def initialize(self,**hyper_params):
if(not "batch_size" in hyper_params.keys()):
batch_size = 16
if(not "layer_sizes" in hyper_params.keys()):
num_samples = [25, 10]
if(not "num_samples" in hyper_params.keys()):
layer_sizes = [256, 256]
if(not "bias" in hyper_params.keys()):
bias = True
if(not "dropout" in hyper_params.keys()):
dropout = 0.0
if(not "lr" in hyper_params.keys()):
lr = 1e-3
if(not "num_walks" in hyper_params.keys()):
num_walks = 1
if(not "length" in hyper_params.keys()):
length = 5
self.graph = sg.StellarGraph(nodes=self.nodes_df,edges=self.edges_df)
self.nodes = list(self.graph.nodes())
del self.nodes_df
del self.edges_df
unsupervised_samples = UnsupervisedSampler(
self.graph, nodes=self.nodes, length=length, number_of_walks=num_walks
)
# Train iterators
train_gen = GraphSAGELinkGenerator(self.graph, batch_size, num_samples)
self.train_flow = train_gen.flow(unsupervised_samples)
# Model defining - Keras functional API + Stellargraph layers
graphsage = GraphSAGE(
layer_sizes=layer_sizes, generator=train_gen, bias=bias, dropout=dropout, normalize="l2"
)
x_inp, x_out = graphsage.in_out_tensors()
prediction = link_classification(
output_dim=1, output_act="sigmoid", edge_embedding_method="ip"
)(x_out)
self.model = keras.Model(inputs=x_inp, outputs=prediction)
self.model.compile(
optimizer=keras.optimizers.Adam(lr=lr),
loss=keras.losses.binary_crossentropy,
metrics=[keras.metrics.binary_accuracy],
)
x_inp_src = x_inp[0::2]
x_out_src = x_out[0]
self.embedding_model = keras.Model(inputs=x_inp_src, outputs=x_out_src)
self.node_gen = GraphSAGENodeGenerator(self.graph, batch_size, num_samples).flow(self.nodes)
return self.model.get_weights()
def initialize(self,**hyper_params):
if(not "batch_size" in hyper_params.keys()):
batch_size = 20
if(not "layer_sizes" in hyper_params.keys()):
num_samples = [20, 10]
if(not "num_samples" in hyper_params.keys()):
layer_sizes = [10, 10 ]
if(not "bias" in hyper_params.keys()):
bias = True
if(not "dropout" in hyper_params.keys()):
dropout = 0.1
if(not "lr" in hyper_params.keys()):
lr = 1e-2
graph = sg.StellarGraph(nodes=self.nodes,edges=self.edges)
# Test split
edge_splitter_test = EdgeSplitter(graph)
self.graph_test, edge_ids_test, edge_labels_test = edge_splitter_test.train_test_split(
p=0.1, method="global", keep_connected=True, seed = 42
)
# Train split
edge_splitter_train = EdgeSplitter(self.graph_test)
self.graph_train, edge_ids_train, edge_labels_train = edge_splitter_train.train_test_split(
p=0.1, method="global", keep_connected=True, seed = 42
)
# Train iterators
train_gen = GraphSAGELinkGenerator(self.graph_train, batch_size, num_samples, seed = 42)
self.train_flow = train_gen.flow(edge_ids_train, edge_labels_train, shuffle=True)
# Test iterators
test_gen = GraphSAGELinkGenerator(self.graph_train, batch_size, num_samples, seed = 42)
self.test_flow = test_gen.flow(edge_ids_test, edge_labels_test, shuffle=True)
# Model defining - Keras functional API + Stellargraph layers
graphsage = GraphSAGE(
layer_sizes=layer_sizes, generator=train_gen, bias=bias, dropout=dropout
)
x_inp, x_out = graphsage.in_out_tensors()
prediction = link_classification(
output_dim=1, output_act="sigmoid", edge_embedding_method="ip"
)(x_out)
self.model = keras.Model(inputs=x_inp, outputs=prediction)
self.model.compile(
optimizer=keras.optimizers.Adam(lr=lr),
loss=keras.losses.binary_crossentropy,
metrics=[keras.metrics.BinaryAccuracy(),keras.metrics.Recall(),keras.metrics.AUC(),keras.metrics.Precision()],
)
