sklearn

1.GaussianNB

# -*- coding: utf-8 -*-
"""
Created on Wed Jun 20 19:23:06 2018

@author: 12046
"""

from sklearn import datasets,cross_validation  
from sklearn.naive_bayes import GaussianNB  
from sklearn.svm import SVC
from sklearn.ensemble import RandomForestClassifier  
from sklearn import metrics  

x,y=datasets.make_classification(n_samples=1000,n_features=10,n_classes=2)  
kf=cross_validation.KFold(len(x),n_folds=10,shuffle=True)  

  
for train_index,test_index in kf:    
    x_train,y_train=x[train_index],y[train_index]  
    x_test,y_test=x[test_index],y[test_index]  
  
clf=GaussianNB()
clf.fit(x_train,y_train)
pred=clf.predict(x_test)  

acc = metrics.accuracy_score(y_test, pred)  
print("Accuracy_score: "+str(acc))  
f1 = metrics.f1_score(y_test, pred)  
print("f1_score: "+str(f1))  
auc = metrics.roc_auc_score(y_test, pred)  
print("roc_auc_score: "+str(auc))  

结果如下图

2.SVC

# -*- coding: utf-8 -*-
"""
Created on Wed Jun 20 19:23:06 2018

@author: 12046
"""

from sklearn import datasets,cross_validation  
from sklearn.naive_bayes import GaussianNB  
from sklearn.svm import SVC
from sklearn.ensemble import RandomForestClassifier  
from sklearn import metrics  

x,y=datasets.make_classification(n_samples=1000,n_features=10,n_classes=2)  
kf=cross_validation.KFold(len(x),n_folds=10,shuffle=True)  

  
for train_index,test_index in kf:    
    x_train,y_train=x[train_index],y[train_index]  
    x_test,y_test=x[test_index],y[test_index]  
  
Cvalues=[1e-02, 1e-01, 1e00, 1e01, 1e02]
for C in Cvalues:
    clf = SVC(C=1e-01, kernel='rbf', gamma=0.1)
    clf.fit(x_train, y_train)
    pred = clf.predict(x_test)

    print("C:"+str(C))
    acc = metrics.accuracy_score(y_test, pred)  
    print("Accuracy_score: "+str(acc))  
    f1 = metrics.f1_score(y_test, pred)  
    print("f1_score: "+str(f1))  
    auc = metrics.roc_auc_score(y_test, pred)  
    print("roc_auc_score: "+str(auc))  
    print()

结果如下

3.RandomForestClassifier

# -*- coding: utf-8 -*-
"""
Created on Wed Jun 20 19:23:06 2018

@author: 12046
"""

from sklearn import datasets,cross_validation  
from sklearn.naive_bayes import GaussianNB  
from sklearn.svm import SVC
from sklearn.ensemble import RandomForestClassifier  
from sklearn import metrics  

x,y=datasets.make_classification(n_samples=1000,n_features=10,n_classes=2)  
kf=cross_validation.KFold(len(x),n_folds=10,shuffle=True)  

  
for train_index,test_index in kf:    
    x_train,y_train=x[train_index],y[train_index]  
    x_test,y_test=x[test_index],y[test_index]  
  
n_estimators_values=[10,100,1000]
for n_estimators in n_estimators_values:
    clf = RandomForestClassifier(n_estimators)
    clf.fit(x_train, y_train)
    pred = clf.predict(x_test)

    print("n_estimators: "+str(n_estimators))
    acc = metrics.accuracy_score(y_test, pred)  
    print("Accuracy_score: "+str(acc))  
    f1 = metrics.f1_score(y_test, pred)  
    print("f1_score: "+str(f1))  
    auc = metrics.roc_auc_score(y_test, pred)  
    print("roc_auc_score: "+str(auc))  
    print()

分析：三种模型的预测效果都差不多