4. Meta-Quantification

Meta-quantification methods wrap an existing base quantifier and add a higher-level strategy — ensembling, adaptive score correction, or bootstrap confidence estimation — to improve accuracy or reliability.

They do not replace the base quantifier; they augment it. This means you can take any method from the aggregative or distribution-matching families and wrap it with a meta-quantifier to gain extra robustness or uncertainty estimates with minimal code changes.

# Take any quantifier...
from mlquantify.matching import DyS
from sklearn.linear_model import LogisticRegression
base = DyS(LogisticRegression())

# ...and wrap it with a meta-quantifier
from mlquantify.meta import EnsembleQ
q = EnsembleQ(base, size=30, n_jobs=-1)
q.fit(X_train, y_train)
print(q.predict(X_test))

See Quantification Foundations for an overview of when meta-methods provide the most benefit.

• 4.1. Ensembles and Adaptation
  • 4.1.1. EnsembleQ — Ensemble of Quantifiers
  • 4.1.2. QuaDapt — Adaptive Score Simulation
  • 4.1.3. AggregativeBootstrap — Confidence Intervals via Bootstrap
  • 4.1.4. Choosing a Meta-Quantifier
  • 4.1.5. Ensemble for Quantification
• 4.2. Bootstrap in Quantification
• 4.3. QuaDapt: Drift-Resilient Score Adaptation