ensemble.py 文件源码

def __init__(self, path, etype, **kwargs):
        super(EnsembleModel, self).__init__(path, etype=etype, **kwargs)
        self.basedir = "models/ensemble/"
        self.goldstd = kwargs.get("goldstd")
        self.data = {}
        self.offsets = []
        self.pipeline = Pipeline(
            [
                #('clf', SGDClassifier(loss='hinge', penalty='l1', alpha=0.0001, n_iter=5, random_state=42)),
                #('clf', SGDClassifier())
                # ('clf', svm.NuSVC(nu=0.01 ))
                ('clf', RandomForestClassifier(class_weight={False:1, True:1}, n_jobs=-1, criterion="entropy", warm_start=True))
                # ('clf', tree.DecisionTreeClassifier(criterion="entropy")),
                # ('clf', MultinomialNB())
                # ('clf', GaussianNB())
                #('clf', svm.SVC(kernel="rbf", degree=2, C=1)),
                #('clf', svm.SVC(kernel="linear", C=2))
                #('clf', DummyClassifier(strategy="constant", constant=True))
            ])