RecurrentRegressor

class RecurrentRegressor(rnn_type: str = 'lstm', n_layers: int = 1, n_units: int = 64, dropout_intermediate: float = 0.2, dropout_output: float = 0.2, bidirectional: bool = False, activation: str = 'tanh', return_sequence_last: bool | None = None, n_epochs: int = 100, callbacks: Callback | list[Callback] | None = None, verbose: bool = False, loss: str = 'mean_squared_error', output_activation: str = 'linear', metrics: str | list[str] = 'mean_squared_error', batch_size: int = 32, use_mini_batch_size: bool = False, random_state: int | np.random.RandomState | None = None, file_path: str = './', save_best_model: bool = False, save_last_model: bool = False, save_init_model: bool = False, best_file_name: str = 'best_model', last_file_name: str = 'last_model', init_file_name: str = 'init_model', optimizer: tf.keras.optimizers.Optimizer | None = None)

Bases: BaseDeepRegressor

Recurrent Neural Network (RNN) regressor.

Adapted from the implementation used in sktime-dl for time series regression.

Parameters:

rnn_typestr, default = “lstm”

Type of RNN layer to use. Options: “lstm”, “gru”, “simple_rnn”

n_layersint, default = 1

Number of RNN layers

n_unitsint, default = 64

Number of units in each RNN layer

dropout_ratefloat, default = 0.2

Dropout rate for regularization

bidirectionalbool, default = False

Whether to use bidirectional RNN layers

activationstr, default = “tanh”

Activation function for RNN layers

return_sequence_lastbool, default = None

Whether RNN layers should return sequences. If None, automatically determined

n_epochsint, default = 100

Number of epochs to train the model

batch_sizeint, default = 32

Number of samples per gradient update

use_mini_batch_sizebool, default = False

Condition on using the mini batch size formula

callbackskeras callback or list of callbacks, default = None

The default list of callbacks are set to ModelCheckpoint and ReduceLROnPlateau

random_stateint, RandomState instance or None, default=None

If int, random_state is the seed used by the random number generator; If RandomState instance, random_state is the random number generator; If None, the random number generator is the RandomState instance used by np.random.

file_pathstr, default = ‘./’

File path when saving model_Checkpoint callback

save_best_modelbool, default = False

Whether or not to save the best model

save_last_modelbool, default = False

Whether or not to save the last model

save_init_modelbool, default = False

Whether to save the initialization of the model

best_file_namestr, default = “best_model”

The name of the file of the best model

last_file_namestr, default = “last_model”

The name of the file of the last model

init_file_namestr, default = “init_model”

The name of the file of the init model

verbosebool, default = False

Whether to output extra information

lossstr, default = “mean_squared_error”

The name of the keras training loss

optimizerkeras.optimizer, default = None

The keras optimizer used for training. If None, uses Adam with lr=0.001

metricsstr or list[str], default=”mean_squared_error”

The evaluation metrics to use during training

output_activationstr, default = “linear”

The output activation for the regressor

Notes

Capabilities

Missing Values	No
Multithreading	No
Univariate	Yes
Multivariate	Yes
Unequal Length	No
Train Estimate	No
Contractable	No

Examples

>>> from aeon.regression.deep_learning import RecurrentRegressor
>>> from aeon.testing.data_generation import make_example_3d_numpy
>>> X, y = make_example_3d_numpy(n_cases=10, n_channels=1, n_timepoints=12,
...                              return_y=True, regression_target=True,
...                              random_state=0)
>>> rgs = RecurrentRegressor(n_epochs=20, batch_size=4)
>>> rgs.fit(X, y)
RecurrentRegressor(...)

Methods

build_model(input_shape, **kwargs)	Construct a compiled, un-trained, keras model that is ready for training.
clone([random_state])	Obtain a clone of the object with the same hyperparameters.
fit(X, y)	Fit time series regressor to training data.
fit_predict(X, y)	Fits the regressor and predicts class labels for X.
get_class_tag(tag_name[, raise_error, ...])	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_params([deep])	Get parameters for this estimator.
get_tag(tag_name[, raise_error, ...])	Get tag value from estimator class.
get_tags()	Get tags from estimator.
load_model(model_path)	Load a pre-trained keras model instead of fitting.
predict(X)	Predicts target variable for time series in X.
reset([keep])	Reset the object to a clean post-init state.
save_last_model_to_file([file_path])	Save the last epoch of the trained deep learning model.
score(X, y[, metric, metric_params])	Scores predicted labels against ground truth labels on X.
set_params(**params)	Set the parameters of this estimator.
set_tags(**tag_dict)	Set dynamic tags to given values.
summary()	Summary function to return the losses/metrics for model fit.

build_model(input_shape: tuple[int, ...], **kwargs: Any) → tf.keras.Model

Construct a compiled, un-trained, keras model that is ready for training.

