skactiveml.pool.ProbabilisticAL#
- class skactiveml.pool.ProbabilisticAL(prior=1, m_max=1, missing_label=nan, metric=None, metric_dict=None, random_state=None)[source]#
Bases:
SingleAnnotatorPoolQueryStrategy(Multi-class) Probabilistic Active Learning
This class implements multi-class probabilistic active learning (McPAL) [1] strategy.
- Parameters
- prior: float, optional (default=1)
Prior probabilities for the Dirichlet distribution of the samples.
- m_max: int, optional (default=1)
Maximum number of hypothetically acquired labels.
- missing_labelscalar or string or np.nan or None, default=np.nan
Value to represent a missing label.
- metricstr or callable, default=None
The metric must be None or a valid kernel as defined by the function sklearn.metrics.pairwise.pairwise_kernels. The kernel is used to calculate the frequency of labels near the candidates and multiplied with the probabilities returned by clf to get a kernel frequency estimate for each class. If metric is set to None, the predict_freq function of the clf will be used instead. If this is not defined, a TypeError is raised.
- metric_dictdict, default=None
Any further parameters that should be passed directly to the kernel function. If metric_dict is None and metric is ‘rbf’ metric_dict is set to {‘gamma’: ‘mean’}.
- random_state: numeric | np.random.RandomState, optional
Random state for candidate selection.
References
- [1] Daniel Kottke, Georg Krempl, Dominik Lang, Johannes Teschner, and Myra
Spiliopoulou. Multi-Class Probabilistic Active Learning, vol. 285 of Frontiers in Artificial Intelligence and Applications, pages 586-594. IOS Press, 2016
Methods
Get metadata routing of this object.
get_params([deep])Get parameters for this estimator.
query(X, y, clf[, fit_clf, sample_weight, ...])Query the next instance to be labeled.
set_params(**params)Set the parameters of this estimator.
- get_metadata_routing()#
Get metadata routing of this object.
Please check User Guide on how the routing mechanism works.
- Returns
- routingMetadataRequest
A
MetadataRequestencapsulating routing information.
- get_params(deep=True)#
Get parameters for this estimator.
- Parameters
- deepbool, default=True
If True, will return the parameters for this estimator and contained subobjects that are estimators.
- Returns
- paramsdict
Parameter names mapped to their values.
- query(X, y, clf, fit_clf=True, sample_weight=None, utility_weight=None, candidates=None, batch_size=1, return_utilities=False)[source]#
Query the next instance to be labeled.
- Parameters
- Xarray-like of shape (n_samples, n_features)
Training data set, usually complete, i.e. including the labeled and unlabeled samples.
- yarray-like of shape (n_samples)
Labels of the training data set (possibly including unlabeled ones indicated by self.MISSING_LABEL.
- clfskactiveml.base.ClassFrequencyEstimator
Model implementing the methods fit and predict_freq.
- fit_clfbool, default=True
Defines whether the classifier should be fitted on X, y, and sample_weight.
- sample_weight: array-like of shape (n_samples), optional (default=None)
Weights of training samples in X.
- utility_weight: array-like, optional (default=None)
Weight for each candidate (multiplied with utilities). Usually, this is to be the density of a candidate in ProbabilisticAL. The length of utility_weight is usually n_samples, except for the case when candidates contains samples (ndim >= 2). Then the length is n_candidates.
- candidatesNone or array-like of shape (n_candidates), dtype=int or
array-like of shape (n_candidates, n_features), optional (default=None) If candidates is None, the unlabeled samples from (X,y) are considered as candidates. If candidates is of shape (n_candidates) and of type int, candidates is considered as the indices of the samples in (X,y). If candidates is of shape (n_candidates, n_features), the candidates are directly given in candidates (not necessarily contained in X). This is not supported by all query strategies.
- batch_sizeint, optional (default=1)
The number of samples to be selected in one AL cycle.
- return_utilitiesbool, optional (default=False)
If true, also return the utilities based on the query strategy.
- Returns
- query_indicesnumpy.ndarray, shape (batch_size)
The query_indices indicate for which candidate sample a label is to queried, e.g., query_indices[0] indicates the first selected sample.
- utilitiesnumpy.ndarray, shape (batch_size, n_samples)
The utilities of all candidate samples after each selected sample of the batch, e.g., utilities[0] indicates the utilities used for selecting the first sample (with index query_indices[0]) of the batch.
- set_params(**params)#
Set the parameters of this estimator.
The method works on simple estimators as well as on nested objects (such as
Pipeline). The latter have parameters of the form<component>__<parameter>so that it’s possible to update each component of a nested object.- Parameters
- **paramsdict
Estimator parameters.
- Returns
- selfestimator instance
Estimator instance.
