In [1]:

    

#支持向量机 根据训练样本的分布搜索所有可能分类器中最佳的那个
from sklearn.datasets import load_iris
digits = load_iris()


    

In [2]:

    

digits.data.shape


    

    
Out[2]:





(150, 4)

In [4]:

    

#切分训练集和测试集
from sklearn.cross_validation import train_test_split


    

In [5]:

    

X_train,Xtest,Y_Train,Y_test=train_test_split(digits.data,
                                             digits.target,
                                            test_size=0.25,
                                             random_state=33)


    

In [6]:

    

Y_Train.shape


    

    
Out[6]:





(112,)

In [7]:

    

Y_test.shape


    

    
Out[7]:





(38,)

In [8]:

    

#导入标准化模块, 标准化数据
from sklearn.preprocessing import StandardScaler
from sklearn.svm import LinearSVC


    

In [9]:

    

ss = StandardScaler()


    

In [10]:

    

X_train = ss.fit_transform(X_train)


    

In [11]:

    

Xtest = ss.transform(Xtest)


    

In [12]:

    

lsvc = LinearSVC()


    

In [13]:

    

lsvc.fit(X_train, Y_Train)


    

    
Out[13]:





LinearSVC(C=1.0, class_weight=None, dual=True, fit_intercept=True,
     intercept_scaling=1, loss='squared_hinge', max_iter=1000,
     multi_class='ovr', penalty='l2', random_state=None, tol=0.0001,
     verbose=0)

In [14]:

    

ypredic = lsvc.predict(Xtest)


    

In [15]:

    

#准确性评估
print 'The Accuracy of Linear SVC is',lsvc.score(Xtest, Y_test)


    

    




The Accuracy of Linear SVC is 0.921052631579

In [16]:

    

from sklearn.metrics import classification_report


    

In [17]:

    

print classification_report(Y_test, ypredic, target_names=digits.target_names.astype(str))


    

    




             precision    recall  f1-score   support

     setosa       1.00      1.00      1.00         8
 versicolor       0.83      0.91      0.87        11
  virginica       0.94      0.89      0.92        19

avg / total       0.92      0.92      0.92        38

In [ ]: