private void button_Cal_Click(object sender, EventArgs e)
{
List <int> BlackList = new List <int>();
double [] ans = (double [])MathV.CalExpression(textBox_expression.Text.Replace("\r\n", ""), MainForm.MainDT, ref BlackList);
int ColNum = 0;
if (checkBox_NewCol.Checked == true)
{
MainForm.MainDT.Columns.Add();
ColNum = MainForm.MainDT.Columns.Count - 1;
}
else
{
ColNum = Tabulation.FindCol(MainForm.MainDT, comboBox_Output.Text);
}
if (ColNum == -1)
{
return;
}
int RealData = 0;
int RowsCount = MainForm.MainDT.Rows.Count;
for (int i = 0; i < RowsCount; i++)
{
if (BlackList.IndexOf(i) == -1)
{
MainForm.MainDT.Rows[i][ColNum] = ans[RealData].ToString();
RealData++;
}
}
Tabulation.InitDataSet(MainForm.MainDT, ref MainForm.nMax, ref MainForm.pageCount, ref MainForm.pageCurrent,
ref MainForm.nCurrent, MainForm.S.label_CurrentPage, MainForm.S.label_TotalPage,
MainForm.S.dataGridView1, MainForm.S.textBox_CurrentPage, MainForm.pageSize);
}
private void comboBox_Cols_TextChanged(object sender, EventArgs e)
{
int ColNum = Tabulation.FindCol(MainForm.MainDT, comboBox_Cols.Text);
if (ColNum != -1)
{
Classification = Tabulation.Classification(MainForm.MainDT, ColNum);
int len = Classification.Length;
if (len > 0)
{
if (len > 2)
{
MessageBox.Show("选项超过两种，请使用多选单选题进行分析！");
}
else
{
listBox_TwoChoices.Items.Clear();
listBox_TwoChoices.Items.AddRange(Classification);
CountTimes = Tabulation.LikilihoodCount(Classification, MainForm.MainDT, ColNum);
StringBuilder OutPut = new StringBuilder();
for (int i = 0; i < len; i++)
{
OutPut.Append(Classification[i]);
OutPut.Append("\t");
OutPut.Append(CountTimes[i].ToString());
OutPut.Append("\r\n");
}
textBox_Likihood.Clear();
textBox_Likihood.AppendText(OutPut.ToString());
label4.Text = "其中有多少样本选择了\"" + listBox_TwoChoices.Items[0].ToString() + "\"?";
}
}
}
}
private void comboBox_Cols_TextChanged(object sender, EventArgs e)
{
int ColNum = Tabulation.FindCol(MainForm.MainDT, comboBox_Cols.Text);
if (ColNum != -1)
{
Classification = Tabulation.Classification(MainForm.MainDT, ColNum);
int len = Classification.Length;
if (len > 0)
{
listBox_MultiChoices.Items.Clear();
listBox_MultiChoices.Items.AddRange(Classification);
textBox_Times.Clear();
for (int i = 0; i < len; i++)
{
textBox_Times.AppendText("0\r\n");
}
CountTimes = Tabulation.LikilihoodCount(Classification, MainForm.MainDT, ColNum);
StringBuilder OutPut = new StringBuilder();
for (int i = 0; i < len; i++)
{
OutPut.Append(Classification[i]);
OutPut.Append("\t");
OutPut.Append(CountTimes[i].ToString());
OutPut.Append("\r\n");
}
textBox_Likihood.Clear();
textBox_Likihood.AppendText(OutPut.ToString());
}
}
}
private void button_add_Click(object sender, EventArgs e)
{
if (comboBox_x.Text.Trim() != "")
{
QuickPlot.QPlot(dt, chart_basic,
Tabulation.FindCol(dt, comboBox_x.Text),
Tabulation.FindCol(dt, comboBox_y.Text), comboBox_type.Text, textBox_Legend.Text, checkBox_IsXLabel.Checked);
}
else
{
QuickPlot.QPlot(dt, chart_basic,
-1,
Tabulation.FindCol(dt, comboBox_y.Text), comboBox_type.Text, textBox_Legend.Text, checkBox_IsXLabel.Checked);
}
}
string BayesClassification()
{
int dtRowsCount = dt.Rows.Count;
int dtColsCount = dt.Columns.Count;
StringBuilder ResultText = new StringBuilder();
string[][] Classification = new string[dtColsCount][];
List <List <string> > Data = new List <List <string> >();
for (int j = 0; j < dtColsCount; j++)
{
Data.Add(new List <string>());
//对每列的数据进行定义
for (int i = 0; i < dtRowsCount; i++)
{
//确保录入的行中无空缺
if (IdentifyNARow(i, dtColsCount))
{
//按行读取每列的数据
Data[j].Add(dt.Rows[i][j].ToString());
}
}
}
//现在我们获得了一个Data矩阵
double Temp = 0;
