add: multilabel SVM binary maximum strategy added

Author: cosmic-cortex

examples/multilabel_svm.py

@@ -0,0 +1,35 @@
+import numpy as np
+import matplotlib.pyplot as plt
+
+from modAL.models import ActiveLearner
+from modAL.multilabel import SVM_binary_minimum
+
+from sklearn.multiclass import OneVsRestClassifier
+from sklearn.svm import LinearSVC
+
+n_samples = 500
+X = np.random.normal(size=(n_samples, 2))
+y = np.array([[int(x1 > 0), int(x2 > 0)] for x1, x2 in X])
+
+n_initial = 10
+initial_idx = np.random.choice(range(len(X)), size=n_initial, replace=False)
+X_initial, y_initial = X[initial_idx], y[initial_idx]
+X_pool, y_pool = np.delete(X, initial_idx, axis=0), np.delete(y, initial_idx, axis=0)
+
+with plt.style.context('seaborn-white'):
+    plt.figure(figsize=(10, 10))
+    plt.scatter(X[:, 0], X[:, 1], c='k', s=20)
+    plt.scatter(X[y[:, 0] == 1, 0], X[y[:, 0] == 1, 1],
+                facecolors='none', edgecolors='b', s=50, linewidths=2, label='class 1')
+    plt.scatter(X[y[:, 1] == 1, 0], X[y[:, 1] == 1, 1],
+                facecolors='none', edgecolors='r', s=100, linewidths=2, label='class 2')
+    plt.legend()
+    plt.show()
+
+learner = ActiveLearner(
+    estimator=OneVsRestClassifier(LinearSVC()),
+    query_strategy=SVM_binary_minimum,
+    X_training=X_initial, y_training=y_initial
+)
+
+learner.query(X_pool)

modAL/__init__.py

@@ -0,0 +1,3 @@
+from .models import ActiveLearner, Committee, CommitteeRegressor
+
+__all__ = ['ActiveLearner', 'Committee', 'CommitteeRegressor']

modAL/multilabel.py

@@ -0,0 +1,25 @@
+import numpy as np
+
+from sklearn.base import BaseEstimator
+
+from modAL.utils.data import modALinput
+from typing import Tuple
+
+
+def SVM_binary_minimum(classifier: BaseEstimator, X_pool: modALinput) -> Tuple[np.ndarray, modALinput]:
+    """
+    SVM binary minimum multilabel active learning strategy. For details see the paper
+    Klaus Brinker, On Active Learning in Multi-label Classification
+    (https://link.springer.com/chapter/10.1007%2F3-540-31314-1_24)
+
+    Args:
+        classifier: The multilabel classifier for which the labels are to be queried. Must be an SVM model
+        such as the ones from sklearn.svm.
+        X: The pool of samples to query from.
+
+    Returns:
+        The index of the instance from X chosen to be labelled; the instance from X chosen to be labelled.
+    """
+    min_abs_dist = np.min(np.abs(classifier.estimator.decision_function(X_pool)), axis=1)
+    query_idx = np.argmin(min_abs_dist)
+    return query_idx, X_pool[query_idx]

tests/example_tests/multilabel_svm.py

@@ -0,0 +1,28 @@
+import numpy as np
+
+from modAL.models import ActiveLearner
+from modAL.multilabel import SVM_binary_minimum
+
+from sklearn.multiclass import OneVsRestClassifier
+from sklearn.svm import LinearSVC
+
+n_samples = 500
+X = np.random.normal(size=(n_samples, 2))
+y = np.array([[int(x1 > 0), int(x2 > 0)] for x1, x2 in X])
+
+n_initial = 10
+initial_idx = np.random.choice(range(len(X)), size=n_initial, replace=False)
+X_initial, y_initial = X[initial_idx], y[initial_idx]
+X_pool, y_pool = np.delete(X, initial_idx, axis=0), np.delete(y, initial_idx, axis=0)
+
+learner = ActiveLearner(
+    estimator=OneVsRestClassifier(LinearSVC()),
+    query_strategy=SVM_binary_minimum,
+    X_training=X_initial, y_training=y_initial
+)
+
+n_queries = 10
+for idx in range(n_queries):
+    query_idx, query_inst = learner.query(X_pool)
+    learner.teach(X_pool[query_idx].reshape(1, -1), y_pool[query_idx].reshape(1, -1))
+    X_pool, y_pool = np.delete(X_pool, query_idx, axis=0), np.delete(y_pool, query_idx, axis=0)