def work(self):
miles = list()
gametimes = list()
icecream = list()
labels = list()
for i in range(self.number):
miles.append(random.randint(500,3000))
gametimes.append(random.random())
icecream.append(random.randint(10,150))
normMat, ranges, minVals = kNN.autoNorm(np.array(miles))
miles_normal = list(normMat[0])
normMat, ranges, minVals = kNN.autoNorm(np.array(gametimes))
gametimes_normal = list(normMat[0])
normMat, ranges, minVals = kNN.autoNorm(np.array(icecream))
icecream_normal = list(normMat[0])
for i in range(self.number):
maxval = max(miles_normal[i], gametimes_normal[i], icecream_normal[i])
if maxval == miles_normal[i]: labels.append(1)
elif maxval == gametimes_normal[i]: labels.append(2)
else: labels.append(3)
with open('datingtest', 'w') as f:
for i in range(self.number):
record = str(miles[i]) + \
'\t' + str(gametimes[i]) + \
'\t' + str(icecream[i]) + \
'\t' + str(labels[i]) + '\n'
f.write(record)
def testKNN2(self):
dataSet, labels = file2matrix('datingTestSet.txt')
normDataSet, ranges, minVals = kNN.autoNorm(dataSet)
testInput = numpy.array([51052, 4.680098, 0.625224])
testInput = (testInput-minVals) / ranges
c = kNN.classify0(testInput, normDataSet, labels, 3)
self.assertEqual(c, 1)
def test_autoNorm(self):
fileName = "datingTestSet.txt"
datingDataMat, datingLabels = kNN.file2matrix(fileName)
print("\n datingDataMat == %s" % (datingDataMat))
normDataSet, ranges, minVals = kNN.autoNorm(datingDataMat)
print("\n normDataSet == %s \n ranges == %s \n minVals == %s \n" %
(normDataSet, ranges, minVals))
def datingClassTest():
hoRatio = 0.50 #hold out 10%
datingDataMat, datingLabels = kNN.file2matrix(
'datingTestSet.txt') #load data setfrom file
normMat, ranges, minVals = kNN.autoNorm(datingDataMat)
m = normMat.shape[0]
numTestVecs = int(m * hoRatio) # 50% train set,50% test set
errorCount = 0.0
errorAns = m
for k in range(20):
errorCount = 0
for i in range(numTestVecs):
classifierResult = kNN.classify0(normMat[i, :],
normMat[numTestVecs:m, :],
datingLabels[numTestVecs:m],
k + 1)
# print "the classifier came back with: %s, the real answer is: %s" % (classifierResult, datingLabels[i])
if (classifierResult != datingLabels[i]): errorCount += 1.0
print "when k is %d the total error rate is: %f" % (k + 1, (
errorCount / float(numTestVecs)))
print errorCount
if errorCount <= errorAns:
errorAns = errorCount
ans = k + 1
print "the best k is", ans
def test_knn_dating():
#%% 利用knn模块的数据读取函数
x, y = knn.file2matrix('datingTestSet2.txt')
norm_x, ranges, minVals = knn.autoNorm(x)
norm_x = np.array(norm_x)
y = np.array(y)
#%% 生成测试数据的比例
train_ratio = 0.9
test_ratio = 0.1
size_data = len(norm_x)
indices = np.random.permutation(size_data)
x_train = norm_x[indices[:int(train_ratio * size_data)]]
y_train = y[indices[:int(train_ratio * size_data)]]
x_test = norm_x[indices[int(test_ratio * size_data):]]
y_test = y[indices[int(test_ratio * size_data):]]
#%%
# 设置分类器，并填充训练数据
knn_classfier = neighbors.KNeighborsClassifier()
knn_classfier.fit(x_train, y_train)
#%%
# 按比例进行测试数据
result = knn_classfier.predict(x_test)
for i in range(100):
if result[i] == y_test[i]:
print(True)
else:
print(False)
def autoNormTest():
returnMat, classLabelVector = kNN.file2matrix(
"C:\\Users\yangy\PycharmProjects\MLIA\kNN\datingTestSet2.txt")
normMat, ranges, minVals = kNN.autoNorm(returnMat)
print('normMat:', normMat)
print('ranges:', ranges)
print('minVals:', minVals)
def datingClassTest():
"""
约会网站测试
:return:
"""
# 设置测试数据比例
hoRatio = 0.1
# 从文件中加载数据
datingDataMat, datingLabels = kNN.file2matrix('datingTestSet2.txt')
# 归一化数据
normMat, ranges, minVals = kNN.autoNorm(datingDataMat)
# m = 数据的行数 即第一维矩阵
m = normMat.shape[0]
# 设置测试的样本数量
numTestVecs = int(m * hoRatio)
print('numTestVecs = ', numTestVecs)
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]))
if classifierResult != datingLabels[i]:
errorCount += 1.0
print('The total error rate is %f' % (errorCount / float(numTestVecs)))
print(errorCount)
def classifyPerson():
resultList = ['not at all', 'in small doses', 'in large doses']
percentTats = float(input("percentage of time spent playing video games?"))
