Question

我试图用自己的类编写复杂的管道，但出现此错误：

TypeError: fit_transform() takes 2 positional arguments but 3 were given

我尝试通过使用自定义LabelBinarizer来解决类似问题的解决方案，但该错误并未解决。

class NewLabelBinarizer(LabelBinarizer):
    def fit(self, X, y=None):
        return super(NewLabelBinarizer, self).fit(X)
    def transform(self, X, y=None):
        return super(NewLabelBinarizer, self).transform(X)
    def fit_transform(self, X, y=None):
        return super(NewLabelBinarizer, self).fit(X).transform(X)

class LabelPreprocessing(NewLabelBinarizer, TransformerMixin):
    def __init__(self, *args, **kwargs):
        pass

    def fit(self, y,X=None):
        super(LabelPreprocessing, self).fit(y)
        return self

    def transform(self, y, X=None):
        y = y.str.findall(r'([a-zA-Z]{3,})') 
        y = y.replace(regex=r'(film)', value=' ')

        return y.values

class PlotPreprocessing(BaseEstimator, TransformerMixin):
    def __init__(self, *args, **kwargs):
        self.REPLACE_BY_SPACE_RE = re.compile('[/(){}\[\]\|@,;]')
        self.BAD_SYMBOLS_RE = re.compile('[^0-9a-z #+_]')

    def fit(self, X, y=None):
        return self

    def transform(self, X, y=None):

        X = X.str.lower()
        X = X.map(lambda x: re.sub(self.REPLACE_BY_SPACE_RE," ",x))
        X = X.map(lambda x: re.sub(r'\s+'," ",x))

        return X.values

pipeline = Pipeline([
    (
'text_preparation', FeatureUnion([
    ('label', Pipeline([
        ('labelPreprocessing', LabelPreprocessing()),
        ('mlb', MultiLabelBinarizer())
    ])), 
    ('plot', PlotPreprocessing()
    )
  ])), 
  ('tfidf_vectorizer', TfidfVectorizer(ngram_range=(1,2),max_df=0.9,min_df=5,token_pattern=r'(\S+)')
  ),
  ('model', LinearRegression())

])

train_X, train_y, test_X, test_y = train_test_split(plot, label)

pipeline.fit(train_X, train_y)
y_pred = pipeline.predict( test_X )

然后我得到

TypeError                                 Traceback (most recent call last)

<ipython-input-27-a8a60de025fd> in <module>()
     17 train_X, train_y, test_X, test_y = train_test_split(plot, label)
     18 
---> 19 pipeline.fit(train_X, train_y)
     20 y_pred = pipeline.predict( test_X )

14 frames

/usr/local/lib/python3.6/dist-packages/sklearn/pipeline.py in fit_transform(self, X, y, **fit_params)
    391                 return Xt
    392             if hasattr(last_step, 'fit_transform'):
--> 393                 return last_step.fit_transform(Xt, y, **fit_params)
    394             else:
    395                 return last_step.fit(Xt, y, **fit_params).transform(Xt)

TypeError: fit_transform() takes 2 positional arguments but 3 were given

我还尝试添加**fit_params以适合/预测参数。

Answer 1

我认为问题出在MultiLabelBinarizer签名上。尝试将其替换为：

class MLBinarizer(MultiLabelBinarizer):
    def fit_transform(self, X, y=None):
        return super(MultiLabelBinarizer, self).fit_transform(X)

请注意，方法fit，fit_transform采用X作为第一个参数。因此，我建议像这样重写您的LabelPreprocessing：

class LabelPreprocessing(NewLabelBinarizer, TransformerMixin):
    def fit(self, X, y=None):
        super(LabelPreprocessing, self).fit(X)
        return self

    def transform(self, y, X=None):
        y = y.str.findall(r'([a-zA-Z]{3,})') 
        y = y.replace(regex=r'(film)', value=' ')

        return y.values

如何解决“ TypeError：fit_transform（）接受2个位置参数，但给出了3个位置参数”

1 个答案: