def KNN(testData, testLabel, trainData, trainLabel):
# 使用二折交叉验证
missCount = 0
print('开始时间:', time.strftime('%Y-%m-%d %H:%M:%S'))
start = time.time()
for i in range(testData.shape[0]):
out = knn.kNNClassify(testData[i], trainData, trainLabel, 1)
if out != testLabel[i]:
missCount += 1
t = testData
testData = trainData
trainData = t
t = testLabel
testLabel = trainLabel
trainLabel = t
for i in range(testData.shape[0]):
out = knn.kNNClassify(testData[i], trainData, trainLabel, 1)
if out != testLabel[i]:
missCount += 1
# 运行结果显示
print('结束时间:', time.strftime('%Y-%m-%d %H:%M:%S'))
end = time.time()
print('test dataset total:',
len(testLabel) + len(trainLabel), ',miss count:', missCount,
',correct ratio:',
1 - missCount / (len(testLabel) + len(trainLabel)), ',miss ratio:',
missCount / (len(testLabel) + len(trainLabel)), ',spend:',
end - start)
def testHandWritingClass(datapath): print "step 1: load data..." train_x, train_y, test_x, test_y = loadDataSet(datapath) print "step 2: training..." pass print "step 3: testing..." numTestSamples = test_x.shape[0] matchCount = 0 for i in xrange(numTestSamples): predict = knn.kNNClassify(test_x[i], train_x, train_y, 3) if predict == test_y[i]: matchCount += 1 accuracy = float(matchCount) / numTestSamples print "step 4: show the result..." print 'The classify accuracy is: %.2f%%' % (accuracy * 100)
def testHandWritingClass(datapath):
print "step 1: load data..."
train_x, train_y, test_x, test_y = loadDataSet(datapath)
print "step 2: training..."
pass
print "step 3: testing..."
numTestSamples = test_x.shape[0]
matchCount = 0
for i in xrange(numTestSamples):
predict = knn.kNNClassify(test_x[i], train_x, train_y, 3)
if predict == test_y[i]:
matchCount += 1
accuracy = float(matchCount) / numTestSamples
print "step 4: show the result..."
print 'The classify accuracy is: %.2f%%' % (accuracy * 100)
import knn
from numpy import *
#生成数据集和类别标签
dataSet,labels = knn.createDataSet()
#定义一个未知类别的数据
testX = array([5.9, 3.1, 5.1, 1.8])
k=3
#调用分类函数对未知数据分类
outputLabel = knn.kNNClassify(testX, dataSet, labels, 3)
print("Your input is:", testX, " and classified to class:", outputLabel)
# Load training examples and tesing examples
print('hello')
X_train = loadImageSet('E:\\PY\\hand\\train-images.idx3-ubyte')
X_train = X_train.reshape(60000, 784)
y_train = loadLabelSet('E:\\PY\\hand\\train-labels.idx1-ubyte')
y_train = y_train.ravel()
X_test = loadImageSet('E:\\PY\\hand\\t10k-images.idx3-ubyte')
X_test = X_test.reshape(10000, 784)
y_test = loadLabelSet('E:\\PY\\hand\\t10k-labels.idx1-ubyte')
length = X_test.shape[0]
count = 0
for i in range(0, length):
if (kNNClassify(X_test[i], X_train, y_train, 5) == y_test[i]):
print(i)
count = count + 1
print('The accuracy is %.2f%%' % (count * 1.0 * 100 / length))
# coding=utf-8
import knn
from numpy import *
import matplotlib.pyplot as plt
import numpy as np
if __name__ == "__main__" :
# create the dataset
dataSet, labels = knn.createDataSet()
print dataSet
# set the K value of KNN
k = 3
# classify using kNN
## test1 data(1.2, 1.0)
testX = array([1.2, 1.0])
outputLabel = knn.kNNClassify(testX, dataSet, labels, k)
print "Your input is:", testX, "and classified to class: ", outputLabel
## test1 data(0.1, 0.3)
testX = array([0.1, 0.3])
outputLabel = knn.kNNClassify(testX, dataSet, labels, k)
print "Your input is:", testX, "and classified to class: ", outputLabel