneType = None, use_query: bool | NoneType = None, process_every_value: bool = False, get_default: Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False)

Bases: FieldOperator

class unitxt.processors.ExtractSafeUnsafeJudgment(data_classification_policy: List[str] = None, _requirements_list: List[str] | Dict[str, str] = [], requirements: List[str] | Dict[str, str] = [], caching: bool = None, apply_to_streams: List[str] = None, dont_apply_to_streams: List[str] = None, field: str | NoneType = None, to_field: str | NoneType = None, field_to_field: List[List[str]] | Dict[str, str] | NoneType = None, use_query: bool | NoneType = None, process_every_value: bool = False, get_default: Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False)

Bases: FieldOperator

class unitxt.processors.ExtractVerbalJudgementBadGood(data_classification_policy: List[str] = None, _requirements_list: List[str] | Dict[str, str] = [], requirements: List[str] | Dict[str, str] = [], caching: bool = None, apply_to_streams: List[str] = None, dont_apply_to_streams: List[str] = None, field: str | NoneType = None, to_field: str | NoneType = None, field_to_field: List[List[str]] | Dict[str, str] | NoneType = None, use_query: bool | NoneType = None, process_every_value: bool = False, get_default: Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False)

Bases: ExtractVerbalJudgment

classes = ['very bad', 'bad', 'mediocre', 'good', 'very good']

class unitxt.processors.ExtractVerbalJudgment(data_classification_policy: List[str] = None, _requirements_list: List[str] | Dict[str, str] = [], requirements: List[str] | Dict[str, str] = [], caching: bool = None, apply_to_streams: List[str] = None, dont_apply_to_streams: List[str] = None, field: str | NoneType = None, to_field: str | NoneType = None, field_to_field: List[List[str]] | Dict[str, str] | NoneType = None, use_query: bool | NoneType = None, process_every_value: bool = False, get_default: Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False)

Bases: FieldOperator

classes = ['not', 'somewhat', 'mostly', 'completely']

class unitxt.processors.ExtractWithRegex(data_classification_policy: List[str] = None, _requirements_list: List[str] | Dict[str, str] = [], requirements: List[str] | Dict[str, str] = [], caching: bool = None, apply_to_streams: List[str] = None, dont_apply_to_streams: List[str] = None, field: str | NoneType = None, to_field: str | NoneType = None, field_to_field: List[List[str]] | Dict[str, str] | NoneType = None, use_query: bool | NoneType = None, process_every_value: bool = False, get_default: Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False, regex: str = __required__, termination_regex: str = None)

Bases: RegexParser

class unitxt.processors.FirstCharacter(data_classification_policy: List[str] = None, _requirements_list: List[str] | Dict[str, str] = [], requirements: List[str] | Dict[str, str] = [], caching: bool = None, apply_to_streams: List[str] = None, dont_apply_to_streams: List[str] = None, field: str | NoneType = None, to_field: str | NoneType = None, field_to_field: List[List[str]] | Dict[str, str] | NoneType = None, use_query: bool | NoneType = None, process_every_value: bool = False, get_default: Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False)

Bases: FieldOperator

class unitxt.processors.FixWhiteSpace(data_classification_policy: List[str] = None, _requirements_list: List[str] | Dict[str, str] = [], requirements: List[str] | Dict[str, str] = [], caching: bool = None, apply_to_streams: List[str] = None, dont_apply_to_streams: List[str] = None, field: str | NoneType = None, to_field: str | NoneType = None, field_to_field: List[List[str]] | Dict[str, str] | NoneType = None, use_query: bool | NoneType = None, process_every_value: bool = False, get_default: Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False)

Bases: FieldOperator

class unitxt.processors.GetSQL(data_classification_policy: List[str] = None, _requirements_list: List[str] | Dict[str, str] = [], requirements: List[str] | Dict[str, str] = [], caching: bool = None, apply_to_streams: List[str] = None, dont_apply_to_streams: List[str] = None, field: str | NoneType = None, to_field: str | NoneType = None, field_to_field: List[List[str]] | Dict[str, str] | NoneType = None, use_query: bool | NoneType = None, process_every_value: bool = False, get_default: Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False)

Bases: FieldOperator

Operator to extract the most likely SQL query from text, often generated by language models.

