def running_one_time(n, dropout, seed, n_conv_feat, lr, l2_regu, nb_layers,
ord_row):
"""
function to run the architecture one time
Inputs:
n: number of runs of the architecture for the same initialization with the weights and biases of the last run,
seed: seed to use for the random sampling between training, testing and validation sets,
n_conv_feat: number of weights to use for the GCNN layer. Default value = 36,
l2_regu: coefficient to use in front of the l2 regularization term. Default value = 1,
dropout: dropout rate on the GCNN output. Default = 0.5,
lr: learning rate. Default value = 0.001
nb_layers: number of GCNN layers
ord_row: number of Chebyshev polynomials for the GCNN layers
Outputs:
auc_test_list, auc_train_list, auc_val_list: lists of the AUC values on the test, train and validation sets for the n runs,
pred_train_list, pred_test_list, pred_val_list: lists of the prediction values on the test, train and validation sets for the n runs,
labels_test, labels_train, labels_val: labels of the test, train and validation sets
"""
#initialization of the matrix, of the training, testing and validation sets
training_set_mask, testing_set_mask, idx_training, idx_testing = preprocessing_dataset.split_train_test(
0.8, M_str, seed, labels)
new_labels_train = np.copy(labels)
new_labels_train[idx_testing] = -1
#creation of a validation set from the training set. Split the training set into 4 parts, one for validation
training_set_mask, validation_set_mask, idx_training, idx_validation = preprocessing_dataset.split_train_validation_4(
3, M_str, seed, new_labels_train)
labels_train = labels * training_set_mask
labels_test = labels * testing_set_mask
labels_val = labels * validation_set_mask
indexes_train = np.concatenate((idx_testing, idx_validation), axis=0)
indexes_validation = np.concatenate((idx_training, idx_testing), axis=0)
indexes_test = np.concatenate((idx_training, idx_validation), axis=0)
labels_test_reduce = np.delete(labels_test, indexes_test, 0)
labels_train_reduce = np.delete(labels_train, indexes_train, 0)
labels_val_reduce = np.delete(labels_val, indexes_validation, 0)
learning_obj = Train_test_matrix_completion(M,
Lrow_age,
Lrow_sex,
Lrow_agesex,
A_age,
A_sex,
A_sexage,
mask_age,
mask_sex,
mask_agesex,
mask_nosignificance,
labels_train,
labels_test,
labels_val,
testing_set_mask,
training_set_mask,
validation_set_mask,
order_chebyshev_row=ord_row,
n_conv_feat=n_conv_feat,
dropout=dropout,
learning_rate=lr,
l2_regu=l2_regu,
nb_layers=nb_layers)
num_iter_test = 10
num_total_iter_training = n
num_iter = 0
list_training_loss = list()
list_training_norm_grad = list()
list_test_pred_error = list()
auc_train_list = []
pred_train_list = []
auc_test_list = []
pred_test_list = []
auc_val_list = []
pred_val_list = []
for k in range(num_iter, num_total_iter_training):
tic = time.time()
# run of the algorithm on the training set
list_of_outputs = learning_obj.session.run(
[
learning_obj.optimizer, learning_obj.loss,
learning_obj.norm_grad, learning_obj.classification_train,
learning_obj.binary_entropy
] + learning_obj.var_grad
) #learning_obj.loss_frob, learning_obj.loss_trace_row, learning_obj.frob_norm_H, learning_obj.frob_norm_W, learning_obj.binary_entropy
current_training_loss = list_of_outputs[1]
norm_grad = list_of_outputs[2]
pred_train = list_of_outputs[3]
pred_train = np.delete(pred_train, indexes_train, 0)
fpr_train, tpr_train, thresholds_train = roc_curve(
labels_train_reduce, pred_train)
roc_auc_train = auc(fpr_train, tpr_train)
X_grad = list_of_outputs[3:]
training_time = time.time() - tic
list_training_loss.append(current_training_loss)
list_training_norm_grad.append(norm_grad)
if (np.mod(num_iter, num_iter_test) == 0):
msg = "[TRN] iter = %03i, cost = %3.2e, |grad| = %.2e (%3.2es), AUC = %3.2e" \
% (num_iter, list_training_loss[-1], list_training_norm_grad[-1], training_time, roc_auc_train)
print msg
auc_train_list.append(roc_auc_train)
pred_train_list.append(pred_train)
tic = time.time()
# run of the algorithm on the validation set
pred_val = learning_obj.session.run(
[learning_obj.classification_val]) #
test_time = time.time() - tic
pred_val = np.delete(pred_val[0], indexes_validation, 0)
fpr, tpr, thresholds = roc_curve(labels_val_reduce, pred_val)
roc_auc_val = auc(fpr, tpr)
auc_val_list.append(roc_auc_val)
pred_val_list.append(pred_val)
msg = "[VAL] iter = %03i, AUC = %3.2e" % (num_iter, roc_auc_val)
print msg
tic = time.time()
# run of the algorithm on the test set
pred_error, pred = learning_obj.session.run([
learning_obj.predictions_error,
learning_obj.classification_test
]) #
test_time = time.time() - tic
pred = np.delete(pred, indexes_test, 0)
list_test_pred_error.append(pred_error)
fpr, tpr, thresholds = roc_curve(labels_test_reduce, pred)
roc_auc = auc(fpr, tpr)
auc_test_list.append(roc_auc)
pred_test_list.append(pred)
