def testGaussWeight():
xArr, yArr = re.loadDataSet('ex0.txt')
xMat = mat(xArr)
yMat = mat(yArr)
fig = plt.figure()
ax = fig.add_subplot(411) # 将画布分成1行1列，将从左到右，从上到下第一块显示图画
plt.yticks(linspace(2.5, 5, 6))
ax.scatter(xMat[:, 1].flatten().A[0],
yMat.T[:, 0].flatten().A[0],
c='purple',
label='realData',
marker='.')
xMat.sort(0)
weights = re.getGaussWeightArr([1, 0.5], xMat, 0.5)
ax = fig.add_subplot(412)
plt.yticks(linspace(0.6, 1, 9))
ax.plot(xMat[:, 1], weights)
plt.text(0.7, 0.75, r'$k=0.5$')
weights = re.getGaussWeightArr([1, 0.5], xMat, 0.1)
ax = fig.add_subplot(413)
plt.yticks(linspace(0, 1, 6))
ax.plot(xMat[:, 1], weights)
plt.text(0.7, 0.5, r'$k=0.1$')
weights = re.getGaussWeightArr([1, 0.5], xMat, 0.01)
ax = fig.add_subplot(414)
plt.yticks(linspace(0, 1, 6))
ax.plot(xMat[:, 1], weights, label='k=0.01')
plt.text(0.7, 0.5, r'$k=0.01$')
plt.show()
def main():
abX, abY = reg.loadDataSet('abalone.txt')
print '------------------------training----------------------'
yHat01 = lwlr.lwlrTest(abX[0:99], abX[0:99], abY[0:99], 0.1)
error01 = rssErr(abY[0:99], yHat01.T)
yHat1 = lwlr.lwlrTest(abX[0:99], abX[0:99], abY[0:99], 1)
error1 = rssErr(abY[0:99], yHat1.T)
yHat10 = lwlr.lwlrTest(abX[0:99], abX[0:99], abY[0:99], 10)
error10 = rssErr(abY[0:99], yHat10.T)
#the result show smaller kernel
print "yHat01:", yHat01, "error01:", error01
print "yHat1", yHat1, "error1:", error1
print "yHat10", yHat10, "error10", error10
print '------------------------testing-------------------------'
yHat01 = lwlr.lwlrTest(abX[100:199], abX[0:99], abY[0:99], 0.1)
error01 = rssErr(abY[100:199], yHat01.T)
yHat1 = lwlr.lwlrTest(abX[100:199], abX[0:99], abY[0:99], 1)
error1 = rssErr(abY[100:199], yHat1.T)
yHat10 = lwlr.lwlrTest(abX[100:199], abX[0:99], abY[0:99], 10)
error10 = rssErr(abY[100:199], yHat10.T)
#the result show smaller kernel
print "error01:", error01
print "error1:", error1
print "error10", error10
def testStandRegres():
xArr, yArr = re.loadDataSet('ex0.txt')
ws = re.standRegres(xArr, yArr)
xMat = mat(xArr)
yMat = mat(yArr)
fig = plt.figure()
ax = fig.add_subplot(111) # 将画布分成1行1列，将从左到右，从上到下第一块显示图画
ax.scatter(xMat[:, 1].flatten().A[0],
yMat.T[:, 0].flatten().A[0],
c='purple',
label='realData',
marker='.')
# scatter散点图
# matrix[a:b,c:d] 第a到b行，且第c到d列 左闭右开
# matrix[a,b] 第a行，第b列
xCopy = xMat.copy()
# xCopy.sort(0)#y轴方向排序
yHat = xCopy * ws
ax.plot(xCopy[:, 1], yHat, c='green')
# print yHat.T.flatten().A[0].size
# print yMat.flatten().A[0].size
# print yHat
# print yMat
correlation = corrcoef(yHat.T, yMat)
print correlation
plt.show()
def main():
abX, abY = reg.loadDataSet("abalone.txt")
print "------------------------training----------------------"
yHat01 = lwlr.lwlrTest(abX[0:99], abX[0:99], abY[0:99], 0.1)
error01 = rssErr(abY[0:99], yHat01.T)
yHat1 = lwlr.lwlrTest(abX[0:99], abX[0:99], abY[0:99], 1)
error1 = rssErr(abY[0:99], yHat1.T)
yHat10 = lwlr.lwlrTest(abX[0:99], abX[0:99], abY[0:99], 10)
error10 = rssErr(abY[0:99], yHat10.T)
# the result show smaller kernel
print "yHat01:", yHat01, "error01:", error01
print "yHat1", yHat1, "error1:", error1
print "yHat10", yHat10, "error10", error10
print "------------------------testing-------------------------"
yHat01 = lwlr.lwlrTest(abX[100:199], abX[0:99], abY[0:99], 0.1)
error01 = rssErr(abY[100:199], yHat01.T)
yHat1 = lwlr.lwlrTest(abX[100:199], abX[0:99], abY[0:99], 1)
error1 = rssErr(abY[100:199], yHat1.T)
yHat10 = lwlr.lwlrTest(abX[100:199], abX[0:99], abY[0:99], 10)
error10 = rssErr(abY[100:199], yHat10.T)
# the result show smaller kernel
print "error01:", error01
print "error1:", error1
print "error10", error10
def main():
xArr, yArr = reg.loadDataSet('ex0.txt')
print yArr[0]
