def get_label(predictor):
key = get_key(predictor, suffix="train_y")
path_to_file = resource_filename(Requirement.parse("molSimplify"),
"molSimplify/tf_nn/" + key + '.csv')
_df = pd.read_csv(path_to_file)
lname = _df.columns.tolist()
assert len(lname) == 1
return lname
def load_sklearn_model(predictor):
key = get_key(predictor, suffix="model")
modelfile = resource_filename(Requirement.parse("molSimplify"),
"molSimplify/sklearn_models/" + key + '.h5')
loaded_model = joblib.load(modelfile)
return loaded_model
def latent_space_uq(predictor,
layer_index=-2,
descriptors=False,
descriptor_names=False,
entropy=False):
key = get_key(predictor, suffix=False)
base_path = resource_filename(Requirement.parse("molSimplify"),
"molSimplify/tf_nn/" + key)
base_path = base_path + 'ensemble_models'
if not os.path.exists(base_path):
print('Ensemble models do not exist now, training...')
ensemble_maker(predictor)
print(('ANN activated for ' + str(predictor)))
model_list = glob.glob(base_path + '/*.h5')
train_mean_x, train_mean_y, train_var_x, train_var_y = load_normalization_data(
predictor)
if (descriptors and descriptor_names):
excitation = tf_ANN_excitation_prepare(predictor, descriptors,
descriptor_names)
excitation = data_normalize(excitation, train_mean_x, train_var_x)
else:
mat = load_training_data(predictor)
mat = np.array(mat, dtype='float64')
train_mat = data_normalize(mat, train_mean_x, train_var_x)
excitation = np.array(train_mat)
### load test data
if (descriptors and descriptor_names):
excitation = tf_ANN_excitation_prepare(predictor, descriptors,
descriptor_names)
excitation_test = data_normalize(excitation, train_mean_x, train_var_x)
else:
mat = load_test_data(predictor)
mat = np.array(mat, dtype='float64')
test_mat = data_normalize(mat, train_mean_x, train_var_x)
excitation_test = np.array(test_mat)
labels = load_test_labels(predictor)
labels_train = load_training_labels(predictor)
if not 'clf' in predictor:
labels = np.array(labels, dtype='float64')
labels_train = np.array(labels_train, dtype='float64')
else:
labels = np.array(labels, dtype='int')
labels_train = np.array(labels_train, dtype='int')
results_list = []
err_list = []
dist_list = []
for model in model_list:
_base = model.split('.')[0]
json_file = open(_base + '.json', 'r')
loaded_model_json = json_file.read()
json_file.close()
loaded_model = model_from_json(loaded_model_json)
loaded_model.load_weights(model)
loaded_model.compile(loss="mse",
optimizer='adam',
metrics=['mse', 'mae', 'mape'])
get_outputs = K.function(
[loaded_model.layers[0].input,
K.learning_phase()], [loaded_model.layers[-1].output])
get_latent = K.function(
[loaded_model.layers[0].input,
K.learning_phase()], [loaded_model.layers[layer_index].output])
print(
('NOTE: you are choosing:', loaded_model.layers[layer_index],
loaded_model.layers[layer_index].name, 'for the latence space!'))
if not 'clf' in predictor:
results = data_rescale(np.array(get_outputs([excitation_test, 0])),
train_mean_y, train_var_y)[0]
else:
results = np.array(get_outputs([excitation_test, 0]))[0]
## get latent dist
training_latent_distance = np.array(get_latent([excitation, 0]))[0]
nn_latent_dist_train, _, __ = dist_neighbor(training_latent_distance,
training_latent_distance,
labels_train,
l=5,
dist_ref=1,
just_nn=True)
nn_dist_avrg_train = np.mean(nn_latent_dist_train)
# print(nn_dist_avrg_train)
test_latent_distance = np.array(get_latent([excitation_test, 0]))[0]
nn_latent_dist_test, nn_dists, nn_labels = dist_neighbor(
test_latent_distance,
training_latent_distance,
labels_train,
l=5,
dist_ref=nn_dist_avrg_train,
just_nn=False)
if not entropy:
# print(nn_latent_dist_test.shape)
# print(min(nn_latent_dist_test), max(nn_latent_dist_test))
dist_list.append(nn_latent_dist_test)
else:
entropy = []
for idx, _dists in enumerate(nn_dists):
entropy.append(get_entropy(_dists, nn_labels[idx]))
dist_list.append(np.array(entropy))
results = results.squeeze(axis=1)
err = np.linalg.norm(labels - results)**2
results_list.append(results)
err_list.append(err)
dist_list = np.transpose(np.array(dist_list))
results_list = np.transpose(np.array(results_list))
result_mean, result_std = np.mean(results_list,
axis=1), np.std(results_list, axis=1)
latent_dist = np.mean(dist_list, axis=1)
labels = np.squeeze(labels, axis=1)
error_for_mean = np.abs(labels - result_mean)
return result_mean, latent_dist, error_for_mean
def ensemble_uq(predictor,
descriptors=False,
descriptor_names=False,
suffix=False):
key = get_key(predictor, suffix)
base_path = resource_filename(Requirement.parse("molSimplify"),
"molSimplify/tf_nn/" + key)
base_path = base_path + 'ensemble_models'
if not os.path.exists(base_path):
print('Ensemble models do not exist now, training...')
ensemble_maker(predictor)
print(('ANN activated for ' + str(predictor)))
model_list = glob.glob(base_path + '/*.h5')
labels = load_test_labels(predictor)
if not 'clf' in predictor:
labels = np.array(labels, dtype='float64')
else:
labels = np.array(labels, dtype='int')
train_mean_x, train_mean_y, train_var_x, train_var_y = load_normalization_data(
predictor)
if (descriptors and descriptor_names):
excitation = tf_ANN_excitation_prepare(predictor, descriptors,
descriptor_names)
excitation = data_normalize(excitation, train_mean_x, train_var_x)
else:
mat = load_test_data(predictor)
mat = np.array(mat, dtype='float64')
train_mat = data_normalize(mat, train_mean_x, train_var_x)
excitation = np.array(train_mat)
print(('excitation is ' + str(excitation.shape)))
print(('actual label:', labels[:3]))
results_list = []
# print('models', model_list)
for idx, model in enumerate(model_list):
_base = model.split('.')[0]
json_file = open(_base + '.json', 'r')
loaded_model_json = json_file.read()
json_file.close()
loaded_model = model_from_json(loaded_model_json)
# load weights into model
loaded_model.load_weights(model)
# complile model
loaded_model.compile(loss="mse",
optimizer='adam',
metrics=['mse', 'mae', 'mape'])
if not 'clf' in predictor:
result = data_rescale(loaded_model.predict(excitation),
train_mean_y, train_var_y)
else:
result = loaded_model.predict(excitation)
result = np.squeeze(result, axis=1)
results_list.append(result)
results_list = np.transpose(np.array(results_list))
# print(results_list.shape)
result_mean, result_std = np.mean(results_list,
axis=1), np.std(results_list, axis=1)
labels = np.squeeze(labels, axis=1)
print((labels.shape, result_mean.shape))
error_for_mean = np.abs(labels - result_mean)
return result_mean, result_std, error_for_mean