机器学习之集成学习和随机森林

 

 

 

"""集成学习"""
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.ensemble import VotingClassifier


X,y=datasets.make_moons(n_samples=500,noise=0.3,random_state=42)
X_train,X_test,y_train,y_test=train_test_split(X,y,random_state=42)

"""使用Hard Voting Classifier"""
voting_clf=VotingClassifier(estimators=[
    ('log_clf',LogisticRegression()),
    ('svm_clf',SVC()),
    ('dt_clf',DecisionTreeClassifier())
],voting='hard')#hard表示少数服从多数
voting_clf.fit(X_train,y_train)
print(voting_clf.score(X_test,y_test))

"""Soft Voting Classifier"""
voting_clf2=VotingClassifier(estimators=[
    ('log_clf',LogisticRegression()),
    ('svm_clf',SVC(probability=True)),
    ('dt_clf',DecisionTreeClassifier())
],voting='soft')#hard表示少数服从多数
voting_clf2.fit(X_train,y_train)
print(voting_clf2.score(X_test,y_test))

结果：

0.896
0.936

 

 

 

 

"""集成学习"""
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.ensemble import VotingClassifier


X,y=datasets.make_moons(n_samples=500,noise=0.3,random_state=42)
X_train,X_test,y_train,y_test=train_test_split(X,y,random_state=42)


"""使用Bagging"""
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import BaggingClassifier

bagging_clf=BaggingClassifier(DecisionTreeClassifier(),
                              n_estimators=500,max_samples=100,
                              bootstrap=True)
bagging_clf.fit(X_train,y_train)
print(bagging_clf.score(X_test,y_test))

bagging_clf2=BaggingClassifier(DecisionTreeClassifier(),
                              n_estimators=5000,max_samples=100,
                              bootstrap=True)
bagging_clf2.fit(X_train,y_train)
print(bagging_clf2.score(X_test,y_test))

 结果：

E:\pythonspace\KNN_function\venv\Scripts\python.exe E:/pythonspace/KNN_function/try.py
E:\pythonspace\KNN_function\venv\lib\site-packages\sklearn\ensemble\weight_boosting.py:29: DeprecationWarning: numpy.core.umath_tests is an internal NumPy module and should not be imported. It will be removed in a future NumPy release.
  from numpy.core.umath_tests import inner1d
0.912
0.92

Process finished with exit code 0

理论上划分的子模型数量越多 ，结果越准确。

 

 

 

"""随机森林和Extra-Trees"""
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)

"""随机森林"""
from sklearn.ensemble import RandomForestClassifier

rf_clf=RandomForestClassifier(n_estimators=500,random_state=666,max_leaf_nodes=16,oob_score=True)
rf_clf.fit(X,y)
print(rf_clf.oob_score_)

"""使用Extra-Trees"""
from sklearn.ensemble import ExtraTreesClassifier
et_clf=ExtraTreesClassifier(n_estimators=500,bootstrap=True,oob_score=True)
et_clf.fit(X,y)
print(et_clf.oob_score_)


"""集成学习解决回归问题"""
from sklearn.ensemble import BaggingRegressor
from sklearn.ensemble import RandomForestRegressor
from sklearn.ensemble import ExtraTreesRegressor

 

"""AdaBoosting"""
from sklearn.ensemble import AdaBoostClassifier
from sklearn.tree import DecisionTreeClassifier
ada_clf=AdaBoostClassifier(DecisionTreeClassifier(max_depth=2),n_estimators=500)
ada_clf.fit(X_tarin,y_train)
print(ada_clf.score(X_test,y_test))

 

"""Gradient Boosting"""
from sklearn.ensemble import GradientBoostingClassifier
gb_clf=GradientBoostingClassifier(max_depth=2,n_estimators=500)
gb_clf.fit(X_train,y_train)
print(gb_clf.score(X_test,y_test))