這篇文章主要講解了如何利用SVM分類。並用在輸出分類精度的同時輸出混淆矩陣。
注意x_train,y_train,x_test,y_test,資料集需要用自己的資料，其中x為多維矩陣，y為類別列表

# coding=utf-8

import numpy as np
from PIL import Image
from sklearn import svm
# 使用交叉驗證的方法，把資料集分為訓練集合測試集
from sklearn.cross_validation import train_test_split

from merge import x_train,y_train,x_test,y_test,X_test

def
 
 test_LinearSVC(train,label,testdata):
    # 選擇模型
    cls = svm.LinearSVC()
    # 把資料交給模型訓練
    cls.fit(train,label.astype('int'))

    # 預測資料
    #print(cls.predict(testdata))
    results=cls.predict(testdata)
    return results

#輸出混淆矩陣
from sklearn.metrics import confusion_matrix
def my_confusion_matrix
 
(y_true, y_pred):
    labels = list(set(y_true))
    conf_mat = confusion_matrix(list(y_true), list(y_pred), labels = labels)
    print ("confusion_matrix(left labels: y_true, up labels: y_pred):")
    print ("labels"," ",end='')
    for i in range(len(labels)):
        print (labels[i]," ",end='')
    print('\n'
 
)
    for i in range(len(conf_mat)):
        print (i," ",end='')
        for j in range(len(conf_mat[i])):
            print (conf_mat[i][j]," ",end='')
        print('\n')
    print


if __name__=="__main__":

    #測試集分類結果---列表
    y_pred = test_LinearSVC(x_train,y_train,x_test)
    label_list = [int(i) for i in y_test]

    #測試集合的精度
    kk = 0
    for i in range(len(y_test)):
        if (y_pred[i] == y_test[i]):
            kk = kk + 1
    print('acc rate is %f' % float(kk / len(y_test)))
    a = list(y_test[:40])
    b = list(y_pred[:40])
    my_confusion_matrix(y_test, y_pred) # 輸出混淆矩陣