def testDimByLevel(self):
tree = kdTree.KdTree()
self.assertEqual(2, tree._dim)
self.assertEqual(0, tree._dim_by_level(0))
self.assertEqual(1, tree._dim_by_level(1))
self.assertEqual(0, tree._dim_by_level(2))
tree = kdTree.KdTree(5)
self.assertEqual(5, tree._dim)
self.assertEqual(0, tree._dim_by_level(0))
self.assertEqual(1, tree._dim_by_level(1))
self.assertEqual(2, tree._dim_by_level(2))
self.assertEqual(0, tree._dim_by_level(5))
self.assertEqual(1, tree._dim_by_level(6))
self.assertEqual(4, tree._dim_by_level(9))
def datingClassTest():
"""
Desc：
对约会网站的测试方法，并将分类错误的数量和分类错误率打印出来
Args：
None
Returns：
None
"""
# 设置测试数据的的一个比例（训练数据集比例=1-hoRatio）
hoRatio = 0.1 # 测试范围,一部分测试一部分作为样本
# 从文件中加载数据
datingDataMat, datingLabels = file2matrix(
"datingTestSet2.txt") # load data setfrom file
# 归一化数据
normMat, ranges, minVals = autoNorm(datingDataMat)
# m 表示数据的行数，即矩阵的第一维
m = normMat.shape[0]
# 设置测试的样本数量， numTestVecs:m表示训练样本的数量
numTestVecs = int(m * hoRatio)
print('numTestVecs=', numTestVecs)
errorCount = 0
kd = kt.KdTree(normMat[numTestVecs:].tolist(), datingLabels)
for i in range(numTestVecs):
# 对数据测试
res = kt.find_nearest(kd, normMat[i])
classifierResult = res.node_type
classifierResult = classify0(normMat[i], normMat[numTestVecs:m],
datingLabels[numTestVecs:m], 3)
print("the classifier came back with: %d, the real answer is: %d" %
(classifierResult, datingLabels[i]))
errorCount += classifierResult != datingLabels[i]
print("the total error rate is: %f" % (errorCount / numTestVecs))
print(errorCount)
def testInsert(self):
tree = kdTree.KdTree()
self.assertTrue(tree.is_empty())
p = kdTree.Point([1, 2])
tree.insert(p)
self.assertFalse(tree.is_empty())
self.assertIsNotNone(tree._root)
def testSearch3(self):
p = kdTree.Point([1, 2])
pp = kdTree.Point([1, 2])
tree = kdTree.KdTree()
tree.insert(p)
self.assertEqual(p, tree.search(pp))
self.assertTrue(
tree.search(pp) is p, "Returned point should be the node's point")
self.assertFalse(
tree.search(pp) is pp,
"Returned point should be the node's point, not the given point")
def testLeveledDist(self):
tree = kdTree.KdTree()
p1 = kdTree.Point([3, 4])
p2 = kdTree.Point([0, 0])
node = kdTree.Node(p2)
self.assertEqual(25, p1.squared_distance_to(p2))
self.assertEqual(5, p1.distance_to(p2))
self.assertEqual(3, tree.leveled_distance(node, p1,
0)) # 0 => X compare
self.assertEqual(4, tree.leveled_distance(node, p1,
1)) # 1 => Y compare
self.assertEqual(3, tree.leveled_distance(node, p1,
2)) # 0 => X compare
def testSearch(self):
p1 = kdTree.Point([3, 4])
p2 = kdTree.Point([0, 0])
p3 = kdTree.Point([1, 2])
tree = kdTree.KdTree()
tree.insert(p1)
tree.insert(p2)
self.assertEqual(p1, tree.search(p1))
self.assertTrue(tree.contains(p1))
self.assertEqual(p2, tree.search(p2))
self.assertTrue(tree.contains(p2))
self.assertEqual(None, tree.search(p3))
self.assertFalse(tree.contains(p3))
def handwritingClassTest():
"""
Desc:
手写数字识别分类器，并将分类错误数和分类错误率打印出来
Args:
None
Returns:
None
"""
# 1. 导入数据
hwLabels = []
trainingFileList = os.listdir("trainingDigits") # load the training set
m = len(trainingFileList)
trainingMat = zeros((m, 1024))
# hwLabels存储0～9对应的index位置， trainingMat存放的每个位置对应的图片向量
for i in range(m):
fileNameStr = trainingFileList[i]
fileStr = fileNameStr.split('.')[0] # take off .txt
classNumStr = int(fileStr.split('_')[0])
hwLabels.append(classNumStr)
# 将 32*32的矩阵->1*1024的矩阵
trainingMat[i] = img2vector('trainingDigits/%s' % fileNameStr)
# 2. 导入测试数据
testFileList = os.listdir('testDigits') # iterate through the test set
errorCount = 0
mTest = len(testFileList)
kd = kt.KdTree(trainingMat.tolist(), hwLabels)
for i in range(mTest):
fileNameStr = testFileList[i]
fileStr = fileNameStr.split('.')[0] # take off .txt
classNumStr = int(fileStr.split('_')[0])
vectorUnderTest = img2vector('testDigits/%s' % fileNameStr)
result = kt.find_nearest(kd, vectorUnderTest[0])
classifierResult = result.node_type
