from sklearn.feature_extraction import DictVectorizer
from sklearn.pipeline import FeatureUnion
from sklearn.pipeline import make_pipeline
from sklearn.base import TransformerMixin

class WordFeatureExtractor(TransformerMixin):
    def transform(self, X, **transform_params):
        return [dict(self._extract_features(data.items())) for data in X]

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

    def _extract_features(self, key_value_pair):
        for key, value in key_value_pair:
            if isinstance(value, basestring):
                for word in value.split():
                    yield '%s.word=%s' % (key, word), True

feature_extractor = FeatureUnion([
    ('dict', DictVectorizer()),
    ('word', make_pipeline(
        WordFeatureExtractor(),
        DictVectorizer())
    )
])

feature_extractor.fit_transform([{'number': 123, 'text': 'foo bar'}, {'number': 321}])
feature_extractor.get_feature_names()

    @if_delegate_has_method(delegate='_final_estimator')
    def get_feature_names(self):
        return self.steps[-1][-1].get_feature_names()