def test_graph_save(self):
n_samples = 10
n_features = 11
n_tasks = 1
batch_size = 10
X = np.random.rand(batch_size, n_samples, n_features)
y = np.ones(shape=(n_samples, n_tasks))
ids = np.arange(n_samples)
dataset = dc.data.NumpyDataset(X, y, None, ids)
g = TensorGraph(model_dir='/tmp/tmpss5_ki5_')
inLayer = Input(shape=(None, n_samples, n_features))
g.add_feature(inLayer)
flatten = Flatten()
g.add_layer(flatten, parents=[inLayer])
dense = Dense(out_channels=1)
g.add_layer(dense, parents=[flatten])
g.add_output(dense)
label_out = Input(shape=(None, 1))
g.add_label(label_out)
loss = LossLayer()
g.add_layer(loss, parents=[dense, label_out])
g.set_loss(loss)
g.fit(dataset, nb_epoch=100)
g.save()
g1 = TensorGraph.load_from_dir('/tmp/tmpss5_ki5_')
print(g1)
print(g1.predict_on_batch(X))
def test_graph_save(self):
n_samples = 10
n_features = 11
n_tasks = 1
batch_size = 10
X = np.random.rand(batch_size, n_samples, n_features)
y = np.ones(shape=(n_samples, n_tasks))
ids = np.arange(n_samples)
dataset = dc.data.NumpyDataset(X, y, None, ids)
g = TensorGraph(model_dir='/tmp/tmpss5_ki5_')
inLayer = Input(shape=(None, n_samples, n_features))
g.add_feature(inLayer)
flatten = Flatten()
g.add_layer(flatten, parents=[inLayer])
dense = Dense(out_channels=1)
g.add_layer(dense, parents=[flatten])
g.add_output(dense)
label_out = Input(shape=(None, 1))
g.add_label(label_out)
loss = LossLayer()
g.add_layer(loss, parents=[dense, label_out])
g.set_loss(loss)
g.fit(dataset, nb_epoch=100)
g.save()
g1 = TensorGraph.load_from_dir('/tmp/tmpss5_ki5_')
print(g1)
print(g1.predict_on_batch(X))
class MLP:
def __init__(self, batch_size):
# save parameters
self.batch_size = batch_size
# define tensorgraph
self.tg = TensorGraph(use_queue=False)
self.feature = Feature(shape=(None, 1024))
# build graph
self.build_graph()
def build_graph(self):
d1 = Dense(out_channels=256, activation_fn=tf.nn.relu, in_layers=[self.feature])
d2 = Dense(out_channels=64, activation_fn=tf.nn.relu, in_layers=[d1])
d3 = Dense(out_channels=16, activation=None, in_layers=[d2])
d4 = Dense(out_channels=2, activation=None, in_layers=[d3])
softmax = SoftMax(in_layers=[d4])
self.tg.add_output(softmax)
self.label = Label(shape=(None, 2))
cost = SoftMaxCrossEntropy(in_layers=[self.label, d4])
loss = ReduceMean(in_layers=[cost])
self.tg.set_loss(loss)
def fit(self, dataset, epochs):
self.tg.fit_generator(self.data_generator(dataset, self.batch_size, epochs=epochs))
def predict(self, dataset):
pred = self.tg.predict_on_generator(self.data_generator(dataset, self.batch_size))
return np.expand_dims(pred, axis=0)
def data_generator(self, dataset, batch_size, epochs=1):
for e in range(epochs):
for X, y, w, idx in dataset.iterbatches(batch_size, pad_batches=True, deterministic=True):
feed_dict = {self.label: to_one_hot(y[:, 0]), self.feature: X} # data for feed
yield feed_dict
def graph_conv_net(batch_size, prior, num_task):
"""
Build a tensorgraph for multilabel classification task
