在 sklearn 中使用带有自定义类的管道

Question

我在 predict 管道流内部遇到问题，每个管道步骤自定义类。

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())
])

所以，上面的代码在这里工作得很好：

 model.fit(X, _Y)

但是我这里有错误

 prediction = model.predict(XT)

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

调试在此处显示该问题：selector.fit(X, Y) 因为 MyFeatureSelector 的新实例是在 predict() 步骤中创建的，而 Y 当时不存在。

我哪里错了？

Answer 1

下面发布的工作版本：

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)

在 sklearn 中使用带有自定义类的管道

Using Pipeline with custom classes in sklearn

python

pipeline

machine-learning

python-2.7

scikit-learn

在 sklearn 中使用带有自定义 类 的管道

Using Pipeline with custom classes in sklearn

python

pipeline

machine-learning

python-2.7

scikit-learn

在 sklearn 中使用带有自定义类的管道