sklearn:随机森林的OOB错误

使用引导程序聚合训练RandomForestClassifier，其中每个新树适合来自训练观察z_i =（x_i，y_i）的引导样本。 袋外（OOB）错误是使用来自各自引导样本中不包含z_i的树的预测计算的每个z_i的平均误差。 这允许RandomForestClassifier在训练时适合和验证[1]。

下面的示例演示了如何在训练期间添加每个新树时测量OOB错误。 得到的图允许从业者接近误差稳定的n_estimators的合适值。

import matplotlib.pyplot as plt

from collections import OrderedDict
from sklearn.datasets import make_classification
from sklearn.ensemble import RandomForestClassifier, ExtraTreesClassifier



RANDOM_STATE = 123

# Generate a binary classification dataset.
X, y = make_classification(n_samples=500, n_features=25,
                           n_clusters_per_class=1, n_informative=15,
                           random_state=RANDOM_STATE)

# NOTE: Setting the `warm_start` construction parameter to `True` disables
# support for paralellised ensembles but is necessary for tracking the OOB
# error trajectory during training.
ensemble_clfs = [
    ("RandomForestClassifier, max_features='sqrt'",
        RandomForestClassifier(warm_start=True, oob_score=True,
                               max_features="sqrt",
                               random_state=RANDOM_STATE)),
    ("RandomForestClassifier, max_features='log2'",
        RandomForestClassifier(warm_start=True, max_features='log2',
                               oob_score=True,
                               random_state=RANDOM_STATE)),
    ("RandomForestClassifier, max_features=None",
        RandomForestClassifier(warm_start=True, max_features=None,
                               oob_score=True,
                               random_state=RANDOM_STATE))
]

# Map a classifier name to a list of (, ) pairs.
error_rate = OrderedDict((label, []) for label, _ in ensemble_clfs)

# Range of `n_estimators` values to explore.
min_estimators = 15
max_estimators = 175

for label, clf in ensemble_clfs:
    for i in range(min_estimators, max_estimators + 1):
        clf.set_params(n_estimators=i)
        clf.fit(X, y)

        # Record the OOB error for each `n_estimators=i` setting.
        oob_error = 1 - clf.oob_score_
        error_rate[label].append((i, oob_error))

# Generate the "OOB error rate" vs. "n_estimators" plot.
for label, clf_err in error_rate.items():
    xs, ys = zip(*clf_err)
    plt.plot(xs, ys, label=label)

plt.xlim(min_estimators, max_estimators)
plt.xlabel("n_estimators")
plt.ylabel("OOB error rate")
plt.legend(loc="upper right")
plt.show()