python gridsearch_python – 如何获得GridSearchCV(随机森林分类器Scikit)的最佳估计

您必须适应您的数据,才能获得最佳参数组合.

from sklearn.grid_search import GridSearchCV

from sklearn.datasets import make_classification

from sklearn.ensemble import RandomForestClassifier

# Build a classification task using 3 informative features

X, y = make_classification(n_samples=1000,

n_features=10,

n_informative=3,

n_redundant=0,

n_repeated=0,

n_classes=2,

random_state=0,

shuffle=False)

rfc = RandomForestClassifier(n_jobs=-1,max_features= 'sqrt' ,n_estimators=50, oob_score = True)

param_grid = {

'n_estimators': [200, 700],

'max_features': ['auto', 'sqrt', 'log2']

}

CV_rfc = GridSearchCV(estimator=rfc, param_grid=param_grid, cv= 5)

CV_rfc.fit(X, y)

print CV_rfc.best_params_