# return number of training and testing examples
return edge_ids_train.shape[0],edge_ids_test.shape[0]
def initialize(self, **hyper_params):
if (not "batch_size" in hyper_params.keys()):
batch_size = 20
if (not "layer_sizes" in hyper_params.keys()):
num_samples = [20, 10]
if (not "num_samples" in hyper_params.keys()):
layer_sizes = [20, 20]
if (not "bias" in hyper_params.keys()):
bias = True
if (not "dropout" in hyper_params.keys()):
dropout = 0.3
if (not "lr" in hyper_params.keys()):
lr = 1e-3
if (not "train_split" in hyper_params.keys()):
train_split = 0.2
self.graph = sg.StellarGraph(nodes=self.nodes, edges=self.edges)
# Train split
edge_splitter_train = EdgeSplitter(self.graph)
graph_train, edge_ids_train, edge_labels_train = edge_splitter_train.train_test_split(
p=train_split, method="global", keep_connected=True)
# Train iterators
train_gen = GraphSAGELinkGenerator(graph_train, batch_size,
num_samples)
self.train_flow = train_gen.flow(edge_ids_train,
edge_labels_train,
shuffle=True)
# Model defining - Keras functional API + Stellargraph layers
graphsage = GraphSAGE(layer_sizes=layer_sizes,
generator=train_gen,
bias=bias,
dropout=dropout)
x_inp, x_out = graphsage.in_out_tensors()
prediction = link_classification(output_dim=1,
output_act="relu",
edge_embedding_method="ip")(x_out)
self.model = keras.Model(inputs=x_inp, outputs=prediction)
self.model.compile(
optimizer=keras.optimizers.Adam(lr=lr),
loss=keras.losses.binary_crossentropy,
metrics=["acc"],
)
return self.model.get_weights()
def create_graphSAGE_model(graph, link_prediction=False):
if link_prediction:
# We are going to train on the original graph
generator = GraphSAGELinkGenerator(graph, batch_size=2, num_samples=[2, 2])
edge_ids_train = np.array([[1, 2], [2, 3], [1, 3]])
train_gen = generator.flow(edge_ids_train, np.array([1, 1, 0]))
else:
generator = GraphSAGENodeGenerator(graph, batch_size=2, num_samples=[2, 2])
train_gen = generator.flow([1, 2], np.array([[1, 0], [0, 1]]))
# if link_prediction:
# edge_ids_train = np.array([[1, 2], [2, 3], [1, 3]])
# train_gen = generator.flow(edge_ids_train, np.array([1, 1, 0]))
# else:
# train_gen = generator.flow([1, 2], np.array([[1, 0], [0, 1]]))
base_model = GraphSAGE(
layer_sizes=[8, 8], generator=generator, bias=True, dropout=0.5
)
if link_prediction:
# Expose input and output sockets of graphsage, for source and destination nodes:
x_inp, x_out = base_model.in_out_tensors()
prediction = link_classification(
output_dim=1, output_act="relu", edge_embedding_method="ip"
)(x_out)
keras_model = Model(inputs=x_inp, outputs=prediction)
else:
x_inp, x_out = base_model.in_out_tensors()
prediction = layers.Dense(units=2, activation="softmax")(x_out)
keras_model = Model(inputs=x_inp, outputs=prediction)
return base_model, keras_model, generator, train_gen
def run_model(self):
graph_sampled, label_series_sampled = self.prepare_data_for_stellargraph(
)
train_targets, valid_targets, test_targets, train_labels, valid_labels, test_labels = self.get_train_valid_test(
label_series_sampled)
batch_size = self.hyperparams["batch_size"]
num_samples = self.hyperparams["num_samples"]
generator = GraphSAGENodeGenerator(graph_sampled, batch_size,
num_samples)
train_gen = generator.flow(train_labels.index,
train_targets,
shuffle=True)
graphsage_model = GraphSAGE(
layer_sizes=self.hyperparams["layer_sizes"],
generator=generator,
bias=self.hyperparams["bias"],
dropout=self.hyperparams["dropout"],
)
x_inp, x_out = graphsage_model.in_out_tensors()
prediction = layers.Dense(units=train_targets.shape[1],
activation="softmax")(x_out)
