def train():
'''对knn进行训练'''
datingDataMat, datingLables = knn.file2matrix('datingTestSet2.txt')
normMat, rangeVals, minVals = knn.autoNorm(datingDataMat)
print normMat
print datingLables
# knn.plotData(datingDataMat, datingLables)
# 用作交叉验证集的数量百分比
hoRatio = 0.10
# 数据集的总数量
m = normMat.shape[0]
# 测试集
numTestVecs = int(m * hoRatio)
errorCount = 0.0
for i in range(numTestVecs):
classifierResult = knn.classify0(normMat[i, :],
normMat[numTestVecs:m, :],
datingLables[numTestVecs:m], 3)
print '分类器返回: %d, 实际的结果是:%d' % (classifierResult, datingLables[i])
if classifierResult != datingLables[i]:
errorCount += 1.0
print '错误率是: %f' % (errorCount / (float(numTestVecs)))
def predict():
resultList = ['一点也不喜欢', '有点喜欢', '非常喜欢']
percentTats = float(raw_input('玩游戏的时间是: '))
ffMiles = float(raw_input('每年的飞行公里数: '))
iceCream = float(raw_input('每年消耗的冰淇淋: '))
datingDataMat, datingLabels = knn.file2matrix('datingTestSet2.txt')
normMat, ranges, minVals = knn.autoNorm(datingDataMat)
inArr = np.array([ffMiles, percentTats, iceCream])
# 对输入数据的正规化处理
inArrNorm = (inArr - minVals) / ranges
classifierResult = knn.classify0(inArrNorm, normMat, datingLabels, 3)
print '预测你可能喜欢这个人的程度:', resultList[classifierResult - 1]
def predict():
resultList = ['一点也不喜欢', '有点喜欢', '非常喜欢']
percentTats = float(raw_input('玩游戏的时间是: '))
ffMiles = float(raw_input('每年的飞行公里数: '))
iceCream = float(raw_input('每年消耗的冰淇淋: '))
datingDataMat, datingLabels = knn.file2matrix('datingTestSet2.txt')
normMat, ranges, minVals = knn.autoNorm(datingDataMat)
inArr = np.array([ffMiles, percentTats, iceCream])
# 对输入数据的正规化处理
inArrNorm = (inArr - minVals) / ranges
classifierResult = knn.classify0(inArrNorm, normMat, datingLabels, 3)
print '预测你可能喜欢这个人的程度:', resultList[classifierResult-1]
def datingClassTest():
hoRatio = 0.10
datingDataMat, datingLabels = knn.file2matix(
'/home/matija/Projects/personal_projects/show-me-the-code/data-science/CollectiveIntelligence/dataSets/datingTestSet1.txt'
)
normMat, ranges, minVals = knn.autoNorm(datingDataMat)
m = normMat.shape[0]
#vectors to test knn clf
numTestVecs = int(m * hoRatio)
errorCount = 0.0
for i in range(numTestVecs):
classifierResult = knn.classify0(normMat[i,:], normMat[numTestVecs:m,:]\
,datingLabels, 3)
print "the classifier came back with: %d, the real answer is: %d"\
%(classifierResult, datingLabels[i])
if (classifierResult != datingLabels[i]): errorCount += 1.0
print "the total error rate is: %f" % (errorCount / float(numTestVecs))
def train():
'''对knn进行训练'''
datingDataMat, datingLables = knn.file2matrix('datingTestSet2.txt')
normMat, rangeVals, minVals = knn.autoNorm(datingDataMat)
print normMat
print datingLables
# knn.plotData(datingDataMat, datingLables)
# 用作交叉验证集的数量百分比
hoRatio = 0.10
# 数据集的总数量
m = normMat.shape[0]
# 测试集
numTestVecs = int(m*hoRatio)
errorCount = 0.0
for i in range(numTestVecs):
classifierResult = knn.classify0(normMat[i, :],
normMat[numTestVecs:m, :],
datingLables[numTestVecs:m],
3)
print '分类器返回: %d, 实际的结果是:%d' % (classifierResult, datingLables[i])
if classifierResult != datingLables[i]:
errorCount += 1.0
print '错误率是: %f' % (errorCount / (float(numTestVecs)))
datingDataMat, datingLabels = knn.file2matrix('datingTestSet.txt')
print(datingDataMat)
print(datingLabels)
# 显示
fig = plt.figure()
ax = fig.add_subplot(111)
# 看不到任何有用的模式信息
ax.scatter(datingDataMat[:, 1], datingDataMat[:, 2])
# 标注上色彩
ax.scatter(datingDataMat[:, 1], datingDataMat[:, 2], 15.0 * array(datingLabels), 15.0 * array(datingLabels))
plt.show()
plt.close()
# 归一化数据
normMat, ranges, minVals = knn.autoNorm(datingDataMat)
print('norm mat:')
print(normMat)
print('range:')
print(ranges)
print('norm mat:')
print(minVals)
# 测试分类器,使用数据集前hoRatio比例做测试集
hoRatio = 0.10
m = normMat.shape[0]
numTestVecs = int(m * hoRatio)
errorCount = 0.0
for i in range(numTestVecs):
classifierResult = knn.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]))
# -*- coding: utf-8 -*-
"""
Created on Fri Sep 21 10:38:54 2018
@author: fsxn2
"""
import knn
import matplotlib
import matplotlib.pyplot as plt
#group,labels=knn.createDataSet()
#print(knn.classify0([0,0],group,labels,3))
group, labels = knn.file2matrix("input.txt")
auto, ranges, minval = knn.autoNorm(group)
print(auto)
print(ranges)
print(minval)
#fig=plt.figure()
#ax=fig.add_subplot(111)
#ax.scatter(group[:,1],group[:2])
#plt.show()
print(knn.classify0([1, 0, 3], group, labels, 3))