msg = "[TST] iter = %03i, cost = %3.2e, AUC = %3.2e" % (
num_iter, list_test_pred_error[-1], roc_auc)
print msg
num_iter += 1
return (auc_test_list, auc_train_list, auc_val_list, pred_train_list,
pred_test_list, pred_val_list, labels_test_reduce,
labels_train_reduce, labels_val_reduce)
def run(seed, gamma, beta, hidden, lr, NB_EPOCH=300):
"""
Main function. Run the architecture for the initialization defined by seed and by the hyperparameters gamma, beta, hidden, lr
Inputs:
seed : seed to defined the initialization of the training/testing/validation split,
gamma, beta, hidden, lr: hyperparameters of the architecture
NB_EPOCH: number of runs to do of the same architecture with different weight initializations. Default: 1000
Outputs:
auc_test, auc_train, auc_val: AUC on the test, train and validation sets
"""
tf.reset_default_graph()
training_set_mask, testing_set_mask, idx_training, idx_testing = preprocessing_dataset.split_train_test(
0.8, M_str, seed, labels)
#create a training and test mask on the data
Otraining = preprocessing_dataset.load_mask(training_set_mask, M_str,
nrRows, nrCols)
Otest = preprocessing_dataset.load_mask(testing_set_mask, M_str, nrRows,
nrCols)
new_labels_train = np.copy(labels)
new_labels_train[idx_testing] = -1
#split train set into 4 parts to create a validation set
training_set_mask, validation_set_mask, idx_training, idx_validation = preprocessing_dataset.split_train_validation_4(
3, M_str, seed, new_labels_train)
Otraining = preprocessing_dataset.load_mask(training_set_mask, M_str,
nrRows, nrCols)
Ovalidation = preprocessing_dataset.load_mask(validation_set_mask, M_str,
nrRows, nrCols)
Otraining = np.concatenate((Otraining, training_set_mask), axis=1)
Ocol = np.zeros((Otest.shape[0], 1))
Otest_support = np.concatenate((Otest, Ocol), axis=1)
Ovalidation_support = np.concatenate((Ovalidation, Ocol), axis=1)
Osupport_t = Otraining + Otest_support + Ovalidation_support
Ovalidation = np.concatenate((Ovalidation, validation_set_mask), axis=1)
Otest = np.concatenate((Otest, testing_set_mask), axis=1)
u_features, v_features, train_labels, train_u_indices, train_v_indices, val_labels, val_u_indices, val_v_indices, test_labels, test_u_indices, test_v_indices = load_data_monti_tadpole(
M, Otraining, Otest, Ovalidation)
m, n = M.shape
# global normalization
support = []
support_t = []
path_support_women = "women_synth_noteasy.csv"
women_support, _, _ = read_tadpole.load_csv_no_header(path_support_women)
women_support = preprocessing_dataset.str_to_float(women_support)
women_support = women_support * M_sup
women_support = sp.csr_matrix(women_support, dtype=np.float32)
support.append(women_support)
support_t.append(women_support.T)
path_support_men = "men_synth_noteasy.csv"
men_support, _, _ = read_tadpole.load_csv_no_header(path_support_men)
men_support = preprocessing_dataset.str_to_float(men_support)
men_support = men_support * M_sup
men_support = sp.csr_matrix(men_support, dtype=np.float32)
support.append(men_support)
support_t.append(men_support.T)
path_support_women_84 = "age_84_92_women_synth_noteasy.csv"
women_84_support, _, _ = read_tadpole.load_csv_no_header(
path_support_women_84)
women_84_support = preprocessing_dataset.str_to_float(women_84_support)
women_84_support = women_84_support * M_sup
women_84_support = sp.csr_matrix(women_84_support, dtype=np.float32)
support.append(women_84_support)
support_t.append(women_84_support.T)
path_support_men_84 = "age_84_92_men_synth_noteasy.csv"
men_84_support, _, _ = read_tadpole.load_csv_no_header(path_support_men_84)
men_84_support = preprocessing_dataset.str_to_float(men_84_support)
men_84_support = men_84_support * M_sup
men_84_support = sp.csr_matrix(men_84_support, dtype=np.float32)
support.append(men_84_support)
support_t.append(men_84_support.T)
path_support_84 = "age_84_92_synth_noteasy.csv"
age84_support, _, _ = read_tadpole.load_csv_no_header(path_support_84)
age84_support = preprocessing_dataset.str_to_float(age84_support)
age84_support = age84_support * M_sup
age84_support = sp.csr_matrix(age84_support, dtype=np.float32)
support.append(age84_support)
support_t.append(age84_support.T)
path_support_women_79 = "age_79_84_women_synth_noteasy.csv"
women_79_support, _, _ = read_tadpole.load_csv_no_header(
path_support_women_79)
women_79_support = preprocessing_dataset.str_to_float(women_79_support)
women_79_support = women_79_support * M_sup
women_79_support = sp.csr_matrix(women_79_support, dtype=np.float32)
support.append(women_79_support)
support_t.append(women_79_support.T)
path_support_men_79 = "age_79_84_men_synth_noteasy.csv"
men_79_support, _, _ = read_tadpole.load_csv_no_header(path_support_men_79)
men_79_support = preprocessing_dataset.str_to_float(men_79_support)
men_79_support = men_79_support * M_sup
men_79_support = sp.csr_matrix(men_79_support, dtype=np.float32)
support.append(men_79_support)
