classification.py

"""Extension template for time series classifiers.

Purpose of this implementation template:
    quick implementation of new estimators following the template
    NOT a concrete class to import! This is NOT a base class or concrete class!
    This is to be used as a "fill-in" coding template.

How to use this implementation template to implement a new estimator:
- make a copy of the template in a suitable location, give it a descriptive name.
- work through all the "todo" comments below
- fill in code for mandatory methods, and optionally for optional methods
- do not write to reserved variables: is_fitted, _is_fitted, _X, _y, classes_,
    n_classes_, fit_time_, _class_dictionary, _threads_to_use, _tags, _tags_dynamic
- you can add more private methods, but do not override BaseEstimator's private methods
    an easy way to be safe is to prefix your methods with "_custom"
- change docstrings for functions and the file
- ensure interface compatibility by sktime.utils.estimator_checks.check_estimator
- once complete: use as a local library, or contribute to sktime via PR
- more details:
  https://www.sktime.net/en/stable/developer_guide/add_estimators.html

Mandatory implements:
    fitting                 - _fit(self, X, y)
    predicting classes      - _predict(self, X)

Optional implements:
    data conversion and capabilities tags - _tags
    fitted parameter inspection           - _get_fitted_params()
    predicting class probabilities        - _predict_proba(self, X)

Testing - required for sktime test framework and check_estimator usage:
    get default parameters for test instance(s) - get_test_params()

copyright: sktime developers, BSD-3-Clause License (see LICENSE file)
"""

# todo: write an informative docstring for the file or module, remove the above
# todo: add an appropriate copyright notice for your estimator
#       estimators contributed to sktime should have the copyright notice at the top
#       estimators of your own do not need to have permissive or BSD-3 copyright

# todo: uncomment the following line, enter authors' GitHub IDs
# __author__ = [authorGitHubID, anotherAuthorGitHubID]

from sktime.classification.base import BaseClassifier

# todo: add any necessary imports here

# todo: for imports of sktime soft dependencies:
# make sure to fill in the "python_dependencies" tag with the package import name
# import soft dependencies only inside methods of the class, not at the top of the file


# todo: change class name and write docstring
class MyTimeSeriesClassifier(BaseClassifier):
    """Custom time series classifier. todo: write docstring.

    todo: describe your custom time series classifier here

    Hyper-parameters
    ----------------
    parama : int
        descriptive explanation of parama
    paramb : string, optional (default='default')
        descriptive explanation of paramb
    paramc : boolean, optional (default= whether paramb is not the default)
        descriptive explanation of paramc
    and so on

    Components
    ----------
    est : sktime.estimator, BaseEstimator descendant
        descriptive explanation of est
    est2: another estimator
        descriptive explanation of est2
    and so on
    """

    # optional todo: override base class estimator default tags here if necessary
    # these are the default values, only add if different to these.
    _tags = {
        # packaging info
        # --------------
        "authors": ["author1", "author2"],  # authors, GitHub handles
        "maintainers": ["maintainer1", "maintainer2"],  # maintainers, GitHub handles
        # author = significant contribution to code at some point
        #     if interfacing a 3rd party estimator, ensure to give credit to the
        #     authors of the interfaced estimator
        # maintainer = algorithm maintainer role, "owner" of the sktime class
        #     for 3rd party interfaces, the scope is the sktime class only
        # specify one or multiple authors and maintainers
        # remove maintainer tag if maintained by sktime core team
        #
        "python_version": None,  # PEP 440 python version specifier to limit versions
        "python_dependencies": None,  # PEP 440 python dependencies specifier,
        # e.g., "numba>0.53", or a list, e.g., ["numba>0.53", "numpy>=1.19.0"]
        # delete if no python dependencies or version limitations
        #
        # estimator tags
        # --------------
        "X_inner_mtype": "numpy3D",  # which type do _fit/_predict accept, usually
        "y_inner_mtype": "numpy1D",  # which type do _fit/_predict return, usually
        # this is one of "numpy3D" (instance, variable, time point),
        # "pd-multiindex" (row index: instance, time; column index: variable) or other
        # machine types, see datatypes/panel/_registry.py for options.
        "capability:multivariate": False,  # ability to handle multivariate X
        "capability:multioutput": False,  # ability to predict multiple columns in y
        "capability:unequal_length": False,
        "capability:missing_values": False,
        "capability:train_estimate": False,
        "capability:feature_importance": False,
        "capability:contractable": False,
        "capability:multithreading": False,
    }

