I have trained a RandomForestClassifier from Python Sckit Learn Module with very big dataset, but question is how can I possibly save this model and let other people apply it on their end. Thank you!
1
-
See scikit-learn.org/stable/tutorial/basic/…EdChum– EdChum2014-04-11 13:07:54 +00:00Commented Apr 11, 2014 at 13:07
Add a comment
|
2 Answers
The recommended method is to use joblib, this will result in a much smaller file than a pickle:
from sklearn.externals import joblib
joblib.dump(clf, 'filename.pkl')
#then your colleagues can load it
clf = joblib.load('filename.pkl')
See the online docs
Comments
Have you tried pickling the RandomForestClassifier using the Pickle module and then saving it to the disk?
Here’s an example based on the pickle docs:
import pickle
classifier = RandomForestClassifier(etc)
output = open('classifier.pkl', 'wb')
pickle.dump(classifier, output)
output.close()
The “other people” could then reload the pickled object as follows:
import pickle
f = open('classifier.pkl', 'rb')
classifier = pickle.load(f)
f.close()
1 Comment
EdChum
joblib is preferred and less verbose (i.e. smaller file): scikit-learn.org/stable/tutorial/basic/…