def train_cv(sess, graph, config):
all_data, info = load_data(
config, filename=config["dataset"],
prohibit_shuffle=True) # shuffle is done by KFold
model = CoreModel(sess, config, info)
load_model_py(model, config["model.py"])
# Training
if config["stratified_kfold"]:
print("[INFO] use stratified K-fold")
kf = StratifiedKFold(n_splits=config["k-fold_num"],
shuffle=config["shuffle_data"],
random_state=123)
else:
kf = KFold(n_splits=config["k-fold_num"],
shuffle=config["shuffle_data"],
random_state=123)
kf_count = 1
fold_data_list = []
output_data_list = []
if all_data["labels"] is not None:
split_base = all_data["labels"]
else:
split_base = all_data["label_list"][0]
if config["stratified_kfold"]:
split_base = np.argmax(split_base, axis=1)
score_metrics = []
if config["task"] == "regression":
metric_name = "mse"
elif config["task"] == "regression_gmfe":
metric_name = "gmfe"
else:
metric_name = "accuracy"
split_data_generator = kf.split(
split_base,
split_base) if config["stratified_kfold"] else kf.split(split_base)
for train_valid_list, test_list in split_data_generator:
print(f"starting fold: {kf_count}")
train_valid_data, test_data = split_data(
all_data,
indices_for_train_data=train_valid_list,
indices_for_valid_data=test_list)
train_data, valid_data = split_data(
train_valid_data, valid_data_rate=config["validation_data_rate"])
# Training
print(train_valid_list)
print(test_list)
start_t = time.time()
model.fit(train_data, valid_data, k_fold_num=kf_count)
train_time = time.time() - start_t
print(f"training time: {train_time}[sec]")
# Test
print("== valid data ==")
start_t = time.time()
valid_cost, valid_metrics, prediction_data = model.pred_and_eval(
valid_data)
infer_time = time.time() - start_t
print(f"final cost = {valid_cost}\n"
f"{metric_name} = {valid_metrics[metric_name]}\n"
f"infer time: {infer_time}[sec]\n")
print("== test data ==")
start_t = time.time()
test_cost, test_metrics, prediction_data = model.pred_and_eval(
test_data)
infer_time = time.time() - start_t
print(f"final cost = {test_cost}\n"
f"{metric_name} = {test_metrics[metric_name]}\n")
score_metrics.append(test_metrics[metric_name])
print(f"infer time: {infer_time}[sec]")
if config["export_model"]:
try:
name, ext = os.path.splitext(config["export_model"])
filename = name + "." + str(kf_count) + ext
print(f"[SAVE] {filename}")
graph_def = graph_util.convert_variables_to_constants(
sess, graph.as_graph_def(), ['output'])
tf.train.write_graph(graph_def, '.', filename, as_text=False)
except:
print('[ERROR] output has been not found')
if "save_edge_result_cv" in config:
output_data = model.output(test_data)
output_data_list.append(output_data)
# save fold data
fold_data = dotdict({})
fold_data.prediction_data = prediction_data
if all_data["labels"] is not None:
fold_data.test_labels = test_data.labels
else:
fold_data.test_labels = test_data.label_list
fold_data.test_data_idx = test_list
if config["task"] == "regression":
fold_data.training_mse = [
el["training_mse"] for el in model.training_metrics_list
]
fold_data.validation_mse = [
el["validation_mse"] for el in model.validation_metrics_list
]
elif config["task"] == "regression_gmfe":
fold_data.training_mse = [
el["training_gmfe"] for el in model.training_metrics_list
]
fold_data.validation_mse = [
el["validation_gmfe"] for el in model.validation_metrics_list
]
else:
fold_data.training_acc = [
el["training_accuracy"] for el in model.training_metrics_list
]
fold_data.validation_acc = [
el["validation_accuracy"]
for el in model.validation_metrics_list
]
fold_data.test_acc = test_metrics[metric_name]
fold_data.training_cost = model.training_cost_list
fold_data.validation_cost = model.validation_cost_list
fold_data.test_cost = test_cost
fold_data.train_time = train_time
fold_data.infer_time = infer_time
fold_data_list.append(fold_data)
kf_count += 1
print(f"cv {metric_name}(mean) = {np.mean(score_metrics)}\n"
f"cv {metric_name}(std.) = {np.std(score_metrics)}\n")
if "save_info_cv" in config and config["save_info_cv"] is not None:
save_path = config["save_info_cv"]
os.makedirs(os.path.dirname(save_path), exist_ok=True)
print(f"[SAVE] {save_path}")
_, ext = os.path.splitext(save_path)
if ext == ".json":
with open(save_path, "w") as fp:
