demonstration of sklearn GridSearchCV spawning multiple threads on linux

grid-cv

# related SF question: https://stackoverflow.com/questions/46351157/why-gridsearchcv-in-scikit-learn-spawn-so-many-threads

import numpy as np

from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import StratifiedKFold
from sklearn.model_selection import GridSearchCV


Cs = 10 ** np.arange(-2, 2, 0.1)
skf = StratifiedKFold(n_splits=10, shuffle=True, random_state=0)
clf = LogisticRegression()
gs = GridSearchCV(
    clf,
    param_grid={'C': Cs, 'penalty': ['l1'],
                'tol': [1e-10], 'solver': ['liblinear']},
    cv=skf,
    scoring='neg_log_loss',
    n_jobs=5,
    verbose=1,
    refit=True)

N = 500000
Xs = np.concatenate([
    np.random.random(N),
    3 + np.random.random(N)
]).reshape(-1, 1)

ys = np.concatenate([
    np.zeros(N),
    np.ones(N)
])

gs.fit(Xs, ys)