ffMiles = float(input("frequent filter miles earned per year"))
iceCream = float(input("liters of ice cream consumed per year"))
datingDataMat, datingLabels = kNN.file2matrix('datingTestSet2.txt')
normMat, ranges, minVals = kNN.autoNorm(datingDataMat)
inArr = numpy.array([ffMiles, percentTats, iceCream])
classifierResult = kNN.classify0((inArr - minVals) / ranges, normMat,
datingDataMat, 3)
print("you will probably like this person: ".resultList[classifierResult -
1])
def classifyperson():
result = ['not at all', 'small doses', 'large dose']
ffmiles = float(input('frequent filter miles earned per year:'))
gametimepercent = float(input('% of time spent on game:'))
icecream = float(input('liters of ice cream consumed per year:'))
datamat, labels = kNN.file2matrix('datingTestSet.txt')
normmat, ranges, minvals = kNN.autoNorm(datamat)
inarry = (array([ffmiles, gametimepercent, icecream]) - minvals) / ranges
classifyresult = kNN.classify0(inarry, normmat, labels, 3)
print("you like this person:", result[classifyresult - 1])
return
def classifyPerson():
resultlist = ['not at all','in small doses','in large doses']
games = float(raw_input(
"percentage of time spent playing video games?"))
flymiles = float(raw_input(
"frequent flier miles earned per year?"))
icecream = float(raw_input(
"liters of ice cream consumed per year?"))
datingdata, datinglabel = kNN.file2matrix('datingTestSet2.txt')
normdata, ranges, minv = kNN.autoNorm(datingdata)
inarr = array([flymiles, games, icecream])
result = kNN.classify0((inarr - minv)/ranges, normdata, datinglabel, 3)
print "you will probably like this person:", resultlist[result-1]
def datingClassTest():
hoRatio = 0.550
datingDataMat, datingLabels = kNN.file2matrix('datingTestSet.txt')
normMat, ranges, minVals = kNN.autoNorm(datingDataMat)
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: %s, the real answer is: %s' % (classifierResult, datingLabels[i])
if (classifierResult != datingLabels[i]):
errorCount += 1.0
print "the total error rate is: %f" % (errorCount / float(numTestVecs))
def datingClassTest():
hoRatio = 0.10
datingDataMat, datingLabels = kNN.file2matrix('datingTestSet2.txt')
normMat, ranges, minVals = kNN.autoNorm(datingDataMat)
m = normMat.shape[0]
numTestVecs = int(m*hoRatio)
errorCount = 0.0
for i in range(numTestVecs):
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])
if classifierResult != datingLabels[i]:
errorCount += 1.0
print "the total error rate is: %f" % (errorCount/float(numTestVecs))
def classifyPerson():
percentTats = float(raw_input("percentage of time playing video games?"))
ffMiles = float(raw_input("frequent flyer miles earned per year?"))
iceCream = float(raw_input("liters of ice cream consumed per year?"))