# classifierResult = classify0(vectorUnderTest, trainingMat, hwLabels, 3)
print("the classifier came back with: %d, the real answer is: %d" %
(classifierResult, classNumStr))
errorCount += classifierResult != classNumStr
print("\nthe total number of errors is: %d" % errorCount)
print("\nthe total error rate is: %f" % (errorCount / mTest))
def testRange(self):
p1 = kdTree.Point([3, 1])
p2 = kdTree.Point([4, 4])
p3 = kdTree.Point([2, 3])
p4 = kdTree.Point([0.5, 0.5])
tree = kdTree.KdTree()
tree.insert(p1)
tree.insert(p2)
tree.insert(p3)
tree.insert(p4)
points = tree.range(kdTree.Point([0, 0]), kdTree.Point([1, 1]))
self.assertEqual(1, len(points))
self.assertTrue(p4 in points)
points = tree.range(kdTree.Point([1, 2]), kdTree.Point([5, 5]))
self.assertEqual(2, len(points))
self.assertTrue(p2 in points)
self.assertTrue(p3 in points)
def testSearch2(self):
p1 = kdTree.Point([3, 1, 3])
p2 = kdTree.Point([4, 4, 2])
p3 = kdTree.Point([2, 3, 4])
tree = kdTree.KdTree(dimensions=3)
tree.insert(p1)
tree.insert(p2)
tree.insert(p3)
self.assertEqual(p1, tree.search(p1))
self.assertEqual(p2, tree.search(p2))
self.assertEqual(p3, tree.search(p3))
p = kdTree.Point([1, 2, 3])
self.assertEqual(None, tree.search(p))
self.assertTrue(tree.contains(p1))
self.assertTrue(tree.contains(p2))
self.assertTrue(tree.contains(p3))
self.assertFalse(tree.contains(p))
def testNearest3D(self):
p1 = kdTree.Point([3, 1, 0])
p2 = kdTree.Point([4, 4, 0])
p3 = kdTree.Point([2, 3, 1])
p4 = kdTree.Point([0.5, 0.5, 10])
tree = kdTree.KdTree(dimensions=3)
tree.insert(p1)
tree.insert(p2)
tree.insert(p3)
tree.insert(p4)
self.assertEqual(4, tree.size())
p = kdTree.Point([2, 2, 1])
nn = tree.nearest(p)
self.assertIsNotNone(nn)
self.assertEqual(p3, nn)
p = kdTree.Point([2, 2, 8])
nn = tree.nearest(p)
self.assertIsNotNone(nn)
self.assertEqual(p4, nn)
def testNearest(self):
p1 = kdTree.Point([3, 1])
p2 = kdTree.Point([4, 4])
p3 = kdTree.Point([2, 3])
p4 = kdTree.Point([0.5, 0.5])
tree = kdTree.KdTree()
tree.insert(p1)
tree.insert(p2)
tree.insert(p3)
tree.insert(p4)
self.assertEqual(4, tree.size())
p = kdTree.Point([1, 2])
nn = tree.nearest(p)
self.assertIsNotNone(nn)
self.assertEqual(p3, nn)
p = kdTree.Point([5, 5])
nn = tree.nearest(p)
self.assertIsNotNone(nn)
self.assertEqual(p2, nn)
import kdTreeFind as kf
from time import clock
from random import random
import sys
reload(sys)
sys.setdefaultencoding('utf8')
def random_point(k):
return [random() for _ in range(k)]
def random_points(k, n):
return [random_point(k) for _ in range(n)]
if __name__ == "__main__":
data = [[2, 3], [5, 4], [9, 6], [4, 7], [8, 1], [7, 2]] # samples
kd = kd1.KdTree(data)
ret = kf.find_nearest(kd, [3.0, 4.5])
print ret
N = 400000
t0 = clock()
kd2 = kd1.KdTree(random_points(3, N))
ret2 = kf.find_nearest(kd2, [0.1, 0.5, 0.8])
t1 = clock()
print "time: ", t1 - t0, "s"
print ret2
print((1 - np.count_nonzero(np.subtract(pred, gt)) / gt.shape[0]) * 100,
"% accuracy")
if __name__ == '__main__':
if len(sys.argv) < 10:
print(
'Usage: [[Python]] digitClassifer.py [1] [training file] [path to training data] [ground truth file] '
'[testing file] [training junk file] [path to junk data] [ground truth file] [testing junk file]'
)
else:
trainVec, testVec, train_labels, test_labels, train_int_classes, test_int_classes, training, testing = pre_processing_pipeline(
)
if int(sys.argv[1]) == 1:
model, model2 = training_pipeline(trainVec, train_labels,
lambda x: kd.KdTree(x, 1),
lambda x1, x2: svm.SVM(x1, x2))
else:
load = open('kdTreeModel.txt', 'rb')
model = pk.load(load)
load = open('svmModel.txt', 'rb')
model2 = pk.load(load)
# kdtree training and testing results
print("\nTesting KDTREE->")
kdtest_classified = classify_pipeline(trainVec, model)
print("\nTraining Accuracy:", end="")
acc(kdtest_classified, train_labels)
outputs(training, kdtest_classified, train_int_classes,
'kdTree-training')
def testIsEmpty(self):
tree = kdTree.KdTree()
self.assertTrue(tree.is_empty())
