基于二乘法的数据预测算法

原理：根据最近8天的销售数据预测最近一天的销售数据

开发工具：JetBrains PyCharm 2017.2.3

代码：

from numpy import *

def standRegres(xArr,yArr):
    xMat = mat(xArr); yMat = mat(yArr).T
    xTx = xMat.T*xMat
    if linalg.det(xTx) == 0.0:
        print("This matrix is singular, cannot do inverse")
        return
    ws = xTx.I * (xMat.T*yMat)
    return ws

def loadDataSet(fileName):
    allDataMat = []
    dataMat = []
    yMat = []
    fr = open(fileName)
    for line in fr.readlines():
        curLine = line.strip().split('\t')
        allDataMat.append(float(curLine[0]))

    ii = 0
    for j in range(len(allDataMat)):
        if (j > 8):
            lineArr = []
            lineArr.append(allDataMat[j - 8])
            lineArr.append(allDataMat[j - 7])
            lineArr.append(allDataMat[j - 6])
            lineArr.append(allDataMat[j - 5])
            lineArr.append(allDataMat[j - 4])
            lineArr.append(allDataMat[j - 3])
            lineArr.append(allDataMat[j - 2])
            lineArr.append(allDataMat[j - 1])
            dataMat.append(lineArr)
            yMat.append(allDataMat[j])
    return yMat,dataMat

#加载数据--X为前8个连续数据。Y为当前值
yArr,xArr = loadDataSet('myDemo.txt')
#print(yArr)
#print(xArr)
#求以前8个数为参数的回归系统（8个常量）
ws = standRegres(xArr,yArr)
print(ws)
#print("3.176513	3.960008".split('\t'))

print('-------------------------')
xMat = mat(xArr)
yMat = mat(yArr)
yHat = xMat*ws

print(yMat.tolist())
print(yHat[:,0].flatten().A[0])
print('-------------------------')
#基于总方差求平均差（波动范围）
print(sqrt(sum((yArr-yHat.T.flatten().A[0])**2)/yHat.size))

'''
print(yArr)
print(corrcoef(yHat.T,yMat))
'''
#画图
import matplotlib.pyplot as plt
fig = plt.figure()
ax = fig.add_subplot(111)

a=[]
for i in range(len(xMat[:,1].flatten().A[0])):
    a.append(i)

ax.scatter(a,yMat.T[:,0].flatten().A[0])
ax.plot(a,yHat)
'''
xCopy = xMat.copy()
xCopy.sort(0)
yHat = xCopy*ws
ax.plot(xCopy[:,1],yHat)

'''
plt.show()

训练数据：

myDemo.txt

3.176513
3.816464
4.550095
4.256571
4.560815
3.929515
3.526170
3.156393
3.110301
3.149813
3.476346
4.119688
4.282233
3.486582
4.655492
3.965162
3.514900
3.125947
4.094115
3.476039
3.210610
3.190612
4.631504
4.295890
3.085028
3.448080
3.167440
3.364266
3.993482
3.891471
3.143259
3.114204
3.851484
4.621899
4.580768
3.620992
3.580501
4.618706
3.676867
4.641845
3.175939
4.264980
3.558448
3.436632
3.831052
3.182853
3.498906
3.946833
3.900583
4.238522
4.233080
3.521557
3.203344
4.278105
3.555705
3.502661
3.859776
4.275956
3.916191
3.587961
3.183004
4.225236
4.231083
4.240544
3.222372
4.021445
3.567479
3.562580
4.262059
3.208813
3.169825
4.193949
3.491678
4.533306
3.550108
4.636427
3.557078
3.552874
3.494159
3.206828
3.195266
4.221292
4.413372
4.184347
3.742878
3.201878
4.648964
3.510117
3.274434
3.579622
3.489244
4.237386
3.913749
3.228990
4.286286
4.628614
3.239536
4.457997
3.513384
3.729674
3.834274
3.811155
3.598316
4.692514
4.604859
3.864912
3.184236
3.500796
3.743365
3.622905
4.310796
3.583357
3.901852
3.233521
3.105266
3.865544
4.628625
4.231213
3.791149
3.968271
4.253910
3.194710
3.996503
3.904358
3.503976
4.557545
3.699876
4.613614
3.140401
4.206717
3.969524
4.476096
3.136528
4.279071
3.200603
3.299012
3.209873
3.632942
3.248361
3.995783
3.563262
3.649712
3.951845
3.145031
3.181577
4.637087
3.404964
3.873188
4.633648
3.154768
4.623637
3.078132
3.913596
3.221817
3.938071
3.880822
4.176436
4.648161
3.332312
4.240614
4.532224
4.557105
4.610072
4.636569
4.229813
3.500860
4.245514
4.605182
3.454340
3.180775
3.380820
4.565020
3.279973
4.554241
4.633520
4.281037
3.844426
3.891601
3.849728
3.492215
4.592374
4.632025
3.756750
3.133555
3.567919
4.363382
3.560165
4.564305
4.215055
4.174999
4.586640
3.960008
3.529963
4.213412
3.908685
3.585821
4.374394
3.213817
3.952681
3.129283