Skip to content

SRPClassifier

Streaming Random Patches ensemble classifier.

The Streaming Random Patches (SRP) 1 is an ensemble method that simulates bagging or random subspaces. The default algorithm uses both bagging and random subspaces, namely Random Patches. The default base estimator is a Hoeffding Tree, but other base estimators can be used (differently from random forest variations).

Parameters

  • model

    Type → base.Estimator | None

    Default → None

    The base estimator.

  • n_models

    Type → int

    Default → 10

    Number of members in the ensemble.

  • subspace_size

    Type → int | float | str

    Default → 0.6

    Number of features per subset for each classifier where M is the total number of features.
    A negative value means M - subspace_size.
    Only applies when using random subspaces or random patches.
    * If int indicates the number of features to use. Valid range [2, M].
    * If float indicates the percentage of features to use, Valid range (0., 1.].
    * 'sqrt' - sqrt(M)+1
    * 'rmsqrt' - Residual from M-(sqrt(M)+1)

  • training_method

    Type → str

    Default → patches

    The training method to use.
    * 'subspaces' - Random subspaces.
    * 'resampling' - Resampling.
    * 'patches' - Random patches.

  • lam

    Type → int

    Default → 6

    Lambda value for resampling.

  • drift_detector

    Type → base.DriftDetector | None

    Default → None

    Drift detector.

  • warning_detector

    Type → base.DriftDetector | None

    Default → None

    Warning detector.

  • disable_detector

    Type → str

    Default → off

    Option to disable drift detectors:
    * If 'off', detectors are enabled.
    * If 'drift', disables concept drift detection and the background learner.
    * If 'warning', disables the background learner and ensemble members are reset if drift is detected.

  • disable_weighted_vote

    Type → bool

    Default → False

    If True, disables weighted voting.

  • seed

    Type → int | None

    Default → None

    Random number generator seed for reproducibility.

  • metric

    Type → ClassificationMetric | None

    Default → None

    The metric to track members performance within the ensemble. This implementation assumes that larger values are better when using weighted votes.

Attributes

  • models

Examples

from river import ensemble
from river import evaluate
from river import metrics
from river.datasets import synth
from river import tree

dataset = synth.ConceptDriftStream(
    seed=42,
    position=500,
    width=50
).take(1000)

base_model = tree.HoeffdingTreeClassifier(
    grace_period=50, delta=0.01,
    nominal_attributes=['age', 'car', 'zipcode']
)
model = ensemble.SRPClassifier(
    model=base_model, n_models=3, seed=42,
)

metric = metrics.Accuracy()

evaluate.progressive_val_score(dataset, model, metric)

Accuracy: 71.97%

Methods

learn_one
predict_one

Predict the label of a set of features x.

Parameters

  • x — 'dict'
  • kwargs

Returns

base.typing.ClfTarget | None: The predicted label.

predict_proba_one

Predict the probability of each label for a dictionary of features x.

Parameters

  • x
  • kwargs

Returns

A dictionary that associates a probability which each label.

reset

Notes

This implementation uses n_models=10 as default given the impact on processing time. The optimal number of models depends on the data and resources available.

  1. Heitor Murilo Gomes, Jesse Read, Albert Bifet. Streaming Random Patches for Evolving Data Stream Classification. IEEE International Conference on Data Mining (ICDM), 2019. ↩