前言
本节学习集成学习
1、原理
集成学习
- 几种机器学习算法都跑一遍
- 少数服从多数决定结果
scikit中
- hard:一人一票
- soft:有权重,每种算法做出结果的概率
差异性
- 每个子模型只看样本数据一部分
- 每个子模型不需要太高的准确率
- bagging:放回取样
- pasting:不放回取样
随机森林
- 决策树在节点划分上,在随机的特征子集上寻找最优划分特征
2、实现
import numpy as np
import matplotlib.pyplot as plt
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.svm import SVC
from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import accuracy_score
"""集成学习"""
# 数据
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()
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42)
# 逻辑回归
log_clf = LogisticRegression()
log_clf.fit(X_train, y_train)
print(log_clf.score(X_test, y_test))
# SVM
svm_clf = SVC()
svm_clf.fit(X_train, y_train)
print(svm_clf.score(X_test, y_test))
# 决策树
dt_clf = DecisionTreeClassifier(random_state=666)
dt_clf.fit(X_train, y_train)
print(dt_clf.score(X_test, y_test))
# 集成学习(投票)
y_predict1 = log_clf.predict(X_test)
y_predict2 = svm_clf.predict(X_test)
y_predict3 = dt_clf.predict(X_test)
y_predict = np.array((y_predict1 + y_predict2 + y_predict3) >= 2, dtype='int') #少数服从多数
print(accuracy_score(y_test, y_predict))
"""使用scikit库实现集成学习"""
from sklearn.ensemble import VotingClassifier
# 使用 Hard Voting Classifier
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)
print(voting_clf.score(X_test, y_test))
# 使用 Soft Voting Classifier
voting_clf2 = VotingClassifier(estimators=[
('log_clf', LogisticRegression()),
('svm_clf', SVC(probability=True)), #计算结果概率
('dt_clf', DecisionTreeClassifier(random_state=666))],
voting='soft')
voting_clf2.fit(X_train, y_train)
print(voting_clf2.score(X_test, y_test))
# 使用 bagging
from sklearn.ensemble import BaggingClassifier
bagging_clf = BaggingClassifier(DecisionTreeClassifier(),
n_estimators=500, max_samples=100,
bootstrap=True) #bootstrap决定取样后放不放回
bagging_clf.fit(X_train, y_train)
print(bagging_clf.score(X_test, y_test))
# oob和n_jobs
bagging_clf = BaggingClassifier(DecisionTreeClassifier(),
n_estimators=500, max_samples=100,
bootstrap=True, oob_score=True,
n_jobs=-1) #oob保证所有样本都能被抽取到,n_jobs进行并行运算
bagging_clf.fit(X, y)
print(bagging_clf.oob_score_)
# 对特征随机采样
random_patches_clf = BaggingClassifier(DecisionTreeClassifier(),
n_estimators=500, max_samples=100,
bootstrap=True, oob_score=True,
max_features=1, bootstrap_features=True)
random_patches_clf.fit(X, y)
print(random_patches_clf.oob_score_)
"""随机森林"""
from sklearn.ensemble import RandomForestClassifier
rf_clf = RandomForestClassifier(n_estimators=500, max_leaf_nodes=16, oob_score=True, random_state=666, n_jobs=-1) #随机森林拥有决策树和BaggingClassifier的所有参数
rf_clf.fit(X, y)
print(rf_clf.oob_score_)
结语
传统的机器学习
大多过了一遍
后续会继续深入学习