数据预处理

1.创建示例数据集

import pandas as pd 

df = pd.DataFrame([ 
['green','M',10.1,'class1'],
['red','L',13.5,'class2'],
['blue','XL',15.3,'class1']])

df.columns = ['color','size','price','classlabel']

结果：

   color size  price classlabel
0  green    M   10.1     class1
1    red    L   13.5     class2
2   blue   XL   15.3     class1

2.映射叙述特征
为了确保机器学习能够正确的解读序数特征，需要将分类字符串转换为整数。

size_mapping = {'XL':3,'L':2,'M':1}
df['size'] = df['size'].map(size_mapping)

print(df)

结果
 color  size  price classlabel
0  green     1   10.1     class1
1    red     2   13.5     class2
2   blue     3   15.3     class1

3.分类标签编码

import pandas as pd 
import numpy as np

df = pd.DataFrame([ 
['green','M',10.1,'class1'],
['red','L',13.5,'class2'],
['blue','XL',15.3,'class1']])

df.columns = ['color','size','price','classlabel']

size_mapping = {'XL':3,'L':2,'M':1}
df['size'] = df['size'].map(size_mapping)

#分类标签整数化
class_mapping = {label:idx for idx,label in enumerate(np.unique(df['classlabel']))}   #分类标签从0开始枚举
df['classlabel'] = df['classlabel'].map(class_mapping)

print(df)

输出：

color  size  price  classlabel
0  green     1   10.1           0
1    red     2   13.5           1
2   blue     3   15.3           0

也可以反向映射键值对，或者使用sklearn中的LabelEncoder

import pandas as pd 
import numpy as np
from sklearn.preprocessing import LabelEncoder

df = pd.DataFrame([ 
['green','M',10.1,'class1'],
['red','L',13.5,'class2'],
['blue','XL',15.3,'class1']])

df.columns = ['color','size','price','classlabel']

size_mapping = {'XL':3,'L':2,'M':1}
df['size'] = df['size'].map(size_mapping)

#分类标签整数化
class_mapping = {label:idx for idx,label in enumerate(np.unique(df['classlabel']))}   #分类标签从0开始枚举
df['classlabel'] = df['classlabel'].map(class_mapping)

CL = LabelEncoder()
y = CL.fit_transform(df['classlabel'].values)
print(y)

输出：

array([0, 1, 0], dtype=int64)

4.为名词特征做热编码

import pandas as pd 
import numpy as np
from sklearn.preprocessing import LabelEncoder
from sklearn.preprocessing import OneHotEncoder

df = pd.DataFrame([ 
['green','M',10.1,'class1'],
['red','L',13.5,'class2'],
['blue','XL',15.3,'class1']])

df.columns = ['color','size','price','classlabel']

size_mapping = {'XL':3,'L':2,'M':1}
df['size'] = df['size'].map(size_mapping)

#分类标签整数化
class_mapping = {label:idx for idx,label in enumerate(np.unique(df['classlabel']))}   #分类标签从0开始枚举
df['classlabel'] = df['classlabel'].map(class_mapping)

CL = LabelEncoder()
y = CL.fit_transform(df['classlabel'].values)

x = df[['color','size','price']].values
color_le = LabelEncoder()
x[:,0] = color_le.fit_transform(x[:,0])

ohe = OneHotEncoder(categorical_features=[0])  #设置虚拟变量
H = ohe.fit_transform(x).toarray()

print(H)

输出

[[ 0.   1.   0.   1.  10.1]
 [ 0.   0.   1.   2.  13.5]
 [ 1.   0.   0.   3.  15.3]]