集成学习voting Classifier在sklearn中的实现

from sklearn import datasets
from sklearn.model_selection import cross_val_score
from sklearn.linear_model import LogisticRegression
from sklearn.naive_bayes import GaussianNB
from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import VotingClassifier

iris = datasets.load_iris()
X, y = iris.data[:,1:3], iris.target
clf1 = LogisticRegression(random_state=1)
clf2 = RandomForestClassifier(random_state=1)
clf3 = GaussianNB()

eclf = VotingClassifier(estimators=[(‘lr‘,clf1),(‘rf‘,clf2),(‘gnb‘,clf3)], voting=‘hard‘)
#使用投票法将三个模型结合在以前，estimotor采用 [(name1,clf1),(name2,clf2),...]这样的输入，和Pipeline的输入相同 voting=‘hard‘表示硬投票

for clf, clf_name in zip([clf1, clf2, clf3, eclf],[‘Logistic Regrsssion‘, ‘Random Forest‘, ‘naive Bayes‘, ‘Ensemble‘]):
    scores = cross_val_score(clf, X, y, cv=5, scoring=‘accuracy‘)
    print(‘Accuracy: {:.2f} (+/- {:.2f}) [{}]‘.format(scores.mean(), scores.std(), clf_name))

Accuracy: 0.90 (+/- 0.05) [Logistic Regrsssion]
Accuracy: 0.93 (+/- 0.05) [Random Forest]
Accuracy: 0.91 (+/- 0.04) [naive Bayes]
Accuracy: 0.95 (+/- 0.05) [Ensemble]

实际当中会报：DeprecationWarning

from itertools import product

import numpy as np
import matplotlib.pyplot as plt

from sklearn import datasets
from sklearn.tree import DecisionTreeClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.svm import SVC
from sklearn.ensemble import VotingClassifier

iris = datasets.load_iris()
X = iris.data[:,[0,2]] #取两列，方便绘图
y = iris.target

clf1 = DecisionTreeClassifier(max_depth=4)
clf2 = KNeighborsClassifier(n_neighbors=7)
clf3 = SVC(kernel=‘rbf‘, probability=True)
eclf = VotingClassifier(estimators=[(‘dt‘,clf1),(‘knn‘,clf2),(‘svc‘,clf3)], voting=‘soft‘, weights=[2,1,1])
#weights控制每个算法的权重, voting=’soft‘ 使用了软权重


clf1.fit(X,y)
clf2.fit(X,y)
clf3.fit(X,y)
eclf.fit(X,y)

x_min, x_max = X[:,0].min() -1, X[:,0].max() + 1
y_min, y_max = X[:,1].min() -1, X[:,1].max() + 1
xx, yy = np.meshgrid(np.arange(x_min, x_max, 0.01), np.arange(y_min, y_max, 0.01))  #创建网格

fig, axes = plt.subplots(2, 2, sharex=‘col‘, sharey=‘row‘, figsize=(10, 8)) #共享X轴和Y轴

for idx, clf, title in zip(product([0, 1],[0, 1]),
                           [clf1, clf2, clf3, eclf],
                           [‘Decision Tree (depth=4)‘, ‘KNN (k=7)‘,
                            ‘Kernel SVM‘, ‘Soft Voting‘]):
    Z = clf.predict(np.c_[xx.ravel(), yy.ravel()]) #起初我以为是预测的X的值，实际上是预测了上面创建的网格的值，以这些值来进行描绘区域
    Z = Z.reshape(xx.shape)
    axes[idx[0], idx[1]].contourf(xx, yy, Z, alpha=0.4)
    axes[idx[0], idx[1]].scatter(X[:, 0],X[:, 1], c=y, s=20, edgecolor=‘k‘)
    axes[idx[0], idx[1]].set_title(title)
plt.show()