In [2]: paste
import pandas as pd
import sklearn.compose
import sklearn.preprocessing
from sklearn.base import clone
import dask.dataframe as dd

import dask_ml.compose
import dask_ml.preprocessing

df = pd.DataFrame({"A": pd.Categorical(["a", "a", "b", "a"]), "B": [1.0, 2, 4, 5]})
ddf = dd.from_pandas(df, npartitions=2).reset_index(drop=True)


b = dask_ml.compose.make_column_transformer(
    (["A"], dask_ml.preprocessing.OneHotEncoder(sparse=False)),
    (["B"], dask_ml.preprocessing.StandardScaler()),
)

## -- End pasted text --

In [3]: b.fit_transform(ddf).compute()
/Users/taugspurger/sandbox/dask/dask/dataframe/multi.py:608: UserWarning: Concatenating dataframes with unknown divisions.
We're assuming that the indexes of each dataframes are
 aligned. This assumption is not generally safe.
  warnings.warn("Concatenating dataframes with unknown divisions.\n"
Out[3]:
   A_a  A_b         B
0  1.0  0.0 -1.264911
1  1.0  0.0 -0.632456
0  0.0  1.0  0.632456
1  1.0  0.0  1.264911