List <string> AllClassi = new List <string>();
List <string> EachProbs = new List <string>();
for (int i = 0; i < dtColsCount; i++)
{
ResultText.Append("第");
ResultText.Append((i + 1).ToString());
ResultText.Append("项特征内的各个类别:\r\n");
Classification[i] = Data[i].Distinct().ToArray();
foreach (string SingleStr in Classification[i])
{
ResultText.Append(SingleStr);
ResultText.Append(" ");
}
ResultText.Append("\r\n");
foreach (string SingleStr in Classification[i])
{
ResultText.Append("P(");
ResultText.Append(SingleStr);
ResultText.Append(") = ");
Temp = FindElement(SingleStr, Data[i].ToArray())
/ Convert.ToDouble(Data[i].Count);
ResultText.Append(Temp.ToString());
ResultText.Append("\r\n");
AllClassi.Add(SingleStr);
EachProbs.Add(Temp.ToString());
}
ResultText.Append("\r\n");
}
double count = 0;
int TotalTimes = 0;
//int InterestCol = FindCol(comboBox_Class.Text);
int InterestCol = Tabulation.FindCol(dt, comboBox_Class.Text);
int InterestColCount = Data[InterestCol].Count;
List <string> str = new List <string>();
List <string> Probs = new List <string>();
string StrAndDis = "";
for (int j = 0; j < dtColsCount; j++)
{
if (j != InterestCol)
{
foreach (string EachStr in Classification[j])
{
foreach (string EachDis in Classification[InterestCol])
{
count = 0;
for (int i = 0; i < InterestColCount; i++)
{
if (Data[InterestCol][i].Trim() == EachDis)
{
if (Data[j][i].Trim() == EachStr)
{
count++;
}
}
}
StrAndDis = EachStr + "|" + EachDis;
ResultText.Append("P(");
ResultText.Append(StrAndDis);
ResultText.Append(") = ");
Temp = count / FindElement(EachDis, Data[InterestCol].ToArray());
ResultText.Append(Temp.ToString());
ResultText.Append("\r\n");
str.Add(StrAndDis);
Probs.Add(Temp.ToString());
TotalTimes++;
}
}
}
}
ResultText.Append("所有类别组合数量总计:");
ResultText.Append(TotalTimes.ToString());
//以下数组用于记录训练集所获得的结果
Result[0] = AllClassi.ToArray();
Result[1] = EachProbs.ToArray();
Result[2] = str.ToArray();
Result[3] = Probs.ToArray();
Result[4] = Classification[InterestCol];
return(ResultText.ToString());
}
private void button_Regression_Click(object sender, EventArgs e)
{
string ColNums = textBox_Cols.Text;
char[] separator = { ',' };
//string是以逗号分隔的
string[] AllNum = ColNums.Split(separator);
//按照逗号分割
List <int> Cols = new List <int>();
foreach (string SingleNum in AllNum)
{
if (SingleNum != "")
{
Cols.Add(Convert.ToInt32(SingleNum) - 1);
}
}
int[] AllColNums = Cols.ToArray();
int yCol = Tabulation.FindCol(MainForm.MainDT, comboBox_y.Text);
List <List <string> > data = new List <List <string> >();
int RowsCount = MainForm.MainDT.Rows.Count;
int InputColsCount = AllColNums.Length;
//计算总共要录入的列数
int count = 0;
//计算实际录入数据数
List <string> Ydata = new List <string>();
for (int i = 0; i < InputColsCount; i++)
{
data.Add(new List <string>());
}
for (int i = 0; i < RowsCount; i++)
{
if (Tabulation.IdentifyNARow(MainForm.MainDT, i, AllColNums))
{
//确认该行无空格
if (MainForm.MainDT.Rows[i][yCol].ToString().Trim() != "")
{
Ydata.Add(MainForm.MainDT.Rows[i][yCol].ToString().Trim());
for (int j = 0; j < InputColsCount; j++)
{
data[j].Add(MainForm.MainDT.Rows[i][j].ToString());
}
count++;
}
}
}
if (count > 2)
{
BigDecimal[,] IndependentVariables = new BigDecimal[count, InputColsCount + 1];
//第一列全是1
for (int i = 0; i < count; i++)
{
IndependentVariables[i, 0] = 1;
}
for (int i = 0; i < count; i++)
{
for (int j = 0; j < InputColsCount; j++)
{
//录入时，BigDecimal数组列数要+1，因为第一列全是1
IndependentVariables[i, j + 1] = data[j][i];
}
}
BigDecimal[,] DependentVariable = new BigDecimal[count, 1];
for (int i = 0; i < count; i++)
{
DependentVariable[i, 0] = Ydata[i];
}
BigDecimal[,] bhat = Stat.MultiRegBeta(IndependentVariables, DependentVariable);
