10000 PyGAD 3.1.0 Release · longamu/GeneticAlgorithmPython@e58005d · GitHub
[go: up one dir, main page]
Skip to content

Commit e58005d

Browse files
ahmedfgadahmedfgad
committed
PyGAD 3.1.0 ReleasePyGAD 3.1.0 Release Notes 1. Fix a bug when the initial population has duplciate genes if a nested gene space is used. 2. The gene_space parameter can no longer be assigned a tuple. 3. Fix a bug when the gene_space parameter has a member of type tuple. 4. A new instance attribute called gene_space_unpacked which has the unpacked gene_space. It is used to solve duplicates. For infinite ranges in the gene_space, they are unpacked to a limited number of values (e.g. 100). 5. Bug fixes when creating the initial population using gene_space attribute. 6. When a dict is used with the gene_space attribute, the new gene value was calculated by summing 2 values: 1) the value sampled from the dict 2) a random value returned from the random mutation range defined by the 2 parameters random_mutation_min_val and random_mutation_max_val. This might cause the gene value to exceed the range limit defined in the gene_space. To respect the gene_space range, this release only returns the value from the dict without summing it to a random value. 7. Formatting the strings using f-string instead of the format() method. ahmedfgad#189 8. In the __init__() of the pygad.GA class, the logged error messages are handled using a try-except block instead of repeating the logger.error() command. ahmedfgad#189 9. A new class named CustomLogger is created in the pygad.cnn module to create a default logger using the logging module assigned to the logger attribute. This class is extended in all other classes in the module. The constructors of these classes have a new parameter named logger which defaults to None. If no logger is passed, then the default logger in the CustomLogger class is used. 10. Except for the pygad.nn module, the print() function in all other modules are replaced by the logging module to log messages. 11. The callback functions/methods on_fitness(), on_parents(), on_crossover(), and on_mutation() can return values. These returned values override the corresponding properties. The output of on_fitness() overrides the population fitness. The on_parents() function/method must return 2 values representing the parents and their indices. The output of on_crossover() overrides the crossover offspring. The output of on_mutation() overrides the mutation offspring. 12. Fix a bug when adaptive mutation is used while fitness_batch_size>1. ahmedfgad#195 13. When allow_duplicate_genes=False and a user-defined gene_space is used, it sometimes happen that there is no room to solve the duplicates between the 2 genes by simply replacing the value of one gene by another gene. This release tries to solve such duplicates by looking for a third gene that will help in solving the duplicates. These examples explain how it works. Check this section for more information. 14. Use probabilities to select parents using the rank parent selection method. ahmedfgad#205 15. The 2 parameters random_mutation_min_val and random_mutation_max_val can accept iterables (list/tuple/numpy.ndarray) with length equal to the number of genes. This enables customizing the mutation range for each individual gene. ahmedfgad#198 16. The 2 parameters init_range_low and init_range_high can accept iterables (list/tuple/numpy.ndarray) with length equal to the number of genes. This enables customizing the initial range for each individual gene when creating the initial population. 17. The data parameter in the predict() function of the pygad.kerasga module can be assigned a data generator. ahmedfgad#115 ahmedfgad#207 18. The predict() function of the pygad.kerasga module accepts 3 optional parameters: 1) batch_size=None, verbose=0, and steps=None. Check documentation of the Keras Model.predict() method for more information. ahmedfgad#207 19. The documentation is updated to explain how mutation works when gene_space is used with int or float data types. Check this section. ahmedfgad#198
1 parent e413018 commit e58005d

File tree

1 file changed

+109
-0
lines changed

1 file changed

+109
-0
lines changed

‎docs/source/releases.rst

Lines changed: 109 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1290,6 +1290,115 @@ Release Date 20 April 2023
12901290
selection.
12911291
https://github.com/ahmedfgad/GeneticAlgorithmPython/issues/179
12921292

