gridsearch_largearray.py

import numpy as np
import sklearn
from sklearn.linear_model import SGDClassifier
from sklearn import grid_search

print("numpy:", np.__version__)
print("sklearn:", sklearn.__version__)

n_samples = 100000
n_features = 5000

X_train = np.random.randn(n_samples, n_features)
y_train = np.random.randint(0, 2, size=n_samples)

print("input data size: %.3fMB" % (X_train.nbytes / 1e6))

model = SGDClassifier(penalty='elasticnet', n_iter=10, shuffle=True)
param_grid = [{
    'alpha' : 10.0 ** -np.arange(1, 7),
    'l1_ratio': [.05, .5, .9, 1],
}]

if __name__ == "__main__":
    gs = grid_search.GridSearchCV(model, param_grid, n_jobs=8, verbose=100)
    gs.fit(X_train, y_train)
    print(gs.best_params_)