print lwlr(xArr[0], xArr, yArr, 1.0)
print lwlr(xArr[0], xArr, yArr, 0.001)
yHat = lwlrTest(xArr, xArr, yArr, 0.003)
print "yHat:", yHat
plot(xArr, yArr)
def testAbalone():
xArr, yArr = re.loadDataSet('abalone.txt')
ws = re.standRegres(xArr, yArr)
print ws
for k in [2, 10]:
calcErr(xArr, yArr, 0, 299, k, 300, 350, ws)
calcErr(xArr, yArr, 0, 299, k, 350, 400, ws)
calcErr(xArr, yArr, 0, 299, k, 400, 450, ws)
calcErr(xArr, yArr, 0, 299, k, 450, 500, ws)
calcErr(xArr, yArr, 0, 299, k, 500, 600, ws)
print ''
def test1():
xArr, yArr = regression.loadDataSet('ex0.txt')
ws = regression.standRegress(xArr, yArr)
xMat = np.mat(xArr)
yMat = np.mat(yArr)
fig = plt.figure()
ax = fig.add_subplot(111)
ax.scatter(xMat[:, 1].flatten().A[0], yMat.T[:, 0].flatten().A[0])
x = xMat.copy()
x.sort(0)
y = x * ws
ax.plot(x[:, 1], y)
plt.show()
def test2():
xArr, yArr = regression.loadDataSet('ex0.txt')
yHat = regression.lwlrTest(xArr, xArr, yArr, 0.01)
xMat = np.mat(xArr)
srtInd = xMat[:, 1].argsort(0)
xSort = xMat[srtInd][:, 0, :]
fig = plt.figure()
ax = fig.add_subplot(111)
ax.plot(xSort[:, 1], yHat[srtInd])
ax.scatter(xMat[:, 1].flatten().A[0],
np.mat(yArr).T.flatten().A[0],
s=2,
c='red')
plt.show()
def lwlrResult(fileName, weight):
xArr, yArr = regression.loadDataSet(fileName)
yHat = regression.lwlrTest(xArr, xArr, yArr, weight) #取得各点的回归系数矩阵
# 画出回归曲线
xMat = mat(xArr)
srtInd = xMat[:, 1].argsort(0)
xSort = xMat[srtInd][:, 0, :]
fig = plt.figure()
ax = fig.add_subplot(111)
ax.plot(xSort[:, 1], yHat[srtInd])
ax.scatter(xMat[:, 1].flatten().A[0],
mat(yArr).T.flatten().A[0],
s=2,
c='red')
plt.show()
def test1():
abX, abY = regression.loadDataSet('abalone.txt')
yHat01 = regression.lwlrTest(abX[0:99], abX[0:99], abY[0:99], 0.1)
yHat1 = regression.lwlrTest(abX[0:99], abX[0:99], abY[0:99], 1)
yHat10 = regression.lwlrTest(abX[0:99], abX[0:99], abY[0:99], 10)
print(regression.rssError(abY[0:99], yHat01.T))
print(regression.rssError(abY[0:99], yHat1.T))
print(regression.rssError(abY[0:99], yHat10.T))
print('-------------------------------------------')
yHat01 = regression.lwlrTest(abX[100:199], abX[0:99], abY[0:99], 0.1)
yHat1 = regression.lwlrTest(abX[100:199], abX[0:99], abY[0:99], 1)
yHat10 = regression.lwlrTest(abX[100:199], abX[0:99], abY[0:99], 10)
print(regression.rssError(abY[100:199], yHat01.T))
print(regression.rssError(abY[100:199], yHat1.T))
print(regression.rssError(abY[100:199], yHat10.T))
def testLwlr():
xArr, yArr = re.loadDataSet('ex0.txt')
xMat = mat(xArr)
yMat = mat(yArr)
fig = plt.figure()
ax = fig.add_subplot(311) # 将画布分成1行1列，将从左到右，从上到下第一块显示图画
privateShow(ax, xMat, yMat, 1.0)
ax = fig.add_subplot(312)
privateShow(ax, xMat, yMat, 0.02)
ax = fig.add_subplot(313)
privateShow(ax, xMat, yMat, 0.002)
plt.show()
def lineResult(fileName):
xArr, yArr = regression.loadDataSet(fileName)
ws = regression.standRegres(xArr, yArr) #取得回归系数矩阵
# 画出回归曲线
xMat = mat(xArr)
yHat = xMat * ws
fig = plt.figure()
ax = fig.add_subplot(111)
xCopy = xMat.copy()
xCopy.sort(0)
yHat = xCopy * ws
ax.plot(xCopy[:, 1], yHat)
ax.scatter(xMat[:, 1].flatten().A[0],
mat(yArr).T.flatten().A[0],
s=2,
c='red')
plt.show()
def plotwMat():
"""
函数说明:绘制岭回归系数矩阵
"""
font = FontProperties(fname=r"c:\windows\fonts\simsun.ttc", size=14)
abX, abY = rg.loadDataSet('abalone.txt')
redgeWeights = ridgeTest(abX, abY)
fig = plt.figure()
ax = fig.add_subplot(111)
ax.plot(redgeWeights)
ax_title_text = ax.set_title(u'log(lambada)与回归系数的关系', FontProperties=font)
ax_xlabel_text = ax.set_xlabel(u'log(lambada)', FontProperties=font)
ax_ylabel_text = ax.set_ylabel(u'回归系数', FontProperties=font)
plt.setp(ax_title_text, size=20, weight='bold', color='red')
plt.setp(ax_xlabel_text, size=10, weight='bold', color='black')