1293+
.. _pygad-310:
1294+
1295+
PyGAD 3.1.0
1296+
-----------
1297+
1298+
Release Date 20 June 2023
1299+
1300+
1. Fix a bug when the initial population has duplciate genes if a
1301+
nested gene space is used.
1302+
1303+
2. The ``gene_space`` parameter can no longer be assigned a tuple.
1304+
1305+
3. Fix a bug when the ``gene_space`` parameter has a member of type
1306+
``tuple``.
1307+
1308+
4. A new instance attribute called ``gene_space_unpacked`` which has
1309+
the unpacked ``gene_space``. It is used to solve duplicates. For
1310+
infinite ranges in the ``gene_space``, they are unpacked to a
1311+
limited number of values (e.g. 100).
1312+
1313+
5. Bug fixes when creating the initial population using ``gene_space``
1314+
attribute.
1315+
1316+
6. When a ``dict`` is used with the ``gene_space`` attribute, the new
1317+
gene value was calculated by summing 2 values: 1) the value sampled
1318+
from the ``dict`` 2) a random value returned from the random
1319+
mutation range defined by the 2 parameters
1320+
``random_mutation_min_val`` and ``random_mutation_max_val``. This
1321+
might cause the gene value to exceed the range limit defined in the
1322+
``gene_space``. To respect the ``gene_space`` range, this release
1323+
only returns the value from the ``dict`` without summing it to a
1324+
random value.
1325+
1326+
7. Formatting the strings using f-string instead of the ``format()``
1327+
method. https://github.com/ahmedfgad/GeneticAlgorithmPython/pull/189
1328+
1329+
8. In the ``__init__()`` of the ``pygad.GA`` class, the logged error
1330+
messages are handled using a ``try-except`` block instead of
1331+
repeating the ``logger.error()`` command.
1332+
https://github.com/ahmedfgad/GeneticAlgorithmPython/pull/189
1333+
1334+
9. A new class named ``CustomLogger`` is created in the ``pygad.cnn``
1335+
module to create a default logger using the ``logging`` module
1336+
assigned to the ``logger`` attribute. This class is extended in all
1337+
other classes in the module. The constructors of these classes have
1338+
a new parameter named ``logger`` which defaults to ``None``. If no
1339+
logger is passed, then the default logger in the ``CustomLogger``
1340+
class is used.
1341+
1342+
10. Except for the ``pygad.nn`` module, the ``print()`` function in all
1343+
other modules are replaced by the ``logging`` module to log
1344+
messages.
1345+
1346+
11. The callback functions/methods ``on_fitness()``, ``on_parents()``,
1347+
``on_crossover()``, and ``on_mutation()`` can return values. These
1348+
returned values override the corresponding properties. The output of
1349+
``on_fitness()`` overrides the population fitness. The
1350+
``on_parents()`` function/method must return 2 values representing
1351+
the parents and their indices. The output of ``on_crossover()``
1352+
overrides the crossover offspring. The output of ``on_mutation()``
1353+
overrides the mutation offspring.
1354+
1355+
12. Fix a bug when adaptive mutation is used while
1356+
``fitness_batch_size``>1.
1357+
https://github.com/ahmedfgad/GeneticAlgorithmPython/issues/195
1358+
1359+
13. When ``allow_duplicate_genes=False`` and a user-defined
1360+
``gene_space`` is used, it sometimes happen that there is no room to
1361+
solve the duplicates between the 2 genes by simply replacing the
1362+
value of one gene by another gene. This release tries to solve such
1363+
duplicates by looking for a third gene that will help in solving the
1364+
duplicates. These examples explain how it works. Check `this
1365+
section <https://pygad.readthedocs.io/en/latest/pygad.html#prevent-duplicates-in-gene-values>`__
1366+
for more information.
1367+
1368+
14. Use probabilities to select parents using the rank parent selection
1369+
method.
1370+
https://github.com/ahmedfgad/GeneticAlgorithmPython/discussions/205
1371+
1372+
15. The 2 parameters ``random_mutation_min_val`` and
1373+
``random_mutation_max_val`` can accept iterables
1374+
(list/tuple/numpy.ndarray) with length equal to the number of genes.
1375+
This enables customizing the mutation range for each individual
1376+
gene.
1377+
https://github.com/ahmedfgad/GeneticAlgorithmPython/discussions/198
1378+
1379+
16. The 2 parameters ``init_range_low`` and ``init_range_high`` can
1380+
accept iterables (list/tuple/numpy.ndarray) with length equal to the
1381+
number of genes. This enables customizing the initial range for each
1382+
individual gene when creating the initial population.
1383+
1384+
17. The ``data`` parameter in the ``predict()`` function of the
1385+
``pygad.kerasga`` module can be assigned a data generator.
1386+
https://github.com/ahmedfgad/GeneticAlgorithmPython/issues/115
1387+
https://github.com/ahmedfgad/GeneticAlgorithmPython/issues/207
1388+
1389+
18. The ``predict()`` function of the ``pygad.kerasga`` module accepts 3
1390+
optional parameters: 1) ``batch_size=None``, ``verbose=0``, and
1391+
``steps=None``. Check documentation of the `Keras
1392+
Model.predict() <https://keras.io/api/models/model_training_apis>`__
1393+
method for more information.
1394+
https://github.com/ahmedfgad/GeneticAlgorithmPython/issues/207
1395+
1396+
19. The documentation is updated to explain how mutation works when
1397+
``gene_space`` is used with ``int`` or ``float`` data types. Check
1398+
`this
1399+
section <https://pygad.readthedocs.io/en/latest/pygad.html#limit-the-gene-value-range-using-the-gene-space-parameter>`__.
1400+
https://github.com/ahmedfgad/GeneticAlgorithmPython/discussions/198
1401+
12931402
PyGAD Projects at GitHub
12941403
========================
12951404

0 commit comments

Comments
 (0)
0