support_t.append(men_79_support.T)
path_support_79 = "age_79_84_synth_noteasy.csv"
age79_support, _, _ = read_tadpole.load_csv_no_header(path_support_79)
age79_support = preprocessing_dataset.str_to_float(age79_support)
age79_support = age79_support * M_sup
age79_support = sp.csr_matrix(age79_support, dtype=np.float32)
support.append(age79_support)
support_t.append(age79_support.T)
path_support_women_74 = "age_74_79_women_synth_noteasy.csv"
women_74_support, _, _ = read_tadpole.load_csv_no_header(
path_support_women_74)
women_74_support = preprocessing_dataset.str_to_float(women_74_support)
women_74_support = women_74_support * M_sup
women_74_support = sp.csr_matrix(women_74_support, dtype=np.float32)
support.append(women_74_support)
support_t.append(women_74_support.T)
path_support_men_74 = "age_74_79_men_synth_noteasy.csv"
men_74_support, _, _ = read_tadpole.load_csv_no_header(path_support_men_74)
men_74_support = preprocessing_dataset.str_to_float(men_74_support)
men_74_support = men_74_support * M_sup
men_74_support = sp.csr_matrix(men_74_support, dtype=np.float32)
support.append(men_74_support)
support_t.append(men_74_support.T)
path_support_74 = "age_74_79_synth_noteasy.csv"
age74_support, _, _ = read_tadpole.load_csv_no_header(path_support_74)
age74_support = preprocessing_dataset.str_to_float(age74_support)
age74_support = age74_support * M_sup
age74_support = sp.csr_matrix(age74_support, dtype=np.float32)
support.append(age74_support)
support_t.append(age74_support.T)
path_support_women_69 = "age_69_74_women_synth_noteasy.csv"
women_69_support, _, _ = read_tadpole.load_csv_no_header(
path_support_women_69)
women_69_support = preprocessing_dataset.str_to_float(women_69_support)
women_69_support = women_69_support * M_sup
women_69_support = sp.csr_matrix(women_69_support, dtype=np.float32)
support.append(women_69_support)
support_t.append(women_69_support.T)
path_support_men_69 = "age_69_74_men_synth_noteasy.csv"
men_69_support, _, _ = read_tadpole.load_csv_no_header(path_support_men_69)
men_69_support = preprocessing_dataset.str_to_float(men_69_support)
men_69_support = men_69_support * M_sup
men_69_support = sp.csr_matrix(men_69_support, dtype=np.float32)
support.append(men_69_support)
support_t.append(men_69_support.T)
path_support_69 = "age_69_74_synth_noteasy.csv"
age69_support, _, _ = read_tadpole.load_csv_no_header(path_support_69)
age69_support = preprocessing_dataset.str_to_float(age69_support)
age69_support = age69_support * M_sup
age69_support = sp.csr_matrix(age69_support, dtype=np.float32)
support.append(age69_support)
support_t.append(age69_support.T)
path_support_women_64 = "age_64_69_women_synth_noteasy.csv"
women_64_support, _, _ = read_tadpole.load_csv_no_header(
path_support_women_64)
women_64_support = preprocessing_dataset.str_to_float(women_64_support)
women_64_support = women_64_support * M_sup
women_64_support = sp.csr_matrix(women_64_support, dtype=np.float32)
support.append(women_64_support)
support_t.append(women_64_support.T)
path_support_men_64 = "age_64_69_men_synth_noteasy.csv"
men_64_support, _, _ = read_tadpole.load_csv_no_header(path_support_men_64)
men_64_support = preprocessing_dataset.str_to_float(men_64_support)
men_64_support = men_64_support * M_sup
men_64_support = sp.csr_matrix(men_64_support, dtype=np.float32)
support.append(men_64_support)
support_t.append(men_64_support.T)
path_support_64 = "age_64_69_synth_noteasy.csv"
age64_support, _, _ = read_tadpole.load_csv_no_header(path_support_64)
age64_support = preprocessing_dataset.str_to_float(age64_support)
age64_support = age64_support * M_sup
age64_support = sp.csr_matrix(age64_support, dtype=np.float32)
support.append(age64_support)
support_t.append(age64_support.T)
path_support_women_59 = "age_59_64_women_synth_noteasy.csv"
women_59_support, _, _ = read_tadpole.load_csv_no_header(
path_support_women_59)
women_59_support = preprocessing_dataset.str_to_float(women_59_support)
women_59_support = women_59_support * M_sup
women_59_support = sp.csr_matrix(women_59_support, dtype=np.float32)
support.append(women_59_support)
support_t.append(women_59_support.T)
path_support_men_59 = "age_59_64_men_synth_noteasy.csv"
men_59_support, _, _ = read_tadpole.load_csv_no_header(path_support_men_59)
men_59_support = preprocessing_dataset.str_to_float(men_59_support)
men_59_support = men_59_support * M_sup
men_59_support = sp.csr_matrix(men_59_support, dtype=np.float32)
support.append(men_59_support)
support_t.append(men_59_support.T)
path_support_59 = "age_59_64_synth_noteasy.csv"
age59_support, _, _ = read_tadpole.load_csv_no_header(path_support_59)
age59_support = preprocessing_dataset.str_to_float(age59_support)
age59_support = age59_support * M_sup
age59_support = sp.csr_matrix(age59_support, dtype=np.float32)
support.append(age59_support)
support_t.append(age59_support.T)