plt.setp(ax_ylabel_text, size=10, weight='bold', color='black')
plt.show()
def plotstageWiseMat():
"""
函数说明:绘制岭回归系数矩阵
Website:
http://www.cuijiahua.com/
Modify:
2017-11-20
"""
font = FontProperties(fname=r"c:\windows\fonts\simsun.ttc", size=14)
xArr, yArr = rg.loadDataSet('abalone.txt')
returnMat = stageWise(xArr, yArr, 0.005, 1000)
fig = plt.figure()
ax = fig.add_subplot(111)
ax.plot(returnMat)
ax_title_text = ax.set_title(u'前向逐步回归:迭代次数与回归系数的关系', FontProperties=font)
ax_xlabel_text = ax.set_xlabel(u'迭代次数', FontProperties=font)
ax_ylabel_text = ax.set_ylabel(u'回归系数', FontProperties=font)
plt.setp(ax_title_text, size=15, weight='bold', color='red')
plt.setp(ax_xlabel_text, size=10, weight='bold', color='black')
plt.setp(ax_ylabel_text, size=10, weight='bold', color='black')
plt.show()
def plotlwlrRegression():
"""
函数说明:绘制多条局部加权回归曲线
Parameters:
无
Returns:
无
"""
font = FontProperties(fname=r"c:\windows\fonts\simsun.ttc", size=14)
xArr, yArr = rg.loadDataSet('ex0.txt') # 加载数据集
yHat_1 = lwlrTest(xArr, xArr, yArr, 1.0) # 根据局部加权线性回归计算yHat
yHat_2 = lwlrTest(xArr, xArr, yArr, 0.01) # 根据局部加权线性回归计算yHat
yHat_3 = lwlrTest(xArr, xArr, yArr, 0.003) # 根据局部加权线性回归计算yHat
xMat = np.mat(xArr) # 创建xMat矩阵
yMat = np.mat(yArr) # 创建yMat矩阵
srtInd = xMat[:, 1].argsort(0) # 排序，返回索引值
xSort = xMat[srtInd][:, 0, :]
fig, axs = plt.subplots(nrows=3, ncols=1, sharex=False,
sharey=False, figsize=(10, 8))
axs[0].plot(xSort[:, 1], yHat_1[srtInd], c='red') # 绘制回归曲线
axs[1].plot(xSort[:, 1], yHat_2[srtInd], c='red') # 绘制回归曲线
axs[2].plot(xSort[:, 1], yHat_3[srtInd], c='red') # 绘制回归曲线
axs[0].scatter(xMat[:, 1].flatten().A[0], yMat.flatten().A[0],
s=20, c='blue', alpha=.5) # 绘制样本点
axs[1].scatter(xMat[:, 1].flatten().A[0], yMat.flatten().A[0],
s=20, c='blue', alpha=.5) # 绘制样本点
axs[2].scatter(xMat[:, 1].flatten().A[0], yMat.flatten().A[0],
s=20, c='blue', alpha=.5) # 绘制样本点
# 设置标题,x轴label,y轴label
axs0_title_text = axs[0].set_title(u'局部加权回归曲线,k=1.0', FontProperties=font)
axs1_title_text = axs[1].set_title(u'局部加权回归曲线,k=0.01', FontProperties=font)
axs2_title_text = axs[2].set_title(
u'局部加权回归曲线,k=0.003', FontProperties=font)
plt.setp(axs0_title_text, size=8, weight='bold', color='red')
plt.setp(axs1_title_text, size=8, weight='bold', color='red')
plt.setp(axs2_title_text, size=8, weight='bold', color='red')
plt.xlabel('X')
plt.show()
def abaloneTest():
""" 预测鲍鱼的年龄
描述：机器学习实战示例8.3 预测鲍鱼的年龄
INPUT：
无
OUPUT：
无
"""
# 加载数据
abX, abY = regression.loadDataSet("./data/abalone.txt")
# 使用不同的核进行预测
oldyHat01 = regression.lwlrTest(abX[0:99], abX[0:99], abY[0:99], 0.1)
oldyHat1 = regression.lwlrTest(abX[0:99], abX[0:99], abY[0:99], 1)
oldyHat10 = regression.lwlrTest(abX[0:99], abX[0:99], abY[0:99], 10)
# 打印出不同的核预测值与训练数据集上的真实值之间的误差大小
print("old yHat01 error Size is :",
regression.rssError(abY[0:99], oldyHat01.T))
print("old yHat1 error Size is :",
regression.rssError(abY[0:99], oldyHat1.T))
print("old yHat10 error Size is :",
regression.rssError(abY[0:99], oldyHat10.T))
# 打印出不同的核预测值与新数据集（测试数据集）上的真实值之间的误差大小
newyHat01 = regression.lwlrTest(abX[100:199], abX[0:99], abY[0:99], 0.1)
print("new yHat01 error Size is :",
regression.rssError(abY[0:99], newyHat01.T))
newyHat1 = regression.lwlrTest(abX[100:199], abX[0:99], abY[0:99], 1)
print("new yHat1 error Size is :",
regression.rssError(abY[0:99], newyHat1.T))
newyHat10 = regression.lwlrTest(abX[100:199], abX[0:99], abY[0:99], 10)
print("new yHat10 error Size is :",
regression.rssError(abY[0:99], newyHat10.T))
# 使用简单的线性回归进行预测，与上面的计算进行比较
standWs = regression.standRegres(abX[0:99], abY[0:99])
standyHat = mat(abX[100:199]) * standWs
print("standRegress error Size is:",
regression.rssError(abY[100:199], standyHat.T.A))