datingDataMatrix, datingLabels = parseDatingData('datingTestSet.txt')
normalizedMatrix, ranges, minimumValues = kNN.autoNorm(datingDataMatrix)
classifierResult = kNN.classify0(
inX=(numpy.array([ffMiles, percentTats, iceCream]) - minimumValues) /
ranges,
dataSet=normalizedMatrix,
labels=datingLabels,
k=3)
print "Your probable result: {}".format(intToCategory(classifierResult))
def classifyPerson():
"""
imput someone information and predicts how much she will like this person
"""
resultList = ['not at all','in small doses','in large doses']
percentTats = float (input(\
"percentage of time spent playing video games?"))
ffMiles = float(input("frequent fliter miles earned per year?"))
iceCream = float(input("liters of ice cream consumed per year?"))
datingDataMat, datingLabels = file2matrix('datingTestSet.txt')
normMat, ranges, minVals = kNN.autoNorm(datingDataMat)
classifierResult = kNN.classify0([ffMiles, percentTats, iceCream ],normMat, \
datingLabels,3)
print ("you will probably like this person : %s" %(resultList[classifierResult - 1]))
def classifyPerson():
#resultList = ['not at all','in small doses', 'in large doses']
percentTats = float(raw_input(\
"percentage of time spent playing video games?"))
ffMiles = float(raw_input("frequent flier miles earned per year?")
) #使用sumlime配置的环境python27无法读取输入数据
iceCream = float(raw_input(
"liters of ice cream consumed per year?")) #点击*.py运行即可，程序末尾添加待输入
datingDataMat, datingLabels = kNN.file2matrix('datingTestSet.txt')
normMat, ranges, minVals = kNN.autoNorm(datingDataMat)
inArr = array([ffMiles, percentTats, iceCream])
classifierResult = kNN.classify0((inArr-\
minVals)/ranges,normMat,datingLabels,3)
print "You will probably like this person: ",\
classifierResult
def TradingClassTest():
hoRatio = 0.50 # hold out 10%
datingDataMat, datingLabels = HandleOverData(
'000875.csv') # load data setfrom file
normMat, ranges, minVals = kNN.autoNorm(datingDataMat)
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])
if (classifierResult != datingLabels[i]):
errorCount += 1.0
print "the total error rate is: %f" % (errorCount / float(numTestVecs))
print errorCount
def classifyPerson():
resultList = ['not at all', 'in small doses', 'in large doses']
# percentTats = float(input("percentage of time spent playing video games?"))
# ffMiles = float(input("frequent flier miles earned per year?"))
# iceCream = float(input("liters of ice cream consumed per year?"))
datingDataMat, datingLabels = file2matrix('resources/datingTestSet2.txt')
normMat, ranges, minVals = kNN.autoNorm(datingDataMat)
inArr = array([
9289,
9.666576,
1.370330,
])
classifierResult = kNN.classify0((inArr - minVals) / ranges, normMat,
datingLabels, 3)
print("You will probably like this person: %s" %
resultList[classifierResult - 1])
def datingClassTest():
hoRatio = 0.50 #hold out 10%
datingDataMat, datingLabels = dataSetMat, classLabelVector = file2matrix(
"resources/datingTestSet.txt") #load data setfrom file
normMat, ranges, minVals = kNN.autoNorm(datingDataMat)
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]))
if (classifierResult != datingLabels[i]): errorCount += 1.0
print("the total error rate is: %f" % (errorCount / float(numTestVecs)))
print(errorCount)
def classifyPerson():
