sktime.transformations.panel.pca

class sktime.transformations.panel.pca.PCATransformer(n_components=None, **kwargs)[source]

Bases: sktime.transformations.base._PanelToPanelTransformer

Transformer that applies Principle Components Analysis to a univariate time series.

Provides a simple wrapper around sklearn.decomposition.PCA.

Parameters
  • n_components (int, float, str or None (default None)) – Number of principle components to retain. By default, all components are retained. See sklearn.decomposition.PCA documentation for a detailed description of all options.

  • **kwargs – Additional parameters passed on to sklearn.decomposition.PCA. See sklearn.decomposition.PCA documentation for a detailed description of all options.

fit(X, y=None)[source]

Fit transformer, finding all principal components.

Parameters

X (nested pandas DataFrame of shape [n_samples, 1]) – Nested dataframe with univariate time-series in cells.

Returns

self

Return type

an instance of self.

transform(X, y=None)[source]

Transform X, transforms univariate time-series using sklearn’s PCA class

Parameters

X (nested pandas DataFrame of shape [n_samples, 1]) – Nested dataframe with univariate time-series in cells.

Returns

Xt – Transformed pandas DataFrame with the same number of rows and the (potentially reduced) PCA transformed column. Time indices of the original column are replaced with 0:( n_components - 1).

Return type

pandas DataFrame