Home

Awesome

Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting

Diffusion Convolutional Recurrent Neural Network

This is a PyTorch implementation of Diffusion Convolutional Recurrent Neural Network in the following paper:
Yaguang Li, Rose Yu, Cyrus Shahabi, Yan Liu, Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting, ICLR 2018.

Requirements

Dependency can be installed using the following command:

pip install -r requirements.txt

Comparison with Tensorflow implementation

In MAE (For LA dataset, PEMS-BAY coming in a while)

HorizonTensorflowPytorch
1 Hour3.693.12
30 Min3.152.82
15 Min2.772.56

Data Preparation

The traffic data files for Los Angeles (METR-LA) and the Bay Area (PEMS-BAY), i.e., metr-la.h5 and pems-bay.h5, are available at Google Drive or Baidu Yun, and should be put into the data/ folder. The *.h5 files store the data in panads.DataFrame using the HDF5 file format. Here is an example:

sensor_0sensor_1sensor_2sensor_n
2018/01/01 00:00:0060.065.070.0...
2018/01/01 00:05:0061.064.065.0...
2018/01/01 00:10:0063.065.060.0...
...............

Here is an article about Using HDF5 with Python.

Run the following commands to generate train/test/val dataset at data/{METR-LA,PEMS-BAY}/{train,val,test}.npz.

# Create data directories
mkdir -p data/{METR-LA,PEMS-BAY}

# METR-LA
python -m scripts.generate_training_data --output_dir=data/METR-LA --traffic_df_filename=data/metr-la.h5

# PEMS-BAY
python -m scripts.generate_training_data --output_dir=data/PEMS-BAY --traffic_df_filename=data/pems-bay.h5

Graph Construction

As the currently implementation is based on pre-calculated road network distances between sensors, it currently only supports sensor ids in Los Angeles (see data/sensor_graph/sensor_info_201206.csv).

python -m scripts.gen_adj_mx  --sensor_ids_filename=data/sensor_graph/graph_sensor_ids.txt --normalized_k=0.1\
    --output_pkl_filename=data/sensor_graph/adj_mx.pkl

Besides, the locations of sensors in Los Angeles, i.e., METR-LA, are available at data/sensor_graph/graph_sensor_locations.csv.

Run the Pre-trained Model on METR-LA

# METR-LA
python run_demo_pytorch.py --config_filename=data/model/pretrained/METR-LA/config.yaml

# PEMS-BAY
python run_demo_pytorch.py --config_filename=data/model/pretrained/PEMS-BAY/config.yaml

The generated prediction of DCRNN is in data/results/dcrnn_predictions.

Model Training

# METR-LA
python dcrnn_train_pytorch.py --config_filename=data/model/dcrnn_la.yaml

# PEMS-BAY
python dcrnn_train_pytorch.py --config_filename=data/model/dcrnn_bay.yaml

There is a chance that the training loss will explode, the temporary workaround is to restart from the last saved model before the explosion, or to decrease the learning rate earlier in the learning rate schedule.

Eval baseline methods

# METR-LA
python -m scripts.eval_baseline_methods --traffic_reading_filename=data/metr-la.h5

PyTorch Results

PyTorch Results

PyTorch Results

PyTorch Results

PyTorch Results

Citation

If you find this repository, e.g., the code and the datasets, useful in your research, please cite the following paper:

@inproceedings{li2018dcrnn_traffic,
  title={Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting},
  author={Li, Yaguang and Yu, Rose and Shahabi, Cyrus and Liu, Yan},
  booktitle={International Conference on Learning Representations (ICLR '18)},
  year={2018}
}