    # todo: add any hyper-parameters and components to constructor
    def __init__(self, est, parama, est2=None, paramb="default", paramc=None):
        # estimators should precede parameters
        #  if estimators have default values, set None and initialize below

        # todo: write any hyper-parameters and components to self
        self.est = est
        self.parama = parama
        self.paramb = paramb
        self.paramc = paramc
        # IMPORTANT: the self.params should never be overwritten or mutated from now on
        # for handling defaults etc, write to other attributes, e.g., self._parama
        # for estimators, initialize a clone, e.g., self.est_ = est.clone()

        # leave this as is
        super().__init__()

        # todo: optional, parameter checking logic (if applicable) should happen here
        # if writes derived values to self, should *not* overwrite self.parama etc
        # instead, write to self._parama, self._newparam (starting with _)

        # todo: default estimators should have None arg defaults
        #  and be initialized here
        #  do this only with default estimators, not with parameters
        # if est2 is None:
        #     self.estimator = MyDefaultEstimator()

        # todo: if tags of estimator depend on component tags, set these here
        #  only needed if estimator is a composite
        #  tags set in the constructor apply to the object and override the class
        #
        # example 1: conditional setting of a tag
        # if est.foo == 42:
        #   self.set_tags(handles-missing-data=True)
        # example 2: cloning tags from component
        #   self.clone_tags(est2, ["enforce_index_type", "handles-missing-data"])

    # todo: implement this, mandatory
    def _fit(self, X, y):
        """Fit time series classifier to training data.

        private _fit containing the core logic, called from fit

        Writes to self:
            Sets fitted model attributes ending in "_".

        Parameters
        ----------
        X : guaranteed to be of a type in self.get_tag("X_inner_mtype")
            if self.get_tag("X_inner_mtype") = "numpy3D":
            3D np.ndarray of shape = [n_instances, n_dimensions, series_length]
            if self.get_tag("X_inner_mtype") = "pd-multiindex:":
            pd.DataFrame with columns = variables,
            index = pd.MultiIndex with first level = instance indices,
            second level = time indices
            for list of other mtypes, see datatypes.SCITYPE_REGISTER
            for specifications, see examples/AA_datatypes_and_datasets.ipynb
        y : guaranteed to be of a type in self.get_tag("y_inner_mtype")
            1D iterable, of shape [n_instances]
            or 2D iterable, of shape [n_instances, n_dimensions]
            class labels for fitting
            if self.get_tag("capaility:multioutput") = False, guaranteed to be 1D
            if self.get_tag("capaility:multioutput") = True, guaranteed to be 2D

        Returns
        -------
        self : Reference to self.
        """

        # implement here
        # IMPORTANT: avoid side effects to X, y
        #
        # Note: when interfacing a model that has fit, with parameters
        #   that are not data (X, y) or data-like,
        #   but model parameters, *don't* add as arguments to fit, but treat as follows:
        #   1. pass to constructor,  2. write to self in constructor,
        #   3. read from self in _fit,  4. pass to interfaced_model.fit in _fit

    # todo: implement this, mandatory
    def _predict(self, X):
        """Predict labels for sequences in X.

        private _predict containing the core logic, called from predict

        Parameters
        ----------
        X : guaranteed to be of a type in self.get_tag("X_inner_mtype")
            if self.get_tag("X_inner_mtype") = "numpy3D":
            3D np.ndarray of shape = [n_instances, n_dimensions, series_length]
            if self.get_tag("X_inner_mtype") = "pd-multiindex:":
            pd.DataFrame with columns = variables,
            index = pd.MultiIndex with first level = instance indices,
            second level = time indices
            for list of other mtypes, see datatypes.SCITYPE_REGISTER
            for specifications, see examples/AA_datatypes_and_datasets.ipynb

        Returns
        -------
        y : should be of mtype in self.get_tag("y_inner_mtype")
            1D iterable, of shape [n_instances]
            or 2D iterable, of shape [n_instances, n_dimensions]
            predicted class labels
            indices correspond to instance indices in X
            if self.get_tag("capaility:multioutput") = False, should be 1D
            if self.get_tag("capaility:multioutput") = True, should be 2D
        """

        # implement here
        # IMPORTANT: avoid side effects to X

    # todo: consider implementing this, optional
    # if you do not implement it, then the default _predict_proba will be called.
    # the default simply calls predict and sets probas to 0 or 1.
    def _predict_proba(self, X):
        """Predicts labels probabilities for sequences in X.

        private _predict_proba containing the core logic, called from predict_proba

        State required:
            Requires state to be "fitted".

