HMMSegmenter¶

class HMMSegmenter(emission_funcs: list, transition_prob_mat: ndarray, initial_probs: ndarray | None = None)[source]¶

Implements a simple HMM fitted with Viterbi algorithm.

The HMM annotation estimator uses the the Viterbi algorithm to fit a sequence of ‘hidden state’ class annotations (represented by an array of integers the same size as the observation) to a sequence of observations.

This is done by finding the most likely path given the emission probabilities - (ie the probability that a particular observation would be generated by a given hidden state), the transition prob (ie the probability of transitioning from one state to another or staying in the same state) and the initial probabilities - ie the belief of the probability distribution of hidden states at the start of the observation sequence).

Current assumptions/limitations of this implementation:

the spacing of time series points is assumed to be equivalent.
it only works on univariate data.
the emission parameters and transition probabilities are
assumed to be known.
if no initial probs are passed, uniform probabilities are
assigned (ie rather than the stationary distribution.)
requires and returns np.ndarrays.

_fit is currently empty as the parameters of the probability distribution are required to be passed to the algorithm.

_predict - first the transition_probability and transition_id matrices are calculated - these are both nxm matrices, where n is the number of hidden states and m is the number of observations. The transition probability matrices record the probability of the most likely sequence which has observation m being assigned to hidden state n. The transition_id matrix records the step before hidden state n that proceeds it in the most likely path. This logic is mostly carried out by helper function _calculate_trans_mats. Next, these matrices are used to calculate the most likely path (by backtracing from the final mostly likely state and the id’s that proceeded it.) This logic is done via a helper func hmm_viterbi_label.

Parameters:

emission_funcslist, shape = [num hidden states]: List should be of length n (the number of hidden states) Either a list of callables [fx_1, fx_2] with signature fx_1(X) -> float or a list of callables and matched keyword arguments for those callables [(fx_1, kwarg_1), (fx_2, kwarg_2)] with signature fx_1(X, **kwargs) -> float (or a list with some mixture of the two). The callables should take a value and return a probability when passed a single observation. All functions should be properly normalized PDFs over the same space as the observed data.
transition_prob_mat: 2D np.ndarry, shape = [num_states, num_states]: Each row should sum to 1 in order to be properly normalized (ie the j’th column in the i’th row represents the probability of transitioning from state i to state j.)
initial_probs: 1D np.ndarray, shape = [num hidden states], optional: A array of probabilities that the sequence of hidden states starts in each of the hidden states. If passed, should be of length n the number of hidden states and should match the length of both the emission funcs list and the transition_prob_mat. The initial probs should be reflective of prior beliefs. If none is passed will each hidden state will be assigned an equal inital prob.

Attributes:

emission_funcslist, shape = [num_hidden_states]: The functions to use in calculating the emission probabilities. Taken from the __init__ param of same name.
transition_prob_mat: 2D np.ndarry, shape = [num_states, num_states]: Matrix of transition probabilities from hidden state to hidden state. Taken from the __init__ param of same name.
initial_probs1D np.ndarray, shape = [num_hidden_states]: Probability over the hidden state identity of the first state. If the __init__ param of same name was passed it will take on that value. Otherwise it is set to be uniform over all hidden states.
num_statesint: The number of hidden states. Set to be the length of the emission_funcs parameter which was passed.
stateslist: A list of integers from 0 to num_states-1. Integer labels for the hidden states.
num_obsint: The length of the observations data. Extracted from data.
trans_prob2D np.ndarray, shape = [num_observations, num_hidden_states]: Shape [num observations, num hidden states]. The max probability that that observation is assigned to that hidden state. Calculated in _calculate_trans_mat and assigned in _predict.
trans_id2D np.ndarray, shape = [num_observations, num_hidden_states]: Shape [num observations, num hidden states]. The state id of the state proceeding the observation is assigned to that hidden state in the most likely path where that occurs. Calculated in _calculate_trans_mat and assigned in _predict.

