天池二手车交易价格预测-task[5]-模型融合
集成模型往往在数据比赛中会有比较好的成绩
主要包括以下三种方法：
- 投票集成
- 平均
- 排名平均
1.简单加权平均
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
2.mean平均，median平均
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))
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))
3.stacking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]
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))
4.Voting投票机制
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)
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))
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)
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))
5.分类stacking融合
from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import ExtraTreesClassifier,GradientBoostingClassifier
import pandas as pd
data_0 = iris.data
data = data_0[:100,:]
target_0 = iris.target
target = target_0[:100]
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)]
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)))
n_splits = 5
skf = StratifiedKFold(n_splits)
skf = skf.split(X, y)
for j, clf in enumerate(clfs):
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)))