In aeon, time series are stored in numpy arrays of shape (d,m), where d is the number of dimensions, m is the series length. Keras/tensorflow assume data is in shape (m,d). This method also assumes (m,d). Transpose should happen in fit.

Parameters:

input_shapetuple

The shape of the data fed into the input layer, should be (m,d)

Returns:

outputa compiled Keras Model

clone(random_state=None)

Obtain a clone of the object with the same hyperparameters.

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)).

Parameters:

random_stateint, RandomState instance, or None, default=None

Sets the random state of the clone. If None, the random state is not set. If int, random_state is the seed used by the random number generator. If RandomState instance, random_state is the random number generator.

Returns:

estimatorobject

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

fit(X, y) → BaseCollectionEstimator

Fit time series regressor to training data.

Parameters:

Xnp.ndarray or list

Input data, any number of channels, equal length series of shape ( n_cases, n_channels, n_timepoints) or 2D np.array (univariate, equal length series) of shape (n_cases, n_timepoints) or list of numpy arrays (any number of channels, unequal length series) of shape [n_cases], 2D np.array (n_channels, n_timepoints_i), where n_timepoints_i is length of series i. Other types are allowed and converted into one of the above.

Different estimators have different capabilities to handle different types of input. If self.get_tag("capability:multivariate") is False, they cannot handle multivariate series, so either n_channels == 1 is true or X is 2D of shape (n_cases, n_timepoints). If self.get_tag( "capability:unequal_length") is False, they cannot handle unequal length input. In both situations, a ValueError is raised if X has a characteristic that the estimator does not have the capability for is passed.

ynp.ndarray

1D np.array of float, of shape (n_cases) - regression targets (ground truth) for fitting indices corresponding to instance indices in X.

Returns:

selfBaseRegressor

Reference to self.

Notes

Changes state by creating a fitted model that updates attributes ending in “_” and sets is_fitted flag to True.

fit_predict(X, y) → ndarray

Fits the regressor and predicts class labels for X.

fit_predict produces prediction estimates using just the train data. By default, this is through 10x cross validation, although some estimators may utilise specialist techniques such as out-of-bag estimates or leave-one-out cross-validation.

Regressors which override _fit_predict will have the capability:train_estimate tag set to True.

Generally, this will not be the same as fitting on the whole train data then making train predictions. To do this, you should call fit(X,y).predict(X)

Parameters:

Xnp.ndarray or list

Input data, any number of channels, equal length series of shape ( n_cases, n_channels, n_timepoints) or 2D np.array (univariate, equal length series) of shape (n_cases, n_timepoints) or list of numpy arrays (any number of channels, unequal length series) of shape [n_cases], 2D np.array (n_channels, n_timepoints_i), where n_timepoints_i is length of series i. other types are allowed and converted into one of the above.

Different estimators have different capabilities to handle different types of input. If self.get_tag("capability:multivariate") is False, they cannot handle multivariate series, so either n_channels == 1 is true or X is 2D of shape (n_cases, n_timepoints). If self.get_tag( "capability:unequal_length") is False, they cannot handle unequal length input. In both situations, a ValueError is raised if X has a characteristic that the estimator does not have the capability for is passed.

ynp.ndarray

1D np.array of float, of shape (n_cases) - regression targets (ground truth) for fitting indices corresponding to instance indices in X.

Returns:

predictionsnp.ndarray

1D np.array of float, of shape (n_cases) - predicted regression labels indices correspond to instance indices in X

classmethod get_class_tag(tag_name, raise_error=True, tag_value_default=None)

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

Parameters:

tag_namestr

Name of tag value.

raise_errorbool, default=True

Whether a ValueError is raised when the tag is not found.

tag_value_defaultany type, default=None

Default/fallback value if tag is not found and error is not raised.

Returns:

tag_value

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

Raises:

ValueError

if raise_error is True and tag_name is not in self.get_tags().keys()

Examples

>>> from aeon.classification import DummyClassifier
>>> DummyClassifier.get_class_tag("capability:multivariate")
True

classmethod get_class_tags()

Get class tags from estimator class and all its parent classes.

Returns:

collected_tagsdict

Dictionary of tag name and tag value pairs. Collected from _tags class attribute via nested inheritance. These are not overridden by dynamic tags set by set_tags or class __init__ calls.

get_fitted_params(deep=True)

Get fitted parameters.

State required:

Requires state to be “fitted”.

Parameters:

deepbool, default=True

If True, will return the fitted parameters for this estimator and contained subobjects that are estimators.

Returns:

fitted_paramsdict

Fitted parameter names mapped to their values.

get_params(deep=True)

Get parameters for this estimator.

Parameters:

deepbool, default=True

If True, will return the parameters for this estimator and contained subobjects that are estimators.

Returns:

paramsdict

Parameter names mapped to their values.

get_tag(tag_name, raise_error=True, tag_value_default=None)

Get tag value from estimator class.

Includes dynamic and overridden tags.

