This message was deleted.
# announcementss
Slackbot
11/13/2020, 9:11 PMThis message was deleted.
✅ 1
c
Chaoyu
11/13/2020, 9:14 PMHi - are you referring to any example notebook you found online?
Chaoyu
11/13/2020, 9:14 PMYou may need to add the
--formatp
PIYUSH AGGARWAL
11/13/2020, 9:15 PMYes, I am referring to this - https://notebook.community/kubeflow/examples/prophet_bento_timeseries/bentoml-kubeflow-prophet
PIYUSH AGGARWAL
11/13/2020, 9:16 PM%%writefile uk_data_predict.py
import bentoml
import fbprophet
import pandas as pd
from fbprophet import Prophet
from bentoml import api, env, artifacts, BentoService
from bentoml.adapters import DataframeInput
from bentoml.handlers import DataframeHandler
from bentoml.artifact import PickleArtifact
from bentoml.service.artifacts.common import PickleArtifact
@bentoml.artifacts([PickleArtifact('model')]) #custom pickle artifact
@env(infer_pip_packages=True)
class UKDataPredict (bentoml.BentoService):
@bentoml.api(input=JsonInput(), batch= True)
def predict(self, df: pd.DataFrame):
final_data = df # Figure out the data used for prediction (all rows and all columns)
predictions = self.artifacts.model.predict(final_data)
return predictions.as_data_frame()
c
Chaoyu
11/13/2020, 9:16 PMI see, that notebook was from 0.8.1, and may have some issue with current version of BentoML
Chaoyu
11/13/2020, 9:16 PMcc @Bo @Jiang
b
Bo
11/13/2020, 9:19 PMWill check out the example notebook
c
Chaoyu
11/13/2020, 9:24 PM@PIYUSH AGGARWAL it might be a bug in the JsonInput implementation or the user BentoService code, I don’t think it needs implementing
--formatb
Bo
11/13/2020, 9:27 PM@PIYUSH AGGARWAL Are you expecting Json data for prediction? Right now, the API endpoint is using
JsonInputc
Chaoyu
11/13/2020, 9:27 PMthe API has changed, it should be
api(input=DataframeInput)p
PIYUSH AGGARWAL
11/13/2020, 9:28 PMI am expecting to feed a dataframe as input for prediction
b
Bo
11/13/2020, 9:30 PM@bentoml.api(input=DataframeInput(), batch=True)
p
PIYUSH AGGARWAL
11/13/2020, 9:33 PM!bentoml run UKDataPredict:20201112213619_0DFFD3 predict --input '{"ds":future_data}'
b
Bo
11/13/2020, 9:33 PMYour initial bentoml CLI command is fine
Make sure you setup the correct orient for your request JSON data. You can find the orient options here: https://docs.bentoml.org/en/latest/api/adapters.html#dataframeinput
Bo
11/13/2020, 9:42 PMthe way BentoML works is it will attempt to convert your incoming data to the data type you expected.
For your bento service, you set DatframeInput for your API endpoint. BentoML will attempt to convert incoming data to dataframe format and pass that to your predict function.
Bo
11/13/2020, 10:01 PMYou can also pass the csv file as input for CLI. Use the option
—input-fileBo
11/13/2020, 10:01 PMThe csv file will convert to dataframe
p
PIYUSH AGGARWAL
11/13/2020, 10:30 PMYup...I did that before...but the problem is that I am now getting the result as json which is difficult to comprehend...How do I get the output (prediction) in the dataframe format?
predictions = self.artifacts.model.predict(final_data)
return predictions.to_data_frame()
It returns the output in the form of json istelf and
predictions = self.artifacts.model.predict(final_data)
return predictions.as_data_frame()
throws an error
4 Views