def show_file2matrix(file_name):
reload(knn)
datingDataMat, datingLabels = knn.file2matrix(file_name)
fig = plt.figure()
ax = fig.add_subplot(111)
ax.scatter(datingDataMat[:,1], datingDataMat[:,2], 15.0*array(datingLabels), 15.0*array(datingLabels))
plt.show()
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 test_auto_norm(self):
date_mat, date_label = knn.file2matrix('datingTestSet2.txt')
norm_mat, ranges, min_val = knn.auto_norm(date_mat)
min_exp = np.array([0., 0., 0.001156])
ranges_exp = np.array([9.1273000e+04, 2.0919349e+01, 1.6943610e+00])
self.assertEqual(True, (min_exp == min_val).all())
self.assertEqual(True, (ranges == ranges_exp).all())
def testknn_matplotlib():
a, b = knn.file2matrix('../datingTestSet.txt')
fig = plt.figure()
ax = fig.add_subplot(111)
ax.scatter(a[:, 1], a[:, 2], 15 * array(b), 15 * array(b))
# ax.scatter(a[:, 1], a[:, 2],b,b)
plt.show()
def show_file2matrix(file_name):
reload(knn)
datingDataMat, datingLabels = knn.file2matrix(file_name)
fig = plt.figure()
ax = fig.add_subplot(111)
ax.scatter(datingDataMat[:, 1], datingDataMat[:, 2],
15.0 * array(datingLabels), 15.0 * array(datingLabels))
plt.show()
def classfiy_person() :
result_list = ['not at all','in small doses','in large doses']
percent_tats= float(input("percentage of time spent playing video games ?"))
ffmiles = float(input("frequent flier miles earned per year ?"))
ice_cream = float(input("liter of ice cream consumed per year ?"))
dating_mat, dating_labels = knn.file2matrix('./knn/datingTestSet2.txt')
normal_mat, ranges, min_values = knn.auto_normal(dating_mat)
inArr = array([ffmiles, percent_tats, ice_cream])
classfiy_result = knn.classify0((inArr - min_values) / ranges, normal_mat, dating_labels, 3)
print("You will probably like this person: ", result_list[classfiy_result - 1], "(" + str(classfiy_result) + ")")
def test_file2matrix(self):
date_mat, date_label = knn.file2matrix('datingTestSet2.txt')
fig = plt.figure()
ax = fig.add_subplot(111)
ax.scatter(date_mat[:, 1], date_mat[:, 2], \
15.0 * np.array(date_label), 15.0 * np.array(date_label))
plt.show()
self.assertEqual((1000, 3), date_mat.shape)
self.assertEqual(1000, len(date_label))
labels_exp = [3, 2, 1, 1, 1, 1, 3, 3, 1, 3]
self.assertEqual(True, labels_exp == date_label[0:10])
def test() :
group, labels = knn.create_dataset()
print(group)
print(labels)
sort = knn.classify0([0,0],group,labels,3)
print("distance is %s !"%(sort))
## pycharm 中的相对路径不一样，需要在 Run -> Edit Configurations 中查看 Working dorectory
#dating_mat, dating_labels = knn.file2matrix('./knn/datingTestSet.txt')
dating_mat, dating_labels = knn.file2matrix('./knn/datingTestSet2.txt')
print(dating_mat)
print(dating_labels)
knn.show_plt(dating_mat,dating_labels)
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 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)))
import matplotlib
import matplotlib.pyplot as plt
import numpy as np
import knn
import mnist_test
group, labels = knn.createDataSet()
bb = knn.classify0([0,0], group, labels, 3)
print bb
cc = knn.knn2([0,0], group, labels, 3)
# 可视化数据
dataSet, labels = knn.file2matrix('data/datingTestSet2.txt')
fig = plt.figure()
ax = fig.add_subplot(111)
ax.scatter(dataSet[:,0], dataSet[:,1], s=15.0*labels, c=15.0*labels)
plt.show()
# 测试误判率
reload(knn)
# testRatio为测试集比例，k为邻居个数
knn.knnTest('../data/datingTestSet2.txt',testRatio=0.2, k=3)
# 测试手写数字识别
mnist_test.mnist_test(500,100, k=7)
#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time : 2018/11/30 16:52
# @Author : zhcf1ess
# @Site :
# @File : createFirstPLT.py
# @Software: PyCharm
from numpy import *
import knn
import matplotlib.pyplot as plt
fig = plt.figure()
ax = fig.add_subplot(111)
datingDataMat, datingLabels = knn.file2matrix(
'../data/ch02/datingTestSet2.txt')
ax.scatter(datingDataMat[:, 1], datingDataMat[:, 2],
15.0 * array(datingLabels), 15.0 * array(datingLabels))
ax.axis([-2, 25, -0.2, 2.0])
plt.xlabel('Percentage of Time Spent Playing Video Games')
plt.ylabel('Liters of Ice Cream Consumed Per Week')
plt.show()
def testknn():
a, b = knn.file2matrix('../datingTestSet.txt')
print(a[:, 1])
import knn
from numpy import *
import matplotlib
import matplotlib.pyplot as plt
datingDataMat, datingLabels = knn.file2matrix(
"machinelearninginaction/Ch02/datingTestSet2.txt")
fig = plt.figure()
ax = fig.add_subplot(111)
ax.scatter(datingDataMat[:, 1], datingDataMat[:, 2],
15.0 * array(datingLabels), 15.0 * array(datingLabels))
plt.show()
# -*- 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))
# This is a sample Python script.
# Press Shift+F10 to execute it or replace it with your code.
# Press Double Shift to search everywhere for classes, files, tool windows, actions, and settings.
import knn
import matplotlib
import matplotlib.pyplot as plt
from array import array
from numpy import *
# Press the green button in the gutter to run the script.
if __name__ == '__main__':
# 数据加载
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:')
import matplotlib
import matplotlib.pyplot as plt
from numpy import array
import knn
datingDataMat,datingLabels,vector = knn.file2matrix('datingTestSet.txt')
fig = plt.figure()
ax = fig.add_subplot(131)
ax.scatter(datingDataMat[:,1],datingDataMat[:,2])
ax = fig.add_subplot(132)
ax.scatter(datingDataMat[:,1],datingDataMat[:,2],15.0*array(vector),15.0*array(vector))
ax = fig.add_subplot(133)
ax.scatter(datingDataMat[:,0],datingDataMat[:,1],15.0*array(vector),15.0*array(vector))
plt.show()