def run_VanilaGANGenerator(train, test, epochs, latent_size, hidden_neurons,
n_samples, learning_rate, random_neg_sample,
real_pos, name):
gan_obj = VanilaGANGenerator(train, test, epochs, latent_size, name)
gan_obj.define_models_GAN(learning_rate, hidden_neurons, type=None)
gan_obj.train_model()
gan_sample = gan_obj.generate_samples(n_samples)
#tsne_plot(gan_sample, name)
ks_result1, ks_result2 = compare_attributes_distribution(
real_pos, gan_sample, name)
fid = calculate_fid(real_pos, gan_sample)
print("Frechet Inception Distance:", fid)
tsne_data_comparision(real_pos, random_neg_sample, gan_sample, name, None,
'VGAN')
get_combined_generated = get_combined_generated_real(
gan_sample, train, name)
# print("Count of Failure and non failure",get_combined_generated.failure.value_counts())
(train_X, train_y) = split_XY(get_combined_generated)
(test_X, test_y) = split_XY(test)
# classify_baseline_model(test_y)
#multiple_classifier(train_X, train_y.values.ravel(), test_X, test_y.values.ravel(), name, ks_result1, ks_result2,
# fid)
# xgb_classifier(train_X, train_y.values.ravel(), test_X, test_y.values.ravel(),name)
# rf_classifier(train_X, train_y.values.ravel(), test_X, test_y.values.ravel(),name)
return gan_sample, ks_result1, ks_result2, fid
def vae_gan_model():
epochs, latent_size = 1500, 50
name = "best_test-2_vae_gan_gantrain_200-128_64_50_0005"
n_layer = 3
hidden_neurons = 128
learning_rate = 0.0002
cgan_sample, vae_sample, ks_result1, ks_result2, fid = run_VAECGAN_Generator(
train_main, test_main, epochs, latent_size, n_samples, n_layer,
learning_rate, hidden_neurons, name, random_neg, random_pos)
print("VAE sample shape", vae_sample.shape)
tsne_data_comparision(random_pos,
random_neg,
cgan_sample,
name,
vae_sample,
method='VAE_CGAN')
get_combined_generated = get_combined_generated_real(
cgan_sample, train_main, name)
(train_X, train_y) = split_XY(get_combined_generated)
(test_X, test_y) = split_XY(test_main)
multiple_classifier(train_X, train_y.values.ravel(), test_X,
test_y.values.ravel(), name, ks_result1, ks_result2,
fid)
print(
"======================Both GAN and VAE=============================")
name = name + "VAE_GAN-both"
get_combined_generated = get_combined_generated_real(
vae_sample, get_combined_generated, name)
(train_X, train_y) = split_XY(get_combined_generated)
(test_X, test_y) = split_XY(test_main)
def cgan_vae_model():
epochs, latent_size = 200, 50
name = "best_test_cgan-vae_100-128_64_50_0005"
n_layer = 2
hidden_neurons = 64
learning_rate = 0.0005
vae_sample, cgan_sample, ks_result1, ks_result2, fid = run_CGAN_VAE_Generator(
train_main, test_main, epochs, latent_size, n_samples, n_layer,
learning_rate, hidden_neurons, name, random_neg, random_pos)
tsne_data_comparision(random_pos, random_neg, vae_sample, name,
cgan_sample, 'CGAN_VAE')
get_combined_generated = get_combined_generated_real(
vae_sample, train_main, name)
(train_X, train_y) = split_XY(get_combined_generated)
(test_X, test_y) = split_XY(test_main)
multiple_classifier(train_X, train_y.values.ravel(), test_X,
test_y.values.ravel(), name, ks_result1, ks_result2,
fid)
print(
"======================Both GAN and VAE=============================")
name = name + "CGAN-VAE-both"
get_combined_generated = get_combined_generated_real(
vae_sample, get_combined_generated, name)
(train_X, train_y) = split_XY(get_combined_generated)
(test_X, test_y) = split_XY(test_main)
def run_VAECGAN_Generator(train, test, epochs, latent_size, n_samples, n_layer,
learning_rate, hidden_neurons, name,
random_neg_sample, random_pos):
vae_sample = pd.read_csv(r'generated_data/VAE_no_mmd.csv').sample(
