零基础入门数据挖掘：Task4 建模与调参

Stacking

简单来说 stacking 就是当用初始训练数据学习出若干个基学习器后，将这几个学习器的预测结果作为新的训练集，来学习一个新的学习器。 开始实践，总之先导入数据和库

import pandas as pd
import numpy as np
import warnings
warnings.filterwarnings('ignore')

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 = [1, 3, 2, 6] 

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
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))

Pred1 MAE: 0.175
Pred2 MAE: 0.075
Pred3 MAE: 0.1

w = [0.3,0.4,0.3] 
Weighted_pre = Weighted_method(test_pre1,test_pre2,test_pre3,w)
print('Weighted_pre MAE:',metrics.mean_absolute_error(y_test_true, Weighted_pre))

Weighted_pre MAE: 0.0575

Stacking融合

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

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_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 = [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))

Stacking_pre MAE: 0.0421348314607

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

Voting投票机制
硬投票

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))

Accuracy: 0.97 (+/- 0.02) [XGBBoosting]
Accuracy: 0.33 (+/- 0.00) [Random Forest]
Accuracy: 0.95 (+/- 0.03) [SVM]
Accuracy: 0.94 (+/- 0.04) [Ensemble]

软投票

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))

Accuracy: 0.96 (+/- 0.02) [XGBBoosting]
Accuracy: 0.33 (+/- 0.00) [Random Forest]
Accuracy: 0.95 (+/- 0.03) [SVM]
Accuracy: 0.96 (+/- 0.02) [Ensemble]

分类的Stacking融合

!pip install mlxtend

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()

https://tianchi.aliyun.com/notebook-ai/detail?spm=5176.12586969.1002.3.1cd8593aw4bbL5&postId=95535