def test_parameter_estimation(self):
X = np.random.uniform(0, 4, 1000)
y = X + np.random.normal(0, 1, 1000)
m = BayesianBootstrapBagging(LinearRegression(),
10000,
1000,
low_mem=False)
m.fit(X.reshape(-1, 1), y)
coef_samples = [b.coef_ for b in m.base_models_]
intercept_samples = [b.intercept_ for b in m.base_models_]
self.assertAlmostEqual(np.mean(coef_samples), 1, delta=0.3)
l, r = central_credible_interval(coef_samples, alpha=0.05)
self.assertLess(l, 1)
self.assertGreater(r, 1)
l, r = highest_density_interval(coef_samples, alpha=0.05)
self.assertLess(l, 1)
self.assertGreater(r, 1)
self.assertAlmostEqual(np.mean(intercept_samples), 0, delta=0.3)
l, r = central_credible_interval(intercept_samples, alpha=0.05)
self.assertLess(l, 0)
self.assertGreater(r, 0)
self.assertAlmostEqual(np.mean(intercept_samples), 0, delta=0.3)
l, r = highest_density_interval(intercept_samples, alpha=0.05)
self.assertLess(l, 0)
self.assertGreater(r, 0)
def plot_regression_wrapper_bootstrap():
X = np.array([[0], [1], [2], [3]])
y = np.array([0, 1, 2, 3]) + np.random.normal(0, 1, 4)
m = BayesianBootstrapBagging(LinearRegression(), 10000, 1000)
m.fit(X, y)
y_predicted = m.predict(X)
y_predicted_interval = m.predict_central_interval(X, 0.05)
plt.scatter(X.reshape(-1, 1), y)
plt.plot(X.reshape(-1, 1), y_predicted)
plt.plot(X.reshape(-1, 1), y_predicted_interval[:,0])
plt.plot(X.reshape(-1, 1), y_predicted_interval[:,1])
plt.show()
def plot_regression_slope_distribution_readme():
X = np.random.normal(0, 1, 5).reshape(-1, 1)
y = X.reshape(1, -1).reshape(5) + np.random.normal(0, 1, 5)
m = BayesianBootstrapBagging(LinearRegression(), 10000, 1000)
m.fit(X, y)
X_plot = np.linspace(min(X), max(X))
y_predicted = m.predict(X_plot.reshape(-1, 1))
y_predicted_interval = m.predict_highest_density_interval(X_plot.reshape(-1, 1), 0.05)
plt.scatter(X.reshape(1, -1), y)
plt.plot(X_plot, y_predicted, label='Mean')
plt.plot(X_plot, y_predicted_interval[:,0], label='95% HDI Lower bound')
plt.plot(X_plot, y_predicted_interval[:,1], label='95% HDI Upper bound')
plt.legend()
plt.savefig('readme_regression.png', bbox_inches='tight')
from bayesian_bootstrap.bootstrap import mean, highest_density_interval, BayesianBootstrapBagging
posterior_samples = mean(X, 10000)
l, r = highest_density_interval(posterior_samples)
plt.title('Bayesian Bootstrap of mean')
sns.distplot(posterior_samples, label='Bayesian Bootstrap Samples')
plt.plot([l, r], [0, 0], linewidth=5.0, marker='o', label='95% HDI')
# -
from bayesian_bootstrap.bootstrap import bayesian_bootstrap
posterior_samples = bayesian_bootstrap(X, np.mean, 10000, 100)
X = np.random.normal(0, 1, 5).reshape(-1, 1)
y = X.reshape(1, -1).reshape(5) + np.random.normal(0, 1, 5)
m = BayesianBootstrapBagging(LinearRegression(), 10000, 1000)
m.fit(X, y)
import utils
p_pre, p_post = utils.load_users_covid('politicians')
rfriends_pre, rfriends_post = utils.load_users_covid('random-friends')
rfollowers_pre, rfollowers_post = utils.load_users_covid('random-followers')
# j_pre, j_post = utils.load_users_covid('journalists-new')
rfriends_big_pre, rfriends_big_post = utils.load_users_covid('random-friends-big')
rfollowers_big_pre, rfollowers_big_post = utils.load_users_covid('random-followers-big')
rfollowers_big_post.to_pickle('random-followers-big_post.pkl')
rfollowers_big_pre.to_pickle('random-followers-big_pre.pkl')