n=1000, random_state=123)
# vae_sample, ks_result1, ks_result2, fid = run_VAEGenerator(train, test, epochs, latent_size,
# n_samples, n_layer,
# hidden_neurons,
# learning_rate, name,
# random_neg)
# # vae_sample, noise = vae_obj.generate_samples(n_samples)
# get_vae_combine = get_combined_generated_real(vae_sample, train, "vae_gan")
vae_combine = get_combined_generated_real(vae_sample, train, name)
cgan_sample, ks_result3, ks_result4, fid2 = run_CGANGenerator(
vae_combine,
test,
epochs,
latent_size,
n_samples,
n_layer,
learning_rate,
hidden_neurons,
name,
random_neg_sample,
random_pos,
model_type='VAE_CGAN')
tsne_data_comparision(random_pos, random_neg_sample, cgan_sample[:, :-1],
name, vae_sample, 'VAE_CGAN')
#get_combined_generated = get_combined_generated_real(cgan_sample, train, name)
return cgan_sample, vae_sample, ks_result3, ks_result4, fid2
print("Count of Failure and non failure", get_combined_generated.shape,
get_combined_generated.failure.value_counts())
(train_X, train_y) = split_XY(get_combined_generated)
(test_X, test_y) = split_XY(test)
#multiple_classifier(train_X, train_y.values.ravel(), test_X, test_y.values.ravel(),
# name, ks_result3, ks_result4, fid2)
print(
"======================Both GAN and VAE=============================")
name = name + "VAE_GAN-both"
get_combined_generated = get_combined_generated_real(
vae_sample, get_combined_generated, name)
(train_X, train_y) = split_XY(get_combined_generated)
(test_X, test_y) = split_XY(test)
def run_VAEGenerator(train, test, epochs, latent, n_samples, n_layer,
hidden_neurons, learning_rate, name, random_neg_sample):
vae_obj = VAEGenerator(train, test, epochs, latent, name)
vae_obj.build_model(n_layer, hidden_neurons, learning_rate)
name = vae_obj.train_model()
vae_sample, noise = vae_obj.generate_samples(n_samples)
print(vae_sample.shape, train.shape)
real_pos = train[train.failure == 1][train.columns.drop('failure')].sample(
frac=1, random_state=123)
ks_result1, ks_result2 = compare_distribution(real_pos, vae_sample, name)
fid = calculate_fid(real_pos, vae_sample)
print("Frechet Inception Distance:", fid)
tsne_data_comparision(real_pos, random_neg_sample, vae_sample, name, 'VAE')
return vae_sample, ks_result1, ks_result2, fid
def run_CGANGenerator(train,
test,
epochs,
latent_size,
n_samples,
n_layer,
learning_rate,
hidden_neurons,
name,
random_neg_sample,
real_pos,
model_type='CGAN'):
gan_obj = CGANGenerator(train, test, epochs, latent_size, name)
gan_obj.define_models_CGAN(n_layer,
n_layer,
learning_rate,
learning_rate,
latent_size,
hidden_neurons,
type=None)
gan_obj.train_model(model_type)
gan_sample = gan_obj.generate_samples(n_samples)
ks_result1, ks_result2 = compare_distribution(real_pos, gan_sample[:, :-1],
name)
fid = calculate_fid(real_pos, gan_sample[:, :-1])
print("Frechet Inception Distance:", fid)
if model_type == 'CGAN':
tsne_data_comparision(real_pos, random_neg_sample, gan_sample[:, :-1],
name, None, model_type)
#get_combined_generated = get_combined_generated_real(gan_sample[:,:-1],train,name)
# print("Count of Failure and non failure",get_combined_generated.failure.value_counts())
#(train_X, train_y) = split_XY(get_combined_generated)
#(test_X, test_y) = split_XY(test)
#multiple_classifier(train_X, train_y.values.ravel(), test_X, test_y.values.ravel(),name,ks_result1,ks_result2,fid)
#xgb_classifier(train_X, train_y.values.ravel(), test_X, test_y.values.ravel(),name)
#rf_classifier(train_X, train_y.values.ravel(), test_X, test_y.values.ravel(),name)
return gan_sample[:, :-1], ks_result1, ks_result2, fid