json.dump(fold_data_list, fp, indent=4, cls=NumPyArangeEncoder)
else:
joblib.dump(fold_data_list, save_path, compress=True)
#
if "save_edge_result_cv" in config and config[
"save_edge_result_cv"] is not None:
result_cv = []
for j, fold_data in enumerate(fold_data_list):
pred_score = np.array(fold_data.prediction_data)
true_label = np.array(fold_data.test_labels)
test_idx = fold_data.test_data_idx
score_list = []
for pair in true_label[0]:
i1, _, j1, i2, _, j2 = pair
s1 = pred_score[0, i1, j1]
s2 = pred_score[0, i2, j2]
score_list.append([s1, s2])
fold = {}
fold["output"] = output_data_list[j][0]
fold["score"] = np.array(score_list)
fold["test_data_idx"] = test_idx
result_cv.append(fold)
save_path = config["save_edge_result_cv"]
os.makedirs(os.path.dirname(save_path), exist_ok=True)
print(f"[SAVE] {save_path}")
_, ext = os.path.splitext(save_path)
if ext == ".json":
with open(save_path, "w") as fp:
json.dump(result_cv, fp, indent=4, cls=NumPyArangeEncoder)
else:
joblib.dump(result_cv, save_path, compress=True)
#
if "save_result_cv" in config and config["save_result_cv"] is not None:
result_cv = []
for j, fold_data in enumerate(fold_data_list):
v = compute_metrics(config, info, fold_data.prediction_data,
fold_data.test_labels)
result_cv.append(v)
save_path = config["save_result_cv"]
print(f"[SAVE] {save_path}")
with open(save_path, "w") as fp:
json.dump(result_cv, fp, indent=4, cls=NumPyArangeEncoder)
#
for i, fold_data in enumerate(fold_data_list):
prefix = "fold" + str(i) + "_"
result_path = config["plot_path"]
os.makedirs(result_path, exist_ok=True)
if config["make_plot"]:
if config["task"] == "regression":
make_cost_acc_plot(fold_data.training_cost,
fold_data.validation_cost,
fold_data.training_mse,
fold_data.validation_mse,
result_path,
prefix=prefix)
pred_score = np.array(fold_data.prediction_data)
plot_r2(config,
fold_data.test_labels,
pred_score,
prefix=prefix)
elif config["task"] == "regression_gmfe":
make_cost_acc_plot(fold_data.training_cost,
fold_data.validation_cost,
fold_data.training_mse,
fold_data.validation_mse,
result_path,
prefix=prefix)
pred_score = np.array(fold_data.prediction_data)
plot_r2(config,
fold_data.test_labels,
pred_score,
prefix=prefix)
elif config["task"] == "link_prediction":
make_cost_acc_plot(fold_data.training_cost,
fold_data.validation_cost,
fold_data.training_acc,
fold_data.validation_acc,
result_path,
prefix=prefix)
else:
make_cost_acc_plot(fold_data.training_cost,
fold_data.validation_cost,
fold_data.training_acc,
fold_data.validation_acc,
result_path,
prefix=prefix)
pred_score = np.array(fold_data.prediction_data)
plot_auc(config,
fold_data.test_labels,
pred_score,
prefix=prefix)
def infer(sess, graph, config):
dataset_filename = config["dataset"]
if "dataset_test" in config:
dataset_filename = config["dataset_test"]
if "test_label_list" in config:
config["label_list"] = config["test_label_list"]
all_data, info = load_data(config,
filename=dataset_filename,
prohibit_shuffle=True)
model = CoreModel(sess, config, info)
load_model_py(model, config["model.py"], is_train=False)
metric_name = ("mse" if config["task"] == "regression" else "gmfe"
if config["task"] == "regression_gmfe" else "accuracy")
# Initialize session
restore_ckpt(sess, config["load_model"])
# Validation
start_t = time.time()
test_cost, test_metrics, prediction_data = model.pred_and_eval(all_data)
infer_time = time.time() - start_t
print(f"final cost = {test_cost}\n"
f"{metric_name} = {test_metrics[metric_name]}\n"
f"infer time: {infer_time}[sec]\n")
if config["save_info_test"] is not None:
result = {}
result["test_cost"] = test_cost
result["test_accuracy"] = test_metrics
result["infer_time"] = infer_time
if config["task"] != "link_prediction":
result["test_metrics"] = compute_metrics(config, info,
prediction_data,
all_data.labels)
save_path = config["save_info_test"]
os.makedirs(os.path.dirname(save_path), exist_ok=True)
print(f"[SAVE] {save_path}")
with open(save_path, "w") as fp:
json.dump(result, fp, indent=4, cls=NumPyArangeEncoder)
if config["save_result_test"] is not None:
filename = config["save_result_test"]
save_prediction(filename, prediction_data)
if config["make_plot"]:
if config["task"] == "regression":
pred_score = np.array(prediction_data)
