def training_batched_som(map_min_size, map_max_size, nb_models, X_train):
for i in range(nb_models):
sm = SOMFactory().build(
X_train,
mapsize=[
random.choice(list(range(map_min_size, map_max_size))),
random.choice(list(range(map_min_size, map_max_size)))
],
normalization='var',
initialization='random',
component_names=names,
lattice="hexa")
sm.train(n_job=1,
verbose=False,
train_rough_len=30,
train_finetune_len=100)
joblib.dump(sm, path + "batched_model_{}.joblib".format(i))
print("end of training model n°" + str(i))
# Study the models trained and plot the errors obtained in order to select the best one
models_pool = glob.glob(path + "batched_model*")
errors = []
for model_filepath in models_pool:
sm = joblib.load(model_filepath)
topographic_error = sm.calculate_topographic_error()
quantization_error = sm.calculate_quantization_error()
errors.append((topographic_error, quantization_error))
e_top, e_q = zip(*errors)
plt.scatter(e_top, e_q)
plt.xlabel("Topographic error")
plt.ylabel("Quantization error")
plt.title("Topographic and quantization errors of the models trained")
plt.show()
def training_specific_som(map_x_size, map_y_size, X_train):
sm = SOMFactory().build(X_train,
mapsize=[map_x_size, map_y_size],
normalization='var',
initialization='random',
component_names=names,
lattice='hexa')
sm.train(n_job=1,
verbose=False,
train_rough_len=30,
train_finetune_len=100)
joblib.dump(sm, path + "batched_model_specific{}.joblib".format(0))
print("Topographic error: " + str(sm.calculate_topographic_error()) +
", Quantization error: " + str(sm.calculate_quantization_error()) +
"\n")
return (sm)
