If I understand you correctly you want to save your trained model so it can be loaded again correct?
There are two methods, using python's pickle
and the other method which is to use joblib
. The recommend method is joblib
as this will result in a much smaller file than a pickle, which dumps a string representation of your object:
from sklearn.externals import joblib
joblib.dump(clf, 'filename.pkl')
#then load it later, remember to import joblib of course
clf = joblib.load('filename.pk1')
See the online docs
Note: sklearn.externals.joblib
is deprecated. Install and use the pure joblib
instead