"""
根据提示输入数据
:return:
"""
ll = ["不喜欢的人", "魅力一般的人", "具有魅力的人"]
x1 = float(raw_input("玩视频游戏所耗时间的百分比？"))
x2 = float(raw_input("每年获得的飞行常客里程数为？"))
x3 = float(raw_input("每周消费的冰淇淋的功升数为？"))
x, y = kNN.file2matrix("datingTestSet2.txt")
normX, rage, minV = kNN.autoNorm(x)
inX = (array([x1, x2, x3]) - minV) / rage
ret = kNN.classify0(inX, x, y, 3)
print "你对的喜欢程度可能是：", ll[int(ret) - 1]
def datingClassTest():
"""
分类器测试：约会分类网站的用户数据分类的测试
:return:
"""
hoRet = 0.10
x, y = kNN.file2matrix("datingTestSet.txt")
normX, rage, minV = kNN.autoNorm(x)
m = normX.shape[0]
errorCount = 0
testNum = int(hoRet * m)
for i in range(testNum):
yr = kNN.classify0(normX[i, :], normX[testNum:m, :], y, 3)
print "第%d个分类为%s，原来分类为%s" % (i, yr, y[i])
if yr != y[i]:
errorCount += 1
print "错误数为：%d，数错误率为：%f%% " % (errorCount, float(errorCount) * 100 / m)
return
import sys
import kNN
from pylab import *
from numpy import *
import numpy as np
import matplotlib
from mpl_toolkits.mplot3d import Axes3D
import matplotlib.pyplot as plt
mat,lab = kNN.file2matrix('datingTestSet2.txt')
normMat, ranges, minVals = kNN.autoNorm(mat)
def randrange(n, vmin, vmax):
return (vmax - vmin)*np.random.rand(n) + vmin
fig = plt.figure()
ax = fig.add_subplot(111,projection='3d')
#ax.scatter(normMat[:,0], normMat[:,1], normMat[:,2], 'o', 'c')
n = 1
for c, m, zl, zh in [('r', 'o', -50, -25), ('b', '^', -30, -5)]:
xs = randrange(n, 23, 32)
ys = randrange(n, 0, 100)
zs = randrange(n, zl, zh)
ClassSet=lab
colorSet = []
for label in ClassSet:
if label is '1':
colorSet.append('r')
elif label is '2':
colorSet.append('b')
elif label is '3':
print('d: ', d)
print('e', e)
group, labels = kNN.createDataSet()
print("I'm group: ", group)
print("I'm labels: ", labels)
k = kNN.classify0([0, 0], group, labels, 3)
print('I am k: ', k)
print('b.min: ', b.min(0))
print('b.max: ', b.max(0))
print('b.mean: ', b.mean(0))
b_m = (b - b.mean(0)) / (b.std(0))
print('b_m: ', b_m)
m = b.shape[0]
x = (b.max(0) - b.min(0))
b_a = (b - np.tile(b.min(0), (m, 1))) / np.tile(x, (m, 1))
print('b_a: ', b_a)
n, o, p = kNN.autoNorm(b)
print('n', n)
print('o: ', o)
print('p: ', p)
#fig = plt.figure()
#ax = fig.add_subplot(111)
#ax.scatter(b[:, 0], b[:, 1], 15*c, 15*c)
#plt.show()
kNN.handwritingClassTest()
'''
File Name: main
Description: 主函数，主要调用kNN.py中的函数
Author: jwj
Date: 2018/1/18
'''
__author__ = 'jwj'
import kNN
if __name__ == '__main__':
group, labels = kNN.createDataSet()
label = kNN.classify([0, 0], group, labels, 3)
print(label)
dataArray, dataLabels = kNN.file2matrix("datingTestSet2.txt")
kNN.autoNorm(dataArray)
normMat, ranges, minVals = kNN.autoNorm(dataArray)
# print(normMat)
# kNN.dataClassTest()
# kNN.classifyPerson()
kNN.handwritingClassTest()
from numpy import array
import kNN
reload(kNN)
normMat, ranges, minVals = kNN.autoNorm('datingDataMat')
print normMat
import kNN
dateDataMat, labels = kNN.file2matrix('./ml/2_kNN/datingTestSet2.txt')
normMat, ranges, minVals = kNN.autoNorm(dateDataMat)
print(normMat[0:0, 2:2])
print(ranges)
print(minVals)
import pandas as pd
import kNN
data = pd.read_table('datingTestSet2.txt', names=['a', 'b', 'c', 'd'])
normData, ranges, minVals = kNN.autoNorm(data.iloc[:, :-1])
datingLabels = data.d
numTestVecs = int(0.1 * normData.shape[0])
errorCount = 0
