基于Python遗传算法的人工神经网络优化

def mat_to_vector(mat_pop_weights):
     pop_weights_vector = []
     for sol_idx in range(mat_pop_weights.shape[0]):
         curr_vector = []
         for layer_idx in range(mat_pop_weights.shape[1]):
             vector_weights = numpy.reshape(mat_pop_weights[sol_idx, layer_idx], newshape=(mat_pop_weights[sol_idx, layer_idx].size))
             curr_vector.extend(vector_weights)
         pop_weights_vector.append(curr_vector)
     return numpy.array(pop_weights_vector)

def vector_to_mat(vector_pop_weights, mat_pop_weights):
    mat_weights = []
    for sol_idx in range(mat_pop_weights.shape[0]):
        start = 0
        end = 0
        for layer_idx in range(mat_pop_weights.shape[1]):
            end = end + mat_pop_weights[sol_idx, layer_idx].size
            curr_vector = vector_pop_weights[sol_idx, start:end]
            mat_layer_weights = numpy.reshape(curr_vector, newshape=(mat_pop_weights[sol_idx, layer_idx].shape))
            mat_weights.append(mat_layer_weights)
            start = end
    return numpy.reshape(mat_weights, newshape=mat_pop_weights.shape)

def predict_outputs(weights_mat, data_inputs, data_outputs, activation="relu"):
    predictions = numpy.zeros(shape=(data_inputs.shape[0]))
    for sample_idx in range(data_inputs.shape[0]):
        r1 = data_inputs[sample_idx, :]
        for curr_weights in weights_mat:
            r1 = numpy.matmul(a=r1, b=curr_weights)
            if activation == "relu":
                r1 = relu(r1)
            elif activation == "sigmoid":
                r1 = sigmoid(r1)
        predicted_label = numpy.where(r1 == numpy.max(r1))[0][0]
        predictions[sample_idx] = predicted_label
    correct_predictions = numpy.where(predictions == data_outputs)[0].size
    accuracy = (correct_predictions/data_outputs.size)*100
    return accuracy, predictions

def fitness(weights_mat, data_inputs, data_outputs, activation="relu"):
    accuracy = numpy.empty(shape=(weights_mat.shape[0]))
    for sol_idx in range(weights_mat.shape[0]):
        curr_sol_mat = weights_mat[sol_idx, :]
        accuracy[sol_idx], _ = predict_outputs(curr_sol_mat, data_inputs, data_outputs, activation=activation)
    return accuracy

import numpy
import GA
import pickle
import ANN
import matplotlib.pyplot

f = open("dataset_features.pkl", "rb")
data_inputs2 = pickle.load(f)
f.close()
features_STDs = numpy.std(a=data_inputs2, axis=0)
data_inputs = data_inputs2[:, features_STDs>50]

f = open("outputs.pkl", "rb")
data_outputs = pickle.load(f)
f.close()
#Genetic algorithm parameters:
#    Mating Pool Size (Number of Parents)
#    Population Size
#    Number of Generations
#    Mutation Percent

sol_per_pop = 8
num_parents_mating = 4
num_generations = 1000
mutation_percent = 10

#Creating the initial population.
initial_pop_weights = []
for curr_sol in numpy.arange(0, sol_per_pop):
    HL1_neurons = 150
    input_HL1_weights = numpy.random.uniform(low=-0.1, high=0.1, 

                                             size=(data_inputs.shape[1], HL1_neurons))

    HL2_neurons = 60
    HL1_HL2_weights = numpy.random.uniform(low=-0.1, high=0.1, 

                                             size=(HL1_neurons, HL2_neurons))

    output_neurons = 4
    HL2_output_weights = numpy.random.uniform(low=-0.1, high=0.1, 

                                              size=(HL2_neurons, output_neurons))

    initial_pop_weights.append(numpy.array([input_HL1_weights, 

                                                HL1_HL2_weights, 

                                                HL2_output_weights]))

pop_weights_mat = numpy.array(initial_pop_weights)
pop_weights_vector = GA.mat_to_vector(pop_weights_mat)

best_outputs = []
accuracies = numpy.empty(shape=(num_generations))

for generation in range(num_generations):
    print("Generation : ", generation)

    # converting the solutions from being vectors to matrices.
    pop_weights_mat = GA.vector_to_mat(pop_weights_vector, 
                                       pop_weights_mat)

    # Measuring the fitness of each chromosome in the population.
    fitness = ANN.fitness(pop_weights_mat, 
                          data_inputs, 
                          data_outputs, 
                          activation="sigmoid")

    accuracies[generation] = fitness[0]
    print("Fitness")
    print(fitness)

    # Selecting the best parents in the population for mating.
    parents = GA.select_mating_pool(pop_weights_vector, 

                                    fitness.copy(), 

                                    num_parents_mating)
    print("Parents")
    print(parents)

    # Generating next generation using crossover.
    offspring_crossover = GA.crossover(parents,

                                       offspring_size=(pop_weights_vector.shape[0]-parents.shape[0], pop_weights_vector.shape[1]))

    print("Crossover")
    print(offspring_crossover)

    # Adding some variations to the offsrping using mutation.
    offspring_mutation = GA.mutation(offspring_crossover, 

                                     mutation_percent=mutation_percent)
    print("Mutation")
    print(offspring_mutation)

    # Creating the new population based on the parents and offspring.
    pop_weights_vector[0:parents.shape[0], :] = parents
    pop_weights_vector[parents.shape[0]:, :] = offspring_mutation

pop_weights_mat = GA.vector_to_mat(pop_weights_vector, pop_weights_mat)
best_weights = pop_weights_mat [0, :]
acc, predictions = ANN.predict_outputs(best_weights, data_inputs, data_outputs, activation="sigmoid")
print("Accuracy of the best solution is : ", acc)

matplotlib.pyplot.plot(accuracies, linewidth=5, color="black")
matplotlib.pyplot.xlabel("Iteration", fontsize=20)
matplotlib.pyplot.ylabel("Fitness", fontsize=20)
matplotlib.pyplot.xticks(numpy.arange(0, num_generations+1, 100), fontsize=15)
matplotlib.pyplot.yticks(numpy.arange(0, 101, 5), fontsize=15)

f = open("weights_"+str(num_generations)+"_iterations_"+str(mutation_percent)+"%_mutation.pkl", "wb")
pickle.dump(pop_weights_mat, f)
f.close()