Task5-模型融合

将多个model进行融合，看是否可以得到一个性能更好的model
1）直接对预测结果进行平均

## 生成一些简单的样本数据，test_prei 代表第i个模型的预测值
test_pre1 = [1.2, 3.2, 2.1, 6.2]
test_pre2 = [0.9, 3.1, 2.0, 5.9]
test_pre3 = [1.1, 2.9, 2.2, 6.0]

# y_test_true 代表第模型的真实值
y_test_true = [1, 3, 2, 6]

from sklearn import metrics
from sklearn import linear_model
import numpy as np
import pandas as pd

## 定义结果的加权平均函数
def Weighted_method(test_pre1,test_pre2,test_pre3,w=[1/3,1/3,1/3]):
    Weighted_result = w[0]*pd.Series(test_pre1)+w[1]*pd.Series(test_pre2)+w[2]*pd.Series(test_pre3)
    return Weighted_result
print('Pred1 MAE:',metrics.mean_absolute_error(y_test_true, test_pre1))
print('Pred2 MAE:',metrics.mean_absolute_error(y_test_true, test_pre2))
print('Pred3 MAE:',metrics.mean_absolute_error(y_test_true, test_pre3))

## 定义结果的加权平均函数(均值)
def Mean_method(test_pre1,test_pre2,test_pre3):
    Mean_result = pd.concat([pd.Series(test_pre1),pd.Series(test_pre2),pd.Series(test_pre3)],axis=1).mean(axis=1)
    return Mean_result
Mean_pre = Mean_method(test_pre1,test_pre2,test_pre3)
print('Mean_pre MAE:',metrics.mean_absolute_error(y_test_true, Mean_pre))
#0.0667

## 定义结果的加权平均函数(中位数)
def Median_method(test_pre1,test_pre2,test_pre3):
    Median_result = pd.concat([pd.Series(test_pre1),pd.Series(test_pre2),pd.Series(test_pre3)],axis=1).median(axis=1)
    return Median_result
Median_pre = Median_method(test_pre1,test_pre2,test_pre3)
print('Median_pre MAE:',metrics.mean_absolute_error(y_test_true, Median_pre))
#0.075

2）starking 融合（回归模型）

def Stacking_method(train_reg1,train_reg2,train_reg3,y_train_true,test_pre1,test_pre2,test_pre3,model_L2= linear_model.LinearRegression()):
    model_L2.fit(pd.concat([pd.Series(train_reg1),pd.Series(train_reg2),pd.Series(train_reg3)],axis=1).values,y_train_true)
    Stacking_result = model_L2.predict(pd.concat([pd.Series(test_pre1),pd.Series(test_pre2),pd.Series(test_pre3)],axis=1).values)
    return Stacking_result

## 生成一些简单的样本数据，test_prei 代表第i个模型的预测值
train_reg1 = [3.2, 8.2, 9.1, 5.2]
train_reg2 = [2.9, 8.1, 9.0, 4.9]
train_reg3 = [3.1, 7.9, 9.2, 5.0]
# y_test_true 代表第模型的真实值
y_train_true = [3, 8, 9, 5]

test_pre1 = [1.2, 3.2, 2.1, 6.2]
test_pre2 = [0.9, 3.1, 2.0, 5.9]
test_pre3 = [1.1, 2.9, 2.2, 6.0]

# y_test_true 代表第模型的真实值
y_test_true = [1, 3, 2, 6]

model_L2= linear_model.LinearRegression()
Stacking_pre = Stacking_method(train_reg1,train_reg2,train_reg3,y_train_true,
                               test_pre1,test_pre2,test_pre3,model_L2)
print('Stacking_pre MAE:',metrics.mean_absolute_error(y_test_true, Stacking_pre))

3）分类模型融合
3.1 投票

from sklearn.datasets import make_blobs
from sklearn import datasets
from sklearn.tree import DecisionTreeClassifier
import numpy as np
from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import VotingClassifier
from xgboost import XGBClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.svm import SVC
from sklearn.model_selection import train_test_split
from sklearn.datasets import make_moons
from sklearn.metrics import accuracy_score,roc_auc_score
from sklearn.model_selection import cross_val_score
from sklearn.model_selection import StratifiedKFold

'''
硬投票：对多个模型直接进行投票，不区分模型结果的相对重要度，最终投票数最多的类为最终被预测的类。
'''
iris = datasets.load_iris()

x=iris.data #连续型
y=iris.target #0,1
#分出训练集和验证集
x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.3)

clf1 = XGBClassifier(learning_rate=0.1, n_estimators=150, max_depth=3, min_child_weight=2, subsample=0.7,
                     colsample_bytree=0.6, objective='binary:logistic')
clf2 = RandomForestClassifier(n_estimators=50, max_depth=1, min_samples_split=4,
                              min_samples_leaf=63,oob_score=True)
clf3 = SVC(C=0.1)

# 硬投票
import warnings
warnings.filterwarnings('ignore')
eclf = VotingClassifier(estimators=[('xgb', clf1), ('rf', clf2), ('svc', clf3)], voting='hard')
for clf, label in zip([clf1, clf2, clf3, eclf], ['XGBBoosting', 'Random Forest', 'SVM', 'Ensemble']):
    scores = cross_val_score(clf, x, y, cv=5, scoring='accuracy')
    print("Accuracy: %0.2f (+/- %0.2f) [%s]" % (scores.mean(), scores.std(), label))

# 软投票
'''
软投票：和硬投票原理相同，增加了设置权重的功能，可以为不同模型设置不同权重，进而区别模型不同的重要度。
'''
eclf = VotingClassifier(estimators=[('xgb', clf1), ('rf', clf2), ('svc', clf3)], voting='soft', weights=[2, 1, 1])
clf1.fit(x_train, y_train)

for clf, label in zip([clf1, clf2, clf3, eclf], ['XGBBoosting', 'Random Forest', 'SVM', 'Ensemble']):
    scores = cross_val_score(clf, x, y, cv=5, scoring='accuracy')
    print("Accuracy: %0.2f (+/- %0.2f) [%s]" % (scores.mean(), scores.std(), label))

可以看出，在这个例子中，软投票的效果还不如硬投票