Return: features and labels layers
"""
tg = TensorGraph(use_queue=False)
if prior == True:
add_on = num_task
else:
add_on = 0
atom_features = Feature(shape=(None, 75 + 2 * add_on))
circular_features = Feature(shape=(batch_size, 256), dtype=tf.float32)
degree_slice = Feature(shape=(None, 2), dtype=tf.int32)
membership = Feature(shape=(None, ), dtype=tf.int32)
deg_adjs = []
for i in range(0, 10 + 1):
deg_adj = Feature(shape=(None, i + 1), dtype=tf.int32)
deg_adjs.append(deg_adj)
gc1 = GraphConv(64 + add_on,
activation_fn=tf.nn.elu,
in_layers=[atom_features, degree_slice, membership] +
deg_adjs)
batch_norm1 = BatchNorm(in_layers=[gc1])
gp1 = GraphPool(in_layers=[batch_norm1, degree_slice, membership] +
deg_adjs)
gc2 = GraphConv(64 + add_on,
activation_fn=tf.nn.elu,
in_layers=[gc1, degree_slice, membership] + deg_adjs)
batch_norm2 = BatchNorm(in_layers=[gc2])
gp2 = GraphPool(in_layers=[batch_norm2, degree_slice, membership] +
deg_adjs)
add = Concat(in_layers=[gp1, gp2])
add = Dropout(0.5, in_layers=[add])
dense = Dense(out_channels=128, activation_fn=tf.nn.elu, in_layers=[add])
batch_norm3 = BatchNorm(in_layers=[dense])
readout = GraphGather(batch_size=batch_size,
activation_fn=tf.nn.tanh,
in_layers=[batch_norm3, degree_slice, membership] +
deg_adjs)
batch_norm4 = BatchNorm(in_layers=[readout])
dense1 = Dense(out_channels=128,
activation_fn=tf.nn.elu,
in_layers=[circular_features])
dense1 = BatchNorm(in_layers=[dense1])
dense1 = Dropout(0.5, in_layers=[dense1])
dense1 = Dense(out_channels=128,
activation_fn=tf.nn.elu,
in_layers=[circular_features])
dense1 = BatchNorm(in_layers=[dense1])
dense1 = Dropout(0.5, in_layers=[dense1])
merge_feat = Concat(in_layers=[dense1, batch_norm4])
merge = Dense(out_channels=256,
activation_fn=tf.nn.elu,
in_layers=[merge_feat])
costs = []
labels = []
for task in range(num_task):
classification = Dense(out_channels=2,
activation_fn=None,
in_layers=[merge])
softmax = SoftMax(in_layers=[classification])
tg.add_output(softmax)
label = Label(shape=(None, 2))
labels.append(label)
cost = SoftMaxCrossEntropy(in_layers=[label, classification])
costs.append(cost)
all_cost = Stack(in_layers=costs, axis=1)
weights = Weights(shape=(None, num_task))
loss = WeightedError(in_layers=[all_cost, weights])
tg.set_loss(loss)
#if prior == True:
# return tg, atom_features,circular_features, degree_slice, membership, deg_adjs, labels, weights#, prior_layer
return tg, atom_features, circular_features, degree_slice, membership, deg_adjs, labels, weights
classification = Dense(out_channels=2,
activation_fn=None,
in_layers=[readout])
softmax = SoftMax(in_layers=[classification])
tg.add_output(softmax)
label = Label(shape=(None, 2))
labels.append(label)
cost = SoftMaxCrossEntropy(in_layers=[label, classification])
costs.append(cost)
all_cost = Stack(in_layers=costs, axis=1)
weights = Weights(shape=(None, len(current_tasks)))
loss = WeightedError(in_layers=[all_cost, weights])
tg.set_loss(loss)
