classification.py 文件源码

def build_grid_search(X, y):
    parameters = {
        "estimator__criterion": ['gini', 'entropy'],
        "estimator__max_depth": [10, 15, 20, 25, None],
        "estimator__max_features": ['auto', 'sqrt', 'log2', None]
    }
    ovr = OneVsRestClassifier(RandomForestClassifier(n_estimators=1000,
                                    oob_score=True, n_jobs=-1, verbose=1))
    model_tunning = GridSearchCV(ovr, param_grid=parameters, verbose=1,
                                 n_jobs=-1, cv=10,
                                 scoring=make_scorer(f1_score))
    model_tunning.fit(X, y)
    test_score = model_tunning.best_score_
    print 'The best test score: ', test_score
    y_score = model_tunning.predict_proba(X_test)
    multiclass_roc(y_score, 'grid_search_02')
    return model_tunning