Clustering Step within Scikit Pipeline

Question

I am trying to do clustering as a step in a Pipeline so that I can use the cluster as an additional feature. I have used this post as a guide but I am getting an error on the call to fit_transform() within the pipeline. My original transformer is working well so the problem comes when trying to cluster on its output in transformer_cluster and join them together with feature_union to get the original features plus the binarized cluster label. What is going wrong here?

import pandas as pd
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.compose import ColumnTransformer
from sklearn.pipeline import Pipeline
from sklearn.base import TransformerMixin
from sklearn.cluster import KMeans
from sklearn.preprocessing import LabelBinarizer
from sklearn.pipeline import FeatureUnion

df = pd.DataFrame({'text': [
    'Here is an example of some text data',
    'here is another sentence of text',
    'yet another random string'],
    'label': [1, 1, 0]
})
X, y = df['text'], df['label']

class KMeans_foo(KMeans):
    def fit_transform(self, X, y = None):
        return self.fit_predict(X)

class ModelTransformer(TransformerMixin):

    def __init__(self, model):
        self.model = model

    def fit(self, *args, **kwargs):
        self.model.fit(*args, **kwargs)
        return self

    def transform(self, X, **transform_params):
        return pd.DataFrame(self.model.predict(X))

tf_idf_pipe = Pipeline(steps = [
    ('tf-idf', TfidfVectorizer(min_df = 0.10, stop_words = 'english'))
])

transformer = ColumnTransformer([
    ('text_pipe', tf_idf_pipe, 'text')],
    sparse_threshold = 0,
    remainder = 'drop'
)

transformer_cluster = Pipeline([
    ('orig', transformer),
    ('cluster', ModelTransformer(KMeans_foo(3))),
    ('binarize', LabelBinarizer())
])

feature_union = FeatureUnion([
    ('orig', transformer),
    ('cluster', transformer_cluster)
])

print('\nTransformed Training Data:')
print(pd.DataFrame(feature_union.fit_transform(pd.DataFrame(X))))
# print(pd.DataFrame(transformer.fit_transform(pd.DataFrame(X))))

# Transform test data
X_test = pd.DataFrame({'text': [
    'Here we have some test data',
    'and another one with text'
]})

print('\nTransformed Test Data:')
print(pd.DataFrame(feature_union.transform(X_test)))
# print(pd.DataFrame(transformer.transform(X_test)))

 Traceback (most recent call last):
  File "/Home/test.py", line 59, in <module>
    print(pd.DataFrame(feature_union.fit_transform(pd.DataFrame(X))))
  File "/Home/venv/lib/python3.9/site-packages/sklearn/pipeline.py", line 1154, in fit_transform
    results = self._parallel_func(X, y, fit_params, _fit_transform_one)
  File "/Home/venv/lib/python3.9/site-packages/sklearn/pipeline.py", line 1176, in _parallel_func
    return Parallel(n_jobs=self.n_jobs)(
  File "/Home/venv/lib/python3.9/site-packages/joblib/parallel.py", line 1046, in __call__
    while self.dispatch_one_batch(iterator):
  File "/Home/venv/lib/python3.9/site-packages/joblib/parallel.py", line 861, in dispatch_one_batch
    self._dispatch(tasks)
  File "/Home/venv/lib/python3.9/site-packages/joblib/parallel.py", line 779, in _dispatch
    job = self._backend.apply_async(batch, callback=cb)
  File "/Home/venv/lib/python3.9/site-packages/joblib/_parallel_backends.py", line 208, in apply_async
    result = ImmediateResult(func)
  File "/Home/venv/lib/python3.9/site-packages/joblib/_parallel_backends.py", line 572, in __init__
    self.results = batch()
  File "/Home/venv/lib/python3.9/site-packages/joblib/parallel.py", line 262, in __call__
    return [func(*args, **kwargs)
  File "/Home/venv/lib/python3.9/site-packages/joblib/parallel.py", line 262, in <listcomp>
    return [func(*args, **kwargs)
  File "/Home/venv/lib/python3.9/site-packages/sklearn/utils/fixes.py", line 117, in __call__
    return self.function(*args, **kwargs)
  File "/Home/venv/lib/python3.9/site-packages/sklearn/pipeline.py", line 870, in _fit_transform_one
    res = transformer.fit_transform(X, y, **fit_params)
  File "/Home/venv/lib/python3.9/site-packages/sklearn/pipeline.py", line 422, in fit_transform
    return last_step.fit_transform(Xt, y, **fit_params_last_step)
TypeError: fit_transform() takes 2 positional arguments but 3 were given

This is what the desired output looks like, minus the additional cluster features:

Transformed Training Data:
          0         1         2         3         4         5
0  0.622766  0.622766  0.000000  0.000000  0.000000  0.473630
1  0.000000  0.000000  0.000000  0.795961  0.000000  0.605349
2  0.000000  0.000000  0.707107  0.000000  0.707107  0.000000

Transformed Test Data:
     0    1    2    3    4    5
0  1.0  0.0  0.0  0.0  0.0  0.0
1  0.0  0.0  0.0  0.0  0.0  1.0