Examples

>>> from aeon.segmentation import HMMSegmenter
>>> from scipy.stats import norm
>>> from numpy import asarray
>>> # define the emission probs for our HMM model:
>>> centers = [3.5,-5]
>>> sd = [.25 for i in centers]
>>> emi_funcs = [(norm.pdf, {'loc': mean,
...  'scale': sd[ind]}) for ind, mean in enumerate(centers)]
>>> hmm = HMMSegmenter(emi_funcs, asarray([[0.25,0.75], [0.666, 0.333]]))
>>> # generate synthetic data (or of course use your own!)
>>> obs = asarray([3.7,3.2,3.4,3.6,-5.1,-5.2,-4.9])
>>> hmm.fit_predict(obs)
array([0., 0., 0., 0., 1., 1., 1.])

Methods

`check_is_fitted`()	Check if the estimator has been fitted.
`clone`()	Obtain a clone of the object with same hyper-parameters.
`clone_tags`(estimator[, tag_names])	Clone/mirror tags from another estimator as dynamic override.
`create_test_instance`([parameter_set, ...])	Construct Estimator instance if possible.
`create_test_instances_and_names`([parameter_set])	Create list of all test instances and a list of names for them.
`fit`(X[, y, axis])	Fit time series segmenter to X.
`fit_predict`(X[, y, axis])	Fit segmentation to data and return it.
`get_class_tag`(tag_name[, tag_value_default, ...])	Get tag value from estimator class (only class tags).
`get_class_tags`()	Get class tags from estimator class and all its parent classes.
`get_fitted_params`([deep])	Get fitted parameters.
`get_metadata_routing`()	Get metadata routing of this object.
`get_param_defaults`()	Get parameter defaults for the object.
`get_param_names`()	Get parameter names for the object.
`get_params`([deep])	Get parameters for this estimator.
`get_tag`(tag_name[, tag_value_default, ...])	Get tag value from estimator class.
`get_tags`()	Get tags from estimator class.
`get_test_params`([parameter_set])	Return testing parameter settings for the estimator.
`is_composite`()	Check if the object is composite.
`load_from_path`(serial)	Load object from file location.
`load_from_serial`(serial)	Load object from serialized memory container.
`predict`(X[, axis])	Create amd return segmentation of X.
`reset`()	Reset the object to a clean post-init state.
`save`([path])	Save serialized self to bytes-like object or to (.zip) file.
`set_fit_request`(*[, axis])	Request metadata passed to the `fit` method.
`set_params`(**params)	Set the parameters of this object.
`set_predict_request`(*[, axis])	Request metadata passed to the `predict` method.
`set_tags`(**tag_dict)	Set dynamic tags to given values.
`to_classification`(change_points, length)	Convert change point locations to a classification vector.
`to_clusters`(change_points, length)	Convert change point locations to a clustering vector.

classmethod get_test_params(parameter_set='default')[source]¶

Return testing parameter settings for the estimator.

Parameters:

parameter_setstr, default=”default”: Name of the set of test parameters to return, for use in tests. If no special parameters are defined for a value, will return “default” set.

Returns:

paramsdict or list of dict

check_is_fitted()[source]¶

Check if the estimator has been fitted.

Raises:

NotFittedError: If the estimator has not been fitted yet.

clone()[source]¶

Obtain a clone of the object with same hyper-parameters.

A clone is a different object without shared references, in post-init state. This function is equivalent to returning sklearn.clone of self. Equal in value to type(self)(**self.get_params(deep=False)).

Returns:

instance of type(self), clone of self (see above)

clone_tags(estimator, tag_names=None)[source]¶

Clone/mirror tags from another estimator as dynamic override.

Parameters:

estimatorobject: Estimator inheriting from :class:BaseEstimator.
tag_namesstr or list of str, default = None: Names of tags to clone. If None then all tags in estimator are used as tag_names.

Returns:

Self: Reference to self.

Notes

Changes object state by setting tag values in tag_set from estimator as dynamic tags in self.

classmethod create_test_instance(parameter_set='default', return_first=True)[source]¶

Construct Estimator instance if possible.

Calls the get_test_params method and returns an instance or list of instances using the returned dict or list of dict.

