Storing Trained Models by Mario Schmidt

Mario Schmidt INVESTOR

| Reward Discussion

According to what I have understood in the "Storing Trained Models" documentation, I am trying to save my trained Logistic Regression model as follow:
clf = LogisticRegression().fit(X, y)
joblib.dump(clf,'clf_trained.pkl')
qb.ObjectStore.Save(model_key, clf)

But I am getting this error message:
TypeError Traceback (most recent call last)
<ipython-input-12-95b33bf4a492> in <module>
3 clf = LogisticRegression().fit(X, y)
4 joblib.dump(clf,'clf_trained.pkl')
----> 5 qb.ObjectStore.Save(model_key, clf)

TypeError: No method matches given arguments for Save

Could anyone tell me which is the right way to do this, please?

Thanks and regards,

Update Backtest

Mario Schmidt

Accepted Answer

Update Backtest

Notebook

The material on this website is provided for informational purposes only and does not constitute an offer to sell, a solicitation to buy, or a recommendation or endorsement for any security or strategy, nor does it constitute an offer to provide investment advisory services by QuantConnect. In addition, the material offers no opinion with respect to the suitability of any security or specific investment. QuantConnect makes no guarantees as to the accuracy or completeness of the views expressed in the website. The views are subject to change, and may have become unreliable for various reasons, including changes in market conditions or economic circumstances. All investments involve risk, including loss of principal. You should consult with an investment professional before making any investment decisions.

Adam W

3.8k ,

`joblib.dump` dumps the serialized model object into a local file, 'clf_trained.pkl', which is fine when working locally but on QC it should be saved specifically to the ObjectStore.

Here's the simplest way to do it with `pickle`:

clf = LogisticRegression().fit(X,y)



import pickle



#### Saving the model



# Serialize the object into bytes 

# (this is basically a non-human readable string that represents the object)

serializedObject = pickle.dumps(clf)



# Save to ObjectStore 

modelKey = "MyModel"

qb.ObjectStore.SaveBytes(modelKey, serializedObject)



#### Loading the model



# Load the object from bytes

serializedObject = bytes( qb.ObjectStore.ReadBytes(modelKey) )



# Deserialize the object

clf = pickle.loads(serializedObject)



# Use clf as normal

Mario Schmidt

1k ,

Thank you very much Adam.

Mario Schmidt INVESTOR

Update Backtest

Notebook

To unlock posting to the community forums please complete at least 30% of Boot Camp.
You can continue your Boot Camp training progress from the terminal. We hope to see you in the community soon!

Platform

QuantConnect Community

Alpha League Competition: $1,000 Weekly Prize Pool

Filter Discussion by Tags

Community Ambassadors

Earn free QuantConnect cloud credits by helping others, each week we airdrop credits to the most active community members.

232,863 Quants.

Online Now

Stay Connected