It prioritizes SQL within markdown code blocks (`sql or `) and defaults to finding the last SELECT statement in the text if no code blocks are found. It attempts to remove trailing text after the first semicolon in the identified query.

process_value(text: str) → str

Extracts the most plausible SQL query from the given text.

Parameters:

text – The input string potentially containing an SQL query and other text (e.g., explanations, markdown).

Returns:

The extracted SQL query string, or a message indicating no query was found.

class unitxt.processors.GetStringAfter(data_classification_policy: List[str] = None, _requirements_list: List[str] | Dict[str, str] = [], requirements: List[str] | Dict[str, str] = [], caching: bool = None, apply_to_streams: List[str] = None, dont_apply_to_streams: List[str] = None, field: str | NoneType = None, to_field: str | NoneType = None, field_to_field: List[List[str]] | Dict[str, str] | NoneType = None, use_query: bool | NoneType = None, process_every_value: bool = False, get_default: Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False, substring: str = __required__)

Bases: FieldOperator

class unitxt.processors.InferDictsToBinaryLogprobs(data_classification_policy: List[str] = None, _requirements_list: List[str] | Dict[str, str] = [], requirements: List[str] | Dict[str, str] = [], caching: bool = None, apply_to_streams: List[str] = None, dont_apply_to_streams: List[str] = None, field: str | NoneType = None, to_field: str | NoneType = None, field_to_field: List[List[str]] | Dict[str, str] | NoneType = None, use_query: bool | NoneType = None, process_every_value: bool = False, get_default: Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False, neg_class_name: str = __required__, pos_class_name: str = __required__, take_logprobs_from_end: bool = False, num_logprobs_to_take: int = 3)

Bases: FieldOperator

class unitxt.processors.ListToEmptyEntitiesTuples(data_classification_policy: List[str] = None, _requirements_list: List[str] | Dict[str, str] = [], requirements: List[str] | Dict[str, str] = [], caching: bool = None, apply_to_streams: List[str] = None, dont_apply_to_streams: List[str] = None, field: str | NoneType = None, to_field: str | NoneType = None, field_to_field: List[List[str]] | Dict[str, str] | NoneType = None, use_query: bool | NoneType = None, process_every_value: bool = False, get_default: Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False)

Bases: FieldOperator

class unitxt.processors.LiteralEval(data_classification_policy: List[str] = None, _requirements_list: List[str] | Dict[str, str] = [], requirements: List[str] | Dict[str, str] = [], caching: bool = None, apply_to_streams: List[str] = None, dont_apply_to_streams: List[str] = None, field: str | NoneType = None, to_field: str | NoneType = None, field_to_field: List[List[str]] | Dict[str, str] | NoneType = None, use_query: bool | NoneType = None, process_every_value: bool = False, get_default: Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False)

Bases: FieldOperator

class unitxt.processors.Lower(data_classification_policy: List[str] = None, _requirements_list: List[str] | Dict[str, str] = [], requirements: List[str] | Dict[str, str] = [], caching: bool = None, apply_to_streams: List[str] = None, dont_apply_to_streams: List[str] = None, field: str | NoneType = None, to_field: str | NoneType = None, field_to_field: List[List[str]] | Dict[str, str] | NoneType = None, use_query: bool | NoneType = None, process_every_value: bool = False, get_default: Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False)

Bases: FieldOperator

class unitxt.processors.LowerCaseTillPunc(data_classification_policy: List[str] = None, _requirements_list: List[str] | Dict[str, str] = [], requirements: List[str] | Dict[str, str] = [], caching: bool = None, apply_to_streams: List[str] = None, dont_apply_to_streams: List[str] = None, field: str | NoneType = None, to_field: str | NoneType = None, field_to_field: List[List[str]] | Dict[str, str] | NoneType = None, use_query: bool | NoneType = None, process_every_value: bool = False, get_default: Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False)