path_support_women_54 = "age_54_59_women_synth_noteasy.csv"
women_54_support, _, _ = read_tadpole.load_csv_no_header(
path_support_women_54)
women_54_support = preprocessing_dataset.str_to_float(women_54_support)
women_54_support = women_54_support * M_sup
women_54_support = sp.csr_matrix(women_54_support, dtype=np.float32)
support.append(women_54_support)
support_t.append(women_54_support.T)
path_support_men_54 = "age_54_59_men_synth_noteasy.csv"
men_54_support, _, _ = read_tadpole.load_csv_no_header(path_support_men_54)
men_54_support = preprocessing_dataset.str_to_float(men_54_support)
men_54_support = men_54_support * M_sup
men_54_support = sp.csr_matrix(men_54_support, dtype=np.float32)
support.append(men_54_support)
support_t.append(men_54_support.T)
path_support_54 = "age_54_59_synth_noteasy.csv"
age54_support, _, _ = read_tadpole.load_csv_no_header(path_support_54)
age54_support = preprocessing_dataset.str_to_float(age54_support)
age54_support = age54_support * M_sup
age54_support = sp.csr_matrix(age54_support, dtype=np.float32)
support.append(age54_support)
support_t.append(age54_support.T)
num_support = len(support)
mask_support_t = []
Osupport_t = sp.csr_matrix(Osupport_t, dtype=np.int)
for i in range(num_support):
mask_support_t.append(Osupport_t.T)
mask_support_t = sp.hstack(mask_support_t, format='csr')
support = sp.hstack(support, format='csr')
support_t = sp.hstack(support_t, format='csr')
# Collect all user and item nodes for test set
test_u = list(set(test_u_indices))
test_v = list(set(test_v_indices))
test_u_dict = {n: i for i, n in enumerate(test_u)}
test_v_dict = {n: i for i, n in enumerate(test_v)}
test_u_indices = np.array([test_u_dict[o] for o in test_u_indices])
test_v_indices = np.array([test_v_dict[o] for o in test_v_indices])
test_support = support[np.array(test_u)]
for i in range(test_support.shape[0]):
for j in range(563, test_support.shape[1], 564):
test_support[i, j] = 0.0
test_support_t = sp.csr_matrix.multiply(support_t, mask_support_t)
# Collect all user and item nodes for validation set
val_u = list(set(val_u_indices))
val_v = list(set(val_v_indices))
val_u_dict = {n: i for i, n in enumerate(val_u)}
val_v_dict = {n: i for i, n in enumerate(val_v)}
val_u_indices = np.array([val_u_dict[o] for o in val_u_indices])
val_v_indices = np.array([val_v_dict[o] for o in val_v_indices])
val_support = support[np.array(val_u)]
for i in range(val_support.shape[0]):
for j in range(563, val_support.shape[1], 564):
val_support[i, j] = 0.0
val_support_t = sp.csr_matrix.multiply(support_t, mask_support_t)
# Collect all user and item nodes for train set
train_u = list(set(train_u_indices))
train_v = list(set(train_v_indices))
train_u_dict = {n: i for i, n in enumerate(train_u)}
train_v_dict = {n: i for i, n in enumerate(train_v)}
train_u_indices = np.array([train_u_dict[o] for o in train_u_indices])
train_v_indices = np.array([train_v_dict[o] for o in train_v_indices])
train_support = support[np.array(train_u)]
train_support_t = sp.csr_matrix.multiply(support_t, mask_support_t)
placeholders = {
'u_features':
tf.sparse_placeholder(tf.float32,
shape=np.array(u_features.shape,
dtype=np.int64)),
'v_features':
tf.sparse_placeholder(tf.float32,
shape=np.array(v_features.shape,
dtype=np.int64)),
'u_features_nonzero':
tf.placeholder(tf.int32, shape=()),
'v_features_nonzero':
tf.placeholder(tf.int32, shape=()),
'labels':
tf.placeholder(tf.float32, shape=(None, )),
'indices_labels':
tf.placeholder(tf.int32, shape=(None, )),
'user_indices':
tf.placeholder(tf.int32, shape=(None, )),
'item_indices':
tf.placeholder(tf.int32, shape=(None, )),
'dropout':
tf.placeholder_with_default(0., shape=()),
'weight_decay':
tf.placeholder_with_default(0., shape=()),
'support':
tf.sparse_placeholder(tf.float32, shape=(None, None)),
'support_t':
tf.sparse_placeholder(tf.float32, shape=(None, None)),
}
div = hidden[0] // num_support
if hidden[0] % num_support != 0:
print(
"""\nWARNING: HIDDEN[0] (=%d) of stack layer is adjusted to %d such that
it can be evenly split in %d splits.\n""" %
(hidden[0], num_support * div, num_support))
hidden[0] = num_support * div
# create model
model = MG_GAE(placeholders,
input_dim=u_features.shape[1],
num_support=num_support,
hidden=hidden,
num_users=m,
num_items=n,
learning_rate=lr,
gamma=gamma,
beta=beta,
logging=True)
# Convert sparse placeholders to tuples to construct feed_dict
test_support = sparse_to_tuple(test_support)
test_support_t = sparse_to_tuple(test_support_t)
val_support = sparse_to_tuple(val_support)
val_support_t = sparse_to_tuple(val_support_t)
train_support = sparse_to_tuple(train_support)
train_support_t = sparse_to_tuple(train_support_t)
u_features = sparse_to_tuple(u_features)
v_features = sparse_to_tuple(v_features)
assert u_features[2][1] == v_features[2][
1], 'Number of features of users and items must be the same!'
