利用sklearn的LabelEncoder对标签进行数字化编码

from sklearn.preprocessing import LabelEncoder

def gen_label_encoder():
    labels = ['BB', 'CC']
    le = LabelEncoder()
    le.fit(labels)
    print 'le.classes_', le.classes_
    for label in le.classes_:
        print label, le.transform([label])[0]
    joblib.dump(le, 'data/label_encoder.h5')

LabelEncoder的说明：

 class LabelEncoder(BaseEstimator, TransformerMixin):
     """Encode labels with value between 0 and n_classes-1.

     Read more in the :ref:`User Guide <preprocessing_targets>`.

     Attributes
     ----------
     classes_ : array of shape (n_class,)
         Holds the label for each class.

     Examples
     --------
     `LabelEncoder` can be used to normalize labels.

     >>> from sklearn import preprocessing
     >>> le = preprocessing.LabelEncoder()
     >>> le.fit([1, 2, 2, 6])
     LabelEncoder()
     >>> le.classes_
     array([1, 2, 6])
     >>> le.transform([1, 1, 2, 6]) #doctest: +ELLIPSIS
     array([0, 0, 1, 2]...)
     >>> le.inverse_transform([0, 0, 1, 2])
     array([1, 1, 2, 6])

     It can also be used to transform non-numerical labels (as long as they are
     hashable and comparable) to numerical labels.

     >>> le = preprocessing.LabelEncoder()
     >>> le.fit(["paris", "paris", "tokyo", "amsterdam"])
     LabelEncoder()
     >>> list(le.classes_)
     ['amsterdam', 'paris', 'tokyo']
     >>> le.transform(["tokyo", "tokyo", "paris"]) #doctest: +ELLIPSIS
     array([2, 2, 1]...)
     >>> list(le.inverse_transform([2, 2, 1]))
     ['tokyo', 'tokyo', 'paris']

     See also
     --------
     sklearn.preprocessing.OneHotEncoder : encode categorical integer features
         using a one-hot aka one-of-K scheme.
     """