-
-
Notifications
You must be signed in to change notification settings - Fork 479
/
Copy pathexample_classification.py
116 lines (86 loc) · 6 KB
/
example_classification.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
import numpy
import pygad
import pygad.nn
import pygad.gann
def fitness_func(ga_instance, solution, sol_idx):
global GANN_instance, data_inputs, data_outputs
predictions = pygad.nn.predict(last_layer=GANN_instance.population_networks[sol_idx],
data_inputs=data_inputs)
correct_predictions = numpy.where(predictions == data_outputs)[0].size
solution_fitness = (correct_predictions/data_outputs.size)*100
return solution_fitness
def callback_generation(ga_instance):
global GANN_instance, last_fitness
population_matrices = pygad.gann.population_as_matrices(population_networks=GANN_instance.population_networks,
population_vectors=ga_instance.population)
GANN_instance.update_population_trained_weights(population_trained_weights=population_matrices)
print(f"Generation = {ga_instance.generations_completed}")
print(f"Fitness = {ga_instance.best_solution()[1]}")
print(f"Change = {ga_instance.best_solution()[1] - last_fitness}")
last_fitness = ga_instance.best_solution(pop_fitness=ga_instance.last_generation_fitness)[1].copy()
# Holds the fitness value of the previous generation.
last_fitness = 0
# Reading the input data.
data_inputs = numpy.load("../data/dataset_features.npy") # Download from https://github.com/ahmedfgad/NumPyANN/blob/master/dataset_features.npy
# Optional step of filtering the input data using the standard deviation.
features_STDs = numpy.std(a=data_inputs, axis=0)
data_inputs = data_inputs[:, features_STDs>50]
# Reading the output data.
data_outputs = numpy.load("../data/outputs.npy") # Download from https://github.com/ahmedfgad/NumPyANN/blob/master/outputs.npy
# The length of the input vector for each sample (i.e. number of neurons in the input layer).
num_inputs = data_inputs.shape[1]
# The number of neurons in the output layer (i.e. number of classes).
num_classes = 4
# Creating an initial population of neural networks. The return of the initial_population() function holds references to the networks, not their weights. Using such references, the weights of all networks can be fetched.
num_solutions = 8 # A solution or a network can be used interchangeably.
GANN_instance = pygad.gann.GANN(num_solutions=num_solutions,
num_neurons_input=num_inputs,
num_neurons_hidden_layers=[150, 50],
num_neurons_output=num_classes,
hidden_activations=["relu", "relu"],
output_activation="softmax")
# population does not hold the numerical weights of the network instead it holds a list of references to each last layer of each network (i.e. solution) in the population. A solution or a network can be used interchangeably.
# If there is a population with 3 solutions (i.e. networks), then the population is a list with 3 elements. Each element is a reference to the last layer of each network. Using such a reference, all details of the network can be accessed.
population_vectors = pygad.gann.population_as_vectors(population_networks=GANN_instance.population_networks)
# To prepare the initial population, there are 2 ways:
# 1) Prepare it yourself and pass it to the initial_population parameter. This way is useful when the user wants to start the genetic algorithm with a custom initial population.
# 2) Assign valid integer values to the sol_per_pop and num_genes parameters. If the initial_population parameter exists, then the sol_per_pop and num_genes parameters are useless.
initial_population = population_vectors.copy()
num_parents_mating = 4 # Number of solutions to be selected as parents in the mating pool.
num_generations = 100 # Number of generations.
mutation_percent_genes = 10 # Percentage of genes to mutate. This parameter has no action if the parameter mutation_num_genes exists.
parent_selection_type = "sss" # Type of parent selection.
crossover_type = "single_point" # Type of the crossover operator.
mutation_type = "random" # Type of the mutation operator.
keep_parents = -1 # Number of parents to keep in the next population. -1 means keep all parents and 0 means keep nothing.
ga_instance = pygad.GA(num_generations=num_generations,
num_parents_mating=num_parents_mating,
initial_population=initial_population,
fitness_func=fitness_func,
mutation_percent_genes=mutation_percent_genes,
parent_selection_type=parent_selection_type,
crossover_type=crossover_type,
mutation_type=mutation_type,
keep_parents=keep_parents,
on_generation=callback_generation)
ga_instance.run()
# After the generations complete, some plots are showed that summarize how the outputs/fitness values evolve over generations.
ga_instance.plot_fitness()
# Returning the details of the best solution.
solution, solution_fitness, solution_idx = ga_instance.best_solution(pop_fitness=ga_instance.last_generation_fitness)
print(f"Parameters of the best solution : {solution}")
print(f"Fitness value of the best solution = {solution_fitness}")
print(f"Index of the best solution : {solution_idx}")
if ga_instance.best_solution_generation != -1:
print(f"Best fitness value reached after {ga_instance.best_solution_generation} generations.")
# Predicting the outputs of the data using the best solution.
predictions = pygad.nn.predict(last_layer=GANN_instance.population_networks[solution_idx],
data_inputs=data_inputs)
print("Predictions of the trained network : {predictions}")
# Calculating some statistics
num_wrong = numpy.where(predictions != data_outputs)[0]
num_correct = data_outputs.size - num_wrong.size
accuracy = 100 * (num_correct/data_outputs.size)
print(f"Number of correct classifications : {num_correct}.")
print(f"Number of wrong classifications : {num_wrong.size}.")
print(f"Classification accuracy : {accuracy}.")