num_features = u_features[2][1]
u_features_nonzero = u_features[1].shape[0]
v_features_nonzero = v_features[1].shape[0]
indices_labels = [563] * train_labels.shape[0]
indices_labels_val = [563] * val_labels.shape[0]
indices_labels_test = [563] * test_labels.shape[0]
# Feed_dicts for validation and test set stay constant over different update steps
train_feed_dict = construct_feed_dict(placeholders, u_features, v_features,
u_features_nonzero,
v_features_nonzero, train_support,
train_support_t, train_labels,
indices_labels, train_u_indices,
train_v_indices, 0.)
# No dropout for validation and test runs
val_feed_dict = construct_feed_dict(placeholders, u_features, v_features,
u_features_nonzero, v_features_nonzero,
val_support, val_support_t, val_labels,
indices_labels_val, val_u_indices,
val_v_indices, 0.)
test_feed_dict = construct_feed_dict(placeholders, u_features, v_features,
u_features_nonzero,
v_features_nonzero, test_support,
test_support_t, test_labels,
indices_labels_test, test_u_indices,
test_v_indices, 0.)
# Collect all variables to be logged into summary
merged_summary = tf.summary.merge_all()
sess = tf.Session()
sess.run(tf.global_variables_initializer())
auc_train = []
auc_test = []
auc_val = []
test_pred = []
for epoch in range(NB_EPOCH):
t = time.time()
# Run single weight update
outs = sess.run([
model.training_op, model.loss, model.indices, model.labels,
model.outputs, model.labels_class, model.classification,
model.inputs, model.gcn_u, model.gcn_v, model.loss_frob,
model.binary_entropy, model.u_inputs, model.v_inputs, model.weight,
model.input_u, model.input_v, model.u_indices, model.v_indices
],
feed_dict=train_feed_dict)
train_avg_loss = outs[1]
label_train = outs[5]
output_train = outs[6]
fpr_train, tpr_train, thresholds_train = roc_curve(
label_train, output_train, pos_label=label_train.max())
roc_auc_train = auc(fpr_train, tpr_train)
auc_train.append(roc_auc_train)
val_avg_loss, val_classification, val_labels_corres = sess.run(
[model.loss, model.classification, model.labels_class],
feed_dict=val_feed_dict) #test_feed_dict)#
fpr_val, tpr_val, thresholds_train = roc_curve(
val_labels_corres, val_classification, pos_label=label_train.max())
roc_auc_val = auc(fpr_val, tpr_val)
auc_val.append(roc_auc_val)
test_avg_loss, test_classification, test_labels_corres = sess.run(
[model.loss, model.classification, model.labels_class],
feed_dict=test_feed_dict)
fpr_test, tpr_test, thresholds_test = roc_curve(
test_labels_corres,
test_classification,
pos_label=label_train.max())
roc_auc_test = auc(fpr_test, tpr_test)
auc_test.append(roc_auc_test)
test_pred.append(test_classification)
if VERBOSE:
print("[*] Epoch:", '%04d' % (epoch + 1), "train_loss=",
"{:.5f}".format(train_avg_loss), "train_auc=",
"{:.5f}".format(roc_auc_train), "val_loss=",
"{:.5f}".format(val_avg_loss), "val_auc=",
"{:.5f}".format(roc_auc_val), "\t\ttime=",
"{:.5f}".format(time.time() - t))
print('test auc = ', roc_auc_test)
sess.close()
return auc_test, auc_train, auc_val
age_file_path = 'ages_synthetic_data_noteasy.csv' age_column, nrRowsa, nrColsa = preprocessing_dataset.load_csv_no_header_float(age_file_path) age_column=age_column.reshape(-1) labels = preprocessing_dataset.str_to_float(labels) labels_save=labels.reshape(-1) M_init= np.concatenate((M_str, labels), axis=1) M_support = np.concatenate((M_str, labels), axis=1) M = preprocessing_dataset.normalization_gae(M_init) M_sup=preprocessing_dataset.normalization_for_supportreal(M_support) seed=0 training_set_mask, testing_set_mask, idx_training, idx_testing=preprocessing_dataset.split_train_test(0.8, M_str, seed, labels) #create a training and test mask on the data Otraining = preprocessing_dataset.load_mask(training_set_mask, M_str, nrRows, nrCols) Otest= preprocessing_dataset.load_mask(testing_set_mask, M_str, nrRows, nrCols) new_labels_train=np.copy(labels) new_labels_train[idx_testing]=-1 #split train set into 4 parts to create a validation set training_set_mask, validation_set_mask, idx_training, idx_validation=preprocessing_dataset.split_train_validation_4(3, M_str, seed, new_labels_train) Otraining = preprocessing_dataset.load_mask(training_set_mask, M_str, nrRows, nrCols) Ovalidation= preprocessing_dataset.load_mask(validation_set_mask, M_str, nrRows, nrCols) Otraining = np.concatenate((Otraining, training_set_mask), axis=1) Ocol = np.zeros((Otest.shape[0], 1 )) Otest_support = np.concatenate((Otest, Ocol), axis=1) Ovalidation_support = np.concatenate((Ovalidation, Ocol), axis=1)
