ensemble_regression.py

import numpy as np
from modAL.disagreement import max_std_sampling
from modAL.models import ActiveLearner, CommitteeRegressor
from sklearn.gaussian_process import GaussianProcessRegressor
from sklearn.gaussian_process.kernels import RBF, WhiteKernel

np.random.seed(0)

# generating the data
X = np.concatenate((np.random.rand(100)-1, np.random.rand(100)))
y = np.abs(X) + np.random.normal(scale=0.2, size=X.shape)

# initializing the regressors
n_initial = 10
kernel = RBF(length_scale=1.0, length_scale_bounds=(1e-2, 1e3)) \
         + WhiteKernel(noise_level=1, noise_level_bounds=(1e-10, 1e+1))

initial_idx = list()
initial_idx.append(np.random.choice(range(100), size=n_initial, replace=False))
initial_idx.append(np.random.choice(range(100, 200), size=n_initial, replace=False))
learner_list = [ActiveLearner(
                        estimator=GaussianProcessRegressor(kernel),
                        X_training=X[idx].reshape(-1, 1), y_training=y[idx].reshape(-1, 1)
                )
                for idx in initial_idx]

# initializing the Committee
committee = CommitteeRegressor(
    learner_list=learner_list,
    query_strategy=max_std_sampling
)

# active regression
n_queries = 10
for idx in range(n_queries):
    query_idx, query_instance = committee.query(X.reshape(-1, 1))
    committee.teach(X[query_idx].reshape(-1, 1), y[query_idx].reshape(-1, 1))