Parameters:

tag_namestr

Name of tag to be retrieved.

raise_errorbool, default=True

Whether a ValueError is raised when the tag is not found.

tag_value_defaultany type, default=None

Default/fallback value if tag is not found and error is not raised.

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 and tag_name is not in self.get_tags().keys()

Examples

>>> from aeon.classification import DummyClassifier
>>> d = DummyClassifier()
>>> d.get_tag("capability:multivariate")
True

get_tags()

Get tags from estimator.

Includes dynamic and overridden tags.

Returns:

collected_tagsdict

Dictionary of tag name and tag value pairs. Collected from _tags class attribute via nested inheritance and then any overridden and new tags from __init__ or set_tags.

load_model(model_path: str) → None

Load a pre-trained keras model instead of fitting.

Pretrained model should be saved using “save_last_model” or “save_best_model” boolean parameter. When calling this function, all functionalities can be used such as predict, etc. with the loaded model.

Parameters:

model_pathstr (path including model name and extension)

The complete path (including file name and ‘.keras’ extension) from which the pre-trained model’s weights and configuration are loaded. Example: model_path=”path/to/file/best_model.keras”

Returns:

None

predict(X) → ndarray

Predicts target variable for time series in X.

Parameters:

Xnp.ndarray or list

Input data, any number of channels, equal length series of shape ( n_cases, n_channels, n_timepoints) or 2D np.array (univariate, equal length series) of shape (n_cases, n_timepoints) or list of numpy arrays (any number of channels, unequal length series) of shape [n_cases], 2D np.array (n_channels, n_timepoints_i), where n_timepoints_i is length of series i other types are allowed and converted into one of the above.

Different estimators have different capabilities to handle different types of input. If self.get_tag("capability:multivariate") is False, they cannot handle multivariate series, so either n_channels == 1 is true or X is 2D of shape (n_cases, n_timepoints). If self.get_tag( "capability:unequal_length") is False, they cannot handle unequal length input. In both situations, a ValueError is raised if X has a characteristic that the estimator does not have the capability for is passed.

Returns:

predictionsnp.ndarray

1D np.array of float, of shape (n_cases) - predicted regression labels indices correspond to instance indices in X

reset(keep=None)

Reset the object to a clean post-init state.

After a self.reset() call, self is equal or similar in value to type(self)(**self.get_params(deep=False)), assuming no other attributes were kept using keep.

Detailed 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 hyperparameters (result of get_params)

Not affected by the reset are:

object attributes containing double-underscores class and object methods, class attributes any attributes specified in the keep argument

Parameters:

keepNone, str, or list of str, default=None

If None, all attributes are removed except hyperparameters. If str, only the attribute with this name is kept. If list of str, only the attributes with these names are kept.

Returns:

selfobject

Reference to self.

Raises:

TypeError

If ‘keep’ is not a string or a list of strings.

save_last_model_to_file(file_path: str = './') → None

Save the last epoch of the trained deep learning model.

Parameters:

file_pathstr, default = “./”

The directory where the model will be saved

Returns:

None

score(X, y, metric='r2', metric_params=None) → float

Scores predicted labels against ground truth labels on X.

Parameters:

Xnp.ndarray or list

Input data, any number of channels, equal length series of shape ( n_cases, n_channels, n_timepoints) or 2D np.array (univariate, equal length series) of shape (n_cases, n_timepoints) or list of numpy arrays (any number of channels, unequal length series) of shape [n_cases], 2D np.array (n_channels, n_timepoints_i), where n_timepoints_i is length of series i. other types are allowed and converted into one of the above.

Different estimators have different capabilities to handle different types of input. If self.get_tag("capability:multivariate") is False, they cannot handle multivariate series, so either n_channels == 1 is true or X is 2D of shape (n_cases, n_timepoints). If self.get_tag( "capability:unequal_length") is False, they cannot handle unequal length input. In both situations, a ValueError is raised if X has a characteristic that the estimator does not have the capability for is passed.

ynp.ndarray

1D np.array of float, of shape (n_cases) - regression targets (ground truth) for fitting indices corresponding to instance indices in X.

metricUnion[str, callable], default=”r2”,

Defines the scoring metric to test the fit of the model. For supported strings arguments, check sklearn.metrics.get_scorer_names.

metric_paramsdict, default=None,

Contains parameters to be passed to the scoring function. If None, no parameters are passed.

Returns:

scorefloat

MSE score of predict(X) vs y

set_params(**params)

Set the parameters of this estimator.

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

Parameters:

**paramsdict

Estimator parameters.

Returns:

selfestimator instance

Estimator instance.

set_tags(**tag_dict)

Set dynamic tags to given values.

Parameters:

**tag_dictdict

Dictionary of tag name and tag value pairs.

Returns:

selfobject

Reference to self.

summary() → dict[str, Any] | None

Summary function to return the losses/metrics for model fit.

Returns:

history: dict or None,

Dictionary containing model’s train/validation losses and metrics