Parameters:

parameter_setstr, default=”default”: Name of the set of test parameters to return, for use in tests. If no special parameters are defined for a value, will return “default” set.
return_firstbool, default=True: If True, return the first instance of the list of instances. If False, return the list of instances.

Returns:

instanceBaseEstimator or list of BaseEstimator: Instance of the class with default parameters. If return_first is False, returns list of instances.

classmethod create_test_instances_and_names(parameter_set='default')[source]¶

Create list of all test instances and a list of names for them.

Parameters:

parameter_setstr, default=”default”: Name of the set of test parameters to return, for use in tests. If no special parameters are defined for a value, will return “default” set.

Returns:

objslist of instances of cls: i-th instance is cls(**cls.get_test_params()[i]).
nameslist of str, same length as objs: i-th element is name of i-th instance of obj in tests convention is {cls.__name__}-{i} if more than one instance otherwise {cls.__name__}.
parameter_setstr, default=”default”: Name of the set of test parameters to return, for use in tests. If no special parameters are defined for a value, will return “default” set.

fit(X, y=None, axis=1)[source]¶

Fit time series segmenter to X.

If the tag fit_is_empty is true, this just sets the is_fitted tag to true. Otherwise, it checks self can handle X, formats X into the structure required by self then passes X (and possibly y) to _fit.

Parameters:

XOne of VALID_INPUT_TYPES: Input time series to fit a segmenter.
yOne of VALID_INPUT_TYPES or None, default None: Training time series, a labeled 1D series same length as X for supervised segmentation.
axisint, default = None: Axis along which to segment if passed a multivariate X series (2D input). If axis is 0, it is assumed each column is a time series and each row is a time point. i.e. the shape of the data is (n_timepoints, n_channels). axis == 1 indicates the time series are in rows, i.e. the shape of the data is (n_channels, n_timepoints)`.``axis is None indicates that the axis of X is the same as self.axis.

Returns:

self: Fitted estimator

fit_predict(X, y=None, axis=1)[source]¶: Fit segmentation to data and return it.

classmethod get_class_tag(tag_name, tag_value_default=None, raise_error=False)[source]¶

Get tag value from estimator class (only class tags).

Parameters:

tag_namestr: Name of tag value.
tag_value_defaultany type: Default/fallback value if tag is not found.
raise_errorbool: Whether a ValueError is raised when the tag is not found.

Returns:

tag_value: Value of the tag_name tag in self. If not found, returns an error if raise_error is True, otherwise it returns tag_value_default.

Raises:

ValueError if raise_error is True i.e. if tag_name is not in self.get_tags(
).keys()

See also

get_tag: Get a single tag from an object.
get_class_tags: Get all tags from a class.
get_class_tag: Get a single tag from a class.

Examples

>>> from aeon.classification import DummyClassifier
>>> d = DummyClassifier()
>>> tags = d.get_tags()

is_composite()[source]¶

Check if the object is composite.

A composite object is an object which contains objects, as parameters. Called on an instance, since this may differ by instance.

Returns:

composite: bool: Whether self contains a parameter which is BaseObject.

property is_fitted[source]¶: Whether fit has been called.

classmethod load_from_path(serial)[source]¶

Load object from file location.

Parameters:

serialobject: Result of ZipFile(path).open(“object).

Returns:

deserialized self resulting in output at path, of cls.save(path)

classmethod load_from_serial(serial)[source]¶

Load object from serialized memory container.

Parameters:

serialobject: First element of output of cls.save(None).

Returns:

deserialized self resulting in output serial, of cls.save(None).

predict(X, axis=1)[source]¶

Create amd return segmentation of X.

Parameters:

XOne of VALID_INPUT_TYPES: Input time series
axisint, default = None: Axis along which to segment if passed a multivariate series (2D input) with n_channels time series. If axis is 0, it is assumed each row is a time series and each column is a time point. i.e. the shape of the data is (n_timepoints,n_channels). axis == 1 indicates the time series are in rows, i.e. the shape of the data is (n_channels, n_timepoints)`.``axis is None indicates that the axis of X is the same as self.axis.

