决策树和随机森林对比

1.用accuracy来对比

# -*-coding:utf-8-*-

"""
accuracy来对比决策树和随机森林
"""
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.datasets import load_wine

#(178, 13)
wine=load_wine()
# print(wine.data.shape)
print(wine.target)
from sklearn.model_selection import train_test_split
Xtrain,Xtest,Ytrain,Ytest=train_test_split(wine.data,wine.target,test_size=0.3)

clf=DecisionTreeClassifier(random_state=0)
rfc=RandomForestClassifier(random_state=0)

clf=clf.fit(Xtrain,Ytrain)
rfc=rfc.fit(Xtrain,Ytrain)

#score就是accuracy
score_c=clf.score(Xtest,Ytest)
score_rfc=rfc.score(Xtest,Ytest)

print("Single Tree:{}".format(score_c),
      "Random Forest:{}".format(score_rfc))

Single Tree:0.8703703703703703 Random Forest:1.0

2.交叉熵验证对比

# -*-coding:utf-8-*-
"""
交叉熵来对比决策树和随机森林
"""
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.datasets import load_wine
from sklearn.model_selection import cross_val_score
import matplotlib.pyplot as plt
plt.switch_backend("TkAgg")
#(178, 13)
wine=load_wine()
# print(wine.data.shape)
print(wine.target)
from sklearn.model_selection import train_test_split
Xtrain,Xtest,Ytrain,Ytest=train_test_split(wine.data,wine.target,test_size=0.3)

rfc=RandomForestClassifier(n_estimators=25)
rfc_s=cross_val_score(rfc,wine.data,wine.target,cv=10)

clf=DecisionTreeClassifier()
clf_s=cross_val_score(clf,wine.data,wine.target,cv=10)


plt.plot(range(1,11),rfc_s,label="RandomForest")
plt.plot(range(1,11),clf_s,label="DecisionTree")
plt.legend()
plt.show()

3.多次平均交叉熵对比

# -*-coding:utf-8-*-

"""
交叉熵平均来对比决策树和随机森林
"""
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.datasets import load_wine
from sklearn.model_selection import cross_val_score
import matplotlib.pyplot as plt
plt.switch_backend("TkAgg")
#(178, 13)
wine=load_wine()
# print(wine.data.shape)
print(wine.target)
from sklearn.model_selection import train_test_split
Xtrain,Xtest,Ytrain,Ytest=train_test_split(wine.data,wine.target,test_size=0.3)

rfc_mc=[]
clf_mc=[]

for i in range(10):
    rfc=RandomForestClassifier(n_estimators=25)
    rfc_s=cross_val_score(rfc,wine.data,wine.target,cv=10).mean()
    rfc_mc.append(rfc_s)

    clf=DecisionTreeClassifier()
    clf_s=cross_val_score(clf,wine.data,wine.target,cv=10).mean()
    clf_mc.append(clf_s)

plt.plot(range(1,11),rfc_mc,label="Random Forest")
plt.plot(range(1,11),clf_mc,label="Decision Tree")
plt.legend()
plt.show()

4.选择合适的estimators

为随机森林选择合适的决策树的数量

# -*-coding:utf-8-*-
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.datasets import load_wine
from sklearn.model_selection import cross_val_score
import matplotlib.pyplot as plt
plt.switch_backend("TkAgg")
#(178, 13)
wine=load_wine()
# print(wine.data.shape)
print(wine.target)
from sklearn.model_selection import train_test_split
Xtrain,Xtest,Ytrain,Ytest=train_test_split(wine.data,wine.target,test_size=0.3)

superpa=[]
for i in range(200):
    rfc=RandomForestClassifier(n_estimators=i+1,n_jobs=-1)
    rfc_s=cross_val_score(rfc,wine.data,wine.target,cv=10).mean()
    superpa.append(rfc_s)
print(max(superpa),superpa.index(max(superpa))+1)
plt.figure(figsize=[20,5])
plt.plot(range(1,201),superpa)
plt.show()