def test_stoc_grade_plot(self):
data_set, label_mat = logRegres.loadDataSet()
print("\n data_set == %s" % (data_set))
print("\n label_mat == %s" % (label_mat))
weights = logRegres.stocGradAscent0(array(data_set), label_mat)
print("\n weights == %s" % (weights))
logRegres.plotBestFit(weights)
def plotSDError(grad_type):
dataMat, labelMat = logRegres.loadDataSet()
dataArr = array(dataMat)
if grad_type == 0:
myHist = stocGradAscent0(dataArr, labelMat)
elif grad_type == 1:
myHist = stocGradAscent1(dataArr, labelMat)
n = shape(dataArr)[0] #number of points to create
xcord1 = []
ycord1 = []
xcord2 = []
ycord2 = []
markers = []
colors = []
fig = plt.figure(figsize=(7, 7))
ax = fig.add_subplot(311)
type1 = ax.plot(myHist[:, 0])
plt.ylabel('X0')
ax = fig.add_subplot(312)
type1 = ax.plot(myHist[:, 1])
plt.ylabel('X1')
ax = fig.add_subplot(313)
type1 = ax.plot(myHist[:, 2])
plt.xlabel('iteration')
plt.ylabel('X2')
plt.show()
def plotBestFit(weights):
import matplotlib.pyplot as plt
dataMat, labelMat = loadDataSet()
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]
print(weights[0])
print(weights[1])
print(weights[2])
ax.plot(x, y)
plt.xlabel('x1')
plt.ylabel('x2')
plt.show()
def test_get():
dataSet, labels = logRegres.loadDataSet()
print dataSet
print labels
#plotUtil.plot2DScatterWith2Type(dataSet,labels,1,0)
print logRegres.gradAscent(dataSet, labels)
def test_grade_plot(self):
data_set, label_mat = logRegres.loadDataSet()
print("\n data_set == %s" % (data_set))
print("\n label_mat == %s" % (label_mat))
weights = logRegres.gradAscent(data_set, label_mat)
print("\n weights == %s" % (weights))
# getA 为将numpy中的矩阵转换为python的array
logRegres.plotBestFit(weights.getA())
def test_best_stoc_grade_plot(self):
data_set, label_mat = logRegres.loadDataSet()
print("\n data_set == %s" % (data_set))
print("\n label_mat == %s" % (label_mat))
# 迭代150次
weights = logRegres.stocGradAscent1(array(data_set), label_mat, 200)
print("\n weights == %s" % (weights))
# getA 为将numpy中的矩阵转换为python的array
logRegres.plotBestFit(weights)
# -*- coding: utf-8 -*- from numpy import * import logRegres data, ls = logRegres.loadDataSet() wei1 = logRegres.gradAscent(data, ls) logRegres.plotBestFit(wei1) reload(logRegres) wei2 = logRegres.stocGradAscent0(array(data), ls) logRegres.plotBestFit(wei2) wei3 = logRegres.stocGradAscent1(array(data), ls) logRegres.plotBestFit(wei3) import logRegres logRegres.multiTest()
#!usr/bin/python #coding:utf8 import logRegres from numpy import * dataMat, Lables = logRegres.loadDataSet() weights = logRegres.stocGradAscent1(array(dataMat), Lables) logRegres.plotBestFit(dataMat, Lables, weights) # x = arange(-3.0, 3.0, 0.1) # print x # logRegres.muliTest()
def main():
dataAttr,labelsMat = logRegres.loadDataSet()
weights = logRegres.gradAscent(dataAttr,labelsMat)
logRegres.plotBestFit(weights)
def run():
dataMat, labelMat = lr.loadDataSet()
weights = lr.stocGradAscent1(dataMat, labelMat)
print weights
lr.plotBestFit(weights)
for j in range(40):
dataIndex = range(m)
for i in range(m):
alpha = 4 / (1.0 + j + i) + 0.01
randIndex = int(random.uniform(0, len(dataIndex)))
h = logRegres.sigmoid(sum(dataMatrix[randIndex] * weights))
error = classLabels[randIndex] - h
#print error
weights = weights + alpha * error * dataMatrix[randIndex]
weightsHistory[j * m + i, :] = weights
del (dataIndex[randIndex])
print(weights)
return weightsHistory
dataMat, labelMat = logRegres.loadDataSet()
dataArr = array(dataMat)
myHist = stocGradAscent1(dataArr, labelMat)
n = shape(dataArr)[0] #number of points to create
xcord1 = []
ycord1 = []
xcord2 = []
ycord2 = []
markers = []
colors = []
fig = plt.figure()
ax = fig.add_subplot(311)
type1 = ax.plot(myHist[:, 0])
def stocGradAscent1(numIter):
dataArr, labelMat = logRegres.loadDataSet()
weights = logRegres.stocGradAscent1(array(dataArr), labelMat, numIter);
print weights
logRegres.plotBestFit(weights);
'''
Created on Oct 6, 2010
@author: Peter
'''
from numpy import *
import matplotlib
import matplotlib.pyplot as plt
from matplotlib.patches import Rectangle
import logRegres
dataArr, labelArr = logRegres.loadDataSet()
dataArray = array(dataArr)
weights = logRegres.stocGradAscent0(dataArray, labelArr)
n = shape(dataArray)[0] #number of points to create
xcord1 = []
ycord1 = []
xcord2 = []
ycord2 = []
markers = []
colors = []
for i in range(n):
if int(labelArr[i]) == 1:
xcord1.append(dataArray[i, 1])
ycord1.append(dataArray[i, 2])
else:
xcord2.append(dataArray[i, 1])
ycord2.append(dataArray[i, 2])
#3.初始权重：设置也是任意的，通常设置为1，多次迭代后都会趋于最有权重参数（前提是有唯一最优解/最大似然函数有唯一极值解）。
#4.迭代的次数：这个多试几次，看图大概就能知道设置为多少，理论上来说迭代次数越大最好，但实际后面的迭代没有太大效果
#5.第三个例子中的X0是直接在文档中就给出的，不需要在程序中添加其值。训练样本和测试样本都是22列（21列属性值 + 1列 标签值01 ）
#5.#程序内容：
#疑问：1.为什么每个数据都要添加一个常数属性呢？
#其他：程序提供的例子有两个属性（不含常数x0=1）,则绘制出的是切分二位空间的直线x1+x2=0，如果是三个属性，则绘制出的是切分三维空间的平面x1+x2+x3=0。
#同理可知，四个属性绘制出的是切分思维空间的立方体（思维图形是想象不出来的，但是其投影是可以想象出来的三维，所以可推测x1+x2+x3+x4=0是思维空间表达式下的三维空间方程）。
#一维是直线，二位是平面，三维是显示空间，平面可能存在交集，但蚂蚁不能从一个平面到另一个平面，甚至不能抬头看见另一个平面。同理现实空间与现实空间也会存在交集，但是去不了，甚至不能抬头看见另一个空间。
#时间：2018年6月8日（星期五） 下午开始，6月12日（星期二）上午完成备注分析
import logRegres
from numpy import *
#从文件夹中提取数据
dataArr, labelMat = logRegres.loadDataSet() #加载数据，存放在列表中
print "\n数据列表是：\n", dataArr #打印数据，测试读取是否异常
print "\n类列表是:\n", labelMat
#用数据和标签 利用梯度上升算法计算 权重
weights = logRegres.gradAscent(dataArr, labelMat) #梯度上升算法计算最佳参数值
stocWeights = logRegres.stocGradAscent1(array(dataArr), labelMat,
500) #随机梯度上升算法计算最佳参数值
print "\n权重w0,w1,w2的值是：\n", weights
####################################### 第一个图：梯度上升算法的例子 #################################
#利用权重绘制直线 利用数据绘制点
print "\n第一个图：梯度上升算法的例子"
#梯度上升算法：批量处理方法（一次性处理所有数）
logRegres.plotBestFit(
weights.getA()) # .getA()将矩阵转换成数组 因为数组可以很方便的任意读取其中的元素，矩阵不行
def gradAscent():
dataArr, labelMat = logRegres.loadDataSet()
weights = logRegres.gradAscent(dataArr, labelMat)
print weights
logRegres.plotBestFit(weights.getA())
def stocGradAscent1(numIter):
dataArr, labelMat = logRegres.loadDataSet()
weights = logRegres.stocGradAscent1(array(dataArr), labelMat, numIter)
print weights
logRegres.plotBestFit(weights)
