Blending集成学习算法及决策边界画法

算法原理

blending集成学习算法即简化的stacking算法，其具体操作流程为：

1. 将数据划分为训练集和测试集(test_set)，其中训练集需要再次划分为训练集(train_set)和验证集
   (val_set)；
2. 创建第一层的多个模型，这些模型可以使同质的也可以是异质的；
3. 使用train_set训练步骤2中的多个模型，然后用训练好的模型预测val_set和test_set得到val_predict,
   test_predict1；
4. 创建第二层的模型,使用val_predict作为训练集训练第二层的模型；
5. 使用第二层训练好的模型对第二层测试集test_predict1进行预测，该结果为整个测试集的结果。

优点：实现简单粗暴，没有太多的理论的分析。

缺点：blending只使用了一部分数据集作为留出集进行验证，也就是只能用上数据中的一部分，实际上这对数据来说是很奢侈浪费的。

代码实现

# -*- coding: utf-8 -*-
"""
Created on Tue May 11 15:47:59 2021

@author: 510009
"""

# 加载相关工具包
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
plt.style.use("ggplot")
%matplotlib inline
import seaborn as sns

# 创建数据
from sklearn import datasets
from sklearn.datasets import make_blobs
from sklearn.model_selection import train_test_split

data, target = make_blobs(
    n_samples=10000,
    centers=2,
    random_state=1,
    cluster_std=1.0
    )

## 创建训练集和测试集
X_train1,X_test,y_train1,y_test = train_test_split(
    data, 
    target, 
    test_size=0.2,
    random_state=1
    )

## 创建训练集和验证集
X_train,X_val,y_train,y_val = train_test_split(
    X_train1, 
    y_train1, 
    test_size=0.3,
    random_state=1
    )

print("The shape of training X:",X_train.shape)
print("The shape of training y:",y_train.shape)
print("The shape of test X:",X_test.shape)
print("The shape of test y:",y_test.shape)
print("The shape of validation X:",X_val.shape)
print("The shape of validation y:",y_val.shape)


# 设置第一层分类器
from sklearn.svm import SVC
from sklearn.ensemble import RandomForestClassifier
from sklearn.neighbors import KNeighborsClassifier
clfs = [
        SVC(probability = True),
        
        RandomForestClassifier(
            n_estimators=5, 
            n_jobs=-1,
            criterion='gini'),
        
        KNeighborsClassifier()
        ]
# 设置第二层分类器
from sklearn.linear_model import LinearRegression
lr = LinearRegression()


# 输出第一层的验证集结果与测试集结果
val_features = np.zeros((X_val.shape[0],len(clfs))) # 初始化验证集结果
test_features = np.zeros((X_test.shape[0],len(clfs))) # 初始化测试集结果
for i,clf in enumerate(clfs):
    clf.fit(X_train,y_train)
    val_feature = clf.predict_proba(X_val)[:, 1]
    test_feature = clf.predict_proba(X_test)[:,1]
    val_features[:,i] = val_feature
    test_features[:,i] = test_feature


# 将第一层的验证集的结果输入第二层训练第二层分类器
lr.fit(val_features,y_val)
# 输出预测的结果
from sklearn.model_selection import cross_val_score
cross_val_score(lr,test_features,y_test,cv=5)

iris实例

# -*- coding: utf-8 -*-
"""
Created on Tue May 11 17:39:37 2021

@author: 510009
"""

# 导入工具包
import matplotlib
import numpy as np
import matplotlib.pyplot as plt
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.svm import SVC
from sklearn.ensemble import RandomForestClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import cross_val_score

# 下载数据集
iris = datasets.load_iris()

X = iris.data
y = iris.target

# 数据集可视化观察
plt.scatter(X[y == 0, 0], X[y == 0, 1], color='red')
plt.scatter(X[y == 1, 0], X[y == 1, 1], color='blue')
# plt.scatter(X[y == 2, 0], X[y == 2, 1], color='green')
plt.show()

# 数据集划分
X_train, X_test, y_train, y_test = train_test_split(
    X,
    y,
    test_size=0.2,
    random_state=1)

X_train, X_val, y_train, y_val = train_test_split(
    X_train,
    y_train,
    test_size=0.3,
    random_state=1)

# 设置第一层分类器
clfs = [
    SVC(probability=True),

    RandomForestClassifier(
        n_estimators=5,
        n_jobs=-1,
        criterion='gini'),

    KNeighborsClassifier()
]

# 设置第二层分类器
lr = LinearRegression()

# 输出第一层的验证集结果与测试集结果
val_features = np.zeros((X_val.shape[0], len(clfs))) # 初始化验证集结果
test_features = np.zeros((X_test.shape[0], len(clfs))) # 初始化测试集结果
for i, clf in enumerate(clfs):
    clf.fit(X_train,y_train)
    val_feature = clf.predict_proba(X_val)[:, 1]
    test_feature = clf.predict_proba(X_test)[:,1]
    val_features[:,i] = val_feature
    test_features[:,i] = test_feature


# 将第一层的验证集的结果输入第二层训练第二层分类器
lr.fit(val_features, y_val)

# 输出预测的结果
scores = cross_val_score(lr, test_features, y_test, cv=5)
print(scores)
print(lr.score(val_features, y_val))