machine-learning - 如何为泰坦尼克号数据集定义 oneHotEncoder

Question

我正在尝试处理泰坦尼克号数据集。数据具有分类值，因此我使用 labelEncoder 将数据更改为数字，而不是文本。之前:

     PassengerId  Survived  Pclass     Sex    Age  SibSp  Parch      Fare Embarked
0              1         0       3    male  22.00      1      0    7.2500        S
1              2         1       1  female  38.00      1      0   71.2833        C
2              3         1       3  female  26.00      0      0    7.9250        S

之后:

     PassengerId  Survived  Pclass  Sex    Age  SibSp  Parch      Fare  Embarked
0              1         0       3    1  22.00      1      0    7.2500         2
1              2         1       1    0  38.00      1      0   71.2833         0
2              3         1       3    0  26.00      0      0    7.9250         2

这是代码:

from sklearn.preprocessing import LabelEncoder

labelencoder_X = LabelEncoder()    
data['Embarked'] = labelencoder_X.fit_transform(data['Embarked'])
data['Sex'] = labelencoder_X.fit_transform(data['Sex'])

现在，因为乘客的性别具有同样的重要性，所以我想使用oneHotEncoder。据我了解，数据应如下所示:

     PassengerId  Survived  Pclass  Male Female    Age  SibSp  Parch      Fare  Embarked
0              1         0       3    1     0     22.00  1      0    7.2500         2
1              2         1       1    0     1     38.00  1      0   71.2833         0
2              3         1       3    0     1     26.00  0      0    7.9250         2  

如何编写代码来执行此操作？我尝试对 oneHotEncoder 使用类似的方法:

from sklearn.preprocessing import LabelEncoder, OneHotEncoder

labelencoder_X = LabelEncoder()    
data['Embarked'] = labelencoder_X.fit_transform(data['Embarked'])
data['Sex'] = labelencoder_X.fit_transform(data['Sex'])

onehotencoder = OneHotEncoder()
data['Embarked'] = onehotencoder.fit_transform(data['Embarked'].values.reshape(-1,1))

但它只是返回相同的结果。我该如何修复它？我是 Scikit 和 ML 的新手，我希望我做得正确。

Answer 1

这就是你可以做到的。

import pandas as pd
from sklearn.preprocessing import OneHotEncoder

# Sample data
   Sex
0    1
1    0
2    0
3    1

# OneHotEncoder
result = OneHotEncoder().fit_transform(df['Sex'].reshape(-1, 1)).toarray()

# Appending columns
df[['Female', 'Male']] = pd.DataFrame(result, index = df.index)

# Resulting dataframe
df
   Sex  Female  Male
0    1     0.0   1.0
1    0     1.0   0.0
2    0     1.0   0.0
3    1     0.0   1.0