Returns:

List: Either a list of indexes of X indicating where each segment begins or a list of integers of len(X) indicating which segment each time point belongs to.

reset()[source]¶

Reset the object to a clean post-init state.

Equivalent to sklearn.clone but overwrites self. After self.reset() call, self is equal in value to type(self)(**self.get_params(deep=False))

Detail behaviour: removes any object attributes, except:

hyper-parameters = arguments of __init__ object attributes containing double-underscores, i.e., the string “__”

runs __init__ with current values of hyper-parameters (result of get_params)

Not affected by the reset are: object attributes containing double-underscores class and object methods, class attributes

save(path=None)[source]¶

Save serialized self to bytes-like object or to (.zip) file.

Behaviour: if path is None, returns an in-memory serialized self if path is a file location, stores self at that location as a zip file

saved files are zip files with following contents: _metadata - contains class of self, i.e., type(self) _obj - serialized self. This class uses the default serialization (pickle).

Parameters:

pathNone or file location (str or Path).: if None, self is saved to an in-memory object if file location, self is saved to that file location. If:

path=”estimator” then a zip file estimator.zip will be made at cwd. path=”/home/stored/estimator” then a zip file estimator.zip will be stored in /home/stored/.

Returns:

if path is None - in-memory serialized self
if path is file location - ZipFile with reference to the file.

set_fit_request(*, axis: bool | None | str = '$UNCHANGED$') → HMMSegmenter[source]¶

Request metadata passed to the fit method.

Note that this method is only relevant if enable_metadata_routing=True (see sklearn.set_config). Please see User Guide on how the routing mechanism works.

The options for each parameter are:

True: metadata is requested, and passed to fit if provided. The request is ignored if metadata is not provided.
False: metadata is not requested and the meta-estimator will not pass it to fit.
None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.
str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Note

This method is only relevant if this estimator is used as a sub-estimator of a meta-estimator, e.g. used inside a Pipeline. Otherwise it has no effect.

Parameters:

axisstr, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED: Metadata routing for axis parameter in fit.

Returns:

selfobject: The updated object.

set_params(**params)[source]¶

Set the parameters of this object.

The method works on simple estimators as well as on nested objects. The latter have parameters of the form <component>__<parameter> so that it’s possible to update each component of a nested object.

Parameters:

**paramsdict: BaseObject parameters

Returns:

selfreference to self (after parameters have been set)

set_predict_request(*, axis: bool | None | str = '$UNCHANGED$') → HMMSegmenter[source]¶

Request metadata passed to the predict method.

Note that this method is only relevant if enable_metadata_routing=True (see sklearn.set_config). Please see User Guide on how the routing mechanism works.

The options for each parameter are:

True: metadata is requested, and passed to predict if provided. The request is ignored if metadata is not provided.
False: metadata is not requested and the meta-estimator will not pass it to predict.
None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.
str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Note

This method is only relevant if this estimator is used as a sub-estimator of a meta-estimator, e.g. used inside a Pipeline. Otherwise it has no effect.

Parameters:

axisstr, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED: Metadata routing for axis parameter in predict.

Returns:

selfobject: The updated object.

set_tags(**tag_dict)[source]¶

Set dynamic tags to given values.

Parameters:

**tag_dictdict: Dictionary of tag name : tag value pairs.

Returns:

Self: Reference to self.

Notes

Changes object state by setting tag values in tag_dict as dynamic tags in self.

classmethod to_classification(change_points: list[int], length: int)[source]¶

Convert change point locations to a classification vector.

Change point detection results can be treated as classification with true change point locations marked with 1’s at position of the change point and remaining non-change point locations being 0’s.

For example change points [2, 8] for a time series of length 10 would result in: [0, 0, 1, 0, 0, 0, 0, 0, 1, 0].

classmethod to_clusters(change_points: list[int], length: int)[source]¶

Convert change point locations to a clustering vector.

Change point detection results can be treated as clustering with each segment separated by change points assigned a distinct dummy label.

For example change points [2, 8] for a time series of length 10 would result in: [0, 0, 1, 1, 1, 1, 1, 1, 2, 2].