utils#

Utility methods for the ProblemTypes enum in EvalML.

Module Contents#

Functions#

`detect_problem_type`	Determine the type of problem is being solved based on the targets (binary vs multiclass classification, regression). Ignores missing and null data.
`handle_problem_types`	Handles problem_type by either returning the ProblemTypes or converting from a str.
`is_binary`	Determines if the provided problem_type is a binary classification problem type.
`is_classification`	Determines if the provided problem_type is a classification problem type.
`is_multiclass`	Determines if the provided problem_type is a multiclass classification problem type.
`is_multiseries`	Determines if the provided problem_type is a multiseries time series problem type.
`is_regression`	Determines if the provided problem_type is a regression problem type.
`is_time_series`	Determines if the provided problem_type is a time series problem type.

Contents#

evalml.problem_types.utils.detect_problem_type(y)[source]#

Determine the type of problem is being solved based on the targets (binary vs multiclass classification, regression). Ignores missing and null data.

Parameters: y (pd.Series) – The target labels to predict.
Returns: ProblemType Enum
Return type: ProblemType

Examples

>>> y = pd.Series([0, 1, 0, 0, 0, 1, 1, 0, 0, 1, 1])
>>> assert detect_problem_type(y) == ProblemTypes.BINARY
...
>>> y = pd.Series([1, 2, 3, 2, 1, 1, 1, 2, 2, 3, 3])
>>> assert detect_problem_type(y) == ProblemTypes.MULTICLASS
...
>>> y = pd.Series([1.6, 4.2, 3.3, 2.9, 4, 1, 5.5, 2, -2, -3.2, 3])
>>> assert detect_problem_type(y) == ProblemTypes.REGRESSION

Raises: ValueError – If the input has less than two classes.

evalml.problem_types.utils.handle_problem_types(problem_type)[source]#

Handles problem_type by either returning the ProblemTypes or converting from a str.

Parameters

problem_type (str or ProblemTypes) – Problem type that needs to be handled.

Returns

ProblemTypes enum

Raises

KeyError – If input is not a valid ProblemTypes enum value.
ValueError – If input is not a string or ProblemTypes object.

Examples

>>> assert handle_problem_types("regression") == ProblemTypes.REGRESSION
>>> assert handle_problem_types("TIME SERIES BINARY") == ProblemTypes.TIME_SERIES_BINARY
>>> assert handle_problem_types("Multiclass") == ProblemTypes.MULTICLASS

evalml.problem_types.utils.is_binary(problem_type)[source]#

Determines if the provided problem_type is a binary classification problem type.

Parameters: problem_type (str or ProblemTypes) – type of supervised learning problem. See evalml.problem_types.ProblemType.all_problem_types for a full list.
Returns: Whether or not the provided problem_type is a binary classification problem type.
Return type: bool

Examples

>>> assert is_binary("Binary")
>>> assert is_binary(ProblemTypes.BINARY)
>>> assert is_binary(ProblemTypes.TIME_SERIES_BINARY)

evalml.problem_types.utils.is_classification(problem_type)[source]#

Determines if the provided problem_type is a classification problem type.

Parameters: problem_type (str or ProblemTypes) – type of supervised learning problem. See evalml.problem_types.ProblemType.all_problem_types for a full list.
Returns: Whether or not the provided problem_type is a classification problem type.
Return type: bool

Examples

>>> assert is_classification("Multiclass")
>>> assert is_classification(ProblemTypes.TIME_SERIES_BINARY)
>>> assert not is_classification(ProblemTypes.REGRESSION)

evalml.problem_types.utils.is_multiclass(problem_type)[source]#

Determines if the provided problem_type is a multiclass classification problem type.

Parameters: problem_type (str or ProblemTypes) – type of supervised learning problem. See evalml.problem_types.ProblemType.all_problem_types for a full list.
Returns: Whether or not the provided problem_type is a multiclass classification problem type.
Return type: bool

Examples

>>> assert is_multiclass("Multiclass")
>>> assert is_multiclass(ProblemTypes.MULTICLASS)
>>> assert is_multiclass(ProblemTypes.TIME_SERIES_MULTICLASS)

evalml.problem_types.utils.is_multiseries(problem_type)[source]#

Determines if the provided problem_type is a multiseries time series problem type.

Parameters: problem_type (str or ProblemTypes) – type of supervised learning problem. See evalml.problem_types.ProblemType.all_problem_types for a full list.
Returns: Whether or not the provided problem_type is a multiseries time series problem type.
Return type: bool

evalml.problem_types.utils.is_regression(problem_type)[source]#

Determines if the provided problem_type is a regression problem type.

Parameters: problem_type (str or ProblemTypes) – type of supervised learning problem. See evalml.problem_types.ProblemType.all_problem_types for a full list.
Returns: Whether or not the provided problem_type is a regression problem type.
Return type: bool

Examples

>>> assert is_regression("Regression")
>>> assert is_regression(ProblemTypes.REGRESSION)
>>> assert is_regression(ProblemTypes.TIME_SERIES_REGRESSION)

evalml.problem_types.utils.is_time_series(problem_type)[source]#

Determines if the provided problem_type is a time series problem type.

Parameters: problem_type (str or ProblemTypes) – type of supervised learning problem. See evalml.problem_types.ProblemType.all_problem_types for a full list.
Returns: Whether or not the provided problem_type is a time series problem type.
Return type: bool

Examples

>>> assert is_time_series("time series regression")
>>> assert is_time_series(ProblemTypes.TIME_SERIES_BINARY)
>>> assert not is_time_series(ProblemTypes.REGRESSION)