# !/usr/bin/env python # -*- coding:utf-8 -*- # @Time : 2018. # @Author : 绿色羽毛 # @Email : [email protected] # @Blog : https://blog.csdn.net/ViatorSun # @Note : 线性回归 import regression from numpy import * import matplotlib.pyplot as plt xArr , yArr = regression.loadDataSet("data.txt") ws = regression.standRegres(xArr,yArr) print(ws) #预测值yHat xMat = mat(xArr) yMat = mat(yArr) yHat = xMat*ws #绘制数据集散列点 fig = plt.figure() #创建子图 ax = fig.add_subplot(1,1,1) #添加一个（1,1,1）子图 x = xMat[:,1].flatten().A[0] y = yMat.T[:,0].flatten().A[0]
# print(yArr[0])
# print(regression.lwlr(xArr[0], xArr, yArr, 1.0))
# print(regression.lwlr(xArr[0], xArr, yArr, 0.001))
#
# yHat = regression.lwlrTest(xArr, xArr, yArr, 0.003)
# xMat = mat(xArr)
# srtInd = xMat[:, 1].argsort(0)
# xSort = xMat[srtInd][:, 0, :]
#
# import matplotlib.pyplot as plt
# fig = plt.figure()
# ax = fig.add_subplot(111)
# # ax.plot(xSort[:, 1], yHat[srtInd])
# ax.scatter(xMat[:, 1].flatten().A[0], mat(yArr).T.flatten().A[0], s=2, c='red')
# plt.show()
# abX, abY = regression.loadDataSet('../data/abalone.txt')
# ridgeWeights = regression.ridgeTest(abX, abY)
# print(ridgeWeights)
#
# import matplotlib.pyplot as plt
# fig = plt.figure()
# ax = fig.add_subplot(111)
# ax.plot(ridgeWeights)
# plt.show()
xArr, yArr = regression.loadDataSet('../data/abalone.txt')
regression.stageWise(xArr, yArr, 0.01, 200)
# -*- coding:utf-8 -*-
import regression
from numpy import *
xArr,yArr = regression.loadDataSet("abalone.txt")
#stageWeight = regression.stageWise(xArr, yArr, 0.01, 200)
#print (stageWeight)
stageWeight = regression.stageWise(xArr, yArr, 0.0001, 50000)
#print (stageWeight)
# coding: utf-8
# linear_regression/test_multiple.py
import regression
import numpy as np
from mpl_toolkits.mplot3d import Axes3D
from matplotlib import cm
import matplotlib.pyplot as plt
import matplotlib.ticker as mtick
if __name__ == "__main__":
srcX, y = regression.loadDataSet('data/houses.txt')
# 新建特征
m, n = srcX.shape
X = regression.normalize(srcX.copy())
X = np.concatenate((np.ones((m, 1)), X), axis=1)
rate = 1
maxLoop = 50
epsilon = 1
result, timeConsumed = regression.bgd(rate, maxLoop, epsilon, X, y)
theta, errors, thetas = result
print('theta is:')
print(theta)
print('........')
# 预测价格
normalizedSize = (1650 - srcX[:, 0].mean(0)) / srcX[:, 0].std(0)
normalizedBr = (3 - srcX[:, 1].mean(0)) / srcX[:, 1].std(0)
# -*- coding=utf-8 -*-
import regression
from numpy import *
xArr,yArr = regression.loadDataSet("ex0.txt")
#l0 = regression.lwlr(xArr[0], xArr, yArr, 1.0)
#l1 = regression.lwlr(xArr[0],xArr,yArr,0.001)
#print ("l0 is %s" % l0)
#print ("l1 is %s" % l1)
yHat = regression.lwlrTest(xArr, xArr, yArr, 1.0)
print ("yHat is %s" % yHat)
xMat = mat(xArr)
#axis=0 按列排序;axis=1 按行排序
#返回xMat下标编号
srtInd = xMat[:,1].argsort(0)
#print("srtInd is %s" % srtInd)
xSort = xMat[srtInd][:,0,:] #这是什么意思？？？？？
#print ("xSort is %s"% xSort)
import matplotlib.pyplot as plt
# coding: utf-8
# linear_regression/test_sgd.py
import regression
from matplotlib import cm
from mpl_toolkits.mplot3d import axes3d
import matplotlib.pyplot as plt
import matplotlib.ticker as mtick
import numpy as np
if __name__ == "__main__":
X, y = regression.loadDataSet('data/ex1.txt');
m,n = X.shape
X = np.concatenate((np.ones((m,1)), X), axis=1)
rate = 0.01
maxLoop = 100
epsilon =0.01
result, timeConsumed = regression.sgd(rate, maxLoop, epsilon, X, y)
theta, errors, thetas = result
# 绘制拟合曲线
fittingFig = plt.figure()
title = 'sgd: rate=%.2f, maxLoop=%d, epsilon=%.3f \n time: %ds'%(rate,maxLoop,epsilon,timeConsumed)
ax = fittingFig.add_subplot(111, title=title)
trainingSet = ax.scatter(X[:, 1].flatten().A[0], y[:,0].flatten().A[0])
xCopy = X.copy()
xCopy.sort(0)
def main():
