actableai.data_imputation.error_detector package

Submodules

actableai.data_imputation.error_detector.base_error_detector module

class actableai.data_imputation.error_detector.base_error_detector.BaseErrorDetector

Bases: abc.ABC

abstract detect_cells() → actableai.data_imputation.error_detector.cell_erros.CellErrors

setup(df: pandas.core.frame.DataFrame, dftypes: actableai.data_imputation.type_recon.type_detector.DfTypes)

actableai.data_imputation.error_detector.cell_erros module

class actableai.data_imputation.error_detector.cell_erros.CellError(column: str, index: int, error_type: actableai.data_imputation.error_detector.cell_erros.ErrorType)

Bases: object

property column

property error_type

property index

class actableai.data_imputation.error_detector.cell_erros.CellErrors(dftypes: actableai.data_imputation.type_recon.type_detector.DfTypes, errors: List[actableai.data_imputation.error_detector.cell_erros.CellError] = ())

Bases: object

append(error: actableai.data_imputation.error_detector.cell_erros.CellError)

property columns: Set[str]

extend(errors: actableai.data_imputation.error_detector.cell_erros.CellErrors)

class actableai.data_imputation.error_detector.cell_erros.CellInfo(column: str, index: int)

Bases: object

column: str

index: int

class actableai.data_imputation.error_detector.cell_erros.ColumnErrors(column_errors: Set[actableai.data_imputation.error_detector.cell_erros.CellError])

Bases: object

property column

class actableai.data_imputation.error_detector.cell_erros.ErrorCandidate(index: int, columns: actableai.data_imputation.error_detector.cell_erros.ErrorColumns)

Bases: object

columns: actableai.data_imputation.error_detector.cell_erros.ErrorColumns

index: int

property potential_columns: Set[str]

class actableai.data_imputation.error_detector.cell_erros.ErrorColumns(columns_from_when: Set[str], columns_from_then: Set[str])

Bases: object

columns_from_then: Set[str]

columns_from_when: Set[str]

class actableai.data_imputation.error_detector.cell_erros.ErrorType(value)

Bases: enum.Enum

An enumeration.

INVALID = 'INVALID'

MISPLACED = 'MISPLACED'

NULL = 'NULL'

TYPO = 'TYPO'

actableai.data_imputation.error_detector.column_format module

class actableai.data_imputation.error_detector.column_format.MatchNumRule(column: str, op: actableai.data_imputation.error_detector.match_condition.ConditionOp, match_val: Union[int, float])

Bases: actableai.data_imputation.error_detector.column_format._MatchRule

find_misplaced(series: pandas.core.series.Series) → Iterator[int]

match_val: Union[int, float]

class actableai.data_imputation.error_detector.column_format.MatchRule(column: str, value: str, op: actableai.data_imputation.error_detector.match_condition.ConditionOp)

Bases: object

column: str

op: actableai.data_imputation.error_detector.match_condition.ConditionOp

classmethod parse(dftypes: actableai.data_imputation.type_recon.type_detector.DfTypes, condition_string: str) → Union[actableai.data_imputation.error_detector.column_format.MatchStrRule, actableai.data_imputation.error_detector.column_format.MatchNumRule, NotImplementedType]

value: str

class actableai.data_imputation.error_detector.column_format.MatchRuleGroup(conditions: List[actableai.data_imputation.error_detector.column_format.MatchRule])

Bases: object

conditions: List[actableai.data_imputation.error_detector.column_format.MatchRule]

class actableai.data_imputation.error_detector.column_format.MatchRules(expect_formats: List[actableai.data_imputation.error_detector.column_format._MatchRule])

Bases: object

append(rule: actableai.data_imputation.error_detector.column_format._MatchRule)

classmethod parse(dtypes, condition_string: str) → actableai.data_imputation.error_detector.column_format.MatchRules

class actableai.data_imputation.error_detector.column_format.MatchStrRule(column: str, op: actableai.data_imputation.error_detector.match_condition.ConditionOp, match_str: str, is_regex: bool)

Bases: actableai.data_imputation.error_detector.column_format._MatchRule

find_misplaced(series: pandas.core.series.Series) → Iterator[int]

is_regex: bool

match_str: str

class actableai.data_imputation.error_detector.column_format.PresetRuleName(value)

Bases: enum.Enum

An enumeration.

