query_by_committee.py

from copy import deepcopy

import numpy as np
from modAL.models import ActiveLearner, Committee
from sklearn.datasets import load_iris
from sklearn.ensemble import RandomForestClassifier

np.random.seed(0)

# loading the iris dataset
iris = load_iris()

# generate the pool
X_pool = deepcopy(iris['data'])
y_pool = deepcopy(iris['target'])

# initializing Committee members
n_members = 2
learner_list = list()

for member_idx in range(n_members):
    # initial training data
    n_initial = 5
    train_idx = np.random.choice(range(X_pool.shape[0]), size=n_initial, replace=False)
    X_train = X_pool[train_idx]
    y_train = y_pool[train_idx]

    # creating a reduced copy of the data with the known instances removed
    X_pool = np.delete(X_pool, train_idx, axis=0)
    y_pool = np.delete(y_pool, train_idx)

    # initializing learner
    learner = ActiveLearner(
        estimator=RandomForestClassifier(n_estimators=10),
        X_training=X_train, y_training=y_train
    )
    learner_list.append(learner)

# assembling the committee
committee = Committee(learner_list=learner_list)

# query by committee
n_queries = 10
for idx in range(n_queries):
    query_idx, query_instance = committee.query(X_pool)
    committee.teach(
        X=X_pool[query_idx].reshape(1, -1),
        y=y_pool[query_idx].reshape(1, )
    )
    # remove queried instance from pool
    X_pool = np.delete(X_pool, query_idx, axis=0)
    y_pool = np.delete(y_pool, query_idx)