xArr, yArr = reg.loadDataSet('abalone.txt')
rntMat = stageWise(xArr, yArr,0.01,200)
print rntMat
# coding: utf-8
# linear_regression/test_lwr.py
import regression
import matplotlib.pyplot as plt
import matplotlib.ticker as mtick
import numpy as np
if __name__ == "__main__":
srcX, y = regression.loadDataSet('data/lwr.txt')
m, n = srcX.shape
srcX = np.concatenate((srcX[:, 0], np.power(srcX[:, 0], 2)), axis=1)
# 特征缩放
X = regression.standardize(srcX.copy())
X = np.concatenate((np.ones((m, 1)), X), axis=1)
rate = 0.1
maxLoop = 1000
epsilon = 0.01
predicateX = regression.standardize(np.matrix([[8, 64]]))
predicateX = np.concatenate((np.ones((1, 1)), predicateX), axis=1)
result, t = regression.lwr(rate, maxLoop, epsilon, X, y, predicateX, 1)
theta, errors, thetas = result
result2, t = regression.lwr(rate, maxLoop, epsilon, X, y, predicateX, 0.1)
theta2, errors2, thetas2 = result2
# 打印特征点
# coding: utf-8
# linear_regression/test_temperature_polynomial.py
import regression
import matplotlib.pyplot as plt
import matplotlib.ticker as mtick
import numpy as np
if __name__ == "__main__":
srcX, y = regression.loadDataSet('temperature.txt')
m, n = srcX.shape
srcX = np.concatenate((srcX[:, 0], np.power(srcX[:, 0], 2)), axis=1)
# 特征缩放
X = regression.standardize(srcX.copy())
X = np.concatenate((np.ones((m, 1)), X), axis=1)
rate = 0.1
maxLoop = 1000
epsilon = 0.01
result, timeConsumed = regression.bgd(rate, maxLoop, epsilon, X, y)
theta, errors, thetas = result
# 打印特征点
fittingFig = plt.figure()
title = 'polynomial with bgd: rate=%.2f, maxLoop=%d, epsilon=%.3f \n time: %ds' % (
rate, maxLoop, epsilon, timeConsumed)
ax = fittingFig.add_subplot(111, title=title)
trainingSet = ax.scatter(srcX[:, 1].flatten().A[0], y[:, 0].flatten().A[0])
# encoding=utf-8
import regression
from numpy import *
xArr, yArr = regression.loadDataSet("filename")
ws = regression.standRegres(xArr, yArr)
'''
# 绘图
xMat = mat(xArr)
yMat = mat(yArr)
yHat = xMat * ws
import matplotlib.pyplot as plt
fig = plt.figure()
ax = fig.add_subplot(111)
ax.scatter(xMat[:, 1].flatten().A[0], yMat.T[:, 0].flatten().A[0])
xCopy = xMat.copy()
xCopy.sort(0)
yHat = xCopy * ws
ax.plot(xCopy[:, 1], yHat)
plt.show()
#相关系数:用来衡量预测值和真实值的匹配程序
corrcoef(yHat.T, yMat)
'''
# 得到数据集中所有点的估计
yHat = regression.lwlrTest(xArr, xArr, yArr, 0.003)
# # 复制，排序
# xCopy = xMat.copy()
# xCopy.sort(0)
# yHat = xCopy * ws
# # plot画线
# ax.plot(xCopy[:,1], yHat)
# # plt.show()
#
# #相关系数
# #print('corrcoef:');print(corrcoef(yHat.T,yMat)) #预测值和真实值得匹配程度
# #corrcoef:
# # [[ 1. 0.13653777]
# # [ 0.13653777 1. ]]
# #end：Liner Regression
xArr,yArr = regression.loadDataSet('ex0.txt')
#对单点进行估计,输出预测值
print('xArr[0]:');print(xArr[0])
# xArr[0]:
# [1.0, 0.067732]
print(yArr[0]) #output: 3.176513
print(regression.lwlr(xArr[0],xArr,yArr,1.0)) #output: martix([[ 3.12204471]])
print(regression.lwlr(xArr[0],xArr,yArr,0.001)) #output: martix([[ 3.20175729]])
#为了得到数据集里所有点的估计，可以调用LwlrTest()函数：
yHat = regression.lwlrTest(xArr,xArr,yArr,0.003)
print('all points about yHat:'); print(yHat)
#查看拟合效果
xMat = mat(xArr) #xArr是什么？
srtInd = xMat[:,1].argsort(0) #对xArr排序
import regression
from numpy import *
xArr, yArr = regression.loadDataSet('abalone.txt')
regression.stageWise(xArr, yArr, 0.01, 200)
regression.stageWise(xArr, yArr, 0.001, 5000)
xMat = mat(xArr)
yMat = mat(yArr).T
xMat = regression.regularize(xMat)
yM = mean(yMat, 0)
yMat = yMat - yM
weights = regression.standRegres(xMat, yMat.T)
print(weights.T)
from regression import loadDataSet
from Multivariate import LinearRegresion
from ROOT import *
from array import array
from math import *
xs, ys = loadDataSet('ex0.txt')
x0, x1 = zip(*xs)
ndata = len(ys)
nregr = 100
dregr = 1.0/nregr
