- 逻辑回归
from pandas import read_csv
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.linear_model import LogisticRegression
filename='/home/duan/文档/pima indians.txt'
names=['preg','plas','pres','skin','test','mass','pedi','age','class']
data=read_csv(filename,names=names)
array= data.values
X= array[:,0:8]
Y= array[:,8]
num_folds=10
seed=7
kfold=KFold(n_splits=num_folds, random_state=seed)
model=LogisticRegression()
result=cross_val_score(model,X,Y,cv=kfold)
print(result.mean())
运行结果为:
0.7695146958304853
2.线性判别分析
## LDA
from pandas import read_csv
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
filename='/home/duan/文档/pima indians.txt'
names=['preg','plas','pres','skin','test','mass','pedi','age','class']
data=read_csv(filename,names=names)
array= data.values
X= array[:,0:8]
Y= array[:,8]
num_folds=10
seed=7
kfold=KFold(n_splits=num_folds, random_state=seed)
model=LinearDiscriminantAnalysis()
result=cross_val_score(model,X,Y,cv=kfold)
print(result.mean())
0.773462064251538
3.K近邻
##K近邻算法
from pandas import read_csv
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.neighbors import KNeighborsClassifier
filename='/home/duan/文档/pima indians.txt'
names=['preg','plas','pres','skin','test','mass','pedi','age','class']
data=read_csv(filename,names=names)
array= data.values
X= array[:,0:8]
Y= array[:,8]
num_folds=10
seed=7
kfold=KFold(n_splits=num_folds, random_state=seed)
model=KNeighborsClassifier()
result=cross_val_score(model,X,Y,cv=kfold)
print(result.mean())
运行结果:
0.7265550239234451
4.贝叶斯分类器
##贝叶斯分类器
from pandas import read_csv
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.naive_bayes import GaussianNB
filename='/home/duan/文档/pima indians.txt'
names=['preg','plas','pres','skin','test','mass','pedi','age','class']
data=read_csv(filename,names=names)
array= data.values
X= array[:,0:8]
Y= array[:,8]
num_folds=10
seed=7
kfold=KFold(n_splits=num_folds, random_state=seed)
model=GaussianNB()
result=cross_val_score(model,X,Y,cv=kfold)
print(result.mean())
运行结果:
0.7551777170198223
5.分类树与回归树
##分类树与回归树
from pandas import read_csv
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.tree import DecisionTreeClassifier
filename='/home/duan/文档/pima indians.txt'
names=['preg','plas','pres','skin','test','mass','pedi','age','class']
data=read_csv(filename,names=names)
array= data.values
X= array[:,0:8]
Y= array[:,8]
num_folds=10
seed=7
kfold=KFold(n_splits=num_folds, random_state=seed)
model=DecisionTreeClassifier()
result=cross_val_score(model,X,Y,cv=kfold)
print(result.mean())
运行结果:
0.6860902255639098
6.SVM
##SVM
from pandas import read_csv
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.svm import SVC
filename='/home/duan/文档/pima indians.txt'
names=['preg','plas','pres','skin','test','mass','pedi','age','class']
data=read_csv(filename,names=names)
array= data.values
X= array[:,0:8]
Y= array[:,8]
num_folds=10
seed=7
kfold=KFold(n_splits=num_folds, random_state=seed)
model=SVC()
result=cross_val_score(model,X,Y,cv=kfold)
print(result.mean())
运行结果:
0.6510252904989747