BentoML

service.py:

import bentoml
from <http://bentoml.io|bentoml.io> import JSON

model_ref = bentoml.sklearn.get('stroke_prediction:latest')
dv = model_ref.custom_objects['dicVectorizer']

model_runner = <http://model_ref.to|model_ref.to>_runner()

svc = bentoml.Service('stroke_prediction', runners=[model_runner])

@svc.api(input= JSON() , output= JSON())
def classify(application_data):
    vector = dv.transform(application_data)
    prediction = model_runner.predict_proba.run(vector)

    return prediction

Model save process:

log_model = LogisticRegression(max_iter=1000, random_state=1,C=100,penalty='l2',solver='lbfgs')

log_model.fit(x_train, y_train)

bentoml.sklearn.save_model('stroke_prediction', log_model,
                           custom_objects={
                               'dicVectorizer': dv
                           })

Solution, add this to save file:

ignatures={
                              "predict_proba": {
                                 "batchable": True,
                                 "batch_dim": 0
                              }