StringBuilder Result = new StringBuilder();
Result.Append(comboBox_y.Text);
Result.Append(" = ");
int ColumnNumberCount = 0;
foreach (BigDecimal EachNum in bhat)
{
if (ColumnNumberCount == 0)
{
Result.Append(MathV.NumberPolish(EachNum.ToString()));
Result.Append(" + ");
}
else if (ColumnNumberCount == InputColsCount)
{
Result.Append(MathV.NumberPolish(EachNum.ToString()));
Result.Append(" ");
Result.Append(MainForm.MainDT.Columns[AllColNums[ColumnNumberCount - 1]].ColumnName);
}
else
{
Result.Append(MathV.NumberPolish(EachNum.ToString()));
Result.Append(" ");
Result.Append(MainForm.MainDT.Columns[AllColNums[ColumnNumberCount - 1]].ColumnName);
Result.Append(" + ");
}
ColumnNumberCount++;
}
MainForm.S.richTextBox1.AppendText(Result.ToString());
}
}
public static string HypothesisTesting(DataTable MainDT, string ColName,
string Statistics, string Operation, string Tail, double Significance, double NullHypothesis)
{
//假设检验
//Statistics为统计量，Operation为运算(>,<,=)
//Tail为单尾双尾，这里内容为双侧、左单侧、右单侧
//Significance为显著性水平
int ColNum = Tabulation.FindCol(MainDT, ColName);
string[] Numbers = Tabulation.ReadVector(MainDT, ColNum).ToArray();
StringBuilder Result = new StringBuilder();
Result.Append("假设检验: ");
Result.Append(Statistics);
Result.Append("\r\n");
Result.Append("显著性水平: ");
Result.Append(Significance.ToString());
Result.Append("\t");
Result.Append(Tail);
Result.Append("\r\n原假设: ");
Result.Append(Statistics);
Result.Append(" ");
Result.Append(Operation);
Result.Append(" ");
Result.Append(NullHypothesis.ToString());
Result.Append("\r\n备择假设: ");
Result.Append(Statistics);
Result.Append(" ");
if (Operation == "=")
{
Result.Append("<>");
}
else if (Operation == "<=")
{
Result.Append(">");
}
else
{
Result.Append("<");
}
Result.Append(" ");
Result.Append(NullHypothesis.ToString());
Result.Append("\r\n");
BigDecimal sum = 0;
BigDecimal mean = 0;
BigDecimal Variance = 0;
BigDecimal Sd = 0;
//Sd为标准差
int count = 0;
BigDecimal sum2 = 0;
//sum2用于计算数字的平方，方便计算方差
Double TempNum = 0;
BigDecimal BigTemp = 0;
//BigTemp用于记录BigDecimal类型的临时数据
double Threshold = 0;
//Threshold为临界值
double PValue = 0;
//Pvalue不用多解释了吧～
foreach (string Num in Numbers)
{
if (Double.TryParse(Num, out TempNum))
{
sum += TempNum;
sum2 += (BigDecimal)TempNum * (BigDecimal)TempNum;
count++;
}
}
//遍历了该列所有数字
if (Statistics == "均值")
{
if (count >= 30)
{
Result.Append(HTHeader_Ztest);
}
else
{
Result.Append(HTHeader_Ttest);
}
if (count <= 1)
{
return("样本数量过少，无法进行假设检验！\r\n");
}
else
{
//开始计算均值和方差
//方差要乘以调整系数
mean = sum / count;
Variance = (sum2 / count - mean * mean) * count / (count - 1);
Result.Append(StrManipulation.PadLeftX(StrManipulation.VariableNamePolish(ColName), ' ', 12));
Result.Append("\t");
Result.Append(StrManipulation.PadLeftX(count.ToString(), ' ', 12));
Result.Append("\t");
Result.Append(StrManipulation.PadLeftX(MathV.NumberPolish(mean.ToString()), ' ', 12));
Result.Append("\t");
Result.Append(StrManipulation.PadLeftX(MathV.NumberPolish(MathV.Sqrt(Variance.ToString()).ToString()), ' ', 12));
Result.Append("\t");
if (count >= 30)
{
//大样本
//z检验
Sd = MathV.Sqrt(Variance.ToString()).ToString();
BigTemp = (mean - NullHypothesis) / (Sd / Math.Sqrt(count));
//BigTemp此时的值为z检验统计量
//样本数count无需大数开方，用普通方法开方即可
if (Tail == "双侧")
{
Threshold = NORMSINV(1 - Significance / 2);
PValue = 2 * (1 - NORMDIST(Math.Abs(Convert.ToDouble(BigTemp.ToString()))));
}
else if (Tail == "左单侧")
{
Threshold = NORMSINV(Significance);
PValue = 1 - NORMDIST(Math.Abs(Convert.ToDouble(BigTemp.ToString())));
}
else if (Tail == "右单侧")
{
Threshold = NORMSINV(1 - Significance);
