转载: scikit-learn学习之回归分析
版权声明:<—— 本文为作者呕心沥血打造,若要转载,请注明出处@http://blog.csdn.net/gamer_gyt <——
======================================================================
本系列博客主要参考 Scikit-Learn 官方网站上的每一个算法进行,并进行部分翻译,如有错误,请大家指正
======================================================================
另外一篇基于《机器学习实战》的Logistic回归分析的博客请参考:点击阅读,其主要是采用Python代码实现回归模型
还有一篇是纯实战案例博客请参考 ,Logistic回归模型案例实战:《机器学习实战》Logistic回归算法(2)
目录:
1、概念
2、简单线性回归(Simple Liner Regession)
3、多元性回归(Mutiple Regession)
4、非线性回归(Logistic Regession)
一:概念
1:集中趋势衡量
2:离散程度的衡量
3:回归中的相关度
4:R平方值
5:皮尔逊相关系数和R平方值计算示例
- #coding:utf-8
- \’\’\’\’\’
- Created on 2015年11月8日
- @author: Administrator
- \’\’\’
- import numpy as np
- import math
- #求解皮尔逊相关系数
- def computeCorrelation(X, Y):
- xBar = np.mean(X)
- yBar = np.mean(Y)
- SSR = 0
- varX = 0
- varY = 0
- for i in range(0, len(X)):
- #对应分子部分
- diffXXBar = X[i] – xBar
- diffYYBar = Y[i] – yBar
- SSR +=(diffXXBar * diffYYBar)
- #对应分母求和部分
- varX += diffXXBar**2
- varY += diffYYBar**2
- SST = math.sqrt(varX * varY)
- return SSR/SST
- def polyfit(x, y, degree):
- results = {}
- #coeffs 为相关系数,x自变量,y因变量,degree为最高幂
- coeffs = np.polyfit(x, y, degree)
- #定义一个字典存放值,值为相关系数list
- results[\’polynomial\’] = coeffs.tolist()
- #p相当于直线方程
- p = np.poly1d(coeffs)
- yhat = p(x) #传入x,计算预测值为yhat
- ybar = np.sum(y)/len(y) #计算均值
- #对应公式
- ssreg = np.sum((yhat – ybar) ** 2)
- sstot = np.sum((y – ybar) ** 2)
- results[\’determination\’] = ssreg / sstot
- print” results :”,results
- return results
- testX = [1, 3, 8, 7, 9]
- testY = [10, 12, 24, 21, 34]
- #输出的是简单线性回归的皮尔逊相关度和R平方值
- print “r : “,computeCorrelation(testX, testY)
- print “r^2 : “,str(computeCorrelation(testX, testY)**2)
- #
- print polyfit(testX, testY, 1)[“determination”]
结果显示为:
二:简单线性回归
1:回归与分类的区别
2:简单线性回归介绍
3:简单线性回归示例
- <span style=“font-family:Microsoft YaHei;”><span style=“font-size:18px;”>#coding:utf8
- \’\’\’\’\’
- Created on 2016年4月24日
- @author: Gamer Think
- \’\’\’
- #Simple Regession
- import numpy as np
- #周广告播放数量
- x = [1,3,2,1,3]
- #周汽车销售数据
- y = [14,24,18,17,27]
- #使用最小二乘法
- def fitSLR(x,y):
- n = len(x)
- denominator = 0
- numerator = 0
- for i in range(0,n):
- numerator += (x[i]-np.mean(x)* (y[i]-np.mean(y)) )
- denominator += (x[i]-np.mean(x))**2
- print “denominator:”,denominator
- print “numerator:”,numerator
- b1 = numerator/float(denominator)
- # b0 = np.mean(y)/float(np.mean(x))
- b0 = np.mean(y)-b1*np.mean(x)
- return b0,b1
- def predict(b0,b1,x):
- return b0+b1*x
- b0,b1 = fitSLR(x,y)
- x_test = 6
- print “y_test:”,predict(b0,b1,x_test)</span></span>
三:多元性回归
- <span style=“font-family:Microsoft YaHei;”><span style=“font-size:18px;”>#coding:utf-8
- \’\’\’\’\’
- Created on 2016年4月24日
- @author: Gamer Think
- \’\’\’
- from sklearn import linear_model
- import numpy as np
- from numpy import genfromtxt #可以将非array格式的list转化为array
- datapath = “data.csv”
- deliverData = genfromtxt(datapath,delimiter=“,”) #将csv文件转化为numpy.array格式
- print “data:”,deliverData
- X= deliverData[:,:-1]
- Y = deliverData[:,-1]
- print “X:”,X
- print “Y:”,Y
- regr = linear_model.LinearRegression()
- regr.fit(X,Y)
- print “coefficients:”,regr.coef_ #与X结合的值
- print “intercept:”,regr.intercept_ #类似于截距
- x_pre = [102,6]
- y_pre = regr.predict(x_pre)
- print “Y-Predict:”,y_pre
- </span></span>
- <span style=“font-family:Microsoft YaHei;”><span style=“font-family:Microsoft YaHei;font-size:18px;”>#coding:utf-8
- \’\’\’\’\’
- Created on 2016年4月24日
- @author: Gamer Think
- \’\’\’
- from numpy import genfromtxt
- import numpy as np
- from sklearn import datasets, linear_model
- dataPath = “dataDumpy.csv”
- deleveryData = genfromtxt(dataPath, delimiter=\’,\’)
- print “data:\n”,deleveryData
- X = deleveryData[:, :-1]
- Y = deleveryData[:, –1]
- print “X: “,X
- print “Y: “,Y
- regr = linear_model.LinearRegression()
- regr.fit(X, Y)
- print “Coefficients:”,regr.coef_ #与X结合的值
- print “Intercept:”,regr.intercept_ #类似于截距
- #
- xPred = [102,6,0,0,1]
- yPred = regr.predict(xPred)
- print “predict y : “,yPred</span></span>
4:关于误差
四:非线性回归
非线性回归又称为逻辑回归
1:概率
非线性回归实例:
- <span style=“font-family:Microsoft YaHei;”><span style=“font-size:18px;”>#coding:utf-8
- \’\’\’\’\’
- Created on 2016年4月24日
- @author: Gamer Think
- \’\’\’
- import numpy as np
- import random
- \’\’\’\’\’
- 梯度下降算法
- 参数说明:X,Y
- theta:一组向量和x相乘的一组值
- alpha:梯度下降时的参数,即每一步下降多少
- m:实例的个数
- numIteration:迭代计算的次数,可以理解为梯度下降多少步
- \’\’\’
- def gradientDescent(X,Y,theta,alpha,m,numIteration):
- x_trains = X.transpose() #X的转置矩阵
- for i in range(0,numIteration):
- hypothesis = np.dot(X,theta) #内积形式,X与theta的乘积 ,求出y的估计值
- loss = hypothesis – Y #估计值与真实值之间的差
- #通用的梯度下降算法,和logistic Regession中所描述的cost函数不一致
- cos = np.sum(loss**2)/(2*m)
- print “Iteration %d | Cost:%f” % (i,cos)
- gradient = np.dot(x_trains,loss)/m
- theta = theta – alpha*gradient
- return theta
- \’\’\’\’\’
- numPoints : 点的个数
- bias :偏好ֵ
- variance : 统计学概念, 偏差和
- 产生样本点和对应的标签
- \’\’\’
- def genData(numPoints,bias,variance):
- X = np.zeros(shape=(numPoints,2)) #归类的数据
- Y = np.zeros(shape=numPoints) #归类的标签
- for i in range(0,numPoints): #从0~len(numPoints)-1执行如下
- X[i][0] = 1
- X[i][1] = i
- #制造target数据
- Y[i] = (i+bias) + random.uniform(0,1)*variance
- return X,Y
- X,Y = genData(100, 25, 10)
- # print “X:”,X
- # print “Y:”,Y
- m, n = np.shape(X)
- n_y = np.shape(Y)
- # print “x shape :”, m, ” “, n
- # print “y length :”,n_y
- numIterations =100000
- alpha = 0.0005
- theta = np.ones(n)
- theta = gradientDescent(X, Y, theta, alpha, m, numIterations)
- print “theta: ” ,theta
- </span></span>