### Install Project Dependencies

Source: https://github.com/gestaltcogteam/d2stgnn/blob/github/README.md

Installs all necessary Python packages listed in the requirements.txt file. Ensure you are in the project's root directory before running this command.

```bash
pip install -r requirements.txt
```

--------------------------------

### Train D2STGNN Model

Source: https://github.com/gestaltcogteam/d2stgnn/blob/github/README.md

Use this command to train the D2STGNN model. Replace $DATASET_NAME with your dataset's name. An example using METR-LA is provided.

```bash
python main.py --dataset=$DATASET_NAME
```

```bash
python main.py --dataset=METR-LA
```

--------------------------------

### Download and Prepare Datasets

Source: https://github.com/gestaltcogteam/d2stgnn/blob/github/README.md

Downloads and extracts raw data and sensor graph files into the datasets directory. It also creates necessary output directories. This command should be run from the project's root directory.

```bash
cd /path/to/project
unzip raw_data.zip -d ./datasets/
unzip sensor_graph.zip -d ./datasets/
rm {sensor_graph.zip,raw_data.zip}
mkdir log output
```

--------------------------------

### Process Raw Data into Training Format

Source: https://github.com/gestaltcogteam/d2stgnn/blob/github/README.md

Generates training-ready data from raw datasets. Replace $DATASET_NAME with the specific dataset you are processing (e.g., METR-LA, PEMS-BAY, PEMS04, PEMS08).

```bash
python datasets/raw_data/$DATASET_NAME/generate_training_data.py
```

--------------------------------

### D2STGNN Citation

Source: https://github.com/gestaltcogteam/d2stgnn/blob/github/README.md

BibTeX entry for citing the D2STGNN model in academic work. This format is commonly used for publications.

```bibtex
@article{DBLP:journals/pvldb/ShaoZWWXCJ22,
  author    = {Zezhi Shao and
               Zhao Zhang and
               Wei Wei and
               Fei Wang and
               Yongjun Xu and
               Xin Cao and
               Christian S. Jensen},
  title     = {Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic
               Forecasting},
  journal   = {Proc. {VLDB} Endow.},
  volume    = {15},
  number    = {11},
  pages     = {2733--2746},
  year      = {2022}
}
```

=== COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.