PValue = 1 - NORMDIST(Math.Abs(Convert.ToDouble(BigTemp.ToString())));
}
Result.Append(StrManipulation.PadLeftX(MathV.NumberPolish(BigTemp.ToString()), ' ', 12));
Result.Append("\t");
Result.Append(StrManipulation.PadLeftX(MathV.NumberPolish(Threshold.ToString()), ' ', 12));
Result.Append("\t");
Result.Append(StrManipulation.PadLeftX(MathV.NumberPolish(PValue.ToString()), ' ', 12));
Result.Append("\r\n");
if (PValue < Significance)
{
Result.Append("在");
Result.Append(Significance.ToString());
Result.Append("的显著性水平上拒绝原假设");
}
else
{
Result.Append("在");
Result.Append(Significance.ToString());
Result.Append("的显著性水平上不拒绝原假设");
}
}
else
{
//小样本
//t检验
Sd = MathV.Sqrt(Variance.ToString()).ToString();
BigTemp = (mean - NullHypothesis) / (Sd / Math.Sqrt(count));
//BigTemp此时的值为z检验统计量
//样本数count无需大数开方，用普通方法开方即可
if (Tail == "双侧")
{
Threshold = TINV(Significance / 2 / 2, count - 1);
//每个放进TINV的值都要除以2，这个bug之后会进行修复
PValue = TDIST(Math.Abs(Convert.ToDouble(BigTemp.ToString()) / 2), count - 1, 2);
}
else if (Tail == "左单侧")
{
Threshold = TINV(Significance / 2, count - 1);
PValue = TDIST(Math.Abs(Convert.ToDouble(BigTemp.ToString()) / 2), count - 1, 1);
}
else if (Tail == "右单侧")
{
Threshold = TINV(Significance / 2, count - 1);
PValue = TDIST(Math.Abs(Convert.ToDouble(BigTemp.ToString()) / 2), count - 1, 1);
}
Result.Append(StrManipulation.PadLeftX(MathV.NumberPolish(BigTemp.ToString()), ' ', 12));
Result.Append("\t");
Result.Append(StrManipulation.PadLeftX(MathV.NumberPolish(Threshold.ToString()), ' ', 12));
Result.Append("\t");
Result.Append(StrManipulation.PadLeftX(MathV.NumberPolish(PValue.ToString()), ' ', 12));
Result.Append("\r\n");
if (PValue < Significance)
{
Result.Append("在");
Result.Append(Significance.ToString());
Result.Append("的显著性水平上拒绝原假设");
}
else
{
Result.Append("在");
Result.Append(Significance.ToString());
Result.Append("的显著性水平上不拒绝原假设");
}
}
Result.Append("\r\n");
return(Result.ToString());
}
}
else if (Statistics == "比率")
{
return("hhh");
}
else
{
//方差
return("hhh");
}
}
private void button_Regression_Click(object sender, EventArgs e)
{
string ColNums = textBox_Cols.Text;
char[] separator = { ',' };
//string是以逗号分隔的
string[] AllNum = ColNums.Split(separator);
//按照逗号分割
List <int> Cols = new List <int>();
foreach (string SingleNum in AllNum)
{
if (SingleNum != "")
{
Cols.Add(Convert.ToInt32(SingleNum) - 1);
}
}
int[] AllColNums = Cols.ToArray();
//MessageBox.Show(AllColNums[0].ToString());
//MessageBox.Show(AllColNums[1].ToString());
int yCol = Tabulation.FindCol(MainForm.MainDT, comboBox_y.Text);
List <List <string> > data = new List <List <string> >();
int RowsCount = MainForm.MainDT.Rows.Count;
int InputColsCount = AllColNums.Length;
//计算总共要录入的列数
int count = 0;
//计算实际录入数据数
List <string> Ydata = new List <string>();
for (int i = 0; i < InputColsCount; i++)
{
data.Add(new List <string>());
}
for (int i = 0; i < RowsCount; i++)
{
if (Tabulation.IdentifyNARow(MainForm.MainDT, i, AllColNums))
{
//确认该行无空格
if (MainForm.MainDT.Rows[i][yCol].ToString().Trim() != "")
{
Ydata.Add(MainForm.MainDT.Rows[i][yCol].ToString().Trim());
for (int j = 0; j < InputColsCount; j++)
{
data[j].Add(MainForm.MainDT.Rows[i][AllColNums[j]].ToString()); //此处队长有bug，已改正
}
count++;
}
}
}
if (count > 2)
{
BigDecimal[,] IndependentVariables = new BigDecimal[count, InputColsCount + 1];
StringBuilder Result = new StringBuilder();
if (count <= InputColsCount + 1)
{
Result.Append("样本量过少，无法估计");
}
else
{
//第一列全是1
for (int i = 0; i < count; i++)
{
IndependentVariables[i, 0] = 1;
}
for (int i = 0; i < count; i++)
{
for (int j = 0; j < InputColsCount; j++)
{
//录入时，BigDecimal数组列数要+1，因为第一列全是1
IndependentVariables[i, j + 1] = data[j][i];
