实现one hot encode的两种方法：

• 利用pandas实现one hot encode:

#  transform a given column into one hot. Use prefix to have multiple dummies>>> import pandas as pd>>> df = pd.DataFrame({'A': ['a', 'b', 'c'], 'B': ['b', 'a', 'c']})>>> # Get one hot encoding of columns B... >>> df   A  B0  a  b1  b  a2  c  c>>> one_hot = pd.get_dummies(df['B'])>>> # Drop columns B as it is now encoded... >>> df = df.drop('B', axis=1)>>> # Join the encoded df... >>> df = df.join(one_hot)>>> df   A  a  b  c0  a  0  1  01  b  1  0  02  c  0  0  1

• 一个定性特征哑编码的demo：

def one_hot(df, cols):    """    @param df pandas DataFrame    @param cols a list of columns to encode     @return a DataFrame with one-hot encoding    """    for each in cols:        dummies = pd.get_dummies(df[each], prefix=each, drop_first=False)        df = pd.concat([df, dummies], axis=1)    return df

• 使用 sklearn进行特征变量哑编码：

>>> from sklearn.preprocessing import OneHotEncoder>>> enc = OneHotEncoder()>>> enc.fit([[0, 0, 3], [1,1,0], [0,2,1], [1,0,2]])OneHotEncoder(categorical_features='all', dtype=
    
     ,       handle_unknown='error', n_values='auto', sparse=True)>>> enc.n_values_array([2, 3, 4])>>> enc.feature_indices_array([0, 2, 5, 9])>>> enc.transform([[0,1,1]])<1x9 sparse matrix of type '
     
      '    with 3 stored elements in Compressed Sparse Row format>>>> enc.transform([[0,1,1]]).toarray()array([[ 1.,  0.,  0.,  1.,  0.,  0.,  1.,  0.,  0.]])
     
    

• 一个保存在全局的Label_Binarizer的demo：

from sklearn.preprocessing import LabelBinarizer label_binarizer = LabelBinarizer()label_binarizer.fit(all_your_labels_list) # need to be global or remembered to use it laterdef one_hot_encode(x):    """    One hot encode a list of sample labels. Return a one-hot encoded vector for each label.    : x: List of sample Labels    : return: Numpy array of one-hot encoded labels    """    return label_binarizer.transform(x)