Closed seyedzadeh closed 5 years ago
My intuition says what you can do is create a population of individuals of length 7 (since you have 7 parameters to optimize) where each gene in the individual can take values from 0 to 1; basically np.random.random((1, 7)).
Then you can inverse transform using the min-max normalization formula like here to convert each gene to the desired parameter range at that position.
For discrete values, you can inverse transform for the index.
I am trying to optimize two outputs of simulation software (I used random forest to train a model for fast prediction of outputs). There are seven input variables three are continuous, and the rest are discrete. I have used DEAP package for multi-objective optimization but only one variable or a set of related variables (something like knapsack). The mentioned seven variables are:
Except ft, for all continues variables, it is possible to define several discrete numbers.
My question is how I can create different individuals for these inputs to define the population?