-
Notifications
You must be signed in to change notification settings - Fork 0
C++ API to train and evaluate predictive and classification models
gertthijs/SiMath
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
========================== = SiMath - version 1.0 = ========================== Examples ------------ How to use SiMath is illustrated with some examples. In the directory "examples" of the source distribution, there are currently two example programs and one data file data.tab. The data matrix comes from the benchmark iris data set (used for instance in R). It has 150 data points with 5 variables. The first column gives the class label. There are three different classes and each class has 50 members. The first example reads in the data, normalises the columns to have zero mean and unit variance. This normalised data matrix is then used to train an SVM classificator. The predicted labels are printed. The second example reads in the data and the number of clusters requested. Then it normalises the columns to have zero mean and unit variance and transforms the data matrix using PCA. Finally a k-means clustering is done using the predefined number of clusters. The cluster numbers are printed in 3 columns corresponding to the three classes. To compile the code against the compiled version of libSiMath, you should use a command like (if SiMath is installed in the default location) # first example $ g++ -I/usr/local/include -L/usr/local/lib -lsimath -o example1 example1.cpp $ ./example1 data.tab # second example $ g++ -I/usr/local/include -L/usr/local/lib -lsimath -o example2 example2.cpp $ ./example2 data.tab 3
About
C++ API to train and evaluate predictive and classification models
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published