《基于VB的 灰色模型预测 和 线性回归预测》由会员分享，可在线阅读，更多相关《基于VB的 灰色模型预测 和 线性回归预测（11页珍藏版）》请在金锄头文库上搜索。
1、 灰色模型预测 GM(1,1)与线性回归预测（一元、多元）新建一个工程，添加一个模块（.bas） ，两个命令按钮：窗体代码：Option ExplicitPrivate Sub Command1_Click() 灰色模型预测Dim Data As StringData = 2.67,3.13,3.25,3.36,3.56,3.72GM1_1_Predict DataEnd SubPrivate Sub Command2_Click() 线性回归预测Dim X1 As String, X2 As String, X3 As String, X4 As String, Y As StringX1
2、= 100.38,99.7,92.3,87.6,87.17,88.3,92.75,100.6,90.05; 最后要加上分号;X2 = 53.24,51.5,50.5,52.4,59.6,59.7,65.2,62.4,53.68; 最后要加上分号;X3 = 226,250,281,272,194,180,105,115,250; 最后要加上分号;Y = 644,640,517,425,385,401,448,599,462 最后 不要 加上分号; 请注意！Linear_Regression_Predict X1 & X2 & X3 & YEnd Sub模块代码：Option ExplicitPr
3、ivate Sub Calculate_1_AGO(X_0() As Double, X_1() As Double) 做一次累加生成 1-AGODim i As Long, TempX As Double, K As LongK = UBound(X_0)ReDim X_1(K)For i = 0 To KTempX = TempX + X_0(i)X_1(i) = TempXNext iEnd SubPrivate Sub Calculate_Matrix_B(X_1() As Double, B() As Double) 计算数据矩阵 BDim i As Long, K As LongK
4、 = UBound(X_1) - 1ReDim B(K, 1) For i = 0 To KB(i, 0) = -0.5 * (X_1(i) + X_1(i + 1)B(i, 1) = 1Next iEnd SubPrivate Sub Calculate_Matrix_YN(X_0() As Double, YN() As Double) 计算数据矩阵 YNDim i As Long, K As LongK = UBound(X_0) - 1ReDim YN(K, 0)For i = 0 To KYN(i, 0) = X_0(i + 1)Next iEnd Sub 函数名：Matrix_Tr
5、anspotation 功能： 计算矩阵的转置 transpotation 参数： m - Integer 型变量，矩阵的行数 n - Integer 型变量，矩阵的列数 mtxA - Double 型 m x n 二维数组，存放原矩阵 mtxAT - Double 型 n x m 二维数组，返回转置矩阵Private Sub Matrix_Transpotation(mtxA() As Double, mtxAT() As Double)Dim i As Integer, j As IntegerDim M As Integer, N As IntegerM = UBound(mtxA, 2
6、)N = UBound(mtxA, 1)ReDim mtxAT(M, N)For i = 0 To MFor j = 0 To NmtxAT(i, j) = mtxA(j, i)Next jNext iEnd Sub 函数名：Matrix_Multiplication 功能： 计算矩阵的乘法 multiplication 参数： m - Integer 型变量，相乘的左边矩阵的行数 n - Integer 型变量，相乘的左边矩阵的列数和右边矩阵的行数 l - Integer 型变量，相乘的右边矩阵的列数 mtxA - Double 型 m x n 二维数组，存放相乘的左边矩阵 mtxB - D
7、ouble 型 n x l 二维数组，存放相乘的右边矩阵 mtxC - Double 型 m x l 二维数组，返回矩阵乘积矩阵Private Sub Matrix_Multiplication(mtxA() As Double, mtxB() As Double, mtxC() As Double)Dim i As Integer, j As Integer, K As IntegerDim M As Integer, N As Integer, L As IntegerM = UBound(mtxA, 1): N = UBound(mtxB, 1): L = UBound(mtxB, 2)
8、ReDim mtxC(M, L)For i = 0 To MFor j = 0 To LmtxC(i, j) = 0#For K = 0 To NmtxC(i, j) = mtxC(i, j) + mtxA(i, K) * mtxB(K, j)Next KNext jNext iEnd Sub 函数名：Matrix_Inversion 功能： 矩阵求逆 参数： n - Integer 型变量，矩阵的阶数 mtxA - Double 型二维数组，体积为 n x n。存放原矩阵 A；返回时存放其逆矩阵 A-1。 返回值：Boolean 型，失败为 False，成功为 TruePrivate Fun
9、ction Matrix_Inversion(mtxA() As Double) As Boolean 局部变量Dim N As IntegerN = UBound(mtxA)ReDim nIs(N) As Integer, nJs(N) As IntegerDim i As Integer, j As Integer, K As IntegerDim d As Double, P As Double 全选主元，消元For K = 0 To Nd = 0# For i = K To NFor j = K To NP = Abs(mtxA(i, j)If (P d) Thend = PnIs(K
10、) = inJs(K) = jEnd IfNext jNext i 求解失败If (d + 1# = 1#) ThenMatrix_Inversion = FalseExit FunctionEnd IfIf (nIs(K) K) ThenFor i = 0 To NP = mtxA(i, K)mtxA(i, K) = mtxA(i, nJs(K)mtxA(i, nJs(K) = PNext iEnd IfmtxA(K, K) = 1# / mtxA(K, K)For j = 0 To NIf (j K) ThenFor j = 0 To NIf (j K) Then mtxA(i, K) = -mtxA(i, K) * mtxA(K, K)Next iNext K 调整恢复行列次序For K = N To 0 Step -1If (nJs(K) K) ThenFor i = 0 To NP = mtxA(i, K)mtxA(i, K) = mtxA(i, nIs(K)mtxA(i, nIs(K) = PNext iEnd IfNext K 求解成功Matrix_Inversion = TrueEnd FunctionPrivate Sub Pred