Bases: FieldOperator

class unitxt.processors.MatchClosestOption(data_classification_policy: List[str] = None, _requirements_list: List[str] | Dict[str, str] = [], requirements: List[str] | Dict[str, str] = [], caching: bool = None, apply_to_streams: List[str] = None, dont_apply_to_streams: List[str] = None, field: str | NoneType = None, to_field: str | NoneType = None, field_to_field: List[List[str]] | Dict[str, str] | NoneType = None, use_query: bool | NoneType = None, process_every_value: bool = False, get_default: Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False, options_field: str = 'options')

Bases: InstanceFieldOperator

class unitxt.processors.PostProcess(data_classification_policy: List[str] = None, _requirements_list: List[str] | Dict[str, str] = [], requirements: List[str] | Dict[str, str] = [], caching: bool = None, operator: unitxt.operators.InstanceFieldOperator = __required__, process_prediction: bool = True, process_references: bool = True)

Bases: MultiStreamOperator

class unitxt.processors.RegexParser(data_classification_policy: List[str] = None, _requirements_list: List[str] | Dict[str, str] = [], requirements: List[str] | Dict[str, str] = [], caching: bool = None, apply_to_streams: List[str] = None, dont_apply_to_streams: List[str] = None, field: str | NoneType = None, to_field: str | NoneType = None, field_to_field: List[List[str]] | Dict[str, str] | NoneType = None, use_query: bool | NoneType = None, process_every_value: bool = False, get_default: Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False, regex: str = __required__, termination_regex: str = None)

Bases: FieldOperator

A processor that uses regex in order to parse a string.

class unitxt.processors.RemoveArticles(data_classification_policy: List[str] = None, _requirements_list: List[str] | Dict[str, str] = [], requirements: List[str] | Dict[str, str] = [], caching: bool = None, apply_to_streams: List[str] = None, dont_apply_to_streams: List[str] = None, field: str | NoneType = None, to_field: str | NoneType = None, field_to_field: List[List[str]] | Dict[str, str] | NoneType = None, use_query: bool | NoneType = None, process_every_value: bool = False, get_default: Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False)

Bases: FieldOperator

class unitxt.processors.RemovePunctuations(data_classification_policy: List[str] = None, _requirements_list: List[str] | Dict[str, str] = [], requirements: List[str] | Dict[str, str] = [], caching: bool = None, apply_to_streams: List[str] = None, dont_apply_to_streams: List[str] = None, field: str | NoneType = None, to_field: str | NoneType = None, field_to_field: List[List[str]] | Dict[str, str] | NoneType = None, use_query: bool | NoneType = None, process_every_value: bool = False, get_default: Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False)

Bases: FieldOperator

class unitxt.processors.ScaleNumberToZeroOneReturnZeroIfFails(data_classification_policy: List[str] = None, _requirements_list: List[str] | Dict[str, str] = [], requirements: List[str] | Dict[str, str] = [], caching: bool = None, apply_to_streams: List[str] = None, dont_apply_to_streams: List[str] = None, field: str | NoneType = None, to_field: str | NoneType = None, field_to_field: List[List[str]] | Dict[str, str] | NoneType = None, use_query: bool | NoneType = None, process_every_value: bool = False, get_default: Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False)

Bases: FieldOperator

class unitxt.processors.SplitStrip(data_classification_policy: List[str] = None, _requirements_list: List[str] | Dict[str, str] = [], requirements: List[str] | Dict[str, str] = [], caching: bool = None, apply_to_streams: List[str] = None, dont_apply_to_streams: List[str] = None, field: str | NoneType = None, to_field: str | NoneType = None, field_to_field: List[List[str]] | Dict[str, str] | NoneType = None, use_query: bool | NoneType = None, process_every_value: bool = False, get_default: Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False, delimiter: str = ' ', strip_every_element: bool = False)

Bases: FieldOperator

class unitxt.processors.StanceToProCon(data_classification_policy: List[str] = None, _requirements_list: List[str] | Dict[str, str] = [], requirements: List[str] | Dict[str, str] = [], caching: bool = None, apply_to_streams: List[str] = None, dont_apply_to_streams: List[str] = None, field: str | NoneType = None, to_field: str | NoneType = None, field_to_field: List[List[str]] | Dict[str, str] | NoneType = None, use_query: bool | NoneType = None, process_every_value: bool = False, get_default: Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False)

Bases: FieldOperator

class unitxt.processors.StrToFloatFormat(data_classification_policy: List[str] = None, _requirements_list: List[str] | Dict[str, str] = [], requirements: List[str] | Dict[str, str] = [], caching: bool = None, apply_to_streams: List[str] = None, dont_apply_to_streams: List[str] = None, field: str | NoneType = None, to_field: str | NoneType = None, field_to_field: List[List[str]] | Dict[str, str] | NoneType = None, use_query: bool | NoneType = None, process_every_value: bool = False, get_default: Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False)

Bases: FieldOperator

class unitxt.processors.StringEquals(data_classification_policy: List[str] = None, _requirements_list: List[str] | Dict[str, str] = [], requirements: List[str] | Dict[str, str] = [], caching: bool = None, apply_to_streams: List[str] = None, dont_apply_to_streams: List[str] = None, field: str | NoneType = None, to_field: str | NoneType = None, field_to_field: List[List[str]] | Dict[str, str] | NoneType = None, use_query: bool | NoneType = None, process_every_value: bool = False, get_default: Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False, string: str = __required__)

Bases: FieldOperator

class unitxt.processors.Substring(data_classification_policy: List[str] = None, _requirements_list: List[str] | Dict[str, str] = [], requirements: List[str] | Dict[str, str] = [], caching: bool = None, apply_to_streams: List[str] = None, dont_apply_to_streams: List[str] = None, field: str | NoneType = None, to_field: str | NoneType = None, field_to_field: List[List[str]] | Dict[str, str] | NoneType = None, use_query: bool | NoneType = None, process_every_value: bool = False, get_default: Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False, begin: int = 0, end: int = None)

Bases: FieldOperator

class unitxt.processors.TakeFirstNonEmptyLine(data_classification_policy: List[str] = None, _requirements_list: List[str] | Dict[str, str] = [], requirements: List[str] | Dict[str, str] = [], caching: bool = None, apply_to_streams: List[str] = None, dont_apply_to_streams: List[str] = None, field: str | NoneType = None, to_field: str | NoneType = None, field_to_field: List[List[str]] | Dict[str, str] | NoneType = None, use_query: bool | NoneType = None, process_every_value: bool = False, get_default: Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False)

Bases: FieldOperator

class unitxt.processors.TakeFirstWord(data_classification_policy: List[str] = None, _requirements_list: List[str] | Dict[str, str] = [], requirements: List[str] | Dict[str, str] = [], caching: bool = None, apply_to_streams: List[str] = None, dont_apply_to_streams: List[str] = None, field: str | NoneType = None, to_field: str | NoneType = None, field_to_field: List[List[str]] | Dict[str, str] | NoneType = None, use_query: bool | NoneType = None, process_every_value: bool = False, get_default: Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False)

Bases: FieldOperator

class unitxt.processors.TakeLastNonEmptyLine(data_classification_policy: List[str] = None, _requirements_list: List[str] | Dict[str, str] = [], requirements: List[str] | Dict[str, str] = [], caching: bool = None, apply_to_streams: List[str] = None, dont_apply_to_streams: List[str] = None, field: str | NoneType = None, to_field: str | NoneType = None, field_to_field: List[List[str]] | Dict[str, str] | NoneType = None, use_query: bool | NoneType = None, process_every_value: bool = False, get_default: Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False)

Bases: FieldOperator

class unitxt.processors.ToListByComma(data_classification_policy: List[str] = None, _requirements_list: List[str] | Dict[str, str] = [], requirements: List[str] | Dict[str, str] = [], caching: bool = None, apply_to_streams: List[str] = None, dont_apply_to_streams: List[str] = None, field: str | NoneType = None, to_field: str | NoneType = None, field_to_field: List[List[str]] | Dict[str, str] | NoneType = None, use_query: bool | NoneType = None, process_every_value: bool = False, get_default: Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False, delimiter: str = ',', strip_every_element: bool = True)

