def test_auto_norm(self):
date_mat, date_label = knn.file2matrix('datingTestSet2.txt')
norm_mat, ranges, min_val = knn.auto_norm(date_mat)
min_exp = np.array([0., 0., 0.001156])
ranges_exp = np.array([9.1273000e+04, 2.0919349e+01, 1.6943610e+00])
self.assertEqual(True, (min_exp == min_val).all())
self.assertEqual(True, (ranges == ranges_exp).all())
def classify_gui(k):
"""
:param k: k值
:return:人群分类
"""
data_mat, class_label_vector = file_to_matrix('../data/dating_test_set_2.txt')
fly_distances = float(input("请输入飞行里程数："))
icecream = float(input("请输入消耗冰淇淋公升数："))
play_time = float(input("请输入玩游戏花费时间百分比："))
norm_data_set, ranges, min_vals = auto_norm(data_mat)
data_person=np.array([fly_distances,icecream,play_time])
norm_person_data=(data_person-min_vals)/ranges
class_person=['不喜欢','一般','极具魅力']
label_person=classify(norm_person_data,norm_data_set,class_label_vector,k)
return class_person[label_person-1]
def classify_person():
"""
对给定的数据进行人群分类判断
:return:
"""
#定义人群分类：[0，1，2]
ff_miles=float(input("每年飞行常客里程数："))
ice_cream=float(input('每周消耗的冰淇淋公升数：'))
percent_game=float(input('玩游戏所消耗的时间百分比：'))
data_mat,class_label_vector=file_to_matrix('../data/dating_test_set_2.txt')
norm_dating_data_set,ranges,min_vals=auto_norm(data_mat)
in_x=np.array([ff_miles,ice_cream,percent_game]) #待验证数据
norm_in_x=(in_x-min_vals)/(ranges)
classify_result=classify(norm_in_x,norm_dating_data_set,class_label_vector,3)
return classify_result
def dating_class_test():
"""
应用测试集测试分类机的错误率
:return: None
"""
hold_out_ratio = 0.10 #拿出作为测试集的数据比例
data_set,labels = file_to_matrix('./data/dating_test_set_2.txt')
norm_data_set,ranges,min_vals=auto_norm(data_set)
size=norm_data_set.shape[0] #获得数据集行数
num_test_size = int(size * hold_out_ratio) #保留行数
error_count = 0.0 #错误统计
for i in range(num_test_size):
classifier_result=classify(norm_data_set[i,:],norm_data_set[num_test_size:size],labels[num_test_size:size],5)
print('分类器返回：%d, 真实答案为：%d'% (classifier_result,labels[i]))
if classifier_result!= labels[i]:
error_count+=1.0
print('分类器错误率为：%0.2f%%' % (error_count/(float(num_test_size))*100))
def test_main_dating(self):
test_ratio = 0.50
dataset_matrix, labels = knn.read_matrix('dating/dataset.txt')
norm_matrix, ranges, min_value = knn.auto_norm(dataset_matrix)
size = norm_matrix.shape[0]
test_num = int(size * test_ratio)
err_count = 0.0
for i in range(test_num):
classifier_result = knn.classify0(norm_matrix[i, :],
norm_matrix[test_num:size,:],
labels[test_num:size],
3)
print "predict: %d real: %d" % (classifier_result, labels[i])
if classifier_result != labels[i]:
err_count += 1.0
err_rate = err_count / float(test_num)
print 'total: %d error: %d rate: %f' % (test_num, err_count, err_rate)