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_debug_logregres(self):
# 分类直线为经过（0，1）（3，4）两个点，则直线为y=x+1
# 其中[x,y,label]分别表示x坐标，y坐标
# label==1表示在直线之上 label==0表示在直线之下
# 由于此处数据数值偏大，因此gradAscent方法中的步长也对应应该变大，否则分类线则不太准确
data_set = [
[1, 3, 1],
[2, 4, 1],
[2, 5, 1],
# [-1, 2, 1],
# [-2, 4, 1],
# [-3, 3, 1],
[1, 1, 0],
[2, 1, 0],
[3, 3, 0]
# [0, 0, 0],
# [-2, -3, 0],
# [-4, -5, 0]
]
data_set = mat(data_set)
m, n = shape(data_set)
print("\n data_set == %s" % (data_set))
# 获取出去label的子矩阵
data_in = data_set[:, :n - 1]
# 初始化设置x0=1?
one = ones((m, 1))
print("\n one == %s" % (one))
data_in = column_stack((one, data_in))
classmat = data_set[:, n - 1:]
classLabel = []
for i in classmat.flat:
classLabel.append(i)
print("\n\n data_in == %s" % (data_in))
print("\n classLabel == %s" % (classLabel))
weights = logRegres.gradAscent(data_in, classLabel)
print("\n weights == %s" % (weights))
# getA 为将numpy中的矩阵转换为python的array
logRegres.plotBestFit1(weights.getA(), data_in, classLabel)
def test_plotBestFit():
dataSet, labels = logRegres.loadDataSet()
weights = logRegres.gradAscent(dataSet, labels)
logRegres.plotBestFit(weights.getA())
import logRegres dataArr, labelMat = logRegres.loadDataSet() print(logRegres.gradAscent(dataArr, labelMat))
''' Created on May 27, 2014 Logistic Regression Main Study @author: Guodong Jin ''' import logRegres from numpy import * dataArr,labelMat = logRegres.loadDataSet() print len(dataArr) print labelMat res_w = logRegres.gradAscent(dataArr, labelMat) print res_w # logRegres.plotBestFit(res_w.getA()) res_w, l_w0, l_w1, l_w2= logRegres.stocGradAscent1_0(array(dataArr), labelMat, 100) logRegres.plotBestFit(res_w) # import matplotlib.pyplot as plt # x = range(len(l_w0)) # fig = plt.figure() # ax = fig.add_subplot(111) # print res_w # ax.plot(x, array(l_w1)) # plt.show()
def gradAscent():
dataArr, labelMat = logRegres.loadDataSet()
weights = logRegres.gradAscent(dataArr, labelMat)
print weights
logRegres.plotBestFit(weights.getA())
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()
import logRegres
import sys
dataArr, labelMat = logRegres.loadDataSet()
matrix = logRegres.gradAscent(dataArr, labelMat)
#print matrix[1]
for line in sys.stdin:
line = line.strip()
lines = line.split('\t')
result = float(matrix[0]) + float(lines[0]) * float(matrix[1]) + float(
lines[1]) * float(matrix[2])
print "%s\t%f" % (line, result)
__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()
#!/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)
# -*- coding:utf-8 -*- import logRegres dataArr, labelMat = logRegres.loadDataSet() print logRegres.gradAscent(dataArr, labelMat)
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)
#__author__: dongj
#date: 2018/7/1
import sys
import os
sys.path.append(os.path.abspath(os.path.dirname(os.getcwd())))
import logRegres
import figure_plot
## step 1: load data
dataArr, labelMat = logRegres.loadDataSet()
test_x = dataArr
test_y = labelMat
## step 2: training...
print("step 2: training...")
print(logRegres.gradAscent(dataArr, labelMat))
optimalWeights = logRegres.gradAscent(dataArr, labelMat)
## step 3: testing
print("step 3: testing...")
accuracy = logRegres.testLogRegres(optimalWeights, test_x, test_y)
## step 4: show the result
print("step 4: show the result...")
print('The classify accuracy is: %.3f%%' % (accuracy * 100))
figure_plot.plotBestFit(optimalWeights.getA())
def main():
dataAttr,labelsMat = logRegres.loadDataSet()
weights = logRegres.gradAscent(dataAttr,labelsMat)
logRegres.plotBestFit(weights)
#!/usr/bin/python # -*- coding:utf-8 -*- import logRegres from numpy import * #5.2.2 训练算法：使用梯度上升找到最佳参数 dataArr, labelMat = logRegres.loadDataSet() print "回归系数:", logRegres.gradAscent(dataArr, labelMat) #5.2.3 分析数据：画出决策边界 weights = logRegres.gradAscent(dataArr, labelMat) logRegres.plotBestFit(weights.getA()) #5.2.4 训练算法：随机梯度上升 dataArr, labelMat = logRegres.loadDataSet() weights = logRegres.stocGradAscent0(array(dataArr), labelMat) logRegres.plotBestFit(weights) weights = logRegres.stocGradAscent1(array(dataArr), labelMat) logRegres.plotBestFit(weights) #5.3.2 测试算法：用Logistic回归进行分类 logRegres.multiTest()
# -*- 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()
def gradAscent():
dataArr, labelMat = logRegres.loadDataSet()
weights = logRegres.gradAscent(dataArr, labelMat)
print weights
logRegres.plotBestFit(weights.getA())
import logRegres
from numpy import *
if __name__ == '__main__':
dataArr, labelMat = logRegres.loadDataSet()
weights = logRegres.gradAscent(dataArr, labelMat)
logRegres.plotBestFit(weights.getA())
weights1 = logRegres.stocGradAscent0(array(dataArr), labelMat)
logRegres.plotBestFit(weights1)
weights2 = logRegres.stocGradAscent1(array(dataArr), labelMat)
logRegres.plotBestFit(weights2)
#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
####################################### 第二个图：随机梯度上升算法的例子 #################################
#随机梯度上升：在线学习方法（新样本来到时，对分类器进行增量式更新）
print "第二个图：随机梯度上升算法的例子" #
logRegres.plotBestFit(stocWeights)
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))
