ensemble_ner.py 文件源码

def __init__(self, path, goldset, base_model, features=None, types=None):
        self.ensemble_pipeline = Pipeline([
            ('clf', ensemble.RandomForestClassifier(criterion="gini", n_estimators=1000))
            ])
        self.base_model = base_model
        self.path = path
        self.predicted = []
        self.res = None
        self.ids, self.data, self.labels = [], [], []
        self.goldset = goldset
        if types: # features is a list of classifier names
            self.types = types
        else:
            self.types = []
        self.feature_names = []
        for t in self.types:
            self.feature_names.append(t)
            self.feature_names.append(t + "_ssm")
        for f in features:
            self.feature_names.append(f)