for i in range(numTestVecs):
classifierResult = kNN.classify0(normData.iloc[i].values,
normData.iloc[numTestVecs:].values,
datingLabels.iloc[numTestVecs:].values, 3)
print "the classifier came back with: %d, the real answer is: %d" % (
classifierResult, data.d[i])
if (classifierResult != data.d[i]):
errorCount += 1
print "the total error rate is: %f" % (errorCount / numTestVecs)
def autoNormTests():
datingDataArray, datingLabels = kNN.file2matrix('datingTestSet2.txt')
normArray, ranges, minVals = kNN.autoNorm(datingDataArray)
print normArray, ranges, minVals
text = document.original_text
text = re.sub("((http:|https:|ftp:|ftps:)//[\w$-_.+!*'(),%=]+)", '', text)
text = re.sub("(@[\w_]+)", '', text)
text = re.sub("(#[\w!$-_.+!*'(),%=]+)", '', text)
text = re.sub("\p{P}+", '', text)
text = re.sub("[\'\":#,!&]+", '', text)
pos = classify_tweet(text).prob('positive')
for category in categories:
sim = np.append(sim, [pos])
if count == 1:
group = np.array([sim])
else:
group = np.append(group, [sim], axis = 0)
labels.append(document.id)
group = kNN.autoNorm(group)
tweet_label = {}
count = 0
count_exer = 0
for document in doc:
count += 1
count_inner = 0
for category in categories:
if count_inner == 0:
sim = np.array([TrainSet.similar(category, document)])
else:
sim = np.append(sim, [TrainSet.similar(category, document)])
count_inner += 1
text = document.original_text
# -*- coding: utf-8 -*- ''' Created on 2015年9月29日 @author: rains ''' import matplotlib.pyplot as plt import numpy as np import os import kNN curdir='f:\\project\\python\\machine-learning-in-action/Ch02' mat1,fab1 = kNN.file2matrix(curdir+"/datingTestSet.txt") #查看训练集 # fig=plt.figure() # ax = fig.add_subplot(111) # ax.scatter(mat1[:,0],mat1[:,1],15.0*np.array(fab1),15.0*np.array(fab1)) # plt.show() #测试归一化 mat1 = kNN.autoNorm(mat1) #测试简单的分类器准确率 kNN.datingClassTest() #手写数字识别 #kNN.handwritingClassTest()
## kNN test function
group, labels = kNN.createDataSet()
result = kNN.classify0([0, 0], group, labels, 3)
### 1.yuehui wangzhan peidui
## load data and dating
datingDataMat, datingLabels = kNN.file2matrix('datingTestSet2.txt')
## plot dataSet
# fig = plt.figure()
# ax = fig.add_subplot(111)
# ax.scatter(datingDataMat[:,0], datingDataMat[:,1], s=15.0*num.array(datingLabels), c=15.0*num.array(datingLabels))
# plt.show()
## normalization
normMat, valueRange, minVals = kNN.autoNorm(datingDataMat)
## test the model
# kNN.datingClassTest()
### 2.shouxie shibei xitong
kNN.handwritingClassTest()
## a complete classifier system
# kNN.classifyPerson()
# print(normMat)
# print(range)
# print(minVals)
from numpy import array
features, labels = kNN.createDataSet()
features
kNN.classify0([0, 0], features, labels, 3)
datamat, labels = kNN.file2matrix('datingTestSet.txt')
'''
fig = plt.figure()
ax = fig.add_subplot(111)
ax.scatter(datamat[:,1], datamat[:,2], 15.0*array(labels), 15.0*array(labels))
plt.show()
'''
normmat, ranges, minvals = kNN.autoNorm(datamat)
print(normmat)
print(ranges)
print(minvals)
# kNN.datingClassTest(0.2,7)
def classifyperson():
result = ['not at all', 'small doses', 'large dose']
ffmiles = float(input('frequent filter miles earned per year:'))
gametimepercent = float(input('% of time spent on game:'))
