Python3入门机器学习经典算法与应用——集成学习

集成学习

kNN

逻辑回归

SVM
			---->投票，少数服从多数
决策树

神经网络

贝叶斯

用numpy实现

什么是集成学习

import numpy as np
import matplotlib.pyplot as plt

from sklearn import datasets

X, y = datasets.make_moons(n_samples=500, noise=0.3, random_state=42)

plt.scatter(X[y==0,0], X[y==0,1])
plt.scatter(X[y==1,0], X[y==1,1])
plt.show()

from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42)

# 逻辑回归预测
from sklearn.linear_model import LogisticRegression

log_clf = LogisticRegression()
log_clf.fit(X_train, y_train)
log_clf.score(X_test, y_test)

0.864

# SVM预测
from sklearn.svm import SVC

svm_clf = SVC()
svm_clf.fit(X_train, y_train)
svm_clf.score(X_test, y_test)

0.896

# 决策树预测
from sklearn.tree import DecisionTreeClassifier

dt_clf = DecisionTreeClassifier(random_state=666)
dt_clf.fit(X_train, y_train)
dt_clf.score(X_test, y_test)

0.864

# 结果
y_predict1 = log_clf.predict(X_test)
y_predict2 = svm_clf.predict(X_test)
y_predict3 = dt_clf.predict(X_test)

# 投票得到最终结果，大于等于2，结果为1，否则为0
y_predict = np.array((y_predict1 + y_predict2 + y_predict3) >= 2, dtype='int')

y_predict[:10]

array([1, 0, 0, 1, 1, 1, 0, 0, 0, 0])

from sklearn.metrics import accuracy_score

# 最终的准确率
accuracy_score(y_test, y_predict)

0.904

使用Voting Classifier

from sklearn.ensemble import VotingClassifier

voting_clf = VotingClassifier(estimators=[
    ('log_clf', LogisticRegression()), 
    ('svm_clf', SVC()),
    ('dt_clf', DecisionTreeClassifier(random_state=666))],
                             voting='hard')

voting_clf.fit(X_train, y_train)
voting_clf.score(X_test, y_test)

0.904