在sklearn中对自定义类使用管道

Question

我在predict内部的管道流中遇到了一个问题，每个管道步骤都有自定义类。在

class MyFeatureSelector():
    def __init__(self, features=5, method='pca'):
        self.features = features
        self.method = method

    def fit(self, X, Y):
        return self

    def transform(self, X, Y=None):
        try:
            if self.features < X.shape[1]:
                if self.method == 'pca':
                    selector = PCA(n_components=self.features)
                elif self.method == 'rfe':
                    selector = RFE(estimator=LinearRegression(n_jobs=-1),
                                   n_features_to_select=self.features,
                                   step=1)
                selector.fit(X, Y)
                return selector.transform(X)
        except Exception as err:
            print('MyFeatureSelector.transform(): {}'.format(err))
        return X

    def fit_transform(self, X, Y=None):
        self.fit(X, Y)
        return self.transform(X, Y)


model = Pipeline([
    ("DATA_CLEANER", MyDataCleaner(demo='', mode='strict')),
    ("DATA_ENCODING", MyEncoder(encoder_name='code')),
    ("FEATURE_SELECTION", MyFeatureSelector(features=15, method='rfe')),
    ("HUBER_MODELLING", HuberRegressor())
])

因此，上面的代码在这里非常有效：

^{pr2}$

但我这里有个错误

 prediction = model.predict(XT)

ERROR: shapes (672,107) and (15,) not aligned: 107 (dim 1) != 15 (dim 0)

调试显示这里的问题：selector.fit(X, Y)，因为MyFeatureSelector的新实例是在predict()步骤中创建的，Y此时不存在。在

我哪里错了？在

Answer 1

工作版本如下：

class MyFeatureSelector():
    def __init__(self, features=5, method='pca'):
        self.features = features
        self.method = method
        self.selector = None
        self.init_selector()


    def init_selector():
        if self.method == 'pca':
            self.selector = PCA(n_components=self.features)
        elif self.method == 'rfe':
        self.selector = RFE(estimator=LinearRegression(n_jobs=-1),
                               n_features_to_select=self.features,
                               step=1)

    def fit(self, X, Y):
       return self

    def transform(self, X, Y=None):
        try:
            if self.features < X.shape[1]:
                if Y is not None:
                    self.selector.fit(X, Y)
                return selector.transform(X)
        except Exception as err:
            print('MyFeatureSelector.transform(): {}'.format(err))
       return X

def fit_transform(self, X, Y=None):
    self.fit(X, Y)
    return self.transform(X, Y)