def build_graph(self, graph_name):
AM, LM = None, None
if graph_name.lower() == 'distance':
lat_lng_list = np.array([[float(e1) for e1 in e[2:4]]
for e in self.dataset.node_station_info])
AM = self.distance_adjacent(lat_lng_list[self.traffic_data_index],
threshold=float(
self.threshold_distance))
LM = self.adjacent_to_laplacian(AM)
if graph_name.lower() == 'interaction':
monthly_interaction = self.dataset.node_monthly_interaction[:,
self.
traffic_data_index, :][:, :,
self
.
traffic_data_index]
monthly_interaction, _ = SplitData.split_data(
monthly_interaction, self.train_test_ratio)
annually_interaction = np.sum(monthly_interaction[-12:], axis=0)
annually_interaction = annually_interaction + annually_interaction.transpose(
)
AM = self.interaction_adjacent(annually_interaction,
threshold=float(
self.threshold_interaction))
LM = self.adjacent_to_laplacian(AM)
if graph_name.lower() == 'correlation':
AM = self.correlation_adjacent(
self.train_data[-30 * int(self.daily_slots):],
threshold=float(self.threshold_correlation))
LM = self.adjacent_to_laplacian(AM)
if graph_name.lower() == 'neighbor':
LM = self.adjacent_to_laplacian(
self.dataset.data.get('contribute_data').get(
'graph_neighbors'))
if graph_name.lower() == 'line':
LM = self.adjacent_to_laplacian(
self.dataset.data.get('contribute_data').get('graph_lines'))
LM = LM[self.traffic_data_index]
LM = LM[:, self.traffic_data_index]
if graph_name.lower() == 'transfer':
LM = self.adjacent_to_laplacian(
self.dataset.data.get('contribute_data').get('graph_transfer'))
return AM, LM
args = vars(parser.parse_args())
data_loader = NodeTrafficLoader(dataset=args["dataset"],
city=args['city'],
closeness_len=int(params['CT']),
period_len=int(params['PT']),
trend_len=int(params['TT']),
data_range=args['DataRange'],
train_data_length=args['TrainDays'],
test_ratio=args['test_ratio'],
with_lm=False,
normalize=False,
MergeIndex=args['MergeIndex'],
MergeWay=args['MergeWay'])
train_closeness, val_closeness = SplitData.split_data(
data_loader.train_closeness, [0.9, 0.1])
train_period, val_period = SplitData.split_data(data_loader.train_period,
[0.9, 0.1])
train_trend, val_trend = SplitData.split_data(data_loader.train_trend,
[0.9, 0.1])
train_y, val_y = SplitData.split_data(data_loader.train_y, [0.9, 0.1])
hm_obj = HM(c=data_loader.closeness_len,
p=data_loader.period_len,
t=data_loader.trend_len)
test_prediction = hm_obj.predict(closeness_feature=data_loader.test_closeness,
period_feature=data_loader.test_period,
trend_feature=data_loader.test_trend)
data_loader = NodeTrafficLoader(
dataset=args['dataset'],
city=args['city'],
data_range=args['DataRange'],
train_data_length=args['TrainDays'],
test_ratio=0.1,
closeness_len=int(args['CT']),
period_len=0,
trend_len=0,
with_lm=False,
with_tpe=False,
normalize=False,
MergeIndex=args['MergeIndex'],
MergeWay="max" if args["dataset"] == "ChargeStation" else "sum")
train_closeness, val_closeness = SplitData.split_data(
data_loader.train_closeness, [0.9, 0.1])
train_y, val_y = SplitData.split_data(data_loader.train_y, [0.9, 0.1])
val_prediction_collector = []
test_prediction_collector = []
print('*************************************************************')
for i in tqdm(range(data_loader.station_number)):
try:
model_obj = ARIMA(
time_sequence=train_closeness[:, i, -1, 0],
order=[args['ar'], args['d'], args['ma']],
seasonal_order=[args['sar'], args['sd'], args['sma'], args['sp']])
external_lstm_len=args['external_lstm_len'],
threshold_distance=args['threshold_distance'],
threshold_correlation=args['threshold_correlation'],
threshold_interaction=args['threshold_interaction'],
normalize=args['normalize'],
graph=args['graph'],
with_lm=True,
with_tpe=True if args['st_method'] == 'gal_gcn' else False,
workday_parser=is_work_day_america
if args['dataset'] == 'Bike' else is_work_day_china,
external_use=args['external_use'],
MergeIndex=args['MergeIndex'],
MergeWay="max" if args["dataset"] == "ChargeStation" else "sum")
# split data
train_closeness, val_closeness = SplitData.split_data(
data_loader.train_closeness, [0.9, 0.1])
train_period, val_period = SplitData.split_data(data_loader.train_period,
[0.9, 0.1])
train_trend, val_trend = SplitData.split_data(data_loader.train_trend,
[0.9, 0.1])
if data_loader.external_dim > 0:
train_ef_closeness, val_ef_closeness = SplitData.split_data(
data_loader.train_ef_closeness, [0.9, 0.1])
train_ef_period, val_ef_period = SplitData.split_data(
data_loader.train_ef_period, [0.9, 0.1])
train_ef_trend, val_ef_trend = SplitData.split_data(
data_loader.train_ef_trend, [0.9, 0.1])
train_ef, val_ef = SplitData.split_data(data_loader.train_ef, [0.9, 0.1])
train_lstm_ef, val_lstm_ef = SplitData.split_data(
data_loader.train_lstm_ef, [0.9, 0.1])
if data_loader.poi_dim is not None and data_loader.poi_dim > 0: