import numpy as np

def loadDataSet():
dataMat = []
labelMat = []
fr = open('D:\\LearningResource\\machinelearninginaction\\Ch05\\testSet.txt')
for line in fr.readlines():
lineArr = line.strip().split()
dataMat.append([1.0, float(lineArr[0]), float(lineArr[1])])
labelMat.append(int(lineArr[2]))
return dataMat,labelMat dataMat,labelMat = loadDataSet()
print(dataMat)
print(labelMat)

def sigmoid(z):
sigmoid = 1.0/(1+np.exp(-z))
return sigmoid def gradAscent(dataMatIn, classLabels):
dataMatrix = np.mat(dataMatIn)
labelMat = np.mat(classLabels).transpose()
m,n = np.shape(dataMatrix)
alpha = 0.001
maxCycles = 500
weights = np.ones((n,1))
for k in range(maxCycles):
h = sigmoid(dataMatrix*weights)
error = (labelMat - h)
weights = weights + alpha * dataMatrix.transpose()* error
return weights weights = gradAscent(dataMat,labelMat)
print(weights)

def stocGradAscent0(dataMatrix, classLabels):
m,n = np.shape(dataMatrix)
alpha = 0.01
weights = np.ones(n)
for i in range(m):
h = sigmoid(sum(np.array(dataMatrix[i])*weights))
error = classLabels[i] - h
weights = weights + alpha * error * np.array(dataMatrix[i])
return weights weights = stocGradAscent0(dataMat,labelMat)
print(weights)

def stocGradAscent1(dataMatrix, classLabels, numIter=150):
m,n = np.shape(dataMatrix)
weights = np.ones(n)
for j in range(numIter):
dataIndex = list(range(m))
for i in range(m):
alpha = 4/(1.0+j+i)+0.0001
randIndex = int(np.random.uniform(0,len(dataIndex)))
h = sigmoid(sum(np.array(dataMatrix[randIndex])*weights))
error = classLabels[randIndex] - h
weights = weights + alpha * error * np.array(dataMatrix[randIndex])
del(dataIndex[randIndex])
return weights weights = stocGradAscent1(dataMat,labelMat)
print(weights)

import matplotlib.pyplot as plt

def plotBestFit():
dataMat,labelMat=loadDataSet()
weights = gradAscent(dataMat,labelMat)
dataArr = np.array(dataMat)
n = np.shape(dataArr)[0]
xcord1 = []
ycord1 = []
xcord2 = []
ycord2 = []
for i in range(n):
if(int(labelMat[i])== 1):
xcord1.append(dataArr[i,1])
ycord1.append(dataArr[i,2])
else:
xcord2.append(dataArr[i,1])
ycord2.append(dataArr[i,2])
fig = plt.figure()
ax = fig.add_subplot(111)
ax.scatter(xcord1, ycord1, s=30, c='red', marker='s')
ax.scatter(xcord2, ycord2, s=30, c='green')
x = np.arange(-3.0, 3.0, 0.1)
y = (-weights[0]-weights[1]*x)/weights[2]
y = np.array(y).reshape(len(x))
ax.plot(x, y)
plt.xlabel('X1')
plt.ylabel('X2');
plt.show() plotBestFit()

def classifyVector(z, weights):
prob = sigmoid(sum(z*weights))
if(prob > 0.5):
return 1.0
else:
return 0.0 def colicTest():
frTrain = open('D:\\LearningResource\\machinelearninginaction\\Ch05\\horseColicTraining.txt')
frTest = open('D:\\LearningResource\\machinelearninginaction\\Ch05\\horseColicTest.txt')
trainingSet = []
trainingLabels = []
for line in frTrain.readlines():
currLine = line.strip().split('\t')
lineArr =[]
for i in range(21):
lineArr.append(float(currLine[i]))
trainingSet.append(lineArr)
trainingLabels.append(float(currLine[21]))
trainWeights = stocGradAscent1(np.array(trainingSet), trainingLabels, 1000)
errorCount = 0
numTestVec = 0.0
for line in frTest.readlines():
numTestVec += 1.0
currLine = line.strip().split('\t')
lineArr =[]
for i in range(21):
lineArr.append(float(currLine[i]))
if(int(classifyVector(np.array(lineArr), trainWeights))!= int(currLine[21])):
errorCount += 1
errorRate = (float(errorCount)/numTestVec)
print("the error rate of this test is: %f" % errorRate)
return errorRate errorRate = colicTest()
print(errorRate) def multiTest():
numTests = 10
errorSum=0.0
for k in range(numTests):
errorSum += colicTest()
print("after %d iterations the average error rate is: %f" % (numTests, errorSum/float(numTests))) multiTest()

吴裕雄 python 机器学习-Logistic(1)的更多相关文章

  1. 吴裕雄 python 机器学习——人工神经网络感知机学习算法的应用

    import numpy as np from matplotlib import pyplot as plt from sklearn import neighbors, datasets from ...

