libcity.data.dataset.trajectory_dataset¶
-
class
libcity.data.dataset.trajectory_dataset.TrajectoryDataset(config)[source]¶ Bases:
libcity.data.dataset.abstract_dataset.AbstractDataset-
cutter_filter()[source]¶ - 切割后的轨迹存储格式: (dict)
- {
- uid: [
- [
checkin_record, checkin_record, …
], [
checkin_record, checkin_record, …
}
-
encode_traj(data)[source]¶ encode the cut trajectory
- Parameters
data (dict) –
the key is uid, the value is the uid’s trajectories. For example: {
- uid: [
trajectory1, trajectory2
]
} trajectory1 = [
checkin_record, checkin_record, …..
]
- Returns
- For example:
- {
data_feature: {…}, pad_item: {…}, encoded_data: {uid: encoded_trajectories}
}
- Return type
dict
-