lr = LinearRegresion(xs,ys)
lwlr = LinearRegresion(xs,ys,lambda x,y: exp(-(x-y)**(x-y)/(2*0.01**2)), 0.0001 )
xlr = [ (1.0,dregr*i) for i in range(nregr) ]
ylr = map( lr.GetValue, xlr )
xlwlr = xlr
ylwlr = map( lwlr.GetValue, xlwlr )
gdata = TGraph( ndata, array('f',x1) , array('f',ys) )
glr = TGraph( nregr, array('f',zip(*xlr)[1]) , array('f',ylr) )
glwlr = TGraph( nregr, array('f',zip(*xlwlr)[1]), array('f',ylwlr) )
gdata.SetMarkerStyle(20)
glr .SetLineWidth(2)
glwlr.SetLineWidth(2)
glr .SetLineColor(kRed)
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Sat May 12 06:19:52 2018
@author: kukuLife
"""
import numpy as np
import regression
X, y = regression.loadDataSet('ex1.txt')
m, n = X.shape
X = np.concatenate((np.ones((m, 1)), X), axis=1)
maxLoop = 1500
epsilon = 0.01
rate = 0.02
theta, thetas, errors = regression.sgd(maxLoop, rate, X, y, epsilon)
__author__ = 'sunbeansoft'
import regression as reg
import matplotlib.pyplot as plt
from numpy import *
xArr, yArr = reg.loadDataSet('ex0.txt')
# wx = reg.standRegres(xArr, yArr)
# print wx
#
# xMat = mat(xArr)
# yMat = mat(yArr)
#
# yHat = xMat * wx
# corrcoef(yHat.H, yMat)
#
# fig = plt.figure()
# ax = fig.add_subplot(111)
# ax.scatter(xMat[:, 1].flatten().A[0], yMat.T[:, 0].flatten().A[0])
# xCopy = xMat.copy()
# xCopy.sort(0)
# yHat = xCopy * wx
# ax.plot(xCopy[:, 1], yHat)
# plt.show()
print reg.lwlr(xArr[0], xArr, yArr, 1.0)
print reg.lwlr(xArr[0], xArr, yArr, 0.001)
yHat = reg.lwlrTest(xArr, xArr, yArr, 0.003)
xMat = mat(xArr)
srtInd = xMat[:, 1].argsort(0)
import numpy as np
import matplotlib as cm
import matplotlib.pyplot as plt
import matplotlib.ticker as mtick
import regression as re
if __name__ == '__main__':
X, y = re.loadDataSet("data/ex1.txt") # coursera的《machine learning》第二周实验数据
m, n = X.shape
X = np.concatenate((np.ones((m, 1)), X), axis=1)
theta, timeConsumed = re.standRegres(X, y)
print('消耗[%s] s \n 参数矩阵:\n %s' % (timeConsumed, theta))
fittingFig = plt.figure()
title = 'StandRegress time: %s' % timeConsumed
ax = fittingFig.add_subplot(111, title=title)
trainingSet = ax.scatter(X[:, 1].flatten().A[0], y[:, 0].flatten().A[0])
xCopy = X.copy()
xCopy.sort(0)
yHat = xCopy * theta
fittingLine, = ax.plot(xCopy[:, 1], yHat, color='g')
ax.set_xlabel('Population of City in 10,000s')
ax.set_ylabel('Profit in $10,000s')
plt.legend([trainingSet, fittingLine],
['Training Set', 'Linear Regression'])
plt.show()
def main():
abX, abY = reg.loadDataSet('abalone.txt')
ridgeWeights = ridgeTest(abX, abY)
plotFigure(ridgeWeights)
import regression
import matplotlib.pyplot as plt
from numpy import *
xArr,yArr=regression.loadDataSet('ex0.txt')
#regression.lwlr(xArr[0],xArr,yArr,1.0)
#a = regression.lwlr(xArr[0],xArr,yArr,0.001)
yHat1 = regression.lwlrTest(xArr, xArr, yArr,1)
yHat2 = regression.lwlrTest(xArr, xArr, yArr,0.01)
yHat3 = regression.lwlrTest(xArr, xArr, yArr,0.003)
#print("yHat1 : %s" % (yHat1))
xMat=mat(xArr)
srtInd = xMat[:,1].argsort(0)
#print("srtInd : %s" % (srtInd))
xSort=xMat[srtInd][:,0,:]
#print("xSort : %s" % (xSort))
fig = plt.figure()
ax1 = fig.add_subplot(311)
ax1.plot(xSort[:,1],yHat1[srtInd])
ax1.scatter(xMat[:,1].flatten().A[0], mat(yArr).T.flatten().A[0] , s=2, c='red')
ax2 = fig.add_subplot(312)
ax2.plot(xSort[:,1],yHat2[srtInd])
ax2.scatter(xMat[:,1].flatten().A[0], mat(yArr).T.flatten().A[0] , s=2, c='red')
ax3 = fig.add_subplot(313)
ax3.plot(xSort[:,1],yHat3[srtInd])
ax3.scatter(xMat[:,1].flatten().A[0], mat(yArr).T.flatten().A[0] , s=2, c='red')
# This Python file uses the following encoding: utf-8
import os, sys
import regression
reload(regression)
from numpy import *
xArr,yArr=regression.loadDataSet('C:\Users\YAN\Desktop\\regression/ex0.txt')
'''
