TransformerMixin自定义变压器的“产量”不适用于TruncatedSVD

Question

我的SKLearn管道包含一个自定义处理，该处理“屈服”了返回值sample.process（）。 管道中的下一个操作是TruncatedSVD，该操作由于似乎无法读取生成器对象而失败。

model = Pipeline([
    ('processor', Pipeline([
        ('processor', DocumentProcessor()),
        ('svd', TruncatedSVD())
    ])),
    ('selector', SelectKBest(score_func = chi2)),
    ('clf', None),
])

错误：

Expected 2D array, got scalar array instead: array=<generator object DocumentProcessor.transform at 0x10ffcc5e8>. Reshape your data either using array.reshape(-1, 1) if your data has a single feature or array.reshape(1, -1) if it contains a single sample.

我如何使TruncatedSVD接受生成器对象？