python - sklearn中VotingClassifier的继承

Question

我正在尝试修改 sklearn VotingClassifier 以便在 RandomSearchCV 中使用。这个想法是，对于更多的分类器，可能的权重组合会爆炸，并且更好地由单个权重选择而不是许多不同的元组来表示。此外，由于权重变化中有信息，因此可以更改为更智能的超参数调整方法。

那么我如何正确地子类化 VotingClassifier 类，因为下面的代码导致 None 被传递给权重或使用默认值并且搜索提示权重不受参数控制(哪个他们是)。

class VotingClassifier2(VotingClassifier):
    def __init__(self, estimators, w1, w2, voting='soft', weights=None, n_jobs=None, flatten_transform=True):
        super().__init__(estimators, voting, weights, n_jobs, flatten_transform)
        if w1:
            tot=w1+w2 
        else:
            breakpoint()
        self.weights = (w1/tot, w2/tot)


pipe = Pipeline(
    [
        [
            "vc",
            VotingClassifier2(
                estimators=[
                    ("xgb", XGBClassifier()),
                    ('lr', LogisticRegression(fit_intercept=True, max_iter=300, solver='lbfgs'))

                ],
                voting="soft",
                weights=None,
                w1=1,
                w2=0

            ),
        ]
    ]
)


opt = RandomizedSearchCV(
    pipe,
    { 
        "vc__w1": uniform(0.1, 1),   
        "vc__w2": uniform(0.1, 1)
    },
    n_iter=5,
    cv=5,
    n_jobs=25,
    return_train_score=False,
    error_score='raise' 
)

最初调用时 w1 和 w2 是 None 但权重已经根据输入的需要计算出来。然后搜索运行但无法设置它们。

RuntimeError: Cannot clone object VotingClassifier2(estimators=[('xgb', XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
       colsample_bynode=1, colsample_bytree=1, gamma=0, learning_rate=0.1,
       max_delta_step=0, max_depth=3, min_child_weight=1, missing=None,
       n_estimators=100, n_jobs=1, nthread=None,
       objectiv...alty='l2', random_state=None, solver='warn',
          tol=0.0001, verbose=0, warm_start=False))]))],
         flatten_transform=True, n_jobs=None, voting='soft', w1=None,
         w2=None, weights=(1.0, 0.0)), as the constructor either does not set or modifies parameter weights

Answer 1

RandomizedSearchCV 通过属性更改估计器的参数，因此如果您想修改 weights 属性以及 w1 和 w2 你可以用 property 装饰器包装它们。另一种选择是直接包装 weights 例如:

import scipy as sp
from dask_ml.xgboost import XGBClassifier
from sklearn.pipeline import Pipeline
from sklearn.linear_model import LogisticRegression
from sklearn.ensemble import VotingClassifier
from sklearn.model_selection import RandomizedSearchCV


class VotingClassifier2(VotingClassifier):
    @property
    def weights(self):
        return self._weights

    @weights.setter
    def weights(self, value): 
        if isinstance(value, float):
            value = [value, 1-value]
        self._weights = value


# setup a client based on your environment 
client = ...

pipe = Pipeline(
    [
        [
            "vc",
            VotingClassifier2(
                estimators=[
                    ("xgb", XGBClassifier(sheduler=client)),
                    ('lr', LogisticRegression(fit_intercept=True, max_iter=300, solver='lbfgs'))

                ],
                voting="soft",
                weights=[.5, .5],
            ),
        ]
    ]
)


opt = RandomizedSearchCV(
    pipe,
    { 
        "vc__weights": sp.stats.uniform(0.1, 1),   
    },
    n_iter=5,
    cv=5,
    n_jobs=25,
    return_train_score=False,
    error_score='raise' 
)

编辑:如果你真的需要使用 w1 和 w2 你应该将它们绑定(bind)到 weights 并从 中删除 weights __init__ 方法参数:

class VotingClassifier2(VotingClassifier):
    def __init__(self, estimators, w1, w2, voting='soft', n_jobs=None, flatten_transform=True):
        super().__init__(estimators, voting, [w1, w2], n_jobs, flatten_transform)
        self.w1 = w1
        self.w2 = w2

    @property
    def w1(self):
        return self.weights[0]

    @w1.setter
    def w1(self, value): 
        if value is not None:
            self.weights[0] = value

    @property
    def w2(self):
        return self.weights[1]

    @w2.setter
    def w2(self, value): 
        if value is not None:
            self.weights[1] = value