}
}
//MathV.ArrayPrint(IndependentVariables);
BigDecimal[,] DependentVariable = new BigDecimal[count, 1];
for (int i = 0; i < count; i++)
{
DependentVariable[i, 0] = Ydata[i];
}
int len12 = IndependentVariables.GetLength(1);//列数
BigDecimal[,] b1 = MathV.MatTrans(IndependentVariables);
BigDecimal[,] b2 = MathV.MatTimes(b1, IndependentVariables);
try
{
BigDecimal[,] b3 = MathV.MatInv(b2, len12);
if (b3 != null)
{
BigDecimal[,] bhat = Stat.MultiRegBeta(b1, b3, IndependentVariables, DependentVariable);
BigDecimal[,] value_beta = Stat.MultiRegP(b3, bhat, IndependentVariables, DependentVariable);
string[] RandF = Stat.MultiRegR(bhat, IndependentVariables, DependentVariable).Split(separator);
//MathV.ArrayPrint(bhat);
Result.Append(StrManipulation.PadRightX(StrManipulation.VariableNamePolish("拟合R^2："), ' ', 12));
Result.Append(MathV.NumberPolish(RandF[0]));
Result.Append("\r\n");
Result.Append(StrManipulation.PadRightX(StrManipulation.VariableNamePolish("调整后R^2："), ' ', 12));
Result.Append(MathV.NumberPolish(RandF[1]));
Result.Append("\r\n");
Result.Append(StrManipulation.PadRightX(StrManipulation.VariableNamePolish("回归F值："), ' ', 12));
Result.Append(MathV.NumberPolish(RandF[2]));
Result.Append("\r\n");
Result.Append(StrManipulation.PadRightX(StrManipulation.VariableNamePolish("回归P值："), ' ', 12));
Result.Append(MathV.NumberPolish(Stat.FINV(Convert.ToDouble(RandF[2]), count - InputColsCount - 1, InputColsCount).ToString()));
Result.Append("\r\n \r\n");
Result.Append(comboBox_y.Text + " = ");
int ColumnNumberCount = 0;
foreach (BigDecimal EachNum in bhat)
{
if (ColumnNumberCount == 0)
{
Result.Append(MathV.NumberPolish(EachNum.ToString()));
Result.Append(" + ");
}
else if (ColumnNumberCount == InputColsCount)
{
Result.Append(MathV.NumberPolish(EachNum.ToString()));
Result.Append(" ");
Result.Append(MainForm.MainDT.Columns[AllColNums[ColumnNumberCount - 1]].ColumnName);
}
else
{
Result.Append(MathV.NumberPolish(EachNum.ToString()));
Result.Append(MainForm.MainDT.Columns[AllColNums[ColumnNumberCount - 1]].ColumnName);
Result.Append(" + ");
}
ColumnNumberCount++;
}
Result.Append("\r\n检验P值: ");
for (int i = 0; i < InputColsCount + 1; i++)
{
Result.Append(MathV.NumberPolish(value_beta[i, 0].ToString()));
Result.Append(" \t");
}
Result.Append("\r\n检验t值: ");
for (int i = 0; i < InputColsCount + 1; i++)
{
Result.Append(MathV.NumberPolish(value_beta[i, 1].ToString()));
Result.Append(" \t");
}
Result.Append("\r\n \r\n");
}
else
{
Result.Append("矩阵不可逆，回归方程无解");
}
}
catch (Exception ex)
{
MessageBox.Show("存在重复自变量");
}
}
MainForm.S.richTextBox1.AppendText(Result.ToString());
}
}
private void button1_Click(object sender, EventArgs e)
{
string ColNums = textBox_Cols.Text;
char[] separator = { ',' };
//string是以逗号分隔的
string[] AllNum = ColNums.Split(separator);
//按照逗号分割
List <int> Cols = new List <int>();
foreach (string SingleNum in AllNum)
{
if (SingleNum != "")
{
Cols.Add(Convert.ToInt32(SingleNum) - 1);
}
}
int[] AllColNums = Cols.ToArray();
//MessageBox.Show(AllColNums[0].ToString());
//MessageBox.Show(AllColNums[1].ToString());
int yCol = Tabulation.FindCol(MainForm.MainDT, comboBox_y.Text);
List <List <string> > data = new List <List <string> >();
int RowsCount = MainForm.MainDT.Rows.Count;
int InputColsCount = AllColNums.Length;
//计算总共要录入的列数
int count = 0;
//计算实际录入数据数
List <string> Ydata = new List <string>();
for (int i = 0; i < InputColsCount; i++)
{
data.Add(new List <string>());
}
for (int i = 0; i < RowsCount; i++)
{
if (Tabulation.IdentifyNARow(MainForm.MainDT, i, AllColNums))
{
//确认该行无空格
if (MainForm.MainDT.Rows[i][yCol].ToString().Trim() != "")