def running_one_time(validation, rank, l2_regu, gamma, gamma_H, gamma_W,
gamma_e, n, seed, cheby, n_conv_feat, lr, ord_row):
"""
function to run the architecture one time
Inputs:
validation : boolean, to include a validation set or not
rank : rank of the SVD decomposition
l2_regu: coefficient to use in front of the l2 regularization term. Default value = 1,
gamma, gamma_H, gamma_W, gamma_e: coefficients in front of the other loss terms of the loss function,
n: number of runs of the architecture for the same initialization with the weights and biases of the last run,
seed: seed to use for the random sampling between training, testing and validation sets,
cheby: boolean, use of a GCNN or a GCN layer. 0: GCN, 1: GCNN. Default value = 1,
n_conv_feat: number of weights to use for the GCNN layer. Default value = 36,
lr: learning rate. Default value = 0.001
ord_row: int, number of chebyshev polynomials to use for the GCNN
Outputs:
auc_test_list, auc_train_list, auc_val_list: lists of the AUC values on the test, train and validation sets for the n runs,
pred_train_list, pred_test_list, pred_val_list: lists of the prediction values on the test, train and validation sets for the n runs,
labels_test, labels_train, labels_val: labels of the test, train and validation sets
"""
#initialization
training_set_mask, testing_set_mask, idx_training, idx_testing = preprocessing_dataset.split_train_test(
0.8, M_str, seed, labels)
#create a training and test mask on the data
Otraining = preprocessing_dataset.load_mask(training_set_mask, M_str,
nrRows, nrCols)
Otest = preprocessing_dataset.load_mask(testing_set_mask, M_str, nrRows,
nrCols)
if validation:
#split train set into 4 parts to create a validation set
new_labels_train = np.copy(labels)
new_labels_train[idx_testing] = -1
training_set_mask, validation_set_mask, idx_training, idx_validation = preprocessing_dataset.split_train_validation_4(
3, M_str, seed, new_labels_train)
Otraining = preprocessing_dataset.load_mask(training_set_mask, M_str,
nrRows, nrCols)
Ovalidation = preprocessing_dataset.load_mask(validation_set_mask,
M_str, nrRows, nrCols)
else:
validation_set_mask = []
idx_validation = []
Odata, _ = preprocessing_dataset.split_train_into_2(Otraining, seed)
Otraining = np.concatenate((Otraining, training_set_mask), axis=1)
if validation:
Oinitial = np.concatenate(
(Odata + Otest + Ovalidation, training_set_mask), axis=1)
else:
Oinitial = np.concatenate((Odata + Otest, training_set_mask), axis=1)
M_init_final = preprocessing_dataset.init_mask(Oinitial, M_init, labels)
#apply SVD initially for detecting the main components of our initialization
initial_W, initial_H = preprocessing_dataset.svd_W_H(M_init_final, rank)
learning_obj = Train_test_matrix_completion(M,
Lrow,
Wrow,
Otraining,
initial_W,
initial_H,
labels,
training_set_mask,
testing_set_mask,
validation_set_mask,
mask_features,
validation,
order_chebyshev_row=ord_row,
cheby=cheby,
n_conv_feat=n_conv_feat,
l2_regu=l2_regu,
gamma=gamma,
gamma_H=gamma_H,
gamma_W=gamma_W,
gamma_e=gamma_e,
learning_rate=lr)
num_iter_test = 10
num_total_iter_training = n
num_iter = 0
list_training_loss = list()
list_training_norm_grad = list()
list_test_pred_error = list()
list_test_times = list()
list_grad_X = list()
auc_train_list = []
pred_train_list = []
auc_val_list = []
pred_val_list = []
auc_test_list = []
pred_test_list = []
num_iter = 0
for k in range(num_iter, num_total_iter_training):
tic = time.time()
list_of_outputs = learning_obj.session.run([
learning_obj.optimizer, learning_obj.loss, learning_obj.norm_grad,
learning_obj.prediction_train, learning_obj.labels_training,
learning_obj.loss_frob, learning_obj.loss_trace_row, learning_obj.