icecream = float(input('liters of ice cream consumed per year:'))
datamat, labels = kNN.file2matrix('datingTestSet.txt')
normmat, ranges, minvals = kNN.autoNorm(datamat)
'datingTestSet2.txt'
) # Load data values and labels from the datingTestSet2.txt
datingLabelArray = np.array(datingLabels)
colormap2 = {1: 'red', 2: 'blue', 3: 'green'} #Define color map with 3 colors
ColoredDatingLabel = []
for things in datingLabelArray: #Get a vector representing the colors
ColoredDatingLabel.append(colormap2[things]) #for each data item
ax2 = FigDating.add_subplot(312, xlim=(0, 100000),
ylim=(0, 25)) #create second sub plot
ax2.scatter(datingDataMat[:, 0],
datingDataMat[:, 1],
s=20,
c=ColoredDatingLabel,
marker='o') #Plot a scatter diagram for the data loaded
normMat, ranges, minVals = kNN.autoNorm(datingDataMat) #normalize the data
ax3 = FigDating.add_subplot(313, xlim=(0, 1),
ylim=(0, 1)) #create third sub plot
ax3.scatter(normMat[:, 0],
normMat[:, 1],
s=20,
c=ColoredDatingLabel,
marker='o') #Plot normalized data
plt.show()
NumberBad = kNN.datingClassTest(0.1)
dictLabel = {'largeDoses': 1, 'smallDoses': 2, 'didntLike': 3}
for line in lines:
line = line.strip()
listFromLine = line.split('\t')
returnMat[index, :] = listFromLine[0:3]
classLabelVector.append(int(dictLabel.get(listFromLine[-1])))
index += 1
print returnMat[1, 2]
import matplotlib.pyplot as plt
fig = plt.figure()
ax = fig.add_subplot(111)
ax.scatter(returnMat[:, 1], returnMat[:, 2], 15.0 * array(classLabelVector),
15.0 * array(classLabelVector))
#plt.show()
dataSet = array([[3, 4, 5], [1, 2, 6], [4, 5, 6]], dtype=float)
minVal = dataSet.min(0)
maxVal = dataSet.max(0)
ranges = maxVal - minVal
normDataSet = zeros(shape(dataSet), dtype=float)
m = dataSet.shape[0]
normDataSet2 = dataSet - tile(minVal, (m, 1))
normDataSet2.astype(float)
print(normDataSet2)
print(tile(ranges, (m, 1)))
normDataSet3 = normDataSet2 / tile(ranges, (m, 1))
import kNN
normMat, ranges, minVal = kNN.autoNorm(returnMat)
print(normMat)
#for the picture
import matplotlib
import matplotlib.pyplot as plt
fig = plt.figure()
ax = fig.add_subplot(111)
ax.scatter(datingDataMat[:, 1], datingDataMat[:, 2])
plt.show()
ax.scatter(datingDataMat[:, 1], datingDataMat[:, 2],
15.0 * array(datingLabels), 15.0 * array(datingLabels))
ax.scatter(datingDataMat[:, 0], datingDataMat[:, 1],
15.0 * array(datingLabels), 15.0 * array(datingLabels))
#for the autoNorm
reload(kNN)
norMat, ranges, minVals = kNN.autoNorm(datingDataMat)
norMat
ranges
minVals
#for the datingClassTest
kNN.datingClassTest()
#for the clasdifyPerson
kNN.classifyPerson()
#for the img2vector
testVector = kNN.img2vector('testDigits/0_13.txt')
testVector[0, 0:31]
testVector[0, 31:63]
# encoding: utf-8
from numpy import *
import kNN
import matplotlib
import matplotlib.pyplot as plt
fig = plt.figure()
ax = fig.add_subplot(111)
datingDataMat, datingLabels = kNN.file2matrix('datingTestSet.txt')
## 由于每个指标的范围不一致, 我们这里需要进行归一化特征值
normMat, ranges, minVals = kNN.autoNorm(datingDataMat)
ax.scatter(normMat[:, 1], normMat[:,2])
# 添加坐标轴的labels
plt.xlabel('Percentage of Time Spent Playing Video Games')
plt.ylabel('Liters of Ice Cream Consumed Per Week')
plt.show()
# -*- coding: utf-8 -*-
"""
Created on Thu Jan 18 21:20:35 2018
@author: ldz
"""
