一、模型融合目标
- 对于多种调参完成的模型进行模型融合。
- 完成对于多种模型的融合,提交融合结果并打卡。
二、内容介绍
模型融合是比赛后期一个重要的环节,大体来说有如下的类型方式。
1、简单加权融合:
回归(分类概率):算术平均融合(Arithmetic mean),几何平均融合(Geometric mean);
2、分类:投票(Voting)
综合:排序融合(Rank averaging),log融合
3、stacking/blending:
构建多层模型,并利用预测结果再拟合预测。
4、boosting/bagging(在xgboost,Adaboost,GBDT中已经用到):
多树的提升方法
三、代码示例
1、回归\分类概率-融合:
1)简单加权平均,结果直接融合
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]
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
from sklearn import metrics
# 各模型的预测结果计算MAE
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))
## 根据加权计算MAE
w = [0.3,0.4,0.3] # 定义比重权值
Weighted_pre = Weighted_method(test_pre1,test_pre2,test_pre3,w)
print('Weighted_pre MAE:',metrics.mean_absolute_error(y_test_true, Weighted_pre))
## 定义结果的加权平均函数
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))
## 定义结果的加权平均函数
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))
2) Stacking融合(回归)
from sklearn import linear_model
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]
分类模型融合
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
1)Voting投票机制:
'''
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
y=iris.target
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
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: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。
'''
x=iris.data
y=iris.target
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=0.8,
colsample_bytree=0.8, 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, probability=True)
# 软投票
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))
2)分类的Stacking\Blending融合
'''
5-Fold Stacking
'''
from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import ExtraTreesClassifier,GradientBoostingClassifier
import pandas as pd
#创建训练的数据集
data_0 = iris.data
data = data_0[:100,:]
target_0 = iris.target
target = target_0[:100]
#模型融合中使用到的各个单模型
clfs = [LogisticRegression(solver='lbfgs'),
RandomForestClassifier(n_estimators=5, n_jobs=-1, criterion='gini'),
ExtraTreesClassifier(n_estimators=5, n_jobs=-1, criterion='gini'),
ExtraTreesClassifier(n_estimators=5, n_jobs=-1, criterion='entropy'),
GradientBoostingClassifier(learning_rate=0.05, subsample=0.5, max_depth=6, n_estimators=5)]
#切分一部分数据作为测试集
X, X_predict, y, y_predict = train_test_split(data, target, test_size=0.3, random_state=2020)
dataset_blend_train = np.zeros((X.shape[0], len(clfs)))
dataset_blend_test = np.zeros((X_predict.shape[0], len(clfs)))
#5折stacking
n_splits = 5
skf = StratifiedKFold(n_splits)
skf = skf.split(X, y)
for j, clf in enumerate(clfs):
#依次训练各个单模型
dataset_blend_test_j = np.zeros((X_predict.shape[0], 5))
for i, (train, test) in enumerate(skf):
#5-Fold交叉训练,使用第i个部分作为预测,剩余的部分来训练模型,获得其预测的输出作为第i部分的新特征。
X_train, y_train, X_test, y_test = X[train], y[train], X[test], y[test]
clf.fit(X_train, y_train)
y_submission = clf.predict_proba(X_test)[:, 1]
dataset_blend_train[test, j] = y_submission
dataset_blend_test_j[:, i] = clf.predict_proba(X_predict)[:, 1]
#对于测试集,直接用这k个模型的预测值均值作为新的特征。
dataset_blend_test[:, j] = dataset_blend_test_j.mean(1)
print("val auc Score: %f" % roc_auc_score(y_predict, dataset_blend_test[:, j]))
clf = LogisticRegression(solver='lbfgs')
clf.fit(dataset_blend_train, y)
y_submission = clf.predict_proba(dataset_blend_test)[:, 1]
print("Val auc Score of Stacking: %f" % (roc_auc_score(y_predict, y_submission)))
'''
Blending
'''
#创建训练的数据集
#创建训练的数据集
data_0 = iris.data
data = data_0[:100,:]
target_0 = iris.target
target = target_0[:100]
#模型融合中使用到的各个单模型
clfs = [LogisticRegression(solver='lbfgs'),
RandomForestClassifier(n_estimators=5, n_jobs=-1, criterion='gini'),
RandomForestClassifier(n_estimators=5, n_jobs=-1, criterion='entropy'),
ExtraTreesClassifier(n_estimators=5, n_jobs=-1, criterion='gini'),
#ExtraTreesClassifier(n_estimators=5, n_jobs=-1, criterion='entropy'),
GradientBoostingClassifier(learning_rate=0.05, subsample=0.5, max_depth=6, n_estimators=5)]
#切分一部分数据作为测试集
X, X_predict, y, y_predict = train_test_split(data, target, test_size=0.3, random_state=2020)
#切分训练数据集为d1,d2两部分
X_d1, X_d2, y_d1, y_d2 = train_test_split(X, y, test_size=0.5, random_state=2020)
dataset_d1 = np.zeros((X_d2.shape[0], len(clfs)))
dataset_d2 = np.zeros((X_predict.shape[0], len(clfs)))
for j, clf in enumerate(clfs):
#依次训练各个单模型
clf.fit(X_d1, y_d1)