model = Model(inputs=x_inp, outputs=prediction)
model.compile(
optimizer=optimizers.Adam(lr=self.hyperparams["lr"]),
loss=losses.categorical_crossentropy,
metrics=["acc"],
)
valid_gen = generator.flow(valid_labels.index, valid_targets)
history = model.fit(
train_gen,
epochs=self.hyperparams["n_epochs"],
validation_data=valid_gen,
verbose=self.hyperparams["verbose"],
shuffle=True,
use_multiprocessing=True,
)
sg.utils.plot_history(history)
test_gen = generator.flow(test_labels.index, test_targets)
test_metrics = model.evaluate(test_gen)
print("\nTest Set Metrics:")
for name, valid in zip(model.metrics_names, test_metrics):
print("\t{}: {:0.4f}".format(name, valid))
def get_dropout(input_tensor, p=0.1, mc=False):
if mc:
return Dropout(p)(input_tensor, training=True)
else:
return Dropout(p)(input_tensor)
graphsage_model = GraphSAGE(layer_sizes=[64, 32, 16],
generator=generator,
activations=["relu", "relu", "linear"],
bias=True,
aggregator=MaxPoolingAggregator,
dropout=0.1)
x_inp, x_out = graphsage_model.in_out_tensors()
x_out = layers.Dense(units=10, activation="relu")(x_out)
x_out = layers.Dense(units=10, activation="relu")(x_out)
x_out = get_dropout(x_out, p=0.1, mc='mc')
prediction = layers.Dense(units=train_targets.shape[1],
activation="softmax")(x_out)
model = Model(inputs=x_inp, outputs=prediction)
model.summary()
##
# model.compile( optimizer=optimizers.Adam(), loss = noderankloss(), metrics=["acc"])
# model.compile( optimizer=optimizers.Adam(), loss="mean_squared_error", metrics=["acc"])
model.compile(optimizer=optimizers.Adam(),
loss=tf.keras.losses.CategoricalCrossentropy(),
metrics=["acc"])
epochs = 20
num_samples = [20, 10]
layer_sizes = [20, 20]
# Train iterators
train_gen = GraphSAGELinkGenerator(G_train, batch_size, num_samples)
train_flow = train_gen.flow(edge_ids_train, edge_labels_train, shuffle=True)
# Model defining - Keras functional API + Stellargraph layers
graphsage = GraphSAGE(
layer_sizes=layer_sizes, generator=train_gen, bias=True, dropout=0.3
)
x_inp, x_out = graphsage.in_out_tensors()
prediction = link_classification(
output_dim=1, output_act="relu", edge_embedding_method="ip"
)(x_out)
model = keras.Model(inputs=x_inp, outputs=prediction)
model.compile(
optimizer=keras.optimizers.Adam(lr=1e-3),
loss=keras.losses.binary_crossentropy,
metrics=["acc"],
)
# Set weights
weights = np.load(path_weights,allow_pickle=True)
def train(G_list,
nodes_subjects_list,
run_num=1,
start_month_id=220,
end_month_id=264):
# 提前定义一些列表方便记录数据，大循环的列表存小循环的列表
graph_history_list_list = []
model_list_list = []
train_gen_list_list = []
time_list_list = []
model_weight_list_list = []
# 选择运行run_num次
run_num = run_num
# 选择进行训练的月份,end_month_id最多取
start_month_id = start_month_id
end_month_id = end_month_id
# 创建文件夹保存model
if not os.path.exists('model'):
os.makedirs('model')
# 创建文件夹保存history
if not os.path.exists('history'):
os.makedirs('history')
# 创建文件夹保存figure
if not os.path.exists('figure'):
os.makedirs('figure')
# 创建文件夹保存figure
if not os.path.exists('figure_distribution'):
os.makedirs('figure_distribution')
# 创建文件夹保存test结果
if not os.path.exists('test_result'):
os.makedirs('test_result')
# 大循环记录训练了几次，计算多次是为了减少variance
# 小循环记录训练的月份
for j in range(run_num):
num_samples = [40]
# 提前定义一些列表记录小循环的数据
graph_history_list = []
model_list = []
train_gen_list = []
time_list = []
model_weight_list = []
test_result = []
# i为0代表220
for i in range(start_month_id - 220, end_month_id - 220):
start = time.time()
# 前一个月训练，后一个月验证
train_idx = i
val_idx = i + 1
test_idx = i + 2
# 用train_idx的数据生成训练集的generator
generator = GraphSAGENodeGenerator(
