scikit-learn：3.4. Model persistence

參考：http://scikit-learn.org/stable/modules/model_persistence.html

训练了模型之后，我们希望能够保存下来，遇到新样本时直接使用已经训练好的保存了的模型。而不用又一次再训练模型。

本节介绍pickle在保存模型方面的应用。

（After training a scikit-learn model, it is desirable to have a way to persist the model for future use without having to retrain. The following section gives you an example of how to persist a model with pickle. We’ll also review a few security and maintainability issues when working with pickle serialization.）

1、persistence example

It is possible to save a model in the scikit by using Python’s built-in persistence model, namely pickle:

>>> from sklearn import svm
>>> from sklearn import datasets
>>> clf = svm.SVC()
>>> iris = datasets.load_iris()
>>> X, y = iris.data, iris.target
>>> clf.fit(X, y)  
SVC(C=1.0, cache_size=200, class_weight=None, coef0=0.0, degree=3, gamma=0.0,
  kernel='rbf', max_iter=-1, probability=False, random_state=None,
  shrinking=True, tol=0.001, verbose=False)

>>> import pickle
>>> s = pickle.dumps(clf)
>>> clf2 = pickle.loads(s)
>>> clf2.predict(X[0])
array([0])
>>> y[0]
0

有些情况下（more efficient on objects that carry large numpy arrays internally）使用joblib’s 取代pickle (joblib.dump & joblib.load)。之后我们甚至能够在还有一个pathon程序中load保存好的模型（pickle也能够。。。）：

>>> from sklearn.externals import joblib
>>> <strong>joblib.dump(clf, 'filename.pkl') 
>>> clf = joblib.load('filename.pkl') </strong>

Note

joblib.dump returns a list of filenames. Each individual numpy array contained in the clf object is serialized as a separate file on the filesystem. All files are required in the same folder when reloading the model with joblib.load.

2、security & maintainability limitations

pickle (and joblib by extension)在maintainability and security方面有些问题。由于：

Never unpickle untrusted data
Models saved in one version of scikit-learn might not load in another version.

为了可以在scikit-learn未来的版本号中重构已保存好的模型，须要pickled时加入一些metadata：

The training data, e.g. a reference to a immutable snapshot
The python source code used to generate the model
The versions of scikit-learn and its dependencies
The cross validation score obtained on the training data

further discussion，refer this talk by Alex Gaynor.