__author__ = 'sunbeansoft' import logRegres as lr from numpy import * dataArr, labelMat = lr.loadDataSet() weight = lr.gradAscent(dataArr, labelMat) lr.plotBestFit(weight.getA()) weight = lr.stocGradAscent0(array(dataArr), labelMat) lr.plotBestFit(weight) weight = lr.stocGradAscent1(array(dataArr), labelMat) lr.plotBestFit(weight) lr.multiTest()
from numpy import * import logRegres dataarr, labelmat = logRegres.loadDataSet() weights = logRegres.gradAscent(dataarr, labelmat) print(weights) print(weights.getA()) #logRegres.plotBestFit(weights.getA()) weights = logRegres.stocGradAscent0(array(dataarr), labelmat) print(weights) #logRegres.plotBestFit(weights) weights = logRegres.stocGradAscent1(array(dataarr), labelmat) print(weights) #logRegres.plotBestFit(weights) logRegres.multiTest()
#!/usr/bin/python
# encoding: utf-8
'''
Created on Nov 28, 2015
@author: yanruibo
'''
import logRegres
import numpy as np
if __name__ == '__main__':
dataArr,labelMat = logRegres.loadDataSet()
#weights = logRegres.gradAscent(dataArr, labelMat)
weights = logRegres.stocGradAscent0(np.array(dataArr), labelMat)
print weights
#logRegres.plotBestFit(weights.getA())
logRegres.plotBestFit(weights)
for j in range(40):
dataIndex = range(m)
for i in range(m):
alpha = 4/(1.0+j+i)+0.01
randIndex = int(random.uniform(0,len(dataIndex)))
h = logRegres.sigmoid(sum(dataMatrix[randIndex]*weights))
error = classLabels[randIndex] - h
#print error
weights = weights + alpha * error * dataMatrix[randIndex]
weightsHistory[j*m + i,:] = weights
del(dataIndex[randIndex])
print weights
return weightsHistory
dataMat,labelMat=logRegres.loadDataSet()
dataArr = array(dataMat)
myHist = stocGradAscent1(dataArr,labelMat)
n = shape(dataArr)[0] #number of points to create
xcord1 = []; ycord1 = []
xcord2 = []; ycord2 = []
markers =[]
colors =[]
fig = plt.figure()
ax = fig.add_subplot(311)
type1 = ax.plot(myHist[:,0])
import logRegres from numpy import * a1, a2 = logRegres.loadDataSet() #print(a1) #print(a2) b1 = logRegres.gradAscent(a1, a2) print(b1.getA()) logRegres.plotBestFit(b1.getA()) ###perfect #c1 = logRegres.stocGradAscent1(array(a1),a2) #logRegres.plotBestFit(c1)
def gradAscent():
dataArr, labelMat = logRegres.loadDataSet()
weights = logRegres.gradAscent(dataArr, labelMat)
print weights
logRegres.plotBestFit(weights.getA())
def test_plotBestFit():
dataSet, labels = logRegres.loadDataSet()
weights = logRegres.gradAscent(dataSet, labels)
logRegres.plotBestFit(weights.getA())
import logRegres
trainData, trainLabels = logRegres.loadDataSet('data/train-set', 13)
weights = logRegres.kgradAscent(trainData, trainLabels)
#print 'weights:\n'
#print weights
testData, testLabels = logRegres.loadDataSet('data/test-set', 13)
print 'Original:'
print testLabels
correct, classified = logRegres.ktest(testData, testLabels, weights)
print 'Classified:'
print classified
#!/usr/bin/env python
# -*- coding: utf-8 -*-
# author:yiluzhang
import logRegres
if __name__ == "__main__":
# 测试批梯度上升
data_arr, label_arr = logRegres.loadDataSet()
weights = logRegres.gradAscent(data_arr, label_arr)
logRegres.plotBestFit(weights)
from numpy import * import logRegres import logRegresGo dataArr, labelMat = logRegres.loadDataSet() weights = logRegres.gradAscent(dataArr, labelMat) logRegres.plotBestFit(weights)
def test_grade(self):
data_set, label_mat = logRegres.loadDataSet()
print("\n data_set == %s" % (data_set))
print("\n label_mat == %s" % (label_mat))
ascent = logRegres.gradAscent(data_set, label_mat)
print("\n ascent == %s" % (ascent))