SmartPercentage = 'SmartPercentage'

SmartTemperature = 'SmartTemperature'

actableai.data_imputation.error_detector.constraint module

class actableai.data_imputation.error_detector.constraint.Condition(col1: str, col2: str, condition: actableai.data_imputation.error_detector.match_condition.ConditionOp)

Bases: object

col1: str

col2: str

condition: actableai.data_imputation.error_detector.match_condition.ConditionOp

property mentioned_columns: Set[str]

classmethod parse(condition_string: str) → actableai.data_imputation.error_detector.constraint.Condition

class actableai.data_imputation.error_detector.constraint.ConditionGroup(conditions: List[actableai.data_imputation.error_detector.constraint.Condition])

Bases: object

conditions: List[actableai.data_imputation.error_detector.constraint.Condition]

property mentioned_columns: Set[str]

classmethod parse(condition_string: str) → actableai.data_imputation.error_detector.constraint.ConditionGroup

class actableai.data_imputation.error_detector.constraint.Constraint(when: actableai.data_imputation.error_detector.constraint.ConditionGroup, then: actableai.data_imputation.error_detector.constraint.ConditionGroup)

Bases: object

<when> condition match, then the data match <then> condition as invalid

property mentioned_columns: Set[str]

classmethod parse(constrain_string: str) → actableai.data_imputation.error_detector.constraint.Constraint

then: actableai.data_imputation.error_detector.constraint.ConditionGroup

when: actableai.data_imputation.error_detector.constraint.ConditionGroup

class actableai.data_imputation.error_detector.constraint.Constraints(constraints: List[actableai.data_imputation.error_detector.constraint.Constraint])

Bases: object

constraints: List[actableai.data_imputation.error_detector.constraint.Constraint]

extends(constraints: actableai.data_imputation.error_detector.constraint.Constraints)

property mentioned_columns: Set[str]

classmethod parse(constraints_string: str) → actableai.data_imputation.error_detector.constraint.Constraints

actableai.data_imputation.error_detector.error_detector module

class actableai.data_imputation.error_detector.error_detector.ErrorDetector

Bases: object

detect_error(df: pandas.core.frame.DataFrame, dftypes: actableai.data_imputation.type_recon.type_detector.DfTypes, expanded_df: pandas.core.frame.DataFrame, expanded_dftypes: actableai.data_imputation.type_recon.type_detector.DfTypes) → actableai.data_imputation.error_detector.cell_erros.CellErrors

property detectors

set_detectors(*detectors: actableai.data_imputation.error_detector.base_error_detector.BaseErrorDetector)

actableai.data_imputation.error_detector.match_condition module

class actableai.data_imputation.error_detector.match_condition.ConditionOp(value)

Bases: enum.Enum

An enumeration.

EQ = '='

GT = '>'

GTE = '>='

IQ = '<>'

LT = '<'

LTE = '<='

actableai.data_imputation.error_detector.misplaced_detector module

class actableai.data_imputation.error_detector.misplaced_detector.MisplacedDetector(*, preset_rules: typing.List[actableai.data_imputation.error_detector.column_format.PresetRuleName] = (), customize_rules: actableai.data_imputation.error_detector.column_format.MatchRules = <actableai.data_imputation.error_detector.column_format.MatchRules object>)