# Data splits
# Tox21 is treated differently: we manually (randomly) split into test, train, and valid directly from train_dataset.X
# (rather than letting deepchem provide the data directly)
# Reason: In the early stages of developing the code, the valid_dataset and test_dataset were empty for tox and
# we observed a comment in the deepchem source code leading us to believe this was intended.
# Thus, when we access valid_dataset.X and test_dataset.X, we don't do it for tox21. We only later
# found that we could access tox21 validation and test. But we do this for all models, so the treatment is fair
#
#
# This treatment is done for all models, so the comparison is fair.
#
if TASK != 'tox_21':
new_train_data = generate_new_X(train_dataset.X, K, technique)
new_train_dataset = dc.data.datasets.DiskDataset.from_numpy(
new_train_data,
class GCN:
def __init__(self, batch_size=50):
# save parameters
self.batch_size = batch_size
# define tensorgraph
self.tg = TensorGraph(use_queue=False)
# define features
self.atom_features = Feature(shape=(None, 75)) # feature of atom. ex) atom / degree / is aromatic and so on
self.indexing = Feature(shape=(None, 2), dtype=tf.int32) # index of atoms in molecules sorted by degree
self.membership = Feature(shape=(None,), dtype=tf.int32) # membership of atoms in molecule
self.deg_adj_list = [Feature(shape=(None, i), dtype=tf.int32) for i in range(1, 12)] # adj list with degree
# build graph
self.build_graph()
def build_graph(self):
# Layer 1
gc1_input = [self.atom_features, self.indexing, self.membership] + self.deg_adj_list
gc1 = GraphConv(64, activation_fn=tf.nn.relu, in_layers=gc1_input)
bn1 = BatchNorm(in_layers=[gc1])
gp1_input = [bn1, self.indexing, self.membership] + self.deg_adj_list
gp1 = GraphPool(in_layers=gp1_input)
# Layer 2
gc2_input = [gp1, self.indexing, self.membership] + self.deg_adj_list
gc2 = GraphConv(64, activation_fn=tf.nn.relu, in_layers=gc2_input)
bn2 = BatchNorm(in_layers=[gc2])
gp2_input = [bn2, self.indexing, self.membership] + self.deg_adj_list
gp2 = GraphPool(in_layers=gp2_input)
# Dense layer 1
d1 = Dense(out_channels=128, activation_fn=tf.nn.relu, in_layers=[gp2])
bn3 = BatchNorm(in_layers=[d1])
# Graph gather layer
gg1_input = [bn3, self.indexing, self.membership] + self.deg_adj_list
gg1 = GraphGather(batch_size=self.batch_size, activation=tf.nn.tanh, in_layers=gg1_input)
# Output dense layer
d2 = Dense(out_channels=2, activation_fn=None, in_layers=[gg1])
softmax = SoftMax(in_layers=[d2])
self.tg.add_output(softmax)
# Set loss function
self.label = Label(shape=(None, 2))
cost = SoftMaxCrossEntropy(in_layers=[self.label, d2])
self.weight = Weights(shape=(None, 1))
loss = WeightedError(in_layers=[cost, self.weight])
self.tg.set_loss(loss)
def fit(self, dataset, epochs:int):
self.tg.fit_generator(self.data_generator(dataset, self.batch_size, epochs=epochs))
def predict(self, dataset):
pred = self.tg.predict_on_generator(self.data_generator(dataset, self.batch_size))
return np.expand_dims(pred, axis=0)
def data_generator(self, dataset, batch_size:int, epochs=1):
for e in range(epochs):
for X, y, w, idx in dataset.iterbatches(batch_size, pad_batches=True, deterministic=True):
feed_dict = {self.label: to_one_hot(y[:, 0]), self.weight: w} # data for feed
ConvMolList = ConvMol.agglomerate_mols(X)
feed_dict[self.atom_features] = ConvMolList.get_atom_features()
feed_dict[self.indexing] = ConvMolList.deg_slice
feed_dict[self.membership] = ConvMolList.membership
deg_adj_list = ConvMolList.get_deg_adjacency_lists()
for i in range(1, len(deg_adj_list)):
feed_dict[self.deg_adj_list[i - 1]] = deg_adj_list[i]
yield feed_dict