Source code for skactiveml.utils._aggregation

import numpy as np
from sklearn.utils import check_array, check_consistent_length

from ._label import is_labeled, is_unlabeled
from ._label_encoder import ExtLabelEncoder
from ._label_dtype import _as_label_array
from ._selection import rand_argmax


[docs] def compute_vote_vectors(y, w=None, classes=None, missing_label=np.nan): """Counts number of votes per class label for each sample. Parameters ---------- y : array-like, shape (n_samples) or (n_samples, n_annotators) Class labels, which may contain also missing labels. w : array-like, shape (n_samples) or (n_samples, n_annotators) or None,\ default=None Class label weights. One-dimensional weights apply to every annotation of the corresponding sample. Two-dimensional weights specify one weight per annotation. If None, every annotation has unit weight. classes : array-like of shape (n_classes,), default=None Holds the label for each class. missing_label : scalar or string or np.nan orNone, default=np.nan Value to represent a missing label. Returns ------- v : numpy.ndarray of shape (n_samples, n_classes) `V[i,j]` counts number of votes per class `j` for sample `i`. """ # check input parameters le = ExtLabelEncoder(classes=classes, missing_label=missing_label) y = le.fit_transform(y) n_classes = len(le.classes_) y = y if y.ndim == 2 else y.reshape((-1, 1)) is_unlabeled_y = is_unlabeled(y, missing_label=-1) y[is_unlabeled_y] = 0 y = y.astype(int) w = _check_vote_weights(y, w) # count class labels per class and weight by confidence scores w[np.logical_or(np.isnan(w), is_unlabeled_y)] = 0 y_off = y + np.arange(y.shape[0])[:, None] * n_classes v = np.bincount( y_off.ravel(), minlength=y.shape[0] * n_classes, weights=w.ravel() ) return v.reshape(-1, n_classes)
[docs] def majority_vote( y, w=None, classes=None, missing_label=np.nan, random_state=None ): """Assigns a label to each sample based on weighted voting. Samples with no labels are assigned with `missing_label`. A matrix without any observed label therefore aggregates to `missing_label` for every sample. That result needs no class vocabulary, so it is returned for `classes=None` as well. Parameters ---------- y : array-like, shape (n_samples,) or (n_samples, n_annotators) Class labels, which may contain also missing labels. w : array-like, shape (n_samples) or (n_samples, n_annotators) or None,\ default=None Class label weights. One-dimensional weights apply to every annotation of the corresponding sample. Two-dimensional weights specify one weight per annotation. If None, every annotation has unit weight. classes : array-like of shape (n_classes,), default=None Holds the label for each class. missing_label : scalar or string or np.nan or None, default=np.nan Value to represent a missing label. random_state : int or RandomState instance or None, default=None Determines random number generation for shuffling the data. Pass an int for reproducible results across multiple function calls. Returns ------- y_aggregated : numpy.ndarray of shape (n_samples,) Assigned labels for each sample. """ # check input parameters y = check_array( _as_label_array(y), ensure_2d=False, dtype=None, ensure_all_finite=False, ) y = y if y.ndim == 2 else y.reshape((-1, 1)) n_samples = y.shape[0] w = _check_vote_weights(y, w) is_labeled_y = np.any(is_labeled(y, missing_label), axis=1) y_labeled = y[is_labeled_y] le = ExtLabelEncoder(classes=classes, missing_label=missing_label) if not np.any(is_labeled_y): if classes is not None: le.fit(y) return y[:, 0].copy() le.fit(y) y_aggregated = np.full((n_samples,), missing_label, dtype=le._dtype) y_labeled_transformed = le.transform(y_labeled) vote_matrix = compute_vote_vectors( y_labeled_transformed, w=w[is_labeled_y], missing_label=-1, classes=np.arange(len(le.classes_)), ) vote_vector = rand_argmax(vote_matrix, random_state, axis=1) y_labeled_inverse_transformed = le.inverse_transform(vote_vector) y_aggregated[is_labeled_y] = y_labeled_inverse_transformed return y_aggregated
def _check_vote_weights(y, w): """Validate weights against a two-dimensional annotation matrix.""" if w is None: return np.ones(y.shape) w = check_array( w, ensure_2d=False, ensure_all_finite=False, dtype=float, copy=True ) check_consistent_length(y, w) if w.ndim == 1: w = np.repeat(w[:, np.newaxis], y.shape[1], axis=1) elif w.shape != y.shape: raise ValueError( "`w` must have shape `(n_samples,)` or the same shape as `y`." ) return w