frob_norm_H, learning_obj.frob_norm_W, learning_obj.binary_entropy
] + learning_obj.var_grad)
current_training_loss = list_of_outputs[1]
norm_grad = list_of_outputs[2]
pred_train = list_of_outputs[3]
labels_train = list_of_outputs[4]
loss_frob = list_of_outputs[5]
loss_trace = list_of_outputs[6]
loss_norm_H = list_of_outputs[7]
loss_norm_W = list_of_outputs[8]
loss_entropy = list_of_outputs[9]
indexes_train = np.concatenate((idx_testing, idx_validation), axis=0)
pred_train = np.delete(pred_train, indexes_train, 0)
labels_train = np.delete(labels_train, indexes_train, 0)
accuracy_train, tn_train, fn_train, tp_train, fp_train, spe_train, sen_train = preprocessing_dataset.accuracy_computation(
pred_train, training_set_mask, labels)
fpr_train, tpr_train, thresholds_train = roc_curve(
labels_train, pred_train)
roc_auc_train = auc(fpr_train, tpr_train)
X_grad = list_of_outputs[10:]
training_time = time.time() - tic
list_training_loss.append(current_training_loss)
list_training_norm_grad.append(norm_grad)
if (np.mod(num_iter, num_iter_test) == 0):
msg = "[TRN] iter = %03i, cost = %3.2e, |grad| = %.2e (%3.2es), accuracy = %3.2e, auc = %3.2e" \
% (num_iter, list_training_loss[-1], list_training_norm_grad[-1], training_time, accuracy_train, roc_auc_train)
print msg
auc_train_list.append(roc_auc_train)
pred_train_list.append(pred_train)
#Test Code
tic = time.time()
pred_error, pred, labels_test = learning_obj.session.run([
learning_obj.predictions_error, learning_obj.predictions,
learning_obj.labels_test
])
test_time = time.time() - tic
if validation:
pred_val, labels_val = learning_obj.session.run(
[learning_obj.predictions_val, learning_obj.labels_val])
indexes_validation = np.concatenate(
(idx_training, idx_testing), axis=0)
pred_val = np.delete(pred_val, indexes_validation, 0)
labels_val = np.delete(labels_val, indexes_validation, 0)
fpr, tpr, thresholds = roc_curve(labels_val, pred_val)
roc_auc_val = auc(fpr, tpr)
auc_val_list.append(roc_auc_val)
pred_val_list.append(pred_val)
msg = "[VAL] iter = %03i, AUC = %3.2e" % (num_iter,
roc_auc_val)
print msg
else:
pred_val_list = []
labels_val = []
indexes_test = np.concatenate((idx_training, idx_validation),
axis=0)
pred = np.delete(pred, indexes_test, 0)
labels_test = np.delete(labels_test, indexes_test, 0)
list_test_pred_error.append(pred_error)
accuracy, tn, fn, tp, fp, spe, sen = preprocessing_dataset.accuracy_computation(
pred, testing_set_mask, labels)
fpr, tpr, thresholds = roc_curve(labels_test, pred)
roc_auc = auc(fpr, tpr)
auc_test_list.append(roc_auc)
pred_test_list.append(pred)
msg = "[TST] iter = %03i, cost = %3.2e, Accuracy = %3.2e (%3.2es), AUC = %3.2e" % (
num_iter, list_test_pred_error[-1], accuracy, test_time,
roc_auc)
print msg
num_iter += 1
return (auc_test_list, auc_train_list, auc_val_list, pred_train_list,
pred_test_list, pred_val_list, labels_test, labels_train,
labels_val)
def running_one_time(l2_regu, gamma_age, gamma_sex, gamma_agesex, gamma_W, gamma_e,n, seed, cheby, n_conv_feat, dropout, lr):
"""
function to run the architecture one time
Inputs:
l2_regu: coefficient to use in front of the l2 regularization term. Default value = 1,
gamma_age, gamma_sex, gamma_agesex, gamma_W, gamma_e: coefficients in front of the other loss terms of the loss function,
n: number of runs of the architecture for the same initialization with the weights and biases of the last run,
seed: seed to use for the random sampling between training, testing and validation sets,
cheby: boolean, use of a GCNN or a GCN layer. 0: GCN, 1: GCNN. Default value = 1,
n_conv_feat: number of weights to use for the GCNN layer. Default value = 36,
dropout: dropout rate on the GCNN output. Default = 0.5,
lr: learning rate. Default value = 0.001
Outputs:
auc_test_list, auc_train_list, auc_val_list: lists of the AUC values on the test, train and validation sets for the n runs,
pred_train_list, pred_test_list, pred_val_list: lists of the prediction values on the test, train and validation sets for the n runs,
labels_test, labels_train, labels_val: labels of the test, train and validation sets
"""
#initialization of the matrix, of the training, testing and validation sets
training_set_mask, testing_set_mask, idx_training, idx_testing=preprocessing_dataset.split_train_test(0.8, M_str, seed, labels)
#create a training and test mask on the data
Otraining = preprocessing_dataset.load_mask(training_set_mask, M_str, nrRows, nrCols)
Otest = preprocessing_dataset.load_mask(testing_set_mask, M_str, nrRows, nrCols)
#creation of a validation set from the training set. Split the training set into 4 parts, one for validation
new_labels_train=np.copy(labels)
