etna.clustering.DTWClustering

class DTWClustering

Bases: HierarchicalClustering

Hierarchical clustering with DTW distance.

Examples

>>> from etna.clustering import DTWClustering
>>> from etna.datasets import TSDataset
>>> from etna.datasets import generate_ar_df
>>> ts = generate_ar_df(periods = 40, start_time = "2000-01-01", n_segments = 10)
>>> ts = TSDataset(TSDataset.to_dataset(ts), freq="D")
>>> model = DTWClustering()
>>> model.build_distance_matrix(ts)
>>> model.build_clustering_algo(n_clusters=3, linkage="average")
>>> segment2cluster = model.fit_predict()
>>> segment2cluster
{'segment_0': 2,
 'segment_1': 1,
 'segment_2': 0,
 'segment_3': 1,
 'segment_4': 1,
 'segment_5': 0,
 'segment_6': 0,
 'segment_7': 1,
 'segment_8': 2,
 'segment_9': 2}

Create instance of DTWClustering.

Methods

build_clustering_algo([n_clusters, linkage])	Build clustering algo (see sklearn.cluster.AgglomerativeClustering) with given params.
build_distance_matrix(ts)	Build distance matrix with DTW distance.
fit_predict()	Fit clustering algorithm and predict clusters according to distance matrix build.
get_centroids(**averaging_kwargs)	Get centroids of clusters.
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.

build_clustering_algo(n_clusters: int = 30, linkage: str | ClusteringLinkageMode = ClusteringLinkageMode.average, **clustering_algo_params)

Build clustering algo (see sklearn.cluster.AgglomerativeClustering) with given params.

Parameters:

• n_clusters (int) – number of clusters to build

• linkage (str | ClusteringLinkageMode) – rule for distance computation for new clusters, allowed “ward”, “single”, “average”, “maximum”, “complete”

Notes

Note that it will reset previous results of clustering in case of reinit algo.

build_distance_matrix(ts: TSDataset)

Build distance matrix with DTW distance.

Parameters:

ts (TSDataset) – TSDataset with series to build distance matrix

fit_predict() → Dict[str, int]

Fit clustering algorithm and predict clusters according to distance matrix build.

Returns:

dict in format {segment: cluster}

Return type:

Dict[str, int]

get_centroids(**averaging_kwargs) → DataFrame

Get centroids of clusters.

Returns:

dataframe with centroids

Return type:

pd.DataFrame

set_params(**params: dict) → Self

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()

Collect all information about etna object in dict.