plot_r2(config, all_data.labels, pred_score)
elif config["task"] == "regression_gmfe":
pred_score = np.array(prediction_data)
plot_r2(config, all_data.labels, pred_score)
elif config["task"] == "link_prediction":
pass
else:
plot_auc(config, all_data.labels, np.array(prediction_data))
if "save_edge_result_test" in config and config[
"save_edge_result_test"] is not None:
#output_left_pred = model.left_pred(all_data)
#print(output_left_pred.shape)
##
output_data = model.output(all_data)
pred_score = np.array(prediction_data)
true_label = np.array(all_data.label_list)
score_list = []
print(true_label.shape)
for pair in true_label[0]:
if len(prediction_data[0].shape) == 2:
i1, _, j1, i2, _, j2 = pair
s1 = pred_score[0, i1, j1]
s2 = pred_score[0, i2, j2]
elif len(prediction_data[0].shape) == 3:
i1, r1, j1, i2, r2, j2 = pair
s1 = pred_score[0, r1, i1, j1]
s2 = pred_score[0, r2, i2, j2]
score_list.append([s1, s2])
fold = {}
fold["output"] = output_data[0]
fold["score"] = np.array(score_list)
save_path = config["save_edge_result_test"]
os.makedirs(os.path.dirname(save_path), exist_ok=True)
print(f"[SAVE] {save_path}")
_, ext = os.path.splitext(save_path)
if ext == ".json":
with open(save_path, "w") as fp:
json.dump(fold, fp, indent=4, cls=NumPyArangeEncoder)
else:
joblib.dump(fold, save_path, compress=True)
if config["prediction_data"] is not None:
obj = {}
obj["prediction_data"] = prediction_data
obj["labels"] = all_data.labels
os.makedirs(os.path.dirname(config["prediction_data"]), exist_ok=True)
joblib.dump(obj, config["prediction_data"], compress=True)
def train(sess, graph, config):
if config["validation_dataset"] is None:
_, train_data, valid_data, info = load_and_split_data(
config,
filename=config["dataset"],
valid_data_rate=config["validation_data_rate"])
else:
print("[INFO] training")
train_data, info = load_data(config, filename=config["dataset"])
print("[INFO] validation")
valid_data, valid_info = load_data(
config, filename=config["validation_dataset"])
info["graph_node_num"] = max(info["graph_node_num"],
valid_info["graph_node_num"])
info["graph_num"] = info["graph_num"] + valid_info["graph_num"]
model = CoreModel(sess, config, info)
load_model_py(model, config["model.py"])
metric_name = ("mse" if config["task"] == "regression" else "gmfe"
if config["task"] == "regression_gmfe" else "accuracy")
if config["profile"]:
vars_to_train = tf.trainable_variables()
print(vars_to_train)
# Training
start_t = time.time()
model.fit(train_data, valid_data)
train_time = time.time() - start_t
print(f"training time: {train_time}[sec]")
if valid_data.num > 0:
# Validation
start_t = time.time()
valid_cost, valid_metrics, prediction_data = model.pred_and_eval(
valid_data)
infer_time = time.time() - start_t
print(f"final cost = {valid_cost}\n"
f"{metric_name} = {valid_metrics[metric_name]}\n"
f"validation time: {infer_time}[sec]\n")
# Saving
if config["save_info_valid"] is not None:
result = {}
result["validation_cost"] = valid_cost
result["validation_accuracy"] = valid_metrics
result["train_time"] = train_time
result["infer_time"] = infer_time
if config["task"] != "link_prediction":
result["valid_metrics"] = compute_metrics(
config, info, prediction_data, valid_data.labels)
##
save_path = config["save_info_valid"]
os.makedirs(os.path.dirname(save_path), exist_ok=True)
print(f"[SAVE] {save_path}")
with open(save_path, "w") as fp:
json.dump(result, fp, indent=4, cls=NumPyArangeEncoder)
if config["export_model"]:
try:
print(f"[SAVE] {config['export_model']}")
graph_def = graph_util.convert_variables_to_constants(
sess, graph.as_graph_def(), ['output'])
tf.train.write_graph(graph_def,
'.',
config["export_model"],
as_text=False)
except:
print('[ERROR] output has been not found')
if config["save_result_valid"] is not None:
filename = config["save_result_valid"]
save_prediction(filename, prediction_data)
if config["make_plot"]:
if config["task"] == "regression" or config[
"task"] == "regression_gmfe":
# plot_cost(config, valid_data, model)
plot_r2(config, valid_data.labels, np.array(prediction_data))
elif config["task"] == "link_prediction":
plot_cost(config, valid_data, model)
else:
plot_cost(config, valid_data, model)
plot_auc(config, valid_data.labels, np.array(prediction_data))