Back to models
Transformer

RandomIntervals

API referenceSource
Multivariate

Random interval feature transformer.

Extracts intervals with random length, position and dimension from series in fit. Transforms each interval subseries using the given transformer(s) and concatenates them into a feature vector in transform.

Currently, the transform is re-fit for every interval in transform. As such, it may not be suitable for some supervised transformers in its current state.

Quickstart

python
from sktime.transformations.random_intervals import RandomIntervals

estimator = RandomIntervals(n_intervals=100, transformers=None, random_state=None, n_jobs=1)

Tags

Capabilities

  • Multivariate
  • Inverse transform: Not supported
  • Missing values: Not supported
  • Removes missing values: Not supported
  • Unequal-length series: Not supported
  • Equalizes series length: Not supported

Properties

Input typescitype:transform-input
Series
Output typescitype:transform-output
Primitives
Label typescitype:transform-labels
None
Fit is emptyfit_is_empty
No
Keeps the time indextransform-returns-same-time-index
No
Requires Xrequires_X
Yes
Requires yrequires_y
No
X and y need the same indexX-y-must-have-same-index
No

Parameters(4)

n_intervalsint, default=100,
The number of intervals of random length, position and dimension to be extracted.
transformerstransformer or list of transformers, default=None,
Transformer(s) used to extract features from each interval. If None, defaults to the SummaryTransformer using [mean, median, min, max, std, 25% quantile, 75% quantile]
n_jobsint, default=1

The number of jobs to run in parallel for both fit and predict. -1 means using all processors.

random_stateint or None, default=None
Seed for random, integer.