G=G_list[train_idx],
batch_size=len(nodes_subjects_list[train_idx]),
num_samples=num_samples,
seed=100)
train_gen = generator.flow(list(
nodes_subjects_list[train_idx].index),
nodes_subjects_list[train_idx].values,
shuffle=False)
# 生成GraphSAGE模型
graphsage_model = GraphSAGE(layer_sizes=[1],
generator=generator,
bias=True,
aggregator=sg.layer.MeanAggregator,
normalize=None)
# 提取输出输出的tensor，用keras来构建模型
x_inp, x_out = graphsage_model.in_out_tensors()
# prediction = layers.Dense(units=1)(x_out)
# 用val_idx的数据生成验证集的generator
generator = GraphSAGENodeGenerator(
G=G_list[val_idx],
batch_size=len(nodes_subjects_list[val_idx]),
num_samples=num_samples,
seed=100)
val_gen = generator.flow(list(nodes_subjects_list[val_idx].index),
nodes_subjects_list[val_idx].values)
# 用test_idx的数据生成验证集的generator
generator = GraphSAGENodeGenerator(
G=G_list[test_idx],
batch_size=len(nodes_subjects_list[test_idx]),
num_samples=num_samples,
seed=100)
test_gen = generator.flow(
list(nodes_subjects_list[test_idx].index),
nodes_subjects_list[test_idx].values)
# 通过输入输出的tensor构建model
model = Model(inputs=x_inp, outputs=x_out)
monitor = EarlyStopping(monitor='val_loss',
min_delta=1e-3,
patience=10,
verbose=2,
mode='auto',
restore_best_weights=True)
model.compile(optimizer=optimizers.Adam(lr=0.05),
loss=losses.mean_squared_error,
metrics=[pearson_r])
history = model.fit(train_gen,
epochs=500,
validation_data=val_gen,
verbose=0,
shuffle=False,
callbacks=[monitor])
test_metrics = model.evaluate(test_gen)
test_result_dict = {}
print("\n" + str(train_idx + 220) + "'s Test Set: " +
str(test_idx + 220) + "'s Metrics:")
for name, val in zip(model.metrics_names, test_metrics):
print("\t{}: {:0.4f}".format(name, val))
test_result_dict[name] = val
json.dump(
test_result_dict,
open(
'test_result/' + str(train_idx + 220) + "_" +
str(test_idx + 220) + '.json', 'w'))
test_preds = model.predict(test_gen)
end = time.time()
# 保存一些结果
graph_history_list.append(history) # 保存训练过程
model_list.append(model) # 保存model
train_gen_list.append(train_gen) # 保存train_gen方便之后算中间层的结果
time_list.append(end - start) # 保存运行时间
model_weight_list.append(model.weights) # 保存model的参数
test_result.append(test_metrics[1])
# # 存模型model
# model.save('model/' + str(train_idx + 220) + "_" + str(val_idx + 220) + '.h5')
# # 存训练过程history
# json.dump(history.history,
# open('history/' + str(train_idx + 220) + "_" + str(val_idx + 220) + '.json', 'w'))
# # 存训练过程图片figure
# sg.utils.plot_history(history)
# plt.title(str(train_idx + 220) + '->' + str(val_idx + 220))
# plt.savefig('figure/' + str(train_idx + 220) + "_" + str(val_idx + 220) + '.png')
# plt.show()
# 存test的prediction的distribution
plt.figure(figsize=(5, 10))
plt.subplot(211)
plt.hist(test_preds, bins=500)
plt.title("Distribution of Prediction of " + str(test_idx + 220))
plt.subplot(212)
plt.hist(nodes_subjects_list[test_idx].values, bins=500)
plt.title("Distribution of Origin of " + str(test_idx + 220))
plt.xlabel("ic=" + str(test_metrics[1]))
plt.savefig('figure_distribution/distribution-' +
str(train_idx + 220) + "_" + str(test_idx + 220) +
'.png',
dpi=300)
plt.show()
print(str(i + 220) + "'s " + str(j + 1) + " run has finished")
print()
# 将小循环的数据保存
graph_history_list_list.append(graph_history_list)
model_list_list.append(model_list)
train_gen_list_list.append(train_gen_list)
time_list_list.append(time_list)
model_weight_list_list.append(model_weight_list)
return graph_history_list_list, model_list_list, train_gen_list_list, time_list_list, model_weight_list_list, test_result