{
Ydata.Add(MainForm.MainDT.Rows[i][yCol].ToString().Trim());
for (int j = 0; j < InputColsCount; j++)
{
data[j].Add(MainForm.MainDT.Rows[i][AllColNums[j]].ToString()); //此处队长有bug，已改正
}
count++;
}
}
}
if (count > 2)
{
BigDecimal[,] IndependentVariables = new BigDecimal[count, InputColsCount + 1];
StringBuilder Result = new StringBuilder();
if (count <= InputColsCount + 1)
{
Result.Append("样本量过少，无法估计");
}
else
{
//第一列全是1
for (int i = 0; i < count; i++)
{
IndependentVariables[i, 0] = 1;
}
for (int i = 0; i < count; i++)
{
for (int j = 0; j < InputColsCount; j++)
{
//录入时，BigDecimal数组列数要+1，因为第一列全是1
IndependentVariables[i, j + 1] = data[j][i];
}
}
//MathV.ArrayPrint(IndependentVariables);
BigDecimal[,] DependentVariable = new BigDecimal[count, 1];
for (int i = 0; i < count; i++)
{
DependentVariable[i, 0] = Ydata[i];
}
int len12 = IndependentVariables.GetLength(1); //列数
BigDecimal[,] b1 = MathV.MatTrans(IndependentVariables);
BigDecimal[,] b2 = MathV.MatTimes(b1, IndependentVariables);
BigDecimal[,] b3 = MathV.MatInv(b2, len12);
if (b3 != null)
{
BigDecimal[,] bhat = Stat.MultiRegBeta(b1, b3, IndependentVariables, DependentVariable);
BigDecimal[,] value_beta = Stat.MultiRegP(b3, bhat, IndependentVariables, DependentVariable);
string[] RandF = Stat.MultiRegR(bhat, IndependentVariables, DependentVariable).Split(separator);
//回归诊断开始
//#初步判断 ： 根据R^2 adjR^2 Fvalue tvalue
Result.Append("1.初步诊断 \r\n");
if ((BigDecimal)RandF[1] < 0.70)
{
Result.Append(" 调整后R^2较小，可能存在遗漏变量\r\n");
}
if ((BigDecimal)RandF[0] - (BigDecimal)RandF[1] > 0.1)
{
Result.Append(" 调整后R^2与R^2差值较大，可能存在冗余变量\r\n");
}
if (Stat.FDIST(Convert.ToDouble(RandF[2]), InputColsCount, count - 1) > 0.01)
{
Result.Append(" 模型拟合情况不好，建议更改解释变量\r\n");
}
else
{
Result.Append(" 模型拟合情况较好\r\n");
}
int count_nonsignifi = 0;
for (int i = 0; i < InputColsCount + 1; i++)
{
if (i == 0)
{
if (value_beta[i, 0] > 0.05)
{
Result.Append(" 常数项在95%置信水平下不显著\r\n");
count_nonsignifi++;
}
}
else
{
if (value_beta[i, 0] > 0.05)
{
Result.Append(" 变量" + (i + 1).ToString() + "在95%置信水平下不显著\r\n");
count_nonsignifi++;
}
}
}
if ((BigDecimal)RandF[0] > 0.7 && count_nonsignifi > ((InputColsCount + 1) / 2))
{
Result.Append(" 高拟合优度伴随着大量非显著解释变量，存在多重共线性\r\n");
}
Result.Append("\r\n");
//#遗漏变量 : 拉姆齐检验
Result.Append("2.模型设定偏误检验（拉姆齐检验）\r\n");
BigDecimal[,] Y_hat = new BigDecimal[count, 1];
Y_hat = MathV.MatTimes(IndependentVariables, bhat);
BigDecimal[,] Ramsey_indep = new BigDecimal[count, InputColsCount + 3];
for (int i = 0; i < count; i++)
{
for (int j = 0; j < InputColsCount + 3; j++)
{
if (j < InputColsCount + 1)
{
Ramsey_indep[i, j] = IndependentVariables[i, j];
}
else if (j == InputColsCount + 1)
{
Ramsey_indep[i, j] = Y_hat[i, 0] * Y_hat[i, 0];
}
else
{
Ramsey_indep[i, j] = Y_hat[i, 0] * Y_hat[i, 0] * Y_hat[i, 0];
}
}
}
BigDecimal[,] b1_ramsey = MathV.MatTrans(Ramsey_indep);
BigDecimal[,] b2_ramsey = MathV.MatTimes(b1_ramsey, Ramsey_indep);
BigDecimal[,] b3_ramsey = MathV.MatInv(b2_ramsey, InputColsCount + 3);
if (b3_ramsey != null && count > InputColsCount + 3)
{
BigDecimal[,] bhat_ramsey = Stat.MultiRegBeta(b1_ramsey, b3_ramsey, Ramsey_indep, DependentVariable);
string[] RandF_ramsey = Stat.MultiRegR(bhat_ramsey, Ramsey_indep, DependentVariable).Split(separator);
double R2_ramsey = Convert.ToDouble(RandF_ramsey[0]);
double F_ramsey = (R2_ramsey - Convert.ToDouble(RandF[0])) * (count - InputColsCount - 2) / ((1 - R2_ramsey) * 2);
double F_P_ramsey = Stat.FDIST(Convert.ToDouble(RandF_ramsey[2]), 2, count - InputColsCount - 2);
if (F_P_ramsey <= 0.001)
{
Result.Append(" 模型在99.9%的置信水平下认为存在偏误\r\n");
}
else
{