Bases: actableai.data_imputation.error_detector.base_error_detector.BaseErrorDetector

detect_cells() → actableai.data_imputation.error_detector.cell_erros.CellErrors

property mentioned_columns: Set[str]

setup(df: pandas.core.frame.DataFrame, dftypes: actableai.data_imputation.type_recon.type_detector.DfTypes)

update_df(df: pandas.core.frame.DataFrame)

actableai.data_imputation.error_detector.null_detector module

class actableai.data_imputation.error_detector.null_detector.NullDetector

Bases: actableai.data_imputation.error_detector.base_error_detector.BaseErrorDetector

detect_cells() → actableai.data_imputation.error_detector.cell_erros.CellErrors

actableai.data_imputation.error_detector.rule_parser module

class actableai.data_imputation.error_detector.rule_parser.RulesBuilder(constraints: actableai.data_imputation.error_detector.constraint.Constraints, match_rules: actableai.data_imputation.error_detector.column_format.MatchRules)

Bases: object

property constraints

property match_rules

classmethod parse(dftypes: actableai.data_imputation.type_recon.type_detector.DfTypes, rules: actableai.data_imputation.error_detector.rule_parser.RulesRaw) → actableai.data_imputation.error_detector.rule_parser.RulesBuilder

class actableai.data_imputation.error_detector.rule_parser.RulesRaw(validations: str, misplaced: str)

Bases: object

misplaced: str

validations: str

actableai.data_imputation.error_detector.smart_column_selector module

class actableai.data_imputation.error_detector.smart_column_selector.SmartErrorCellSelector

Bases: object

append_candidate(candidate: actableai.data_imputation.error_detector.cell_erros.ErrorCandidate)

find_actual_errors(df: pandas.core.frame.DataFrame, dftypes: actableai.data_imputation.type_recon.type_detector.DfTypes, focused_columns: Set[str]) → Iterable[actableai.data_imputation.error_detector.cell_erros.CellError]

reset()

actableai.data_imputation.error_detector.validation_constraints_checker module

class actableai.data_imputation.error_detector.validation_constraints_checker.ValidationConstrainsChecker(constraints: actableai.data_imputation.error_detector.constraint.Constraints)

Bases: object

detect_most_possible_candidates(df: pandas.core.frame.DataFrame) → List[actableai.data_imputation.error_detector.cell_erros.ErrorCandidate]

detect_typo_cells(df: pandas.core.frame.DataFrame) → List[actableai.data_imputation.error_detector.cell_erros.CellError]

find_all_unmatched(df: pandas.core.frame.DataFrame) → List[actableai.data_imputation.error_detector.cell_erros.ErrorCandidate]

property mentioned_columns: Set[str]

actableai.data_imputation.error_detector.validation_detector module

class actableai.data_imputation.error_detector.validation_detector.ValidationDetector(constraints: Optional[actableai.data_imputation.error_detector.constraint.Constraints] = NotImplemented)

Bases: actableai.data_imputation.error_detector.base_error_detector.BaseErrorDetector

property constraints

detect_cells() → actableai.data_imputation.error_detector.cell_erros.CellErrors

classmethod from_constraints(constraints_string: str)

setup_constraints(constraints: actableai.data_imputation.error_detector.constraint.Constraints)

Module contents

class actableai.data_imputation.error_detector.CellErrors(dftypes: actableai.data_imputation.type_recon.type_detector.DfTypes, errors: List[actableai.data_imputation.error_detector.cell_erros.CellError] = ())

Bases: object

append(error: actableai.data_imputation.error_detector.cell_erros.CellError)

property columns: Set[str]

extend(errors: actableai.data_imputation.error_detector.cell_erros.CellErrors)

class actableai.data_imputation.error_detector.ColumnErrors(column_errors: Set[actableai.data_imputation.error_detector.cell_erros.CellError])

Bases: object

property column

class actableai.data_imputation.error_detector.ConditionOp(value)

Bases: enum.Enum

An enumeration.

