python对离散变量的one-hot编码方法

import pandas as pd
import os
os.getcwd() 
os.chdir('E:\study\kaggle\Titanic')
from sklearn.preprocessing import OneHotEncoder 
from sklearn.preprocessing import LabelEncoder 
data = pd.read_csv('train.csv')

data['Sex'].value_counts()
Out[38]: 
male  577
female 314
Name: Sex, dtype: int64 #可以看到，变量Sex为字符型变量，取值有male和female两种

Sex_ohe_1 = pd.get_dummies(data['Sex'])
Sex_ohe_1.head()
Out[40]: 
 female male
0  0  1
1  1  0
2  1  0
3  1  0
4  0  1

Sex_ohe_2 = OneHotEncoder(sparse=False).fit_transform(data['Sex'].reshape((-1,1))) 
 
ValueError: could not convert string to float: male 

le_sex=LabelEncoder().fit(data['Sex']) 
Sex_label=le_sex.transform(data['Sex']) 
Sex_label= LabelEncoder().fit_transform(data['Sex']) #fit_transform等价于fit和transform两个函数结合
ohe_sex=OneHotEncoder(sparse=False).fit(Sex_label.reshape(-1,1)) 
Sex_ohe=ohe_sex.transform(Sex_label.reshape(-1,1)) 
Sex_ohe_3 = OneHotEncoder(sparse=False).fit_transform(Sex_label.reshape((-1,1)))