#---------标准回归----------#
print (xArr[0:2])
ws=regression.standRegres(xArr,yArr)
print ws
xMat=mat(xArr)
yMat=mat(yArr)
yHat=xMat*ws
import matplotlib.pyplot as pl
fig=pl.figure()
ax=fig.add_subplot(111)
ax.scatter(xMat[:,1].flatten().A[0],yMat.T[:,0].flatten().A[0])
xCopy=xMat.copy(0)# sort along the first axis
yHat=xCopy*ws
ax.plot(xCopy[:,1],yHat)
pl.show()
'''
#print(corrcoef(yHat.T,yMat))
'''
print yArr[0]
print(regression.lwlr(xArr[0],xArr,yArr,1.0))
print(regression.lwlr(xArr[0],xArr,yArr,0.001))
'''
'''
#----------局部回归--------#
import regression
from numpy import *
xArray, yArray = regression.loadDataSet("./regression/abalone.txt")
# yHat01 = regression.lwlrTest(xArray[100:199], xArray[0:99], yArray[0:99], 0.1)
# yHat1 = regression.lwlrTest(xArray[100:199], xArray[0:99], yArray[0:99], 1)
# yHat10 = regression.lwlrTest(xArray[100:199], xArray[0:99], yArray[0:99], 10)
# print regression.rssError(yArray[100:199], yHat01)
# print regression.rssError(yArray[100:199], yHat1)
# print regression.rssError(yArray[100:199], yHat10)
# wsStand = regression.standRegres(xArray[0:99], yArray[0:99])
# yHat = mat(xArray[100:199]) * wsStand
# print regression.rssError(yArray[100:199], yHat.T.A)
# ridgeWeights = regression.ridgeTest(xArray, yArray)
# import matplotlib.pyplot as plt
# fig = plt.figure()
# ax = fig.add_subplot(111)
# ax.plot(ridgeWeights)
# plt.show()
print regression.stageWise(xArray, yArray, 0.01, 200)
# coding: utf-8
# linear_regression/test_temperature_normal.py
import regression as re
from matplotlib import cm
from mpl_toolkits.mplot3d import axes3d
import matplotlib.pyplot as plt
import matplotlib.ticker as mtick
import numpy as np
if __name__ == '__main__':
X, y = re.loadDataSet('data/temperature.txt');
m, n = X.shape
X = np.concatenate((np.ones((m, 1)), X), axis=1)
rate = 0.0001
maxLoop = 1000
epsilon = 0.01
result, timeConsumed = re.bgd(rate, maxLoop, epsilon, X, y)
theta, errors, thetas = result
# 绘制拟合曲线
fittingFig = plt.figure()
title = 'bgd: rate=%.3f, maxLoop=%d, epsilon=%.3f \n time: %ds' % (rate, maxLoop, epsilon, timeConsumed)
ax = fittingFig.add_subplot(111, title=title)
trainingSet = ax.scatter(X[:, 1].flatten().A[0], y[:, 0].flatten().A[0])
xCopy = X.copy()
xCopy.sort(0)
# -*- coding: utf-8 -*-
"""
Created on Fri May 12 16:07:29 2017
@author: 凯风
"""
import regression
from numpy import *
from imp import reload
import matplotlib.pyplot as plt
reload(regression)
xArr, yArr = regression.loadDataSet('ex0.txt')
xArr[0:2]
ws = regression.standRegres(xArr, yArr) # 求回归系数
ws
xMat = mat(xArr)
yMat = mat(yArr)
yHat = xMat * ws # 拟合曲线
# 绘制拟合直线和散点图
fig = plt.figure()
ax = fig.add_subplot(111)
ax.scatter(xMat[:, 1].flatten().A[0], yMat.T[:, 0].flatten().A[0])
xCopy = xMat.copy()
xCopy.sort(0)
yHat = xCopy * ws
ax.plot(xCopy[:, 1], yHat)
plt.show()
# xArr, yArr = regression.loadDataSet('ex0.txt')
# yHat = regression.lwlrTest(xArr,xArr,yArr,0.01)
# print yHat
# xMat = mat(xArr)
# srtInd = xMat[:,1].argsort(0)
# xSort = xMat[srtInd][:,0,:]
# fig = plt.figure()
# ax = fig.add_subplot(111)
# ax.plot(xSort[:,1], yHat[srtInd])
# ax.scatter(xMat[:,1].flatten().A[0], mat(yArr).T.flatten().A[0], s=2, c='red')
# plt.show()
#################### baoyu nianling #############################
abX, abY = regression.loadDataSet('abalone.txt')
# yHat01 = regression.lwlrTest(abX[0:99],abX[0:99],abY[0:99],0.1)
# yHat02 = regression.lwlrTest(abX[0:99],abX[0:99],abY[0:99],1)
# yHat03 = regression.lwlrTest(abX[0:99],abX[0:99],abY[0:99],10)
# print regression.rssError(abY[0:99], yHat01.T)
# print regression.rssError(abY[0:99], yHat02.T)
# print regression.rssError(abY[0:99], yHat03.T)
#print regression.ridgeRegres(abX, abY, 1)
