In [1]:

    

# Keeping models around for later use.


    

In [2]:

    

from sklearn import datasets, tree


    

In [3]:

    

X, y = datasets.make_classification()


    

In [4]:

    

dt = tree.DecisionTreeClassifier()
dt.fit(X, y)


    

    
Out[4]:





DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,
            max_features=None, max_leaf_nodes=None, min_samples_leaf=1,
            min_samples_split=2, min_weight_fraction_leaf=0.0,
            random_state=None, splitter='best')

In [5]:

    

from sklearn.externals import joblib


    

In [6]:

    

joblib.dump(dt, 'dtree.clf')


    

    
Out[6]:





['dtree.clf',
 'dtree.clf_01.npy',
 'dtree.clf_02.npy',
 'dtree.clf_03.npy',
 'dtree.clf_04.npy']

In [7]:

    

# How it works.


    

In [8]:

    

from sklearn import ensemble


    

In [10]:

    

rf = ensemble.RandomForestClassifier()
rf.fit(X, y)


    

    
Out[10]:





RandomForestClassifier(bootstrap=True, class_weight=None, criterion='gini',
            max_depth=None, max_features='auto', max_leaf_nodes=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, n_estimators=10, n_jobs=1,
            oob_score=False, random_state=None, verbose=0,
            warm_start=False)

In [11]:

    

joblib.dump(rf, "rf.clf")


    

    
Out[11]:





['rf.clf',
 'rf.clf_01.npy',
 'rf.clf_02.npy',
 'rf.clf_03.npy',
 'rf.clf_04.npy',
 'rf.clf_05.npy',
 'rf.clf_06.npy',
 'rf.clf_07.npy',
 'rf.clf_08.npy',
 'rf.clf_09.npy',
 'rf.clf_10.npy',
 'rf.clf_11.npy',
 'rf.clf_12.npy',
 'rf.clf_13.npy',
 'rf.clf_14.npy',
 'rf.clf_15.npy',
 'rf.clf_16.npy',
 'rf.clf_17.npy',
 'rf.clf_18.npy',
 'rf.clf_19.npy',
 'rf.clf_20.npy',
 'rf.clf_21.npy',
 'rf.clf_22.npy',
 'rf.clf_23.npy',
 'rf.clf_24.npy',
 'rf.clf_25.npy',
 'rf.clf_26.npy',
 'rf.clf_27.npy',
 'rf.clf_28.npy',
 'rf.clf_29.npy',
 'rf.clf_30.npy',
 'rf.clf_31.npy',
 'rf.clf_32.npy',
 'rf.clf_33.npy',
 'rf.clf_34.npy',
 'rf.clf_35.npy',
 'rf.clf_36.npy',
 'rf.clf_37.npy',
 'rf.clf_38.npy',
 'rf.clf_39.npy',
 'rf.clf_40.npy',
 'rf.clf_41.npy',
 'rf.clf_42.npy',
 'rf.clf_43.npy',
 'rf.clf_44.npy',
 'rf.clf_45.npy',
 'rf.clf_46.npy',
 'rf.clf_47.npy',
 'rf.clf_48.npy',
 'rf.clf_49.npy',
 'rf.clf_50.npy',
 'rf.clf_51.npy']

In [12]:

    

dir(joblib)


    

    
Out[12]:





['Logger',
 'MemorizedResult',
 'Memory',
 'Parallel',
 'PrintTime',
 '__builtins__',
 '__doc__',
 '__file__',
 '__name__',
 '__package__',
 '__path__',
 '__version__',
 '_compat',
 '_multiprocessing_helpers',
 'cpu_count',
 'delayed',
 'disk',
 'dump',
 'format_stack',
 'func_inspect',
 'hash',
 'hashing',
 'load',
 'logger',
 'memory',
 'my_exceptions',
 'numpy_pickle',
 'parallel',
 'pool']

In [ ]: