The genes are always integers even if the gene_space attribute has float values.

[ahmedfgad]

In the next code, the initial_population parameter is used to feed an initial population that has 8 solutions with 2 genes each. The gene_space parameter is used which has the half values starting from 0.5 to 15.5.

When the mutation is applied, it is expected that some genes have floating-point values like 3.5, 6.5, 0.5, 2.5, etc. But all genes are integers.

import pygad
import numpy

init_pop = ((1, 1), (3, 3), (5, 5), (7, 7), (9, 9), (11, 11), (13, 13), (15, 15))

def fitness_func(solution, solution_idx):
    fitness = numpy.sum(solution)
    return fitness

gene_space = numpy.arange(0.5, 15.5, 1)

ga_instance = pygad.GA(initial_population=init_pop,
                       num_generations=4,
                       num_parents_mating=8,
                       fitness_func=fitness_func,
                       gene_space=gene_space)

ga_instance.run()

[ahmedfgad]

After inspecting the code, then the problem happened due to mismatch between the types of the initial_population and gene_type. Let me clarify.

The initial population is created as follows:

init_pop = ((1, 1), (3, 3), (5, 5), (7, 7), (9, 9), (11, 11), (13, 13), (15, 15))

Then, init_pop is assigned to initial_population in the constructor of the pygad.GA class:

initial_population = init_pop

Inside PyGAD, a NumPy array is created out of initial_population:

self.initial_population = numpy.array(initial_population)

The data type of this array is deduced automatically from the values inside initial_population. Because all the values used in init_pop are integers, then the type of initial_population is set to integer. As a result, when a value like 4.5 is assigned to this array, the value will be automatically casted into an integer to be 4.

To make things work, here is the solution:
Rather than using this line:

init_pop = ((1, 1), (3, 3), (5, 5), (7, 7), (9, 9), (11, 11), (13, 13), (15, 15))

Use this line:

init_pop = np.array(((1, 1), (3, 3), (5, 5), (7, 7), (9, 9), (11, 11), (13, 13), (15, 15)), dtype=float)

Or just write at least a single value as float to make the code things the array is float. In the next line, the first value is now 1.0 rather than 1:

init_pop = ((1.0, 1), (3, 3), (5, 5), (7, 7), (9, 9), (11, 11), (13, 13), (15, 15))

[ahmedfgad]

Thanks to Marios Giouvanakis, a PhD candidate in Electrical & Computer Engineer, Aristotle University of Thessaloniki (Αριστοτέλειο Πανεπιστήμιο Θεσσαλονίκης), Greece, for emailing me about this bug.