load decision tree from file in scikit-learn

Question

In python scikit learn, there is a method called export_graphviz to export a decision tree to dot file.

I want to ask if there is a method to import a dot file to scikit learn as a decision tree? like some function called sklearn.tree.import_graphviz() ?

Answer 1

AFAIK There is no easy way to do that. Graphviz can only be used to visualise the decision tree. If you wish to save the model you can use Pickle to save the model. For example:

import cPickle
# save the classifier
with open('my_dumped_classifier.pkl', 'wb') as fid:
    cPickle.dump(gnb, fid)    

# load it again
with open('my_dumped_classifier.pkl', 'rb') as fid:
    gnb_loaded = cPickle.load(fid)