etna.experimental.classification.PredictabilityAnalyzer#

class PredictabilityAnalyzer(feature_extractor: BaseTimeSeriesFeatureExtractor, classifier: ClassifierMixin, threshold: float = 0.5)[source]#

Bases: TimeSeriesBinaryClassifier

Class for holding time series predictability prediction.

Note

This class requires classification extension to be installed. Read more about this at installation page.

Init PredictabilityAnalyzer with given parameters.

Parameters:

feature_extractor (BaseTimeSeriesFeatureExtractor) – Instance of time series feature extractor.
classifier (ClassifierMixin) – Instance of classifier with sklearn interface.
threshold (float) – Positive class probability threshold.

Methods

`analyze_predictability`(ts)	Analyse the time series in the dataset for predictability.
`download_model`(model_name, dataset_freq, path)	Return the list of available models.
`dump`(path, args, *kwargs)	Save the object.
`fit`(x, y)	Fit the classifier.
`get_available_models`()	Return the list of available models.
`get_series_from_dataset`(ts)	Transform the dataset into the array with time series samples.
`load`(path, args, *kwargs)	Load the object.
`masked_crossval_score`(x, y, mask)	Calculate classification metrics on cross-validation.
`predict`(x)	Predict classes with threshold.
`predict_proba`(x)	Predict probabilities of the positive class.
`set_params`(**params)	Return new object instance with modified parameters.
`to_dict`()	Collect all information about etna object in dict.

Attributes

This class stores its __init__ parameters as attributes.

`NEGATIVE_CLASS`
`POSITIVE_CLASS`

analyze_predictability(ts: TSDataset) → Dict[str, int][source]#

Analyse the time series in the dataset for predictability.

Parameters:: ts (TSDataset) – Dataset with time series.
Returns:: The indicators of predictability for the each segment in the dataset.
Return type:: Dict[str, int]

static download_model(model_name: str, dataset_freq: str, path: str)[source]#

Return the list of available models.

Parameters:

model_name (str) – Name of the pretrained model.
dataset_freq (str) – Frequency of the dataset.
path (str) – Path to save the file with model.

Raises:

ValueError: – If the model does not exist in s3.

dump(path: str, *args, **kwargs)[source]#

Save the object.

Parameters:: path (str) –

fit(x: List[ndarray], y: ndarray) → TimeSeriesBinaryClassifier[source]#

Fit the classifier.

Parameters:

x (List[ndarray]) – Array with time series.
y (ndarray) – Array of class labels.

Returns:

Fitted instance of classifier.

Return type:

TimeSeriesBinaryClassifier

static get_available_models() → List[str][source]#

Return the list of available models.

Return type:: List[str]

static get_series_from_dataset(ts: TSDataset) → List[ndarray][source]#

Transform the dataset into the array with time series samples.

Series in the result array are sorted in the alphabetical order of the corresponding segment names.

Parameters:: ts (TSDataset) – TSDataset with the time series.
Returns:: Array with time series from TSDataset.
Return type:: List[ndarray]

static load(path: str, *args, **kwargs)[source]#

Load the object.

Warning

This method uses dill module which is not secure. It is possible to construct malicious data which will execute arbitrary code during loading. Never load data that could have come from an untrusted source, or that could have been tampered with.

Parameters:: path (str) –

masked_crossval_score(x: List[ndarray], y: ndarray, mask: ndarray) → Dict[str, list][source]#

Calculate classification metrics on cross-validation.

Parameters:

x (List[ndarray]) – Array with time series.
y (ndarray) – Array of class labels.
mask (ndarray) – Fold mask (array where for each element there is a label of its fold)

Returns:

Classification metrics for each fold

Return type:

Dict[str, list]

predict(x: List[ndarray]) → ndarray[source]#

Predict classes with threshold.

Parameters:: x (List[ndarray]) – Array with time series.
Returns:: Array with predicted labels.
Return type:: ndarray

predict_proba(x: List[ndarray]) → ndarray[source]#

Predict probabilities of the positive class.

Parameters:: x (List[ndarray]) – Array with time series.
Returns:: Probabilities for classes.
Return type:: ndarray

set_params(**params: dict) → Self[source]#

Return new object instance with modified parameters.

Method also allows to change parameters of nested objects within the current object. For example, it is possible to change parameters of a model in a Pipeline.

Nested parameters are expected to be in a <component_1>.<...>.<parameter> form, where components are separated by a dot.

Parameters:: **params (dict) – Estimator parameters
Returns:: New instance with changed parameters
Return type:: Self

Examples

>>> from etna.pipeline import Pipeline
>>> from etna.models import NaiveModel
>>> from etna.transforms import AddConstTransform
>>> model = NaiveModel(lag=1)
>>> transforms = [AddConstTransform(in_column="target", value=1)]
>>> pipeline = Pipeline(model, transforms=transforms, horizon=3)
>>> pipeline.set_params(**{"model.lag": 3, "transforms.0.value": 2})
Pipeline(model = NaiveModel(lag = 3, ), transforms = [AddConstTransform(in_column = 'target', value = 2, inplace = True, out_column = None, )], horizon = 3, )

to_dict()[source]#: Collect all information about etna object in dict.