Saving Patsy for sklean inference

Question

I am a huge lover of your sklego project, especially patsy implementation within sklean.

However, there is one thing I still would like your opinion on - how do you use a pipeline containing PatsyTransformer only for inference?

As the pickling is not yet supported on the patsy side I came up with a workaround.

import seaborn as sns
from joblib import dump, load
from sklego.preprocessing import PatsyTransformer
from sklearn.linear_model import LinearRegression
from sklearn.pipeline import Pipeline

# Load The data

data = sns.load_dataset("tips")

# Basic Pipeline
pipe = Pipeline([
    ("patsy", PatsyTransformer("tip + C(day)")),
    ("model", LinearRegression())
])

data

# Train the pipeline
pipe.fit(data, data['total_bill'])

from sklearn.base import BaseEstimator, TransformerMixin

# Class for inferencing with pre-trained model (fit only passes, no training happens)
class Model_Inferencer(BaseEstimator, TransformerMixin):
    """
    Function that applyes pre-trained models within a pipeline setting.
    """

    def __init__(self, pre_trained_model=None):
        self.pre_trained_model = pre_trained_model

    def transform(self, X):

        preds = self.pre_trained_model.predict(X)
        return preds

    def predict(self, X):

        preds = self.pre_trained_model.predict(X)
        return preds

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

pipe.predict(data)[:10]

# Save the model
dump(pipe['model'], 'model_github.joblib')

# Load The model
loaded_model = load('model_github.joblib')

# Create Inference Pipeline
pipe_inference = Pipeline([
    ("patsy", PatsyTransformer("tip + C(day)")),
    ("inferencer", Model_Inferencer(loaded_model))
])


# Inference pipeline needs to be fitted 
# pipe_inference.fit(data)

# Save predictions (works only when fitted)
pipe_inference.predict(data)

I also tried saving the info by hand:

import h5py

def save_patsy(patsy_step, filename):
    """Save the coefficients of a linear model into a .h5 file."""
    with h5py.File(filename, 'w') as hf:
        hf.create_dataset("design_info",  data=patsy_step.design_info_)

def load_coefficients(patsy_step, filename):
    """Attach the saved coefficients to a linear model."""
    with h5py.File(filename, 'r') as hf:
        design_info = hf['design_info'][:]
    patsy_step.design_info_ = design_info


save_patsy(pipe['patsy'], "clf.h5")

However, a bummer error will occur.

 Object dtype dtype('O') has no native HDF5 equivalent