        Accesses in self:
            Fitted model attributes ending in "_"

        Parameters
        ----------
        X : guaranteed to be of a type in self.get_tag("X_inner_mtype")
            if self.get_tag("X_inner_mtype") = "numpy3D":
            3D np.ndarray of shape = [n_instances, n_dimensions, series_length]
            if self.get_tag("X_inner_mtype") = "pd-multiindex:":
            pd.DataFrame with columns = variables,
            index = pd.MultiIndex with first level = instance indices,
            second level = time indices
            for list of other mtypes, see datatypes.SCITYPE_REGISTER
            for specifications, see examples/AA_datatypes_and_datasets.ipynb

        Returns
        -------
        y : 2D array of shape [n_instances, n_classes] - predicted class probabilities
            1st dimension indices correspond to instance indices in X
            2nd dimension indices correspond to possible labels (integers)
            (i, j)-th entry is predictive probability that i-th instance is of class j
        """

        # implement here
        # IMPORTANT: avoid side effects to X

    # todo: consider implementing this, optional
    # implement only if different from default:
    #   default retrieves all self attributes ending in "_"
    #   and returns them with keys that have the "_" removed
    # if not implementing, delete the method
    #   avoid overriding get_fitted_params
    def _get_fitted_params(self):
        """Get fitted parameters.

        private _get_fitted_params, called from get_fitted_params

        State required:
            Requires state to be "fitted".

        Returns
        -------
        fitted_params : dict with str keys
            fitted parameters, keyed by names of fitted parameter
        """
        # implement here
        #
        # when this function is reached, it is already guaranteed that self is fitted
        #   this does not need to be checked separately
        #
        # parameters of components should follow the sklearn convention:
        #   separate component name from parameter name by double-underscore
        #   e.g., componentname__paramname

    # todo: return default parameters, so that a test instance can be created
    #   required for automated unit and integration testing of estimator
    @classmethod
    def get_test_params(cls, parameter_set="default"):
        """Return testing parameter settings for the estimator.

        Parameters
        ----------
        parameter_set : str, 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.
            Reserved values for classifiers:
                "results_comparison" - used for identity testing in some classifiers
                    should contain parameter settings comparable to "TSC bakeoff"

        Returns
        -------
        params : dict or list of dict, default = {}
            Parameters to create testing instances of the class
            Each dict are parameters to construct an "interesting" test instance, i.e.,
            `MyClass(**params)` or `MyClass(**params[i])` creates a valid test instance.
            `create_test_instance` uses the first (or only) dictionary in `params`
        """

        # todo: set the testing parameters for the estimators
        # Testing parameters can be dictionary or list of dictionaries
        #
        # this can, if required, use:
        #   class properties (e.g., inherited); parent class test case
        #   imported objects such as estimators from sktime or sklearn
        # important: all such imports should be *inside get_test_params*, not at the top
        #            since imports are used only at testing time
        #
        # The parameter_set argument is not used for most automated, module level tests.
        #   It can be used in custom, estimator specific tests, for "special" settings.
        #   For classification, this is also used in tests for reference settings,
        #       such as published in benchmarking studies, or for identity testing.
        # A parameter dictionary must be returned *for all values* of parameter_set,
        #   i.e., "parameter_set not available" errors should never be raised.
        #
        # A good parameter set should primarily satisfy two criteria,
        #   1. Chosen set of parameters should have a low testing time,
        #      ideally in the magnitude of few seconds for the entire test suite.
        #       This is vital for the cases where default values result in
        #       "big" models which not only increases test time but also
        #       run into the risk of test workers crashing.
        #   2. There should be a minimum two such parameter sets with different
        #      sets of values to ensure a wide range of code coverage is provided.
        #
        # example 1: specify params as dictionary
        # any number of params can be specified
        # params = {"est": value0, "parama": value1, "paramb": value2}
        #
        # example 2: specify params as list of dictionary
        # note: Only first dictionary will be used by create_test_instance
        # params = [{"est": value1, "parama": value2},
        #           {"est": value3, "parama": value4}]
        #
        # example 3: parameter set depending on param_set value
        #   note: only needed if a separate parameter set is needed in tests
        # if parameter_set == "special_param_set":
        #     params = {"est": value1, "parama": value2}
        #     return params
        #
        # # "default" params
        # params = {"est": value3, "parama": value4}
        # return params