Result.Append(" 模型设定在99.9%的置信水平下认为无偏误\r\n");
}
}
else
{
Result.Append(" ！样本量过少，无法进行拉姆齐检验\r\n");
}
Result.Append("");
Result.Append("\r\n3.多重共线性检验：方差膨胀因子(VIF)\r\n");
//#多重共线性检验：方差膨胀因子（VIF）
int count_vif;
if (InputColsCount == 1)
{
Result.Append(" ！一个自变量无法进行方差膨胀因子检验\r\n");
}
else
{
for (int i = 0; i < InputColsCount; i++)
{
BigDecimal[,] Vif_dep = new BigDecimal[count, 1];
BigDecimal[,] Vif_indep = new BigDecimal[count, InputColsCount];
for (int j = 0; j < count; j++)
{
count_vif = 0;
Vif_dep[j, 0] = IndependentVariables[j, i + 1];
for (int k = 0; k < InputColsCount + 1; k++)
{
if (k != i + 1)
{
Vif_indep[j, count_vif] = IndependentVariables[j, k];
count_vif++;
}
}
}
//MathV.ArrayPrint(Vif_indep);
// MathV.ArrayPrint(Vif_dep);
BigDecimal[,] b1_vif = MathV.MatTrans(Vif_indep);
BigDecimal[,] b2_vif = MathV.MatTimes(b1_vif, Vif_indep);
BigDecimal[,] b3_vif = MathV.MatInv(b2_vif, InputColsCount);
if (b3_vif != null)
{
BigDecimal[,] bhat_vif = Stat.MultiRegBeta(b1_vif, b3_vif, Vif_indep, Vif_dep);
string[] RandF_vif = Stat.MultiRegR(bhat_vif, Vif_indep, Vif_dep).Split(separator);
//MessageBox.Show(RandF_vif[0]);
BigDecimal VIF = 1 / (1 - Convert.ToDouble(RandF_vif[0]));
if (VIF <= 10)
{
Result.Append(" 变量" + (i + 1).ToString() + "在模型中共线性较弱，可以保留\r\n");
}
else if (VIF > 10 && VIF < 100)
{
Result.Append(" 变量" + (i + 1).ToString() + "在模型中共线性较强，建议剔除\r\n");
}
else
{
Result.Append(" 变量" + (i + 1).ToString() + "在模型中共线性极强，强烈建议剔除\r\n");
}
}
}
}
//#异方差 : White 检验
Result.Append("\r\n4.异方差检验：怀特检验与LM统计量\r\n");
//Y_hat2 与 u^hat2
BigDecimal[,] u_hat2 = new BigDecimal[count, 1];
BigDecimal[,] u_hat = new BigDecimal[count, 1];
BigDecimal[,] Y_hat2 = new BigDecimal[count, 1];
BigDecimal[,] White_indep = new BigDecimal[count, 3];
BigDecimal[,] White_dep = new BigDecimal[count, 1];
for (int i = 0; i < count; i++)
{
u_hat2[i, 0] = (DependentVariable[i, 0] - Y_hat[i, 0]) * (DependentVariable[i, 0] - Y_hat[i, 0]);
Y_hat2[i, 0] = Y_hat[i, 0] * Y_hat[i, 0];
u_hat[i, 0] = (DependentVariable[i, 0] - Y_hat[i, 0]);
White_indep[i, 0] = 1;
White_indep[i, 1] = Y_hat[i, 0];
White_indep[i, 2] = Y_hat2[i, 0];
White_dep[i, 0] = u_hat2[i, 0];
}
BigDecimal[,] b1_white = MathV.MatTrans(White_indep);
BigDecimal[,] b2_white = MathV.MatTimes(b1_white, White_indep);
BigDecimal[,] b3_white = MathV.MatInv(b2_white, 3);
if (b3_white != null)
{
BigDecimal[,] bhat_white = Stat.MultiRegBeta(b1_white, b3_white, White_indep, White_dep);
string[] RandF_white = Stat.MultiRegR(bhat_white, White_indep, White_dep).Split(separator);
BigDecimal LM_white = count * Convert.ToDouble(RandF_white[0]);
//MessageBox.Show(LM_white.ToString());
BigDecimal P_white = 1 - Stat.chi2(Convert.ToDouble(LM_white.ToString()), 2);
//MessageBox.Show(P_white2.ToString());
Result.Append(" LM统计量 \t");
Result.Append(" =\t");
Result.Append(StrManipulation.PadLeftX(MathV.NumberPolish(LM_white.ToString()), ' ', 12));
Result.Append("\r\n");
Result.Append(" LM > chi(2)\t");
Result.Append(" =\t");
Result.Append(StrManipulation.PadLeftX(MathV.NumberPolish(P_white.ToString()), ' ', 12));
Result.Append("\r\n");
if (P_white > 0.05)
{
Result.Append(" 在95%的置信度上认为样本同方差\r\n \r\n");
}
else
{
Result.Append(" 在95%的置信度上认为样本异方差\r\n");
Result.Append(" 解决方法：变量取对数回归,结果如下：\r\n");
BigDecimal[,] ln_indep = new BigDecimal[count, InputColsCount + 1];
BigDecimal[,] ln_dep = new BigDecimal[count, 1];
for (int i = 0; i < count; i++)
{
for (int j = 0; j < InputColsCount; j++)
{
ln_indep[i, j + 1] = Math.Log(Convert.ToDouble(IndependentVariables[i, j + 1].ToString()));
}
ln_indep[i, 0] = 1;
ln_dep[i, 0] = Math.Log(Convert.ToDouble(DependentVariable[i, 0].ToString()));
}
