Last active
August 12, 2020 20:21
-
-
Save roncho12/60178f12ea4c3a74764fd645c6f2fe13 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import numpy as np | |
from mlxtend.evaluate import bootstrap_point632_score | |
def bootstrap_estimate_and_ci(estimator, X, y, scoring_func=None, random_seed=0, | |
method='.632', alpha=0.05, n_splits=200): | |
scores = bootstrap_point632_score(estimator, X, y, scoring_func=scoring_func, | |
n_splits=n_splits, random_seed=random_seed, | |
method=method) | |
estimate = np.mean(scores) | |
lower_bound = np.percentile(scores, 100*(alpha/2)) | |
upper_bound = np.percentile(scores, 100*(1-alpha/2)) | |
stderr = np.std(scores) | |
return estimate, lower_bound, upper_bound, stderr | |
#================# | |
# Examples # | |
#================# | |
from sklearn.base import clone | |
from sklearn.datasets import make_classification | |
from sklearn.linear_model import LogisticRegression | |
from sklearn.metrics import recall_score, f1_score, precision_score, roc_auc_score | |
X, y = make_classification(n_redundant=0) | |
estimator = LogisticRegression(solver='lbfgs') | |
# Calculate a bootstrap estimate for accuracy and a 95% confidence interval | |
est, low, up, stderr = bootstrap_estimate_and_ci(estimator, X, y) | |
print(f"estimate: {est:.2f}, confidence interval: [{low:.2f}, {up:.2f}], " | |
f"standard error: {stderr:.2f}") | |
# Calculate a bootstrap estimate for recall and a 95% confidence interval | |
est, low, up, stderr = bootstrap_estimate_and_ci(estimator, X, y, | |
scoring_func=recall_score) | |
# Calculate a bootstrap estimate for precision and a 99% confidence interval | |
est, low, up, stderr = bootstrap_estimate_and_ci(estimator, X, y, | |
scoring_func=precision_score, | |
alpha=0.01) | |
# Calculate a bootstrap estimate for f1-score and a 90% confidence interval | |
est, low, up, stderr = bootstrap_estimate_and_ci(estimator, X, y, | |
scoring_func=f1_score, | |
alpha=0.1) | |
# Calculate a bootstrap estimate for ROC AUC and a 95% confidence interval | |
# It's a hack, but it's short and simple. | |
cloned_estimator = clone(estimator) | |
cloned_estimator.predict = cloned_estimator.decision_function | |
est, low, up, stderr = bootstrap_estimate_and_ci(cloned_estimator, X, y, | |
scoring_func=roc_auc_score) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment