task 1 blending

Blending是一种模型融合的方式，第一层通过将训练集出一部分作为holdout set,然后通过剩下的数据生成模型对holdout set 进行预测，第二层，直接对预测结果建模生成第二层的模型

Blending第一层将训练集需要划分为训练集(train_set)和验证集(val_set)。第一层中可以选择多个模型，这些模型可以是同质的也可以是异质的。然后分别使用训练集对这些模型训练，将训练好的模型对验证集进行验证得到预测特征。这些预测特征将作为第二层的训练集。第一层模型的训练代码如下:

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
plt.style.use("ggplot")
%matplotlib inline
import seaborn as sns

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)

决策边界如下：