Bases: SplitStrip

class unitxt.processors.ToListByCommaSpace(data_classification_policy: List[str] = None, _requirements_list: List[str] | Dict[str, str] = [], requirements: List[str] | Dict[str, str] = [], caching: bool = None, apply_to_streams: List[str] = None, dont_apply_to_streams: List[str] = None, field: str | NoneType = None, to_field: str | NoneType = None, field_to_field: List[List[str]] | Dict[str, str] | NoneType = None, use_query: bool | NoneType = None, process_every_value: bool = False, get_default: Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False, delimiter: str = ', ', strip_every_element: bool = True)

Bases: SplitStrip

class unitxt.processors.ToString(data_classification_policy: List[str] = None, _requirements_list: List[str] | Dict[str, str] = [], requirements: List[str] | Dict[str, str] = [], caching: bool = None, apply_to_streams: List[str] = None, dont_apply_to_streams: List[str] = None, field: str | NoneType = None, to_field: str | NoneType = None, field_to_field: List[List[str]] | Dict[str, str] | NoneType = None, use_query: bool | NoneType = None, process_every_value: bool = False, get_default: Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False)

Bases: FieldOperator

class unitxt.processors.ToStringStripped(data_classification_policy: List[str] = None, _requirements_list: List[str] | Dict[str, str] = [], requirements: List[str] | Dict[str, str] = [], caching: bool = None, apply_to_streams: List[str] = None, dont_apply_to_streams: List[str] = None, field: str | NoneType = None, to_field: str | NoneType = None, field_to_field: List[List[str]] | Dict[str, str] | NoneType = None, use_query: bool | NoneType = None, process_every_value: bool = False, get_default: Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False)

Bases: FieldOperator

class unitxt.processors.ToYesOrNone(data_classification_policy: List[str] = None, _requirements_list: List[str] | Dict[str, str] = [], requirements: List[str] | Dict[str, str] = [], caching: bool = None, apply_to_streams: List[str] = None, dont_apply_to_streams: List[str] = None, field: str | NoneType = None, to_field: str | NoneType = None, field_to_field: List[List[str]] | Dict[str, str] | NoneType = None, use_query: bool | NoneType = None, process_every_value: bool = False, get_default: Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False)

Bases: FieldOperator

class unitxt.processors.Upper(data_classification_policy: List[str] = None, _requirements_list: List[str] | Dict[str, str] = [], requirements: List[str] | Dict[str, str] = [], caching: bool = None, apply_to_streams: List[str] = None, dont_apply_to_streams: List[str] = None, field: str | NoneType = None, to_field: str | NoneType = None, field_to_field: List[List[str]] | Dict[str, str] | NoneType = None, use_query: bool | NoneType = None, process_every_value: bool = False, get_default: Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False)

Bases: FieldOperator

class unitxt.processors.YesNoToInt(data_classification_policy: List[str] = None, _requirements_list: List[str] | Dict[str, str] = [], requirements: List[str] | Dict[str, str] = [], caching: bool = None, apply_to_streams: List[str] = None, dont_apply_to_streams: List[str] = None, field: str | NoneType = None, to_field: str | NoneType = None, field_to_field: List[List[str]] | Dict[str, str] | NoneType = None, use_query: bool | NoneType = None, process_every_value: bool = False, get_default: Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False)

Bases: FieldOperator

class unitxt.processors.YesToOneElseZero(data_classification_policy: List[str] = None, _requirements_list: List[str] | Dict[str, str] = [], requirements: List[str] | Dict[str, str] = [], caching: bool = None, apply_to_streams: List[str] = None, dont_apply_to_streams: List[str] = None, field: str | NoneType = None, to_field: str | NoneType = None, field_to_field: List[List[str]] | Dict[str, str] | NoneType = None, use_query: bool | NoneType = None, process_every_value: bool = False, get_default: Any = None, not_exist_ok: bool = False, not_exist_do_nothing: bool = False)

Bases: FieldOperator

unitxt.processors.process_instance_value(self, value, instance)