# ridgeWeights = regression.ridgeTest(abX, abY)
# print ridgeWeights
# fig = plt.figure()
# -*- coding=utf-8 -*-
import regression
from numpy import *
xArr, yArr = regression.loadDataSet("ex0.txt")
#l0 = regression.lwlr(xArr[0], xArr, yArr, 1.0)
#l1 = regression.lwlr(xArr[0],xArr,yArr,0.001)
#print ("l0 is %s" % l0)
#print ("l1 is %s" % l1)
yHat = regression.lwlrTest(xArr, xArr, yArr, 1.0)
print("yHat is %s" % yHat)
xMat = mat(xArr)
#axis=0 按列排序;axis=1 按行排序
#返回xMat下标编号
srtInd = xMat[:, 1].argsort(0)
#print("srtInd is %s" % srtInd)
xSort = xMat[srtInd][:, 0, :] #这是什么意思？？？？？
#print ("xSort is %s"% xSort)
import matplotlib.pyplot as plt
fig = plt.figure()
ax = fig.add_subplot(111)
ax.plot(xSort[:, 1], mat(yHat[srtInd])) #这里有问题？？？？？
ax.scatter(mat(xArr)[:, 1].flatten().A[0],
mat(yArr).T.flatten().A[0],
s=2,
c='blue')
# -*- coding:utf-8 -*-
import regression
from numpy import *
abX,abY = regression.loadDataSet("abalone.txt")
ridgeWeight = regression.ridgeTest(abX, abY)
#print ("ridgeWeight is %s" % ridgeWeight)
#展现回归系数与log（lam）的关系
#lam非常小时，与线性回归一致
#lam非常大时，系数全部缩减成0
import matplotlib.pyplot as plt
fig = plt.figure()
ax = fig.add_subplot(111)
ax.plot(ridgeWeight)
plt.show()
# 预测鲍鱼的年龄
import regression
def rssError(yArr, yHatArr):
return ((yArr - yHatArr)**2).sum()
if __name__ == '__main__':
xArr, yArr = regression.loadDataSet('../data/abalone.txt')
# yHat01 = regression.lwlrTest(xArr[0:99], xArr[0:99], yArr[0:99], 0.1)
# yHat1 = regression.lwlrTest(xArr[0:99], xArr[0:99], yArr[0:99], 1)
# yHat10 = regression.lwlrTest(xArr[0:99], xArr[0:99], yArr[0:99], 10)
# # 为了分析预测误差的大小，可以用函数 rssError() 计算出这一指标
# print(rssError(yArr[0:99], yHat01.T))
# print(rssError(yArr[0:99], yHat1.T))
# print(rssError(yArr[0:99], yHat10.T))
# print('在新数据上的误差：')
# yHat01 = regression.lwlrTest(xArr[100:199], xArr[0:99], yArr[0:99], 0.1)
# yHat1 = regression.lwlrTest(xArr[100:199], xArr[0:99], yArr[0:99], 1)
# yHat10 = regression.lwlrTest(xArr[100:199], xArr[0:99], yArr[0:99], 10)
# print(rssError(yArr[100:199], yHat01.T))
# print(rssError(yArr[100:199], yHat1.T))
# print(rssError(yArr[100:199], yHat10.T))
# 使用岭回归的方式
ridgeWeights = regression.ridgeTest(xArr, yArr)
import matplotlib.pyplot as plt
fig = plt.figure()
ax = fig.add_subplot(111)
import regression
#xArr,yArr=regression.loadDataSet('ex0.txt')
#regValue = regression.lwlr(xArr[0],xArr,yArr,1.0)
#print(regValue)
#regression.lwlr(xArr[0],xArr,yArr,0.001)
xArr,yArr=regression.loadDataSet('abalone.txt')
regression.stageWise(xArr,yArr,0.01,200)
denom = xTx + np.eye(np.shape(xMat)[1]) * lam
if np.linalg.det(denom) == 0.0:
print("This matrix is singular, cannot do inverse")
return
ws = denom.I * (xMat.T * yMat)
return ws
def ridgeTest(xArr, yArr):
xMat = np.mat(xArr)
yMat = np.mat(yArr).T
yMean = np.mean(yMat, 0)
yMat = yMat - yMean
xMeans = np.mean(xMat, 0)
xVar = np.var(xMat, 0)
xMat = (xMat - xMeans) / xVar
numTestPts = 30
wMat = np.zeros((numTestPts, np.shape(xMat)[1]))
for i in range(numTestPts):
ws = ridgeRegress(xMat, yMat, np.exp(i - 10))
wMat[i, :] = ws.T
return wMat
abX, abY = regression.loadDataSet('abalone.txt')
ridgeWeights = ridgeTest(abX, abY)
fig = plt.figure()
ax = fig.add_subplot(111)
ax.plot(ridgeWeights)
plt.show()
import regression
import matplotlib.pyplot as plt
from numpy import *
xArr,yArr=regression.loadDataSet('/home/everton.gago/projetos/braskem/data/data.csv')
ws = regression.standRegres(xArr,yArr)
xMat=mat(xArr)
yMat=mat(yArr)
yHat = xMat*ws
corr = corrcoef(yHat.T, yMat)
print 'Corr Coef: ', corr
fig = plt.figure()
ax = fig.add_subplot(111)
ax.scatter(xMat[:,1].flatten().A[0], yMat.T[:,0].flatten().A[0])
xCopy=xMat.copy()
xCopy.sort(0)
yHat=xCopy*ws
ax.plot(xCopy[:,1],yHat)
plt.show()
