编码与哑变量

处理缺失值

import pandas as pd
import numpy as np

df = pd.read_csv("./Narrativedata.csv", index_col=0)
df.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 891 entries, 0 to 890
Data columns (total 4 columns):
 #   Column    Non-Null Count  Dtype  
---  ------    --------------  -----  
 0   Age       714 non-null    float64
 1   Sex       891 non-null    object 
 2   Embarked  889 non-null    object 
 3   Survived  891 non-null    object 
dtypes: float64(1), object(3)
memory usage: 34.8+ KB

df["Age"].fillna(df["Age"].mean(), inplace=True)

df.dropna(axis=0, inplace=True)

df.shape

(889, 4)

preprocessing.LabelEncoder：标签专用，能够将分类转换为分类数值

from sklearn.preprocessing import LabelEncoder

label = df.iloc[:,-1]
le = LabelEncoder()
le_data = le.fit_transform(label)
df["Survived"] = le_data
df.shape

(889, 4)

pd.DataFrame(le.inverse_transform(le_data)).head()

	0
0	No
1	Yes
2	Yes
3	Yes
4	No

le.classes_

array(['No', 'Unknown', 'Yes'], dtype=object)

preprocessing.OrdinalEncoder：特征专用，能够将分类特征转换为分类数值

from sklearn.preprocessing import OrdinalEncoder

df_ = df.copy(deep=True)
feature = df_.iloc[:,1:-1]
ordinal = OrdinalEncoder(categories="auto")
result = ordinal.fit_transform(feature)

ordinal.categories_

[array(['female', 'male'], dtype=object), array(['C', 'Q', 'S'], dtype=object)]

ordinal.feature_names_in_

array(['Sex', 'Embarked'], dtype=object)

df.shape

(889, 4)

preprocessing.OneHotEncoder：独热编码，创建哑变量

from sklearn.preprocessing import OneHotEncoder

onehot = OneHotEncoder(categories="auto").fit(df.iloc[:,1:-1])
result = onehot.transform(df.iloc[:,1:-1]).toarray()
result

array([[0., 1., 0., 0., 1.],
       [1., 0., 1., 0., 0.],
       [1., 0., 0., 0., 1.],
       ...,
       [1., 0., 0., 0., 1.],
       [0., 1., 1., 0., 0.],
       [0., 1., 0., 1., 0.]])

onehot.get_feature_names_out()

array(['Sex_female', 'Sex_male', 'Embarked_C', 'Embarked_Q', 'Embarked_S'],
      dtype=object)

features = pd.DataFrame(result)
features.shape

(889, 5)

data_full = pd.concat([df,pd.DataFrame(result)],axis=1)
# 搞不懂了

data_full.dropna(axis=0,inplace=True)

data_full.head()

	Age	Sex	Embarked	Survived	0	1	2	3	4
0	22.0	male	S	0.0	0.0	1.0	0.0	0.0	1.0
1	38.0	female	C	2.0	1.0	0.0	1.0	0.0	0.0
2	26.0	female	S	2.0	1.0	0.0	0.0	0.0	1.0
3	35.0	female	S	2.0	1.0	0.0	0.0	0.0	1.0
4	35.0	male	S	0.0	0.0	1.0	0.0	0.0	1.0

data_full.drop(axis=1, columns=["Sex","Embarked"], inplace=True)

data_full.columns = ["Age", "Survived", 'Sex_female', 'Sex_male', 'Embarked_C', 'Embarked_Q', 'Embarked_S']

data_full.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 887 entries, 0 to 888
Data columns (total 7 columns):
 #   Column      Non-Null Count  Dtype  
---  ------      --------------  -----  
 0   Age         887 non-null    float64
 1   Survived    887 non-null    float64
 2   Sex_female  887 non-null    float64
 3   Sex_male    887 non-null    float64
 4   Embarked_C  887 non-null    float64
 5   Embarked_Q  887 non-null    float64
 6   Embarked_S  887 non-null    float64
dtypes: float64(7)
memory usage: 55.4 KB