BigDecimal[,] b1_ln = MathV.MatTrans(ln_indep);
BigDecimal[,] b2_ln = MathV.MatTimes(b1_ln, ln_indep);
BigDecimal[,] b3_ln = MathV.MatInv(b2, len12);
if (b3_ln != null)
{
BigDecimal[,] bhat_ln = Stat.MultiRegBeta(b1_ln, b3_ln, ln_indep, ln_dep);
BigDecimal[,] value_beta_ln = Stat.MultiRegP(b3_ln, bhat_ln, ln_indep, ln_dep);
string[] RandF_ln = Stat.MultiRegR(bhat_ln, ln_indep, ln_dep).Split(separator);
//MathV.ArrayPrint(bhat);
Result.Append(StrManipulation.PadRightX(StrManipulation.VariableNamePolish("拟合R^2："), ' ', 12));
Result.Append(MathV.NumberPolish(RandF_ln[0]));
Result.Append("\r\n");
Result.Append(StrManipulation.PadRightX(StrManipulation.VariableNamePolish("调整后R^2："), ' ', 12));
Result.Append(MathV.NumberPolish(RandF_ln[1]));
Result.Append("\r\n");
Result.Append(StrManipulation.PadRightX(StrManipulation.VariableNamePolish("回归F值："), ' ', 12));
Result.Append(MathV.NumberPolish(RandF_ln[2]));
Result.Append("\r\n");
Result.Append("\r\n");
Result.Append(comboBox_y.Text);
Result.Append(" = ");
int ColumnNumberCount = 0;
foreach (BigDecimal EachNum in bhat_ln)
{
if (ColumnNumberCount == 0)
{
Result.Append(MathV.NumberPolish(EachNum.ToString()));
Result.Append(" + ");
}
else if (ColumnNumberCount == InputColsCount)
{
Result.Append(MathV.NumberPolish(EachNum.ToString()));
Result.Append(" ");
Result.Append(" ln " + MainForm.MainDT.Columns[AllColNums[ColumnNumberCount - 1]].ColumnName);
}
else
{
Result.Append(MathV.NumberPolish(EachNum.ToString()));
Result.Append(" ln " + MainForm.MainDT.Columns[AllColNums[ColumnNumberCount - 1]].ColumnName);
Result.Append(" + ");
}
ColumnNumberCount++;
}
Result.Append("\r\n检验P值: ");
for (int i = 0; i < InputColsCount + 1; i++)
{
Result.Append(MathV.NumberPolish(value_beta_ln[i, 0].ToString()));
Result.Append(" \t");
}
Result.Append("\r\n检验t值: ");
for (int i = 0; i < InputColsCount + 1; i++)
{
Result.Append(MathV.NumberPolish(value_beta_ln[i, 1].ToString()));
Result.Append(" \t");
}
Result.Append("\r\n\r\n");
}
else
{
Result.Append("矩阵不可逆，回归方程无解 \r\n");
}
}
}
//#自相关(3阶内） ：
Result.Append("5.自相关检验：拉格朗日乘子(LM) \r\n");
BigDecimal[,] u_hat_Auto = new BigDecimal[count - 3, 1];
BigDecimal[,] indep_Auto = new BigDecimal[count - 3, InputColsCount + 4];
for (int i = 0; i < count - 3; i++)
{
u_hat_Auto[i, 0] = u_hat[i + 3, 0];
for (int j = 0; j < InputColsCount + 1; j++)
{
indep_Auto[i, j] = IndependentVariables[i + 3, j];
}
indep_Auto[i, InputColsCount + 1] = u_hat[i + 2, 0];
indep_Auto[i, InputColsCount + 2] = u_hat[i + 1, 0];
indep_Auto[i, InputColsCount + 3] = u_hat[i, 0];
}
BigDecimal[,] b1_Auto = MathV.MatTrans(indep_Auto);
BigDecimal[,] b2_Auto = MathV.MatTimes(b1_Auto, indep_Auto);
BigDecimal[,] b3_Auto = MathV.MatInv(b2_Auto, InputColsCount + 4);
if (b3_Auto != null)
{
BigDecimal[,] bhat_Auto = Stat.MultiRegBeta(b1_Auto, b3_Auto, indep_Auto, u_hat_Auto);
string[] RandF_Auto = Stat.MultiRegR(bhat_Auto, indep_Auto, u_hat_Auto).Split(separator);
BigDecimal LM_Auto = (count - 3) * Convert.ToDouble(RandF_Auto[0].ToString());
BigDecimal P_Auto = 1 - Stat.chi2(Convert.ToDouble(LM_Auto.ToString()), 3);
Result.Append(" LM统计量 \t");
Result.Append(" =\t");
Result.Append(StrManipulation.PadLeftX(MathV.NumberPolish(LM_Auto.ToString()), ' ', 12));
Result.Append("\r\n");
Result.Append(" LM > chi(2)\t");
Result.Append(" =\t");
Result.Append(StrManipulation.PadLeftX(MathV.NumberPolish(P_Auto.ToString()), ' ', 12));
Result.Append("\r\n");
if (P_Auto <= 0.05)
{
Result.Append(" 在95%的置信水平下拒绝原假设，认为模型序列存在自相关\r\n \r\n");
}
else
{
Result.Append(" 在95%的置信水平下接受原假设，认为模型序列不存在自相关\r\n \r\n");
}
}
MainForm.S.richTextBox1.AppendText(Result.ToString());
}
}
}
}