EQ = '='

GT = '>'

GTE = '>='

IQ = '<>'

LT = '<'

LTE = '<='

class actableai.data_imputation.error_detector.ErrorDetector

Bases: object

detect_error(df: pandas.core.frame.DataFrame, dftypes: actableai.data_imputation.type_recon.type_detector.DfTypes, expanded_df: pandas.core.frame.DataFrame, expanded_dftypes: actableai.data_imputation.type_recon.type_detector.DfTypes) → actableai.data_imputation.error_detector.cell_erros.CellErrors

property detectors

set_detectors(*detectors: actableai.data_imputation.error_detector.base_error_detector.BaseErrorDetector)

class actableai.data_imputation.error_detector.MatchNumRule(column: str, op: actableai.data_imputation.error_detector.match_condition.ConditionOp, match_val: Union[int, float])

Bases: actableai.data_imputation.error_detector.column_format._MatchRule

column: str

find_misplaced(series: pandas.core.series.Series) → Iterator[int]

match_val: Union[int, float]

op: actableai.data_imputation.error_detector.match_condition.ConditionOp

class actableai.data_imputation.error_detector.MatchRules(expect_formats: List[actableai.data_imputation.error_detector.column_format._MatchRule])

Bases: object

append(rule: actableai.data_imputation.error_detector.column_format._MatchRule)

classmethod parse(dtypes, condition_string: str) → actableai.data_imputation.error_detector.column_format.MatchRules

class actableai.data_imputation.error_detector.MatchStrRule(column: str, op: actableai.data_imputation.error_detector.match_condition.ConditionOp, match_str: str, is_regex: bool)

Bases: actableai.data_imputation.error_detector.column_format._MatchRule

column: str

find_misplaced(series: pandas.core.series.Series) → Iterator[int]

is_regex: bool

match_str: str

op: actableai.data_imputation.error_detector.match_condition.ConditionOp

class actableai.data_imputation.error_detector.MisplacedDetector(*, preset_rules: typing.List[actableai.data_imputation.error_detector.column_format.PresetRuleName] = (), customize_rules: actableai.data_imputation.error_detector.column_format.MatchRules = <actableai.data_imputation.error_detector.column_format.MatchRules object>)

Bases: actableai.data_imputation.error_detector.base_error_detector.BaseErrorDetector

detect_cells() → actableai.data_imputation.error_detector.cell_erros.CellErrors

property mentioned_columns: Set[str]

setup(df: pandas.core.frame.DataFrame, dftypes: actableai.data_imputation.type_recon.type_detector.DfTypes)

update_df(df: pandas.core.frame.DataFrame)

class actableai.data_imputation.error_detector.NullDetector

Bases: actableai.data_imputation.error_detector.base_error_detector.BaseErrorDetector

detect_cells() → actableai.data_imputation.error_detector.cell_erros.CellErrors

class actableai.data_imputation.error_detector.PresetRuleName(value)

Bases: enum.Enum

An enumeration.

SmartPercentage = 'SmartPercentage'

SmartTemperature = 'SmartTemperature'

class actableai.data_imputation.error_detector.RulesBuilder(constraints: actableai.data_imputation.error_detector.constraint.Constraints, match_rules: actableai.data_imputation.error_detector.column_format.MatchRules)

Bases: object

property constraints

property match_rules

classmethod parse(dftypes: actableai.data_imputation.type_recon.type_detector.DfTypes, rules: actableai.data_imputation.error_detector.rule_parser.RulesRaw) → actableai.data_imputation.error_detector.rule_parser.RulesBuilder

class actableai.data_imputation.error_detector.ValidationDetector(constraints: Optional[actableai.data_imputation.error_detector.constraint.Constraints] = NotImplemented)

Bases: actableai.data_imputation.error_detector.base_error_detector.BaseErrorDetector

property constraints

detect_cells() → actableai.data_imputation.error_detector.cell_erros.CellErrors

classmethod from_constraints(constraints_string: str)

setup_constraints(constraints: actableai.data_imputation.error_detector.constraint.Constraints)