Python opencv 机器学习 3.knn k近邻 ocr识别字符 使用letter-recognition.data（opencv自带）

import cv2
import numpy as np
import matplotlib.pyplot as plt

data = np.loadtxt('letter-recognition.data', dtype='float32', delimiter=',',
                  converters={0: lambda ch: ord(ch)-ord('A')})

# 将数据分为两部分，各10000个，分别为训练数据和测试数据
train, test = np.vsplit(data, 2)

response, trainData = np.hsplit(train, [1])
labels, testData = np.hsplit(test, [1])

# 初始化knn,测试准确率
knn = cv2.ml.KNearest_create()
knn.train(trainData, cv2.ml.ROW_SAMPLE, response)
ret, result, neighbours, dist = knn.findNearest(testData, k=5)

correct = np.count_nonzero(result == labels)
accuracy = correct*100.0/10000
print(accuracy)