Diff: pca.cpp

Revision:

0:8670ef66c0e3

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/pca.cpp	Mon Nov 25 14:26:29 2019 +0000
@@ -0,0 +1,72 @@
+
+#include "pca.h"
+#include <Eigen/Dense.h>
+
+using namespace Eigen;
+
+ /*
+  * Normalize the Matrix X
+  */
+ MatrixXd PCA::featurnormail(MatrixXd &X)
+{
+    //I don't know why to use the transpose
+    //compute the mean of every dimension
+    MatrixXd X1 = X.transpose();
+    MatrixXd meanval = X1.colwise().mean();
+    
+    //normalization
+    RowVectorXd meanvecRow = meanval;
+    X1.rowwise() -= meanvecRow;
+    
+    return X1.transpose();
+}
+
+ /*
+  * Compute the Covariane Matrix of X, put to C
+  * C = 1/m * X * X.transpose 
+  */
+void PCA::ComComputeCov(MatrixXd &X, MatrixXd &C)
+{
+   
+    C = X*X.adjoint();//same as XT*X a
+    //translate to array
+    C = C.array() / X.cols();
+}
+ 
+ 
+/*
+ * Compute the eigenvalue and eigenvector of C
+ * val = (first eigenvalue) --smallest --not important
+ *              .
+ *              .
+ *              .
+ *       (last eigenvalue)  --largest -- important
+ *
+ * vec = (first eigenvector, ... , last eigenvector)
+ *           not important          important
+ */
+void PCA::ComputEig(MatrixXd &C, MatrixXd &vec, MatrixXd &val)
+{
+    //SelfAdjointEigenSolver will sort the values automatically
+    SelfAdjointEigenSolver<MatrixXd> eig(C);
+    vec = eig.eigenvectors();
+    val = eig.eigenvalues();
+}
+ 
+/* Compute the dimension need to include enough information of raw data.
+ * form large index to small index, since the val is sorted from small to large.
+ * in some cases, just decide the number of dimension, instead of compute it.
+ */
+int PCA::ComputDim(MatrixXd &val)
+{
+    int dim;
+    double sum = 0;
+    for (int i = val.rows() - 1; i >= 0;--i)
+    {
+        sum += val(i, 0);
+        dim = i;
+        if (sum / val.sum()>=0.8)//80% of the information
+            break;
+    }
+    return val.rows() - dim;
+}
\ No newline at end of file