  2. 吴裕雄 python 机器学习——分类决策树模型

    import numpy as np import matplotlib.pyplot as plt from sklearn import datasets from sklearn.model_s ...

  3. 吴裕雄 python 机器学习——回归决策树模型

    import numpy as np import matplotlib.pyplot as plt from sklearn import datasets from sklearn.model_s ...

  4. 吴裕雄 python 机器学习——线性判断分析LinearDiscriminantAnalysis

    import numpy as np import matplotlib.pyplot as plt from matplotlib import cm from mpl_toolkits.mplot ...

  5. 吴裕雄 python 机器学习——逻辑回归

    import numpy as np import matplotlib.pyplot as plt from matplotlib import cm from mpl_toolkits.mplot ...

  6. 吴裕雄 python 机器学习——ElasticNet回归

    import numpy as np import matplotlib.pyplot as plt from matplotlib import cm from mpl_toolkits.mplot ...

  7. 吴裕雄 python 机器学习——Lasso回归

    import numpy as np import matplotlib.pyplot as plt from sklearn import datasets, linear_model from s ...

  8. 吴裕雄 python 机器学习——岭回归

    import numpy as np import matplotlib.pyplot as plt from sklearn import datasets, linear_model from s ...

  9. 吴裕雄 python 机器学习——线性回归模型

    import numpy as np from sklearn import datasets,linear_model from sklearn.model_selection import tra ...

随机推荐

  1. Mysql数据类型DECIMAL(M,D)用法

    在MySQL数据类型中,例如INT,FLOAT,DOUBLE,CHAR,DECIMAL等,它们都有各自的作用,下面我们就主要来介绍一下MySQL数据类型中的DECIMAL类型的作用和用法. 一般赋予浮 ...

  2. 线程守护进程与GIL

    为何要用多线程 多线程指的是,在一个进程中开启多个线程,简单的讲:如果多个任务共用一块地址空间,那么必须在一个进程内开启多个线程.详细的讲分为4点: 1. 多线程共享一个进程的地址空间 2. 线程比进 ...

  3. JavaScript Best Practices (w3cschool)

    JavaScript Best Practices (w3cschool) Local Variables: ·      总是在前面集中定义变量,(包括 for 的i).(strict mode) ...

  4. JS中 == ,===, !=, !==的区别

    一个等号是赋值操作,==先转换类型再比较,===先判断类型,如果不是同一类型直接为false. === 判断规则 如果类型不同,就[不相等]  如果两个都是数值,并且是同一个值,那么[相等]:(!例外 ...

  5. 迭代器 -> 固定的思路. for循环

    一个数据类型中包含了__iter__函数表示这个数据是可迭代的 dir(数据): 返回这个数据可以执行的所有操作 判断迭代器和可迭代对象的方案(野路子) __iter__ 可迭代的 __iter__ ...

  6. angularjs,Jsonp跨域访问页面

    angularjs1.6.8版本跨域 <!DOCTYPE html> <html ng-app="test"> <head> <meta ...

  7. uiautomator 代码记录 : BT发送测试

    package rom; import java.lang.*; import java.util.Random; import java.io.File; import com.android.ui ...

  8. [Unity优化]UI优化(一):RaycastTarget

    参考链接: http://www.manew.com/thread-100366-1-1.html https://www.jianshu.com/p/3082ebf8a342 https://blo ...

  9. elasticssearch+kibanna入门(撰写中)

    看到一篇elasticssearch+kibanna的文章,觉得很好,不过例子是python的,所以使用java自己安装一下: https://mp.weixin.qq.com/s?__biz=MjM ...

  10. gentoo kvm qemu virt-manager - Unable to complete install: error creating macvtap interface macvtap0@: Operation not supported'

    碰到这个一般是内核没有开启相应的 macvtap 选项,开启相应选项后,就不会报错了. Device Drivers ---> Network Device Support ---> &l ...