y_submission = clf.predict_proba(X_d2)[:, 1]
dataset_d1[:, j] = y_submission
#对于测试集,直接用这k个模型的预测值作为新的特征。
dataset_d2[:, j] = clf.predict_proba(X_predict)[:, 1]
print("val auc Score: %f" % roc_auc_score(y_predict, dataset_d2[:, j]))
#融合使用的模型
clf = GradientBoostingClassifier(learning_rate=0.02, subsample=0.5, max_depth=6, n_estimators=30)
clf.fit(dataset_d1, y_d2)
y_submission = clf.predict_proba(dataset_d2)[:, 1]
print("Val auc Score of Blending: %f" % (roc_auc_score(y_predict, y_submission)))
3)分类的Stacking融合
import warnings
warnings.filterwarnings('ignore')
import itertools
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
import matplotlib.gridspec as gridspec
from sklearn import datasets
from sklearn.linear_model import LogisticRegression
from sklearn.neighbors import KNeighborsClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.ensemble import RandomForestClassifier
from mlxtend.classifier import StackingClassifier
from sklearn.model_selection import cross_val_score
from mlxtend.plotting import plot_learning_curves
from mlxtend.plotting import plot_decision_regions
# 以python自带的鸢尾花数据集为例
iris = datasets.load_iris()
X, y = iris.data[:, 1:3], iris.target
clf1 = KNeighborsClassifier(n_neighbors=1)
clf2 = RandomForestClassifier(random_state=1)
clf3 = GaussianNB()
lr = LogisticRegression()
sclf = StackingClassifier(classifiers=[clf1, clf2, clf3],
meta_classifier=lr)
label = ['KNN', 'Random Forest', 'Naive Bayes', 'Stacking Classifier']
clf_list = [clf1, clf2, clf3, sclf]
fig = plt.figure(figsize=(10,8))
gs = gridspec.GridSpec(2, 2)
grid = itertools.product([0,1],repeat=2)
clf_cv_mean = []
clf_cv_std = []
for clf, label, grd in zip(clf_list, label, grid):
scores = cross_val_score(clf, X, y, cv=3, scoring='accuracy')
print("Accuracy: %.2f (+/- %.2f) [%s]" %(scores.mean(), scores.std(), label))
clf_cv_mean.append(scores.mean())
clf_cv_std.append(scores.std())
clf.fit(X, y)
ax = plt.subplot(gs[grd[0], grd[1]])
fig = plot_decision_regions(X=X, y=y, clf=clf)
plt.title(label)
plt.show()
3、一些其它方法
def Ensemble_add_feature(train,test,target,clfs):
# n_flods = 5
# skf = list(StratifiedKFold(y, n_folds=n_flods))
train_ = np.zeros((train.shape[0],len(clfs*2)))
test_ = np.zeros((test.shape[0],len(clfs*2)))
for j,clf in enumerate(clfs):
'''依次训练各个单模型'''
# print(j, clf)
'''使用第1个部分作为预测,第2部分来训练模型,获得其预测的输出作为第2部分的新特征。'''
# X_train, y_train, X_test, y_test = X[train], y[train], X[test], y[test]
clf.fit(train,target)
y_train = clf.predict(train)
y_test = clf.predict(test)
## 新特征生成
train_[:,j*2] = y_train**2
test_[:,j*2] = y_test**2
train_[:, j+1] = np.exp(y_train)
test_[:, j+1] = np.exp(y_test)
# print("val auc Score: %f" % r2_score(y_predict, dataset_d2[:, j]))
print('Method ',j)
train_ = pd.DataFrame(train_)
test_ = pd.DataFrame(test_)
return train_,test_
from sklearn.model_selection import cross_val_score, train_test_split
from sklearn.linear_model import LogisticRegression
clf = LogisticRegression()
data_0 = iris.data
data = data_0[:100,:]
target_0 = iris.target
target = target_0[:100]
x_train,x_test,y_train,y_test=train_test_split(data,target,test_size=0.3)
x_train = pd.DataFrame(x_train) ; x_test = pd.DataFrame(x_test)
#模型融合中使用到的各个单模型
clfs = [LogisticRegression(),
RandomForestClassifier(n_estimators=5, n_jobs=-1, criterion='gini'),
ExtraTreesClassifier(n_estimators=5, n_jobs=-1, criterion='gini'),
ExtraTreesClassifier(n_estimators=5, n_jobs=-1, criterion='entropy'),
GradientBoostingClassifier(learning_rate=0.05, subsample=0.5, max_depth=6, n_estimators=5)]
New_train,New_test = Ensemble_add_feature(x_train,x_test,y_train,clfs)
clf = LogisticRegression()
# clf = GradientBoostingClassifier(learning_rate=0.02, subsample=0.5, max_depth=6, n_estimators=30)
clf.fit(New_train, y_train)
y_emb = clf.predict_proba(New_test)[:, 1]
print("Val auc Score of stacking: %f" % (roc_auc_score(y_test, y_emb)))
四、经验总结
比赛的融合这个问题,个人的看法来说其实涉及多个层面,也是提分和提升模型鲁棒性的一种重要方法:
1)结果层面的融合,这种是最常见的融合方法,其可行的融合方法也有很多,比如根据结果的得分进行加权融合,还可以做Log,exp处理等。在做结果融合的时候,有一个很重要的条件是模型结果的得分要比较近似,然后结果的差异要比较大,这样的结果融合往往有比较好的效果提升。
2)特征层面的融合,这个层面其实感觉不叫融合,准确说可以叫分割,很多时候如果我们用同种模型训练,可以把特征进行切分给不同的模型,然后在后面进行模型或者结果融合有时也能产生比较好的效果。
3)模型层面的融合,模型层面的融合可能就涉及模型的堆叠和设计,比如加Staking层,部分模型的结果作为特征输入等,这些就需要多实验和思考了,基于模型层面的融合最好不同模型类型要有一定的差异,用同种模型不同的参数的收益一般是比较小的。