new_labels_train[idx_testing]=-1
training_set_mask, validation_set_mask, idx_training, idx_validation=preprocessing_dataset.split_train_validation_4(3, M_str, seed, new_labels_train)
Otraining = preprocessing_dataset.load_mask(training_set_mask, M_str, nrRows, nrCols)
Ovalidation= preprocessing_dataset.load_mask(validation_set_mask, M_str, nrRows, nrCols)
Odata, _=preprocessing_dataset.split_train_into_2(Otraining, seed)
Otraining = np.concatenate((Otraining, training_set_mask), axis=1)
Oinitial=np.concatenate((Odata+Otest+Ovalidation, training_set_mask), axis=1)
M_init_final=preprocessing_dataset.init_mask(Oinitial, M_init, labels)
learning_obj = Train_test_matrix_completion(M, M_init_final, A_age, A_sex, A_sexage, mask_age, mask_sex, mask_agesex , mask_nosignificance, Lrow_age, Lrow_sex, Lrow_agesex, Otraining,
labels, training_set_mask, testing_set_mask, validation_set_mask, mask_features,
order_chebyshev_row = ord_row,cheby=cheby, n_conv_feat=n_conv_feat, l2_regu=l2_regu,dropout=dropout,
gamma_age=gamma_age, gamma_sex=gamma_sex, gamma_agesex=gamma_agesex, gamma_W=gamma_W, gamma_e=gamma_e, learning_rate=lr)
num_iter_test = 10
num_total_iter_training = n
num_iter = 0
list_training_loss = list()
list_training_norm_grad = list()
list_test_pred_error = list()
auc_train_list=[]
pred_train_list=[]
auc_test_list=[]
pred_test_list=[]
auc_val_list=[]
pred_val_list=[]
for k in range(num_iter, num_total_iter_training):
tic = time.time()
# run of the algorithm on the training set
list_of_outputs = learning_obj.session.run([learning_obj.optimizer, learning_obj.loss, learning_obj.norm_grad, learning_obj.prediction_train, learning_obj.labels_training, learning_obj.loss_frob, learning_obj.frob_norm_W, learning_obj.binary_entropy, learning_obj.loss_trace_row_age, learning_obj.loss_trace_row_agesex, learning_obj.loss_trace_row_sex] + learning_obj.var_grad)
current_training_loss = list_of_outputs[1]
norm_grad = list_of_outputs[2]
pred_train = list_of_outputs[3]
labels_train =list_of_outputs[4]
loss_frob = list_of_outputs[5]
loss_frob_W = list_of_outputs[6]
loss_entropy =list_of_outputs[7]
loss_age =list_of_outputs[8]
loss_agesex = list_of_outputs[9]
loss_sex= list_of_outputs[10]
indexes_train = np.concatenate((idx_testing, idx_validation), axis=0)
pred_train = np.delete(pred_train, indexes_train,0)
labels_train = np.delete(labels_train, indexes_train,0)
accuracy_train, tn_train, fn_train, tp_train, fp_train, spe_train, sen_train=preprocessing_dataset.accuracy_computation(pred_train, training_set_mask, labels)
fpr_train, tpr_train, thresholds_train=roc_curve(labels_train, pred_train)
roc_auc_train = auc(fpr_train, tpr_train)
X_grad = list_of_outputs[10:]
training_time = time.time() - tic
list_training_loss.append(current_training_loss)
list_training_norm_grad.append(norm_grad)
if (np.mod(num_iter, num_iter_test)==0):
msg = "[TRN] iter = %03i, cost = %3.2e, |grad| = %.2e (%3.2es), accuracy = %3.2e, auc = %3.2e" \
% (num_iter, list_training_loss[-1], list_training_norm_grad[-1], training_time, accuracy_train, roc_auc_train)
print msg
auc_train_list.append(roc_auc_train)
pred_train_list.append(pred_train)
#Test Code
tic = time.time()
# run of the algorithm on the validation and test sets
pred_error, pred, labels_test, pred_val, labels_val= learning_obj.session.run([learning_obj.predictions_error, learning_obj.predictions, learning_obj.labels_test,
learning_obj.predictions_val, learning_obj.labels_val])
test_time = time.time() - tic
indexes_validation = np.concatenate((idx_training, idx_testing), axis=0)
pred_val = np.delete(pred_val, indexes_validation,0)
labels_val = np.delete(labels_val, indexes_validation,0)
fpr, tpr, thresholds=roc_curve(labels_val, pred_val)
roc_auc_val = auc(fpr, tpr)
auc_val_list.append(roc_auc_val)
pred_val_list.append(pred_val)
msg = "[VAL] iter = %03i, AUC = %3.2e" % (num_iter, roc_auc_val)
print msg
indexes_test = np.concatenate((idx_training, idx_validation), axis=0)
pred = np.delete(pred, indexes_test,0)
labels_test = np.delete(labels_test, indexes_test,0)
list_test_pred_error.append(pred_error)
accuracy, tn, fn, tp, fp, spe, sen= preprocessing_dataset.accuracy_computation(pred, testing_set_mask, labels)
fpr, tpr, thresholds=roc_curve(labels_test, pred)
roc_auc = auc(fpr, tpr)
auc_test_list.append(roc_auc)
pred_test_list.append(pred)
msg = "[TST] iter = %03i, cost = %3.2e, Accuracy = %3.2e (%3.2es), AUC = %3.2e" % (num_iter, list_test_pred_error[-1], accuracy, test_time, roc_auc)
print msg
num_iter += 1
return (auc_test_list, auc_train_list, auc_val_list, pred_train_list, pred_test_list, pred_val_list, labels_test, labels_train, labels_val)