# =============================================================================
'''testDatingClassifier'''
# =============================================================================
from kNN import file2matrix, autoNorm, classify0
hoRatio = 0.10 #hold out 10%
k = 3
datingDataMat, datingLabels = file2matrix(
'datingTestSet2.txt') #load data setfrom file
normMat, ranges, minVals = autoNorm(datingDataMat)
m = normMat.shape[0]
numTestVecs = int(m * hoRatio)
errorCount = 0.0
for i in range(numTestVecs):
classifierResult = classify0(normMat[i, :], normMat[numTestVecs:m, :],
datingLabels[numTestVecs:m], k)
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)))
print("number of error:" + str(errorCount))
print("number of test:" + str(numTestVecs))
def main4():
datingDataMat,datingLabels = kNN.file2matrix('datingTestSet2.txt')
# 获得归一化参数
normMat, ranges, minVals = kNN.autoNorm(datingDataMat)
import sys
import kNN
from pylab import *
from numpy import *
import numpy as np
import matplotlib
from mpl_toolkits.mplot3d import Axes3D
import matplotlib.pyplot as plt
mat, lab = kNN.file2matrix('datingTestSet2.txt')
normMat, ranges, minVals = kNN.autoNorm(mat)
def randrange(n, vmin, vmax):
return (vmax - vmin) * np.random.rand(n) + vmin
fig = plt.figure()
ax = fig.add_subplot(111, projection='3d')
#ax.scatter(normMat[:,0], normMat[:,1], normMat[:,2], 'o', 'c')
n = 1
for c, m, zl, zh in [('r', 'o', -50, -25), ('b', '^', -30, -5)]:
xs = randrange(n, 23, 32)
ys = randrange(n, 0, 100)
zs = randrange(n, zl, zh)
ClassSet = lab
colorSet = []
for label in ClassSet:
if label is '1':
colorSet.append('r')
# type "print answer" to see result
ax1.scatter(testvector[0], testvector[1], s= 20, c= colormap1[answer], marker = 'x' ) #plot first point
#second point - created, classified and plotted
testvector = [.5, .5]
answer = kNN.classify0(testvector,group, labels, 3)
ax1.scatter(testvector[0], testvector[1], s= 20, c= colormap1[answer], marker = 'x' )
#third point - created, classified and plotted
testvector = [.75, .75]
answer = kNN.classify0(testvector,group, labels, 3)
ax1.scatter(testvector[0], testvector[1], s= 20, c= colormap1[answer], marker = 'x' )
'''Perform K-Nearest Neighbor classification on the datingTestSet2 data set. Do not forget to include the data set in the working directory'''
datingDataMat,datingLabels = kNN.file2matrix('datingTestSet2.txt') # Load data values and labels from the datingTestSet2.txt
datingLabelArray = np.array(datingLabels)
colormap2 = { 1:'red', 2:'blue', 3:'green' } #Define color map with 3 colors
ColoredDatingLabel = []
for things in datingLabelArray: #Get a vector representing the colors
ColoredDatingLabel.append(colormap2[things]) #for each data item
ax2 = FigDating.add_subplot(312, xlim=(0,100000), ylim=(0,25)) #create second sub plot
ax2.scatter(datingDataMat[:,0], datingDataMat[:,1], s= 20, c= ColoredDatingLabel, marker = 'o' ) #Plot a scatter diagram for the data loaded
normMat, ranges, minVals = kNN.autoNorm(datingDataMat) #normalize the data
ax3 = FigDating.add_subplot(313, xlim=(0,1), ylim=(0,1)) #create third sub plot
ax3.scatter(normMat[:,0], normMat[:,1], s = 20, c= ColoredDatingLabel, marker = 'o' ) #Plot normalized data
plt.show()
NumberBad = kNN.datingClassTest(0.1)
